Fix families (#10)

* fixing language families and updating pythonv ersion on cldf validation * cldf conversion
lexibank · Mar 5, 2024 · b230310 · b230310
1 parent 20c9716
commit b230310
Show file tree

Hide file tree

Showing 8 changed files with 69 additions and 63 deletions.
diff --git a/.github/workflows/cldf-validation.yml b/.github/workflows/cldf-validation.yml
@@ -12,7 +12,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.6]
+        python-version: [3.9]
 
     steps:
     - uses: actions/checkout@v2

diff --git a/README.md b/README.md
@@ -42,7 +42,7 @@ This dataset comprises 69 language varieties spoken in Columbia. The orthography
 - **Synonymy:** 1.18
 - **Invalid lexemes:** 0
 - **Tokens:** 158,489
-- **Segments:** 109 (0 BIPA errors, 0 CTLS sound class errors, 109 CLTS modified)
+- **Segments:** 109 (0 BIPA errors, 0 CLTS sound class errors, 109 CLTS modified)
 - **Inventory size (avg):** 32.99
 
 # Contributors

diff --git a/cldf/README.md b/cldf/README.md
@@ -14,8 +14,8 @@ property | value
 [dc:identifier](http://purl.org/dc/terms/identifier) | https://gist.github.com/LinguList/7481097
 [dc:license](http://purl.org/dc/terms/license) | https://creativecommons.org/licenses/by/4.0/
 [dcat:accessURL](http://www.w3.org/ns/dcat#accessURL) | https://github.com/lexibank/hubercolumbian
-[prov:wasDerivedFrom](http://www.w3.org/ns/prov#wasDerivedFrom) | <ol><li><a href="https://github.com/lexibank/hubercolumbian/tree/f9c8fdd">lexibank/hubercolumbian v3.0-12-gf9c8fdd</a></li><li><a href="https://github.com/glottolog/glottolog/tree/v4.4">Glottolog v4.4</a></li><li><a href="https://github.com/concepticon/concepticon-data/tree/v2.5.0">Concepticon v2.5.0</a></li><li><a href="https://github.com/cldf-clts/clts/tree/v2.1.0">CLTS v2.1.0</a></li></ol>
-[prov:wasGeneratedBy](http://www.w3.org/ns/prov#wasGeneratedBy) | <ol><li><strong>lingpy-rcParams</strong>: <a href="./lingpy-rcParams.json">lingpy-rcParams.json</a></li><li><strong>python</strong>: 3.8.10</li><li><strong>python-packages</strong>: <a href="./requirements.txt">requirements.txt</a></li></ol>
+[prov:wasDerivedFrom](http://www.w3.org/ns/prov#wasDerivedFrom) | <ol><li><a href="https://github.com/lexibank/hubercolumbian/tree/afb03a3">lexibank/hubercolumbian v4.0.1-1-gafb03a3</a></li><li><a href="https://github.com/glottolog/glottolog/tree/v4.8">Glottolog v4.8</a></li><li><a href="https://github.com/concepticon/concepticon-data/tree/v3.1.0">Concepticon v3.1.0</a></li><li><a href="https://github.com/cldf-clts/clts/tree/v2.2.0">CLTS v2.2.0</a></li></ol>
+[prov:wasGeneratedBy](http://www.w3.org/ns/prov#wasGeneratedBy) | <ol><li><strong>lingpy-rcParams</strong>: <a href="./lingpy-rcParams.json">lingpy-rcParams.json</a></li><li><strong>python</strong>: 3.9.6</li><li><strong>python-packages</strong>: <a href="./requirements.txt">requirements.txt</a></li></ol>
 [rdf:ID](http://www.w3.org/1999/02/22-rdf-syntax-ns#ID) | hubercolumbian
 [rdf:type](http://www.w3.org/1999/02/22-rdf-syntax-ns#type) | http://www.w3.org/ns/dcat#Distribution
 
@@ -73,8 +73,8 @@ Name/Property | Datatype | Description
 `Glottolog_Name` | `string` | 
 [ISO639P3code](http://cldf.clld.org/v1.0/terms.rdf#iso639P3code) | `string` | 
 [Macroarea](http://cldf.clld.org/v1.0/terms.rdf#macroarea) | `string` | 
-[Latitude](http://cldf.clld.org/v1.0/terms.rdf#latitude) | `decimal` | 
-[Longitude](http://cldf.clld.org/v1.0/terms.rdf#longitude) | `decimal` | 
+[Latitude](http://cldf.clld.org/v1.0/terms.rdf#latitude) | `decimal`<br>&ge; -90<br>&le; 90 | 
+[Longitude](http://cldf.clld.org/v1.0/terms.rdf#longitude) | `decimal`<br>&ge; -180<br>&le; 180 | 
 `Family` | `string` | 
 `Name_in_Source` | `string` | 
 

diff --git a/cldf/cldf-metadata.json b/cldf/cldf-metadata.json
@@ -17,25 +17,25 @@
         {
             "rdf:about": "https://github.com/lexibank/hubercolumbian",
             "rdf:type": "prov:Entity",
-            "dc:created": "v3.0-12-gf9c8fdd",
+            "dc:created": "v4.0.1-1-gafb03a3",
             "dc:title": "Repository"
         },
         {
             "rdf:about": "https://github.com/glottolog/glottolog",
             "rdf:type": "prov:Entity",
-            "dc:created": "v4.4",
+            "dc:created": "v4.8",
             "dc:title": "Glottolog"
         },
         {
             "rdf:about": "https://github.com/concepticon/concepticon-data",
             "rdf:type": "prov:Entity",
-            "dc:created": "v2.5.0",
+            "dc:created": "v3.1.0",
             "dc:title": "Concepticon"
         },
         {
             "rdf:about": "https://github.com/cldf-clts/clts",
             "rdf:type": "prov:Entity",
-            "dc:created": "v2.1.0",
+            "dc:created": "v2.2.0",
             "dc:title": "CLTS"
         }
     ],
@@ -46,7 +46,7 @@
         },
         {
             "dc:title": "python",
-            "dc:description": "3.8.10"
+            "dc:description": "3.9.6"
         },
         {
             "dc:title": "python-packages",
@@ -55,9 +55,6 @@
     ],
     "rdf:ID": "hubercolumbian",
     "rdf:type": "http://www.w3.org/ns/dcat#Distribution",
-    "dialect": {
-        "commentPrefix": null
-    },
     "tables": [
         {
             "dc:conformsTo": "http://cldf.clld.org/v1.0/terms.rdf#FormTable",
@@ -181,7 +178,7 @@
                     {
                         "datatype": "string",
                         "propertyUrl": "http://cldf.clld.org/v1.0/terms.rdf#glottocode",
-                        "valueUrl": "http://glottolog.org/resource/languoid/id/{glottolog_id}",
+                        "valueUrl": "http://glottolog.org/resource/languoid/id/{Glottocode}",
                         "name": "Glottocode"
                     },
                     {
@@ -251,7 +248,7 @@
                     {
                         "datatype": "string",
                         "propertyUrl": "http://cldf.clld.org/v1.0/terms.rdf#concepticonReference",
-                        "valueUrl": "http://concepticon.clld.org/parameters/{concepticon_id}",
+                        "valueUrl": "http://concepticon.clld.org/parameters/{Concepticon_ID}",
                         "name": "Concepticon_ID"
                     },
                     {

diff --git a/cldf/languages.csv b/cldf/languages.csv
@@ -29,7 +29,7 @@ Guayabero,Guayabero,guay1257,Guayabero,guo,South America,2.8969,-71.844,Guahiboa
 Ika,Ika,arhu1242,Arhuaco,arh,South America,10.7018,-73.6363,Chibchan,ika
 Inga,Inga,inga1252,Inga,inb,South America,1.00313,-76.8606,Quechuan,inga
 Jitnu,Jitnu,maca1259,Macaguán,mbn,South America,6.34582,-71.2671,Guahiboan,jitnu
-Jupda,Jupda,hupd1244,Hupdë,jup,South America,0.58622,-69.8359,Nadahup,jupda
+Jupda,Jupda,hupd1244,Hupdë,jup,South America,0.58622,-69.8359,Naduhup,jupda
 Kakua,Kakua,cacu1241,Kakua,cbv,South America,0.88778,-69.5659,Kakua-Nukak,kakua
 Kamsa,Kamsá,cams1241,Camsá,kbh,South America,1.14537,-76.8931,Camsá,kamsá
 Kogui,Kogui,cogu1240,Cogui,kog,South America,10.9485,-73.8043,Chibchan,kogui
@@ -49,7 +49,7 @@ Resigaro,Resígaro,resi1247,Resígaro,rgr,South America,-2.48139,-71.3578,Arawak
 Secoya,Secoya,seco1241,Secoya,sey,South America,-0.459785,-75.5547,Tucanoan,secoya
 Siona,Siona,sion1247,Siona-Tetete,snn,South America,0.31733,-76.0237,Tucanoan,siona
 Siriano,Siriano,siri1274,Siriano,sri,South America,0.436515,-70.184,Tucanoan,siriano
-Saliba,Sáliba,sali1298,Sáliba,slc,South America,5.30115,-69.3843,Jodi-Saliban,sáliba
+Saliba,Sáliba,sali1298,Sáliba,slc,South America,5.30115,-69.3843,Saliban,sáliba
 Tanimuca,Tanimuca,tani1257,Tanimuca-Retuarã,tnc,South America,-0.59023,-70.3853,Tucanoan,tanimuca
 Tariano,Tariano,tari1256,Tariana,tae,South America,0.440205,-68.9042,Arawakan,tariano
 Tatuyo,Tatuyo,tatu1247,Tatuyo,tav,South America,0.55582,-70.5327,Tucanoan,tatuyo

diff --git a/cldf/lingpy-rcParams.json b/cldf/lingpy-rcParams.json
@@ -64,7 +64,7 @@
         10,
         10
     ],
-    "filename": "lingpy-2021-07-22",
+    "filename": "lingpy-2024-03-05",
     "gap_symbol": "-",
     "gap_weight": 0.5,
     "gop": -2,
@@ -123,7 +123,7 @@
     "scorer": {},
     "sonar": true,
     "stress": "\u02c8\u02cc'",
-    "timestamp": "2021-07-22 09:53",
+    "timestamp": "2024-03-05 12:26",
     "tones": "\u00b9\u00b2\u00b3\u2074\u2075\u2076\u2077\u2078\u2079\u2070\u2081\u2082\u2083\u2084\u2085\u2086\u2087\u2088\u2089\u20800123456789\u02e5\u02e6\u02e7\u02e8\u02e9\u02ea\u02eb-\ua708-\ua709-\ua70a-\ua70b-\ua70c-\ua70d-\ua70e-\ua70f-\ua710-\ua711-\ua712-\ua713-\ua714-\ua715-\ua716-\ua717-\ua718-\ua719-\ua71a-\ua700-\ua701-\ua702-\ua703-\ua704-\ua705-\ua706-\ua707",
     "tree_calc": "neighbor",
     "unique_sequences": true,

diff --git a/cldf/requirements.txt b/cldf/requirements.txt
@@ -1,48 +1,57 @@
 appdirs==1.4.4
-bs4==0.0.1
-certifi==2021.5.30
-chardet==4.0.0
-cldfbench==1.7.1
-cldfcatalog==1.3.2
-clldutils==3.9.0
-colorlog==5.0.1
-csvw==1.11.0
-gitdb==4.0.7
-greenlet==1.1.0
-idna==2.10
-iniconfig==1.1.1
-isodate==0.6.0
-lingpy==2.6.8
-Markdown==3.3.4
-networkx==2.6.1
-newick==1.3.0
-numpy==1.21.0
-openpyxl==3.0.7
-packaging==21.0
-pluggy==0.13.1
+attrs==23.2.0
+Babel==2.14.0
+bibtexparser==2.0.0b7
+bs4==0.0.2
+certifi==2024.2.2
+cldfbench==1.14.0
+cldfcatalog==1.5.1
+cldfzenodo==2.1.1
+clldutils==3.22.1
+colorama==0.4.6
+colorlog==6.8.2
+csvw==3.3.0
+exceptiongroup==1.2.0
+gitdb==4.0.11
+idna==3.6
+iniconfig==2.0.0
+isodate==0.6.1
+jsonschema==4.21.1
+lingpy==2.6.13
+lxml==5.1.0
+Markdown==3.5.2
+nameparser==1.1.3
+networkx==3.2.1
+newick==1.9.0
+numpy==1.26.4
+openpyxl==3.1.2
+packaging==23.2
+pluggy==1.4.0
 purl==1.6
-py==1.10.0
 pybtex==0.24.0
-pycldf==1.22.0
+pycldf==1.37.0
 pyclts==3.1.1
-pyconcepticon==2.8.0
-pycountry==20.7.3
-pyglottolog==3.6.0
-pylexibank==3.2.0
-pytest==6.2.4
-regex==2021.7.6
-requests==2.25.1
+pyconcepticon==3.0.0
+pycountry==23.12.11
+pyglottolog==3.12.0
+pylatexenc==2.10
+pylexibank==3.4.0
+pytest==8.0.2
+python-dateutil==2.9.0.post0
+rdflib==7.0.0
+referencing==0.33.0
+regex==2023.12.25
+requests==2.31.0
 rfc3986==1.5.0
-scipy==1.7.0
-segments==2.2.0
+segments==2.2.1
 six==1.16.0
-smmap==4.0.0
-soupsieve==2.2.1
-SQLAlchemy==1.4.20
-tabulate==0.8.9
-termcolor==1.1.0
-tqdm==4.61.2
-uritemplate==3.0.1
-urllib3==1.26.6
+smmap==5.0.1
+soupsieve==2.5
+SQLAlchemy==1.4.52
+tabulate==0.9.0
+termcolor==2.4.0
+tqdm==4.66.2
+uritemplate==4.1.1
+urllib3==2.2.1
 xlrd==2.0.1
-zenodoclient==0.4.1
+zenodoclient==0.5.1
diff --git a/etc/languages.tsv b/etc/languages.tsv
@@ -29,7 +29,7 @@ Guayabero	Guayabero	guayabero	guay1257	Guayabero	guo	South America	2.8969	-71.84
 Ika	Ika	ika	arhu1242	Arhuaco	arh	South America	10.7018	-73.6363	Chibchan
 Inga	Inga	inga	inga1252	Inga	inb	South America	1.00313	-76.8606	Quechuan
 Jitnu	Jitnu	jitnu	maca1259	Macaguán	mbn	South America	6.34582	-71.2671	Guahiboan
-Jupda	Jupda	jupda	hupd1244	Hupdë	jup	South America	0.58622	-69.8359	Nadahup
+Jupda	Jupda	jupda	hupd1244	Hupdë	jup	South America	0.58622	-69.8359	Naduhup
 Kakua	Kakua	kakua	cacu1241	Kakua	cbv	South America	0.88778	-69.5659	Kakua-Nukak
 Kamsa	Kamsá	kamsá	cams1241	Camsá	kbh	South America	1.14537	-76.8931	Camsá
 Kogui	Kogui	kogui	cogu1240	Cogui	kog	South America	10.9485	-73.8043	Chibchan
@@ -49,7 +49,7 @@ Resigaro	Resígaro	resígaro	resi1247	Resígaro	rgr	South America	-2.48139	-71.3
 Secoya	Secoya	secoya	seco1241	Secoya	sey	South America	-0.459785	-75.5547	Tucanoan
 Siona	Siona	siona	sion1247	Siona-Tetete	snn	South America	0.31733	-76.0237	Tucanoan
 Siriano	Siriano	siriano	siri1274	Siriano	sri	South America	0.436515	-70.184	Tucanoan
-Saliba	Sáliba	sáliba	sali1298	Sáliba	slc	South America	5.30115	-69.3843	Jodi-Saliban
+Saliba	Sáliba	sáliba	sali1298	Sáliba	slc	South America	5.30115	-69.3843	Saliban
 Tanimuca	Tanimuca	tanimuca	tani1257	Tanimuca-Retuarã	tnc	South America	-0.59023	-70.3853	Tucanoan
 Tariano	Tariano	tariano	tari1256	Tariana	tae	South America	0.440205	-68.9042	Arawakan
 Tatuyo	Tatuyo	tatuyo	tatu1247	Tatuyo	tav	South America	0.55582	-70.5327	Tucanoan