Fmi (#223)

* new mapfile for sciencespo in dc

* changed identifier, language and other stuff in fmi mapfile, adjusted eudatcore reader

* changes for identifier

mdingestion/community/fmi.py

@@ -6,12 +6,49 @@ class FMI(Community):
     NAME = 'fmi'
     IDENTIFIER = NAME
     URL = 'https://fmi.b2share.csc.fi/api/oai2d'
-    SCHEMA = SchemaType.DublinCore
+    SCHEMA = SchemaType.Eudatcore
     SERVICE_TYPE = ServiceType.OAI
-    OAI_METADATA_PREFIX = 'oai_dc'
-    OAI_SET = '8343aaf9-f598-4529-9359-7ce2d9bd3e63'
+    OAI_METADATA_PREFIX = 'eudatcore'
+    OAI_SET = '77f140b0-d4aa-437e-80d4-32c0abd3746f'
 
     def update(self, doc):
-        doc.discipline = self.discipline(doc, 'Meteorology')
+        doc.discipline = self._discipline(doc, 'Meteorology')
         doc.publisher = 'Finnish Meteorological Institute'
-        # doc.funding_reference = self.find('Funder')
+        doc.keywords = self.keywords()
+        doc.language = self.language()
+        self._identifier(doc)
+        #doc.funding_reference = self.find('Funder')
+
+    def _identifier(self, doc):
+        for id in self.find('identifier'):
+            if 'doi:' in id:
+                doc.doi = id.split('doi:')[-1]
+            if 'pid:' in id:
+                doc.pid = id.split('pid:')[-1]
+            if 'url:' in id:
+                doc.source = id.split('url:')[-1]
+
+    def _discipline(self, doc, default=None):
+        disc = self.find('discipline')
+        if disc:
+            _disc = []
+            for d in disc:
+                _disc.append(d.split('→')[-1])
+            disc = _disc
+        else:
+            disc = [default]
+        return disc
+
+    def keywords(self):
+        _keywords = self.find('keyword')
+        if not _keywords:
+            _keywords = self.find('subject')
+        return _keywords
+
+    def language(self):
+        _language = self.find('language')
+        if not _language or _language[0] == '':
+            _language = []
+            for lang in self._reader.parser.doc.find_all('language'):
+                _language.append(lang.get('language_name'))
+        return _language

mdingestion/community/sciencepodc.py

@@ -0,0 +1,19 @@
+from .base import Community
+from ..service_types import SchemaType, ServiceType
+
+
+class SciencesPoDublinCore(Community):
+    NAME = 'sciencespodc'
+    IDENTIFIER = NAME
+    URL = 'https://data.sciencespo.fr/oai'
+    SCHEMA = SchemaType.DublinCore
+    SERVICE_TYPE = ServiceType.OAI
+    OAI_METADATA_PREFIX = 'oai_dc'
+    OAI_SET = None
+#   PRODUCTIVE = True
+#   DATE = '2021-10-20'
+
+    def update(self, doc):
+        doc.discipline = self.discipline(doc, 'Social Sciences')
+        if not doc.publication_year:
+            doc.publication_year = self.find('header.datestamp')

mdingestion/reader/eudatcore.py

@@ -11,11 +11,11 @@ class EudatcoreReader(XMLReader):
     def parse(self, doc):
         doc.title = self.find('title')
         doc.description = self.find('description')
-        doc.doi = self.find('identifier')
-        doc.pid = self.find('identifier')
-        doc.source = self.find('identifier')
-        doc.keywords = self.find('subject')
-        doc.discipline = self.discipline(doc)
+        doc.doi = self.find_doi('identifier', identifierType="DOI")
+        doc.pid = self.find_pid('identifier', identifierType="PID")
+        doc.source = self.find_source('identifier', identifierType="URL")
+        doc.keywords = self.find('keyword')
+        doc.discipline = self.find('discipline')
         doc.related_identifier = self.find('relatedIdentifier')
         doc.creator = self.find('creator')
         doc.publisher = self.find('publisher')
@@ -25,11 +25,12 @@ def parse(self, doc):
         doc.rights = self.find('rights')
         doc.contact = self.find('contact')
         doc.language = self.find('language')
-        doc.resource_type = self.find('resource_type')
+        doc.resource_type = self.find('resourceType')
         doc.format = self.find('format')
         doc.size = self.find('size')
         doc.version = self.find('version')
-        doc.temporal_coverage = self.find('temporal_coverage')
+        doc.instrument = self.find('instrument')
+        doc.temporal_coverage = self.find('temporalCoverage')
         doc.geometry = self.find_geometry()
         doc.places = self.find('geoLocationPlace')