Merge pull request #88 from opendata-swiss/feat/add-conformsTo-field

Harvest conforms_to field to the dataset
opendata-swiss · Nov 8, 2023 · a96cf78 · a96cf78
2 parents 7e4ae2d + 4205f56
commit a96cf78
Show file tree

Hide file tree

Showing 5 changed files with 32 additions and 3 deletions.
diff --git a/ckanext/dcatapchharvest/profiles.py b/ckanext/dcatapchharvest/profiles.py
@@ -526,6 +526,11 @@ def parse_dataset(self, dataset_dict, dataset_ref):  # noqa
             dataset_ref, FOAF.page
         )
 
+        # Conformance
+        dataset_dict['conforms_to'] = self._object_value_list(
+            dataset_ref, DCT.conformsTo
+        )
+
         # Resources
         for distribution in self._distributions(dataset_ref):
             resource_dict = {
@@ -704,7 +709,6 @@ def graph_from_dataset(self, dataset_dict, dataset_ref):  # noqa
         items = [
             ('language', DCT.language, None, Literal),
             ('theme', DCAT.theme, None, URIRef),
-            ('conforms_to', DCT.conformsTo, None, Literal),
             ('alternate_identifier', ADMS.identifier, None, Literal),
             ('has_version', DCT.hasVersion, None, Literal),
             ('is_version_of', DCT.isVersionOf, None, Literal),
@@ -818,6 +822,12 @@ def graph_from_dataset(self, dataset_dict, dataset_ref):  # noqa
             g.add((doc, RDF.type, FOAF.Document))
             g.add((dataset_ref, FOAF.page, doc))
 
+        # Conformance
+        conformance_uris = dataset_dict.get('conforms_to', [])
+        for uri in conformance_uris:
+            ref = URIRef(uri)
+            g.add((dataset_ref, DCT.conformsTo, ref))
+
         # Themes
         groups = self._get_dataset_value(dataset_dict, 'groups', [])
         for group_name in groups:
@@ -860,7 +870,6 @@ def graph_from_dataset(self, dataset_dict, dataset_ref):  # noqa
             #  Lists
             items = [
                 ('language', DCT.language, None, Literal),
-                ('conforms_to', DCT.conformsTo, None, Literal),
             ]
             self._add_list_triples_from_dict(resource_dict, distribution,
                                              items)
@@ -1248,7 +1257,6 @@ def graph_from_dataset(self, dataset_dict, dataset_ref):
             #  Lists
             items = [
                 ("language", DCT.language, None, Literal),
-                ("conforms_to", DCT.conformsTo, None, Literal),
             ]
             self._add_list_triples_from_dict(resource_dict, distribution,
                                              items)

diff --git a/ckanext/dcatapchharvest/tests/fixtures/1901.xml b/ckanext/dcatapchharvest/tests/fixtures/1901.xml
@@ -92,5 +92,7 @@
     <foaf:page>
       <foaf:Document rdf:about="https://example.com/documentation-dataset-2"/>
     </foaf:page>
+    <dct:conformsTo rdf:resource="http://resource.geosciml.org/ontology/timescale/gts"/>
+    <dct:conformsTo rdf:resource="https://inspire.ec.europa.eu/documents"/>
   </dcat:Dataset>
 </rdf:RDF>
diff --git a/ckanext/dcatapchharvest/tests/fixtures/dataset.json b/ckanext/dcatapchharvest/tests/fixtures/dataset.json
@@ -5,6 +5,10 @@
   "url": "http://example.com/ds1",
   "version": "1.0b",
   "issued": "2015-06-26T15:21:09.034694",
+  "conforms_to": [
+        "http://resource.geosciml.org/ontology/timescale/gts",
+        "https://inspire.ec.europa.eu/documents"
+      ],
   "keywords": {
     "fr": [],
     "de": [

diff --git a/ckanext/dcatapchharvest/tests/test_dcatap_ch_parse.py b/ckanext/dcatapchharvest/tests/test_dcatap_ch_parse.py
@@ -125,6 +125,10 @@ def test_dataset_all_fields(self):
             sorted(dataset['documentation']),
             ['https://example.com/documentation-dataset-1', 'https://example.com/documentation-dataset-2']
         )
+        eq_(
+            sorted(dataset['conforms_to']),
+            [u'http://resource.geosciml.org/ontology/timescale/gts', u'https://inspire.ec.europa.eu/documents']
+        )
 
         # Dataset URI
         eq_(extras['uri'], u'https://opendata.swiss/dataset/7451e012-64b2-4bbc-af20-a0e2bc61b585')

diff --git a/ckanext/dcatapchharvest/tests/test_dcatap_ch_serialize.py b/ckanext/dcatapchharvest/tests/test_dcatap_ch_serialize.py
@@ -64,6 +64,17 @@ def test_graph_from_dataset(self):
         for documentation_link in dataset['documentation']:
             assert self._triple(g, dataset_ref, FOAF.page, URIRef(documentation_link))
 
+        # Conformance
+        conforms_to = dataset.get("conforms_to", [])
+        # Check if the number of triples matches the number of conformance uris
+        eq_(
+            len(list(g.triples((dataset_ref, DCT.conformsTo, None)))),
+            len(conforms_to)
+        )
+        for link in conforms_to:
+            # Check if the triple (dataset_ref, DCT.conformsTo, URIRef(link)) exists in the graph
+            assert (dataset_ref, DCT.conformsTo, URIRef(link)) in g
+
         # List
         for item in [
             ('language', DCT.language, Literal),