Merge pull request #101 from opendata-swiss/fix/handle-contact-point-…

…without-email Fix/handle contact point without email
opendata-swiss · Apr 3, 2024 · cd90fec · cd90fec
2 parents 8cfbb02 + 4cd4861
commit cd90fec
Show file tree

Hide file tree

Showing 4 changed files with 52 additions and 5 deletions.
diff --git a/ckanext/dcatapchharvest/profiles.py b/ckanext/dcatapchharvest/profiles.py
@@ -858,15 +858,25 @@ def graph_from_dataset(self, dataset_dict, dataset_ref):  # noqa
 
         # Contact details
         if dataset_dict.get('contact_points'):
-            contact_points = self._get_dataset_value(dataset_dict, 'contact_points')  # noqa
+            contact_points = self._get_dataset_value(
+                dataset_dict, 'contact_points'
+            )
             for contact_point in contact_points:
+                if not contact_point.get('email') \
+                        or not contact_point.get('name'):
+                    continue
+
                 contact_details = BNode()
                 contact_point_email = \
                     EMAIL_MAILTO_PREFIX + contact_point['email']
                 contact_point_name = contact_point['name']
 
                 g.add((contact_details, RDF.type, VCARD.Organization))
-                g.add((contact_details, VCARD.hasEmail, URIRef(contact_point_email)))  # noqa
+                g.add((
+                    contact_details,
+                    VCARD.hasEmail,
+                    URIRef(contact_point_email)
+                ))
                 g.add((contact_details, VCARD.fn, Literal(contact_point_name)))
 
                 g.add((dataset_ref, DCAT.contactPoint, contact_details))
@@ -1247,8 +1257,11 @@ def contact_details(self, dataset_dict, dataset_ref, g):
         if dataset_dict.get("contact_points"):
             contact_points = self._get_dataset_value(
                 dataset_dict, "contact_points"
-            )  # noqa
+            )
             for contact_point in contact_points:
+                if not contact_point.get('email') \
+                        or not contact_point.get('name'):
+                    continue
                 contact_details = BNode()
                 contact_point_email = \
                     EMAIL_MAILTO_PREFIX + contact_point["email"]

diff --git a/ckanext/dcatapchharvest/tests/fixtures/dataset.json b/ckanext/dcatapchharvest/tests/fixtures/dataset.json
@@ -101,6 +101,18 @@
     "https://example.com/documentation-dataset-1",
     "https://example.com/documentation-dataset-2"
   ],
+  "contact_points": [
+    {
+      "name": "Maria Muster",
+      "email": "[email protected]"
+    },
+    {
+      "name": "Maria Muster"
+    },
+    {
+      "email": "[email protected]"
+    }
+  ],
   "resources": [
     {
       "id": "e2c50e70-67ad-4f86-bb1b-3f93867eadaa",

diff --git a/ckanext/dcatapchharvest/tests/test_dcatap_ch_serialize.py b/ckanext/dcatapchharvest/tests/test_dcatap_ch_serialize.py
@@ -9,7 +9,7 @@
 
 from ckanext.dcat import utils
 from ckanext.dcat.processors import RDFSerializer
-from ckanext.dcat.profiles import DCAT, DCT, FOAF, OWL, SCHEMA, XSD
+from ckanext.dcat.profiles import DCAT, DCT, FOAF, OWL, SCHEMA, VCARD, XSD
 
 import ckanext.dcatapchharvest.dcat_helpers as dh
 
@@ -63,6 +63,17 @@ def test_graph_from_dataset(self):
         for documentation_link in dataset['documentation']:
             assert self._triple(g, dataset_ref, FOAF.page, URIRef(documentation_link))
 
+        # Contact points
+        eq_(len([t for t in g.triples((dataset_ref, DCAT.contactPoint, None))]), 1)
+
+        contact_point = next(g.objects(dataset_ref, DCAT.contactPoint))
+        eq_(next(g.objects(contact_point, RDF.type)), VCARD.Organization)
+        eq_(
+            next(g.objects(contact_point, VCARD.hasEmail)),
+            URIRef("mailto:[email protected]")
+        )
+        eq_(next(g.objects(contact_point, VCARD.fn)), Literal("Maria Muster"))
+
         # Conformance
         conforms_to = dataset.get("conforms_to", [])
         # Check if the number of triples matches the number of conformance uris

diff --git a/ckanext/dcatapchharvest/tests/test_swiss_schemaorg_serialize.py b/ckanext/dcatapchharvest/tests/test_swiss_schemaorg_serialize.py
@@ -7,7 +7,7 @@
 
 from ckanext.dcat import utils
 from ckanext.dcat.processors import RDFSerializer
-from ckanext.dcat.profiles import SCHEMA
+from ckanext.dcat.profiles import SCHEMA, VCARD
 
 from rdflib import URIRef
 import ckanext.dcatapchharvest.dcat_helpers as dh
@@ -40,6 +40,17 @@ def test_graph_from_dataset(self):
         assert self._triple(g, dataset_ref, SCHEMA.version, dataset['version'])
         assert self._triple(g, dataset_ref, SCHEMA.identifier, extras['identifier'])
 
+        # Contact points
+        eq_(len([t for t in g.triples((dataset_ref, SCHEMA.contactPoint, None))]), 1)
+
+        contact_point = next(g.objects(dataset_ref, SCHEMA.contactPoint))
+        eq_(next(g.objects(contact_point, RDF.type)), VCARD.Organization)
+        eq_(
+            next(g.objects(contact_point, VCARD.hasEmail)),
+            URIRef("mailto:[email protected]")
+        )
+        eq_(next(g.objects(contact_point, VCARD.fn)), Literal("Maria Muster"))
+
         # Dates
         assert self._triple(g, dataset_ref, SCHEMA.datePublished, dataset['issued'])
         assert len(list(g.objects(dataset_ref, SCHEMA.dateModified))) == 0