Merge pull request #258 from GovDataOfficial/improve-access-service-t…

…ests Improves access service tests
ckan · Oct 4, 2023 · 33498df · 33498df
2 parents 93bf901 + 47a1633
commit 33498df
Show file tree

Hide file tree

Showing 3 changed files with 106 additions and 0 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -2,6 +2,8 @@
 
 ## [Unreleased](https://github.com/ckan/ckanext-dcat/compare/v1.5.1...HEAD)
 
+* Improve access service tests (#258)
+* Fix missing access service items when parsing dataset (#256)
 
 ## [v1.5.1](https://github.com/ckan/ckanext-dcat/compare/v1.5.0...v1.5.1) - 2023-06-20
 

diff --git a/ckanext/dcat/tests/test_euro_dcatap_2_profile_parse.py b/ckanext/dcat/tests/test_euro_dcatap_2_profile_parse.py
@@ -431,6 +431,65 @@ def test_parse_distribution_access_service_literal(self):
 
         self._run_parse_access_service(expected_access_services)
 
+    def test_dataset_distribution_access_service_list_values_only(self):
+
+        data = '''<?xml version="1.0" encoding="utf-8" ?>
+        <rdf:RDF
+         xmlns:dct="http://purl.org/dc/terms/"
+         xmlns:dcat="http://www.w3.org/ns/dcat#"
+         xmlns:dcatap="http://data.europa.eu/r5r/"
+         xmlns:schema="http://schema.org/"
+         xmlns:time="http://www.w3.org/2006/time"
+         xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+         xmlns:rdfs="http://www.w3.org/2000/01/rdf-schema#">
+        <dcat:Dataset rdf:about="http://example.org">
+            <dcat:distribution>
+                <dcat:Distribution rdf:about="https://data.some.org/catalog/datasets/9df8df51-63db-37a8-e044-0003ba9b0d98/1">
+                    <dct:description>Das ist eine deutsche Beschreibung der Distribution</dct:description>
+                    <dct:title>Download WFS Naturräume Geest und Marsch (GML)</dct:title>
+                    <dcat:accessService>
+                        <dcat:DataService>
+                            <dcat:endpointURL rdf:resource="http://publications.europa.eu/webapi/rdf/sparql"/>
+                            <dcat:servesDataset rdf:resource="http://example.org" />
+                        </dcat:DataService>
+                    </dcat:accessService>
+                </dcat:Distribution>
+            </dcat:distribution>
+        </dcat:Dataset>
+        </rdf:RDF>
+        '''
+
+        p = RDFParser(profiles=DCAT_AP_PROFILES)
+
+        p.parse(data)
+
+        datasets = [d for d in p.datasets()]
+
+        assert len(datasets) == 1
+
+        dataset = datasets[0]
+
+        # Resources
+        assert len(dataset['resources']) == 1
+
+        resource = dataset['resources'][0]
+
+        # Access services
+        access_service_list = json.loads(resource.get('access_services'))
+        assert len(access_service_list) == 1
+
+        access_service = access_service_list[0]
+
+        # List
+        endpoint_url_list = access_service.get('endpoint_url')
+        print(access_service)
+        assert len(endpoint_url_list) == 1
+        assert 'http://publications.europa.eu/webapi/rdf/sparql' in endpoint_url_list
+
+        serves_dataset_list = access_service.get('serves_dataset')
+        assert len(serves_dataset_list) == 1
+        assert 'http://example.org' in serves_dataset_list
+
     def _build_access_services_graph_from_list(self, access_service_list):
         """
         Creates an access service graph based on the given list.

diff --git a/ckanext/dcat/tests/test_euro_dcatap_2_profile_serialize.py b/ckanext/dcat/tests/test_euro_dcatap_2_profile_serialize.py
@@ -542,6 +542,51 @@ def test_access_services_absent(self):
         assert len(object_list) == 0
         assert 'access_services' not in dataset['resources'][0]
 
+    def test_access_services_list_values_only(self):
+
+        resource = {
+            'id': 'c041c635-054f-4431-b647-f9186926d021',
+            'package_id': '4b6fe9ca-dc77-4cec-92a4-55c6624a5bd6',
+            'name': 'Distribution name',
+            'access_services': json.dumps([
+                {
+                    'endpoint_url': ['http://publications.europa.eu/webapi/rdf/sparql'],
+                    'serves_dataset': ['http://data.europa.eu/88u/dataset/eu-whoiswho-the-official-directory-of-the-european-union']
+                }
+            ])
+        }
+
+        dataset = {
+            'id': '4b6fe9ca-dc77-4cec-92a4-55c6624a5bd6',
+            'name': 'test-dataset',
+            'title': 'Test DCAT dataset',
+            'resources': [
+                resource
+            ]
+        }
+
+        s = RDFSerializer(profiles=DCAT_AP_PROFILES)
+        g = s.g
+
+        dataset_ref = s.graph_from_dataset(dataset)
+
+        assert len([t for t in g.triples((dataset_ref, DCAT.distribution, None))]) == 1
+
+        distribution = self._triple(g, dataset_ref, DCAT.distribution, None)[2]
+
+        assert len([t for t in g.triples((distribution, DCAT.accessService, None))]) == 1
+
+        # Access services
+        access_service_object = self._triple(g, distribution, DCAT.accessService, None)[2]
+
+        access_services = json.loads(resource['access_services'])
+
+        # Lists
+        self._assert_values_list(g, access_service_object, DCAT.endpointURL,
+                            self._get_typed_list(access_services[0].get('endpoint_url'), URIRef))
+        self._assert_values_list(g, access_service_object, DCAT.servesDataset,
+                            self._get_typed_list(access_services[0].get('serves_dataset'), URIRef))
+
     def _assert_simple_value(self, graph, object, predicate, value):
         """
         Checks if a triple with the given value is present in the graph