def _build_graph_and_check_format_mediatype(self, dataset_dict, expected_format, expected_mediatype):
"""
Creates a graph based on the given dict and checks for dct:format and dct:mediaType in the
first resource element.
:param dataset_dict:
dataset dict, expected to contain one resource
:param expected_format:
expected list of dct:format items in the resource
:param expected_mediatype:
expected list of dcat:mediaType items in the resource
"""
self.graph = rdflib.Graph()
dataset_ref = URIRef("http://example.org/datasets/1")
dcat = EuropeanDCATAPProfile(self.graph, False)
dcat.graph_from_dataset(dataset_dict, dataset_ref)
dcatde = DCATdeProfile(self.graph, False)
dcatde.graph_from_dataset(dataset_dict, dataset_ref)
# graph should contain the expected nodes
resource_ref = list(self.graph.objects(dataset_ref, self.DCAT.distribution))[0]
dct_format = list(self.graph.objects(resource_ref, self.DCT['format']))
dcat_mediatype = list(self.graph.objects(resource_ref, self.DCAT.mediaType))
self.assertEqual(expected_format, dct_format)
self.assertEqual(expected_mediatype, dcat_mediatype)
def test_graph_from_dataset_only_dcatde_contact_point_values(self):
### prepare ###
self.graph = rdflib.Graph()
dataset_dict = self._get_default_dataset_dict()
# remove fields processed by ckanext-dcat default profile
dataset_dict.pop('maintainer')
dataset_dict.pop('maintainer_email')
dataset_dict.pop('author')
dataset_dict.pop('author_email')
dataset_ref = URIRef("http://testuri/")
### execute ###
dcat = EuropeanDCATAPProfile(self.graph, False)
dcat.graph_from_dataset(dataset_dict, dataset_ref)
dcatde = DCATdeProfile(self.graph, False)
dcatde.graph_from_dataset(dataset_dict, dataset_ref)
### assert ###
# contactPoint
self._assert_contact_point(dataset_ref, [self.VCARD.fn, self.VCARD.hasEmail])
def test_graph_from_dataset(self):
""" test dcat and dcatde profiles """
dataset_dict = {
"id":
"dct:identifier",
"notes":
"dct:description",
"title":
"dct:title",
"url":
"dcat:landingPage",
"version":
"owl:versionInfo",
"metadata_created":
"2017-07-06T13:08:40",
"metadata_modified":
"2017-07-06T13:08:41",
"license_id":
"nocheck",
"groups": [{
"name": "GRUPPEA"
}, {
"name": "GRUPPEB"
}],
"tags": [{
"name": "dcat:keyword"
}, {
"name": "tagB"
}],
"author":
"nocheck",
"author_email":
"nocheck",
"maintainer":
"nocheck",
"maintainer_email":
"nocheck",
"extras":
self._transform_to_key_value({
"contributorID": ["dcatde:contributorID"],
"qualityProcessURI":
"dcatde:qualityProcessURI",
"documentation":
"foaf:page",
"frequency":
"dct:accrualPeriodicity",
"version_notes":
"adms:versionNotes",
"dcat_type":
"dct:type",
"author_url":
"nocheck",
"maintainer_url":
"nocheck",
"maintainer_tel":
"nocheck",
'maintainer_street':
"nocheck",
'maintainer_city':
"nocheck",
'maintainer_zip':
"nocheck",
'maintainer_country':
"nocheck",
"publisher_name":
"nocheck",
"publisher_email":
"nocheck",
"publisher_url":
"nocheck",
"originator_name":
"nocheck",
"originator_email":
"nocheck",
"originator_url":
"nocheck",
"contributor_name":
"nocheck",
"contributor_email":
"nocheck",
"contributor_url":
"nocheck",
"access_rights":
"dct:accessRights",
"provenance":
"dct:provenance",
"politicalGeocodingLevelURI":
"dcatde:politicalGeocodingLevelURI",
"politicalGeocodingURI": ["dcatde:politicalGeocodingURI"],
"geocodingText": ["dcatde:geocodingText"],
"legalbasisText": ["dcatde:legalbasisText"],
"temporal_start":
"2017-07-06T13:08:40",
"temporal_end":
"2017-07-06T13:08:41",
"spatial":
"{\"type\":\"Polygon\",\"coordinates\":[[[8.852920532226562," +
"47.97245599240245],[9.133758544921875,47.97245599240245]," +
"[9.133758544921875,48.17249666038475],[8.852920532226562," +
"48.17249666038475],[8.852920532226562,47.97245599240245]]]}",
"language": ["dct:language"],
"conforms_to": ["dct:conformsTo"],
"alternate_identifier": ["adms:identifier"],
"used_datasets": ["dct:relation", "bla"],
"has_version": ["dct:hasVersion"],
"is_version_of": ["dct:isVersionOf"]
}),
"resources": [{
"id":
"id",
"name":
"dct:title",
"description":
"dct:description",
"url":
"dcat:accessURL",
"format:":
"dct:format",
"mimetype":
"dcat:mediaType",
"size":
10,
"hash":
24,
"extras":
self._transform_to_key_value({
"issued": "dct:issued",
"modified": "dct:modified",
"documentation": "foaf:page",
"download_url": "dcat:downloadURL",
"plannedAvailability": "dcatde:plannedAvailability",
"licenseAttributionByText":
"dcatde:licenseAttributionByText",
"license": "dct:license",
"rights": "dct:rights",
"status": "adms:status",
"language": ["dct:language"],
"conforms_to": ["dct:conformsTo"],
})
}]
}
dataset_ref = URIRef("http://testuri/")
dcat = EuropeanDCATAPProfile(self.graph, False)
dcat.graph_from_dataset(dataset_dict, dataset_ref)
dcatde = DCATdeProfile(self.graph, False)
dcatde.graph_from_dataset(dataset_dict, dataset_ref)
# Assert structure of graph - basic values
extras = dataset_dict["extras"]
for key in dataset_dict:
self._check_simple_items(dataset_dict, dataset_ref, key)
for key in extras:
self._check_simple_items(dataset_dict, dataset_ref, key)
# issued, modified
self.assertEqual(
len(list(self.graph.objects(dataset_ref, self.DCT.issued))), 1,
"dct:issued not found")
self.assertEqual(
len(list(self.graph.objects(dataset_ref, self.DCT.modified))), 1,
"dct:modified not found")
# groups, tags
self._assert_list(dataset_ref, self.DCAT.theme, [
self.dcat_theme_prefix + x["name"] for x in dataset_dict["groups"]
])
self._assert_list(dataset_ref, self.DCAT.keyword,
[x["name"] for x in dataset_dict["tags"]])
# author, maintainer, originator, contributor, publisher
self._assert_contact_info(dataset_ref, self.DCATDE.originator)
self._assert_contact_info(dataset_ref, self.DCATDE.maintainer)
self._assert_contact_info(dataset_ref, self.DCT.contributor)
self._assert_contact_info(dataset_ref, self.DCT.creator)
self._assert_contact_info(dataset_ref, self.DCT.publisher)
# contactPoint
contact_point = next(
self.graph.objects(dataset_ref, self.DCAT.contactPoint))
vcard_attrs = [
self.VCARD.fn, self.VCARD.hasEmail, self.VCARD.hasURL,
self.VCARD.hasTelephone, self.VCARD.hasStreetAddress,
self.VCARD.hasLocality, self.VCARD.hasCountryName,
self.VCARD.hasPostalCode
]
for v_attr in vcard_attrs:
self.assertEqual(
len(list(self.graph.objects(contact_point, v_attr))), 1,
self.DCAT.contactPoint + str(v_attr) + " not found")
# temporal
temporal = list(self.graph.objects(dataset_ref, self.DCT.temporal))[0]
self.assertEqual(
len(list(self.graph.objects(temporal, self.SCHEMA.startDate))), 1,
self.SCHEMA.startDate + " not found")
self.assertEqual(
len(list(self.graph.objects(temporal, self.SCHEMA.endDate))), 1,
self.SCHEMA.endDate + " not found")
# spatial
for spatial in list(self.graph.objects(dataset_ref, self.DCT.spatial)):
geonodes = len(
list(self.graph.objects(spatial, self.LOCN.geometry)))
adminnodes = len(
list(self.graph.objects(spatial, self.LOCN.adminUnitL2)))
if geonodes > 0:
self.assertEqual(geonodes, 2,
self.LOCN.geometry + " not present, 2x")
elif adminnodes > 0:
self.assertEqual(adminnodes, 1,
self.LOCN.adminUnitL2 + " not present")
else:
self.fail("No valid spatial blocks found.")
# lists in extras
self._assert_list(dataset_ref, self.DCT.language,
self._get_value_from_extras(extras, "language"))
self._assert_list(dataset_ref, self.DCT.conformsTo,
self._get_value_from_extras(extras, "conforms_to"))
self._assert_list(
dataset_ref, self.ADMS.identifier,
self._get_value_from_extras(extras, "alternate_identifier"))
self._assert_list(dataset_ref, self.DCT.relation,
self._get_value_from_extras(extras, "used_datasets"))
self._assert_list(dataset_ref, self.DCT.hasVersion,
self._get_value_from_extras(extras, "has_version"))
self._assert_list(dataset_ref, self.DCT.isVersionOf,
self._get_value_from_extras(extras, "is_version_of"))
self._assert_list(
dataset_ref, self.DCATDE.politicalGeocodingURI,
self._get_value_from_extras(extras, "politicalGeocodingURI"))
self._assert_list(dataset_ref, self.DCATDE.geocodingText,
self._get_value_from_extras(extras, "geocodingText"))
self._assert_list(
dataset_ref, self.DCATDE.legalbasisText,
self._get_value_from_extras(extras, "legalbasisText"))
self._assert_list(dataset_ref, self.DCATDE.contributorID,
self._get_value_from_extras(extras, "contributorID"))
# resources
resource = dataset_dict["resources"][0]
resource_ref = list(
self.graph.objects(dataset_ref, self.DCAT.distribution))[0]
resource_extras = resource["extras"]
for key in resource:
self._check_simple_items(resource, resource_ref, key)
for key in resource_extras:
self._check_simple_items(resource, resource_ref, key)
# size
self.assertEqual(
len(list(self.graph.objects(resource_ref, self.DCAT.byteSize))), 1,
self.DCAT.byteSize + " not found")
# hash
self.assertEqual(
len(list(self.graph.objects(resource_ref, self.SPDX.checksum))), 1,
self.SPDX.checksum + " not found")
# lists
self._assert_list(
resource_ref, self.DCT.language,
self._get_value_from_extras(resource_extras, "language"))
self._assert_list(
resource_ref, self.DCT.conformsTo,
self._get_value_from_extras(resource_extras, "conforms_to"))
def test_graph_from_dataset(self):
""" test dcat and dcatde profiles """
### prepare ###
self.graph = rdflib.Graph()
dataset_dict = self._get_default_dataset_dict()
dataset_ref = URIRef("http://testuri/")
dcat = EuropeanDCATAPProfile(self.graph, False)
dcat.graph_from_dataset(dataset_dict, dataset_ref)
dcatde = DCATdeProfile(self.graph, False)
dcatde.graph_from_dataset(dataset_dict, dataset_ref)
# Assert structure of graph - basic values
extras = dataset_dict["extras"]
for key in dataset_dict:
self._check_simple_items(dataset_dict, dataset_ref, key)
for key in extras:
self._check_simple_items(dataset_dict, dataset_ref, key)
# issued, modified
self.assertEqual(len(list(self.graph.objects(dataset_ref, self.DCT.issued))), 1,
"dct:issued not found")
self.assertEqual(len(list(self.graph.objects(dataset_ref, self.DCT.modified))), 1,
"dct:modified not found")
# groups, tags
self._assert_list(dataset_ref, self.DCAT.theme,
[self.dcat_theme_prefix + x["name"] for x in dataset_dict["groups"]])
self._assert_list(dataset_ref, self.DCAT.keyword,
[x["name"] for x in dataset_dict["tags"]])
# author, maintainer, originator, contributor, publisher
self._assert_contact_info(dataset_ref, self.DCATDE.originator)
self._assert_contact_info(dataset_ref, self.DCATDE.maintainer)
self._assert_contact_info(dataset_ref, self.DCT.contributor)
self._assert_contact_info(dataset_ref, self.DCT.creator)
self._assert_contact_info(dataset_ref, self.DCT.publisher)
# contactPoint
self._assert_contact_point(dataset_ref)
# temporal
temporal = list(self.graph.objects(dataset_ref, self.DCT.temporal))[0]
self.assertEqual(len(list(self.graph.objects(temporal, self.SCHEMA.startDate))), 1,
self.SCHEMA.startDate + " not found")
self.assertEqual(len(list(self.graph.objects(temporal, self.SCHEMA.endDate))), 1,
self.SCHEMA.endDate + " not found")
# spatial
for spatial in list(self.graph.objects(dataset_ref, self.DCT.spatial)):
geonodes = len(list(self.graph.objects(spatial, self.LOCN.geometry)))
adminnodes = len(list(self.graph.objects(spatial, self.LOCN.adminUnitL2)))
if geonodes > 0:
self.assertEqual(geonodes, 2, self.LOCN.geometry + " not present, 2x")
elif adminnodes > 0:
self.assertEqual(adminnodes, 1, self.LOCN.adminUnitL2 + " not present")
else:
self.fail("No valid spatial blocks found.")
# lists in extras
self._assert_list(dataset_ref, self.DCT.language,
self._get_value_from_extras(extras, "language"))
self._assert_list(dataset_ref, self.DCT.conformsTo,
self._get_value_from_extras(extras, "conforms_to"))
self._assert_list(dataset_ref, self.ADMS.identifier,
self._get_value_from_extras(extras, "alternate_identifier"))
self._assert_list(dataset_ref, self.DCT.relation,
self._get_value_from_extras(extras, "used_datasets"))
self._assert_list(dataset_ref, self.DCT.hasVersion,
self._get_value_from_extras(extras, "has_version"))
self._assert_list(dataset_ref, self.DCT.isVersionOf,
self._get_value_from_extras(extras, "is_version_of"))
self._assert_list(dataset_ref, self.DCATDE.politicalGeocodingURI,
self._get_value_from_extras(extras, "politicalGeocodingURI"))
self._assert_list(dataset_ref, self.DCATDE.geocodingDescription,
self._get_value_from_extras(extras, "geocodingText"))
self._assert_list(dataset_ref, self.DCATDE.legalBasis,
self._get_value_from_extras(extras, "legalbasisText"))
self._assert_list(dataset_ref, self.DCATDE.contributorID,
self._get_value_from_extras(extras, "contributorID"))
# resources
resource = dataset_dict["resources"][0]
resource_ref = list(self.graph.objects(dataset_ref, self.DCAT.distribution))[0]
resource_extras = resource["extras"]
for key in resource:
self._check_simple_items(resource, resource_ref, key)
for key in resource_extras:
self._check_simple_items(resource, resource_ref, key)
# size
self.assertEqual(len(list(self.graph.objects(resource_ref, self.DCAT.byteSize))), 1,
self.DCAT.byteSize + " not found")
# hash
self.assertEqual(len(list(self.graph.objects(resource_ref, self.SPDX.checksum))), 1,
self.SPDX.checksum + " not found")
# lists
self._assert_list(resource_ref, self.DCT.language,
self._get_value_from_extras(resource_extras, "language"))
self._assert_list(resource_ref, self.DCT.conformsTo,
self._get_value_from_extras(resource_extras, "conforms_to"))