def test_distribution_format_IMT_field(self):
g = Graph()
dataset1 = URIRef("http://example.org/datasets/1")
g.add((dataset1, RDF.type, DCAT.Dataset))
distribution1_1 = URIRef("http://example.org/datasets/1/ds/1")
imt = BNode()
g.add((imt, RDF.type, DCT.IMT))
g.add((imt, RDF.value, Literal('text/turtle')))
g.add((imt, RDFS.label, Literal('Turtle')))
g.add((distribution1_1, RDF.type, DCAT.Distribution))
g.add((distribution1_1, DCT['format'], imt))
g.add((dataset1, DCAT.distribution, distribution1_1))
p = RDFParser(profiles=['euro_dcat_ap'])
p.g = g
datasets = [d for d in p.datasets()]
resource = datasets[0]['resources'][0]
eq_(resource['format'], u'Turtle')
eq_(resource['mimetype'], u'text/turtle')
def test_distribution_format_format_normalized(self):
g = Graph()
dataset1 = URIRef("http://example.org/datasets/1")
g.add((dataset1, RDF.type, DCAT.Dataset))
distribution1_1 = URIRef("http://example.org/datasets/1/ds/1")
g.add((distribution1_1, RDF.type, DCAT.Distribution))
g.add((distribution1_1, DCAT.mediaType, Literal('text/csv')))
g.add((distribution1_1, DCT['format'],
Literal('Comma Separated Values')))
g.add((dataset1, DCAT.distribution, distribution1_1))
p = RDFParser(profiles=['euro_dcat_ap'])
p.g = g
datasets = [d for d in p.datasets()]
resource = datasets[0]['resources'][0]
if toolkit.check_ckan_version(min_version='2.3'):
eq_(resource['format'], u'CSV')
eq_(resource['mimetype'], u'text/csv')
else:
eq_(resource['format'], u'Comma Separated Values')
def test_spatial_one_dct_spatial_instance_no_uri(self):
g = Graph()
dataset = URIRef('http://example.org/datasets/1')
g.add((dataset, RDF.type, DCAT.Dataset))
location_ref = BNode()
g.add((dataset, DCT.spatial, location_ref))
g.add((location_ref, RDF.type, DCT.Location))
g.add((location_ref, LOCN.geometry,
Literal('{"type": "Point", "coordinates": [23, 45]}',
datatype=GEOJSON_IMT)))
g.add((location_ref, SKOS.prefLabel, Literal('Newark')))
p = RDFParser(profiles=['euro_dcat_ap'])
p.g = g
datasets = [d for d in p.datasets()]
extras = self._extras(datasets[0])
assert_true('spatial_uri' not in extras)
eq_(extras['spatial_text'], 'Newark')
eq_(extras['spatial'], '{"type": "Point", "coordinates": [23, 45]}')
def test_datasets_none_found(self):
p = RDFParser()
p.g = Graph()
eq_(len([d for d in p.datasets()]), 0)
def test_spatial_both_geojson_and_wkt(self):
g = Graph()
dataset = URIRef('http://example.org/datasets/1')
g.add((dataset, RDF.type, DCAT.Dataset))
spatial_uri = URIRef('http://geonames/Newark')
g.add((dataset, DCT.spatial, spatial_uri))
g.add((spatial_uri, RDF.type, DCT.Location))
g.add((spatial_uri, LOCN.geometry,
Literal('{"type": "Point", "coordinates": [23, 45]}',
datatype=GEOJSON_IMT)))
g.add((spatial_uri, LOCN.geometry,
Literal('POINT (67 89)', datatype=GSP.wktLiteral)))
p = RDFParser(profiles=['euro_dcat_ap'])
p.g = g
datasets = [d for d in p.datasets()]
extras = self._extras(datasets[0])
eq_(extras['spatial'], '{"type": "Point", "coordinates": [23, 45]}')
def test__datasets(self):
p = RDFParser()
p.g = _default_graph()
eq_(len([d for d in p._datasets()]), 3)
def test_profiles_are_called_on_datasets(self):
p = RDFParser()
p._profiles = [MockRDFProfile1, MockRDFProfile2]
p.g = _default_graph()
for dataset in p.datasets():
assert dataset['profile_1']
assert dataset['profile_2']
def test_tags_with_commas(self):
g = Graph()
dataset = URIRef('http://example.org/datasets/1')
g.add((dataset, RDF.type, DCAT.Dataset))
g.add((dataset, DCAT.keyword, Literal('Tree, forest, shrub')))
p = RDFParser(profiles=['euro_dcat_ap'])
p.g = g
datasets = [d for d in p.datasets()]
eq_(len(datasets[0]['tags']), 3)
def test_datasets(self):
p = RDFParser()
p.g = _default_graph()
datasets = []
for dataset in p.datasets():
assert 'title' in dataset
datasets.append(dataset)
eq_(len(datasets), 3)
def test_dataset_version_adms(self):
g = Graph()
dataset1 = URIRef("http://example.org/datasets/1")
g.add((dataset1, RDF.type, DCAT.Dataset))
g.add((dataset1, ADMS.version, Literal('2.3a')))
p = RDFParser(profiles=['euro_dcat_ap'])
p.g = g
dataset = [d for d in p.datasets()][0]
eq_(dataset['version'], u'2.3a')
def test_spatial_uri_only(self):
g = Graph()
dataset = URIRef('http://example.org/datasets/1')
g.add((dataset, RDF.type, DCAT.Dataset))
spatial_uri = URIRef('http://geonames/Newark')
g.add((dataset, DCT.spatial, spatial_uri))
p = RDFParser(profiles=['euro_dcat_ap'])
p.g = g
datasets = [d for d in p.datasets()]
extras = self._extras(datasets[0])
eq_(extras['spatial_uri'], 'http://geonames/Newark')
assert_true('spatial_text' not in extras)
assert_true('spatial' not in extras)
def test_dataset_license_from_distribution_by_uri(self):
# license_id retrieved from the URI of dcat:license object
g = Graph()
dataset = URIRef("http://example.org/datasets/1")
g.add((dataset, RDF.type, DCAT.Dataset))
distribution = URIRef("http://example.org/datasets/1/ds/1")
g.add((dataset, DCAT.distribution, distribution))
g.add((distribution, RDF.type, DCAT.Distribution))
g.add((distribution, DCT.license,
URIRef("http://www.opendefinition.org/licenses/cc-by")))
p = RDFParser(profiles=['euro_dcat_ap'])
p.g = g
dataset = [d for d in p.datasets()][0]
eq_(dataset['license_id'], 'cc-by')
def test_dataset_license_from_distribution_by_title(self):
# license_id retrieved from dct:title of dcat:license object
g = Graph()
dataset = URIRef("http://example.org/datasets/1")
g.add((dataset, RDF.type, DCAT.Dataset))
distribution = URIRef("http://example.org/datasets/1/ds/1")
g.add((distribution, RDF.type, DCAT.Distribution))
g.add((dataset, DCAT.distribution, distribution))
license = BNode()
g.add((distribution, DCT.license, license))
g.add((license, DCT.title, Literal("Creative Commons Attribution")))
p = RDFParser(profiles=['euro_dcat_ap'])
p.g = g
dataset = [d for d in p.datasets()][0]
eq_(dataset['license_id'], 'cc-by')
def test_distribution_format_format_only(self):
g = Graph()
dataset1 = URIRef("http://example.org/datasets/1")
g.add((dataset1, RDF.type, DCAT.Dataset))
distribution1_1 = URIRef("http://example.org/datasets/1/ds/1")
g.add((distribution1_1, RDF.type, DCAT.Distribution))
g.add((distribution1_1, DCT['format'], Literal('CSV')))
g.add((dataset1, DCAT.distribution, distribution1_1))
p = RDFParser(profiles=['euro_dcat_ap'])
p.g = g
datasets = [d for d in p.datasets()]
resource = datasets[0]['resources'][0]
eq_(resource['format'], u'CSV')
def test_distribution_format_imt_normalized(self):
g = Graph()
dataset1 = URIRef("http://example.org/datasets/1")
g.add((dataset1, RDF.type, DCAT.Dataset))
distribution1_1 = URIRef("http://example.org/datasets/1/ds/1")
g.add((distribution1_1, RDF.type, DCAT.Distribution))
g.add((distribution1_1, DCAT.mediaType, Literal('text/unknown-imt')))
g.add((dataset1, DCAT.distribution, distribution1_1))
p = RDFParser(profiles=['euro_dcat_ap'])
p.g = g
datasets = [d for d in p.datasets()]
resource = datasets[0]['resources'][0]
eq_(resource['format'], u'text/unknown-imt')
eq_(resource['mimetype'], u'text/unknown-imt')
def test_spatial_rdfs_label(self):
g = Graph()
dataset = URIRef('http://example.org/datasets/1')
g.add((dataset, RDF.type, DCAT.Dataset))
spatial_uri = URIRef('http://geonames/Newark')
g.add((dataset, DCT.spatial, spatial_uri))
g.add((spatial_uri, RDF.type, DCT.Location))
g.add((spatial_uri, RDFS.label, Literal('Newark')))
p = RDFParser(profiles=['euro_dcat_ap'])
p.g = g
datasets = [d for d in p.datasets()]
extras = self._extras(datasets[0])
eq_(extras['spatial_text'], 'Newark')
def test_distribution_download_url(self):
g = Graph()
dataset1 = URIRef("http://example.org/datasets/1")
g.add((dataset1, RDF.type, DCAT.Dataset))
distribution1_1 = URIRef("http://example.org/datasets/1/ds/1")
g.add((distribution1_1, RDF.type, DCAT.Distribution))
g.add((distribution1_1, DCAT.downloadURL,
Literal('http://download.url.org')))
g.add((dataset1, DCAT.distribution, distribution1_1))
p = RDFParser(profiles=['euro_dcat_ap'])
p.g = g
datasets = [d for d in p.datasets()]
resource = datasets[0]['resources'][0]
eq_(resource['url'], u'http://download.url.org')
eq_(resource['download_url'], u'http://download.url.org')
def test_spatial_wkt_only(self):
g = Graph()
dataset = URIRef('http://example.org/datasets/1')
g.add((dataset, RDF.type, DCAT.Dataset))
spatial_uri = URIRef('http://geonames/Newark')
g.add((dataset, DCT.spatial, spatial_uri))
g.add((spatial_uri, RDF.type, DCT.Location))
g.add((spatial_uri, LOCN.geometry,
Literal('POINT (67 89)', datatype=GSP.wktLiteral)))
p = RDFParser(profiles=['euro_dcat_ap'])
p.g = g
datasets = [d for d in p.datasets()]
extras = self._extras(datasets[0])
# NOTE: geomet returns floats for coordinates on WKT -> GeoJSON
eq_(extras['spatial'],
'{"type": "Point", "coordinates": [67.0, 89.0]}')
def test_spatial_wrong_geometries(self):
g = Graph()
dataset = URIRef('http://example.org/datasets/1')
g.add((dataset, RDF.type, DCAT.Dataset))
spatial_uri = URIRef('http://geonames/Newark')
g.add((dataset, DCT.spatial, spatial_uri))
g.add((spatial_uri, RDF.type, DCT.Location))
g.add((spatial_uri, LOCN.geometry,
Literal('Not GeoJSON', datatype=GEOJSON_IMT)))
g.add((spatial_uri, LOCN.geometry,
Literal('Not WKT', datatype=GSP.wktLiteral)))
p = RDFParser(profiles=['euro_dcat_ap'])
p.g = g
datasets = [d for d in p.datasets()]
extras = self._extras(datasets[0])
assert_true('spatial' not in extras)