def test_download_url_over_access_url(self):
node = BNode()
g = Graph()
access_url = faker.uri()
g.add((node, RDF.type, DCAT.Distribution))
g.add((node, DCT.title, Literal(faker.sentence())))
g.add((node, DCAT.accessURL, Literal(access_url)))
resource = resource_from_rdf(g)
resource.validate()
assert resource.url == access_url
download_url = faker.uri()
g.add((node, DCAT.downloadURL, Literal(download_url)))
resource = resource_from_rdf(g)
resource.validate()
assert resource.url == download_url
def test_resource_title_ignore_dynamic_url(self):
node = BNode()
g = Graph()
url = 'https://www.somewhere.com/endpoint.json?param=value'
g.set((node, RDF.type, DCAT.Distribution))
g.set((node, DCAT.downloadURL, URIRef(url)))
resource = resource_from_rdf(g)
resource.validate()
assert resource.title == 'Nameless resource'
def test_resource_generic_title(self):
node = BNode()
g = Graph()
url = 'https://www.somewhere.com/no-extension/'
g.set((node, RDF.type, DCAT.Distribution))
g.set((node, DCAT.downloadURL, URIRef(url)))
resource = resource_from_rdf(g)
resource.validate()
assert resource.title == 'Nameless resource'
def test_resource_title_from_url(self):
node = BNode()
g = Graph()
url = 'https://www.somewhere.com/somefile.csv'
g.set((node, RDF.type, DCAT.Distribution))
g.set((node, DCAT.downloadURL, URIRef(url)))
resource = resource_from_rdf(g)
resource.validate()
assert resource.title == 'somefile.csv'
def test_resource_title_from_format(self):
node = BNode()
g = Graph()
url = 'https://www.somewhere.com/no-extension/'
g.set((node, RDF.type, DCAT.Distribution))
g.set((node, DCAT.downloadURL, URIRef(url)))
g.set((node, DCT.term('format'), Literal('CSV')))
resource = resource_from_rdf(g)
resource.validate()
assert resource.title == 'csv resource'
def test_resource_html_description(self):
node = BNode()
g = Graph()
description = faker.paragraph()
html_description = '<div>{0}</div>'.format(description)
g.add((node, RDF.type, DCAT.Distribution))
g.add((node, DCT.title, Literal(faker.sentence())))
g.add((node, DCT.description, Literal(html_description)))
g.add((node, DCAT.downloadURL, Literal(faker.uri())))
resource = resource_from_rdf(g)
resource.validate()
assert resource.description == description
def test_can_extract_from_rdf_resource(self):
node = BNode()
g = Graph()
title = faker.sentence()
url = faker.uri()
g.add((node, RDF.type, DCAT.Distribution))
g.add((node, DCT.title, Literal(title)))
g.add((node, DCAT.downloadURL, Literal(url)))
resource = resource_from_rdf(g.resource(node))
resource.validate()
assert isinstance(resource, Resource)
assert resource.title == title
assert resource.url == url
def test_minimal_resource_fields(self):
node = BNode()
g = Graph()
title = faker.sentence()
url = faker.uri()
g.add((node, RDF.type, DCAT.Distribution))
g.add((node, DCT.title, Literal(title)))
g.add((node, DCAT.downloadURL, Literal(url)))
resource = resource_from_rdf(g)
resource.validate()
self.assertIsInstance(resource, Resource)
self.assertEqual(resource.title, title)
self.assertEqual(resource.url, url)
def test_match_existing_resource_by_url(self):
dataset = DatasetFactory(resources=ResourceFactory.build_batch(3))
existing_resource = dataset.resources[1]
node = BNode()
g = Graph()
new_title = faker.sentence()
g.add((node, RDF.type, DCAT.Distribution))
g.add((node, DCT.title, Literal(new_title)))
g.add((node, DCAT.downloadURL, Literal(existing_resource.url)))
resource = resource_from_rdf(g, dataset)
resource.validate()
assert isinstance(resource, Resource)
assert resource.title == new_title
assert resource.id == existing_resource.id
def test_all_resource_fields(self):
node = BNode()
g = Graph()
title = faker.sentence()
url = faker.uri()
description = faker.paragraph()
filesize = faker.pyint()
issued = faker.date_time_between(start_date='-60d', end_date='-30d')
modified = faker.past_datetime(start_date='-30d')
mime = faker.mime_type()
sha1 = faker.sha1()
g.add((node, RDF.type, DCAT.Distribution))
g.add((node, DCT.title, Literal(title)))
g.add((node, DCT.description, Literal(description)))
g.add((node, DCAT.downloadURL, Literal(url)))
g.add((node, DCT.issued, Literal(issued)))
g.add((node, DCT.modified, Literal(modified)))
g.add((node, DCAT.bytesSize, Literal(filesize)))
g.add((node, DCAT.mediaType, Literal(mime)))
g.add((node, DCT.term('format'), Literal('CSV')))
checksum = BNode()
g.add((node, SPDX.checksum, checksum))
g.add((checksum, RDF.type, SPDX.Checksum))
g.add((checksum, SPDX.algorithm, SPDX.checksumAlgorithm_sha1))
g.add((checksum, SPDX.checksumValue, Literal(sha1)))
resource = resource_from_rdf(g)
resource.validate()
assert isinstance(resource, Resource)
assert resource.title == title
assert resource.url == url
assert resource.description == description
assert resource.filesize == filesize
assert resource.mime == mime
assert isinstance(resource.checksum, Checksum)
assert resource.checksum.type == 'sha1'
assert resource.checksum.value == sha1
assert resource.published == issued
assert resource.modified == modified
assert resource.format == 'csv'