def test_minimal(self):
dataset = DatasetFactory.build() # Does not have an URL
d = dataset_to_rdf(dataset)
g = d.graph
assert isinstance(d, RdfResource)
assert len(list(g.subjects(RDF.type, DCAT.Dataset))) is 1
assert g.value(d.identifier, RDF.type) == DCAT.Dataset
assert isinstance(d.identifier, BNode)
assert d.value(DCT.identifier) == Literal(dataset.id)
assert d.value(DCT.title) == Literal(dataset.title)
assert d.value(DCT.issued) == Literal(dataset.created_at)
assert d.value(DCT.modified) == Literal(dataset.last_modified)
def test_minimal(self):
dataset = DatasetFactory.build() # Does not have an URL
d = dataset_to_rdf(dataset)
g = d.graph
self.assertIsInstance(d, RdfResource)
self.assertEqual(len(list(g.subjects(RDF.type, DCAT.Dataset))), 1)
self.assertEqual(g.value(d.identifier, RDF.type), DCAT.Dataset)
self.assertIsInstance(d.identifier, BNode)
self.assertEqual(d.value(DCT.identifier), Literal(dataset.id))
self.assertEqual(d.value(DCT.title), Literal(dataset.title))
self.assertEqual(d.value(DCT.issued), Literal(dataset.created_at))
self.assertEqual(d.value(DCT.modified), Literal(dataset.last_modified))
def test_attach_does_not_duplicate(self):
attached_datasets = []
for i in range(2):
dataset = DatasetFactory.build()
dataset.extras['harvest:domain'] = 'test.org'
dataset.extras['harvest:remote_id'] = str(i)
dataset.last_modified = datetime.now()
dataset.save()
attached_datasets.append(dataset)
datasets = DatasetFactory.create_batch(3)
with NamedTemporaryFile() as csvfile:
writer = csv.DictWriter(csvfile,
fieldnames=['local', 'remote'],
delimiter=b';',
quotechar=b'"')
writer.writeheader()
for index, dataset in enumerate(datasets):
writer.writerow({
'local': str(dataset.id),
'remote': str(index)
})
csvfile.flush()
result = actions.attach('test.org', csvfile.name)
dbcount = Dataset.objects(**{
'extras__harvest:remote_id__exists': True
}).count()
self.assertEqual(result.success, len(datasets))
self.assertEqual(dbcount, result.success)
for index, dataset in enumerate(datasets):
dataset.reload()
self.assertEqual(dataset.extras['harvest:domain'], 'test.org')
self.assertEqual(dataset.extras['harvest:remote_id'], str(index))
def test_attach_does_not_duplicate(self):
attached_datasets = []
for i in range(2):
dataset = DatasetFactory.build()
dataset.extras['harvest:domain'] = 'test.org'
dataset.extras['harvest:remote_id'] = str(i)
dataset.last_modified = datetime.now()
dataset.save()
attached_datasets.append(dataset)
datasets = DatasetFactory.create_batch(3)
with NamedTemporaryFile() as csvfile:
writer = csv.DictWriter(csvfile,
fieldnames=['local', 'remote'],
delimiter=b';',
quotechar=b'"')
writer.writeheader()
for index, dataset in enumerate(datasets):
writer.writerow({
'local': str(dataset.id),
'remote': str(index)
})
csvfile.flush()
result = actions.attach('test.org', csvfile.name)
dbcount = Dataset.objects(**{
'extras__harvest:remote_id__exists': True
}).count()
assert result.success == len(datasets)
assert dbcount == result.success
for index, dataset in enumerate(datasets):
dataset.reload()
assert dataset.extras['harvest:domain'] == 'test.org'
assert dataset.extras['harvest:remote_id'] == str(index)
def process(self, item):
mock_process.send(self, item=item)
return DatasetFactory.build(title='dataset-{0}'.format(item.remote_id))
