class AggregatorDetailViewTest(TestCase):
def setUp(self):
self.client_login('admin')
self.aggregator = AggregatorFactory()
self.export_url = reverse('aggregator_export',
args=(self.aggregator.pk, ))
self.workflow_url = reverse('aggregator_workflow',
args=[
self.aggregator.pk,
])
def test_get(self):
response = self.client.get(self.aggregator.get_absolute_url())
self.assertContains(response, self.aggregator.name)
def test_contains_edit_link(self):
response = self.client.get(self.aggregator.get_absolute_url())
self.assertContains(response,
self.aggregator.get_absolute_url() + 'edit/')
def test_contains_archiveitems(self):
item1 = ArchiveItemFactory()
item2 = ArchiveItemFactory()
for item in (item1, item2):
AggregatorArchiveItem.objects.create(aggregator=self.aggregator,
archiveitem=item)
response = self.client.get(self.aggregator.get_absolute_url())
self.assertContains(response, item1.get_absolute_url())
self.assertContains(response, item2.get_absolute_url())
def test_contains_rule(self):
self.aggregator.silk_rule = 'tanto gentile e tanto onesta pare'
self.aggregator.save()
response = self.client.get(self.aggregator.get_absolute_url())
self.assertContains(response, self.aggregator.silk_rule)
def test_contains_schedulers(self):
response = self.client.get(self.aggregator.get_absolute_url())
self.assertContains(response, 'No scheduler found')
scheduler = AggregatorSchedulerFactory(object_id=self.aggregator.pk)
response = self.client.get(self.aggregator.get_absolute_url())
self.assertNotContains(response, 'No scheduler found')
self.assertContains(response, scheduler.get_absolute_url())
def test_contains_silk_link(self):
response = self.client.get(self.aggregator.get_absolute_url())
silk_url = 'http://{}:{}/workbench/'.format(
settings.SILK_EXTERNAL_HOST, settings.SILK_EXTERNAL_PORT)
self.assertContains(response, silk_url)
def test_can_download_silk_project_file(self):
self.client_login('admin')
response = self.client.get(self.aggregator.get_absolute_url())
self.assertContains(response, self.export_url + '?download')
response = self.client.get(self.export_url + '?download')
self.assertEqual(response['Content-Type'], 'text/xml; charset=utf-8')
self.assertTrue(response.has_header('Content-Disposition'))
self.assertNotEqual(response.content.strip(), '')
def test_can_run_workflow(self):
self.client_login('admin')
Scheduler.objects.all().delete()
response = self.client.get(self.aggregator.get_absolute_url())
self.assertContains(response, self.workflow_url)
response = self.client.post(self.workflow_url)
self.assertEqual(response.status_code, 302)
self.assertTrue(
response['Location'].startswith('http://testserver/s/task/'))
self.assertEqual(Scheduler.objects.count(), 1)
def test_can_view_silk_project_file_without_downloading(self):
self.client_login('admin')
response = self.client.get(self.export_url)
self.assertEqual(response['Content-Type'], 'text/xml; charset=utf-8')
self.assertFalse(response.has_header('Content-Disposition'))
self.assertNotEqual(response.content.strip(), '')
def test_silk_project_file_is_valid(self):
import xml.etree.ElementTree as ET
self.client_login('admin')
item1 = ArchiveItemFactory()
item2 = ArchiveItemFactory()
for item in (item1, item2):
AggregatorArchiveItem.objects.create(aggregator=self.aggregator,
archiveitem=item)
response = self.client.get(self.export_url)
tree = ET.fromstring(response.content)
self.assertIn((settings.TRIPLE_DATABASE['PREFIXES']['sdv1'], 'sd'),
[(x.get('namespace'), x.get('id'))
for x in tree.findall('.//Prefix')])
# check datasources
datasources = tree.findall('.//DataSource')
self.assertEqual(len(datasources), 3)
self.assertEqual(datasources[0].get('id'), 'master-graph')
mastergraph = datasources[0]
datasources = datasources[1:]
# check datasources endpoints
self.assertEqual(
mastergraph.find('Param[@name="host"]').get('value'),
settings.TRIPLE_DATABASE_MASTER['HOST'])
self.assertEqual([get_virtuoso_endpoint()] * 2, [
x.find('Param[@name="endpointURI"]').get("value")
for x in datasources
])
# check datasources graph names
self.assertEqual(
mastergraph.find('Param[@name="graph"]').get('value'),
settings.TRIPLE_DATABASE_MASTER["KWARGS"]["graph"])
self.assertEqual(
[item1.datagraph_mapped_name, item2.datagraph_mapped_name],
[x.find('Param[@name="graph"]').get("value") for x in datasources])
# check tasks
datasource_ids = [x.get('id') for x in datasources]
tasks = tree.findall('.//LinkingTask')
self.assertEqual(len(tasks), 2)
self.assertEqual(datasource_ids,
[x.find('.//Interlink').get('id') for x in tasks])
# check task parameters
for datasource_id, task in zip(datasource_ids, tasks):
self.assertEqual(
task.find('.//SourceDataset').get('dataSource'), datasource_id)
self.assertEqual(
task.find('.//TargetDataset').get('dataSource'),
'master-graph')
self.assertEqual(
task.find('.//SourceDataset').find('RestrictTo').text.strip(),
'?a rdf:type <{}> .'.format(self.aggregator.entity_type))
self.assertEqual(
task.find('.//TargetDataset').find('RestrictTo').text.strip(),
'b -> {}'.format(self.aggregator.vertex_selector))
self.assertIsNone(task.find('.//LinkageRule').text)
self.assertIsNone(task.find('.//Filter').text)
self.assertIsNone(task.find('.//Outputs').text)
self.assertIsNone(task.find('.//PositiveEntities').text)
self.assertIsNone(task.find('.//NegativeEntities').text)
self.assertIsNone(
task.find('.//Alignment/').find('{}Alignment'.format(
'{http://knowledgeweb.'
'semanticweb.org'
'/heterogeneity/alignment#}')).text)
class AggregatorDetailViewTest(TestCase):
def setUp(self):
self.client_login('admin')
self.aggregator = AggregatorFactory()
self.export_url = reverse(
'aggregator_export', args=(self.aggregator.pk, )
)
self.workflow_url = reverse(
'aggregator_workflow', args=[self.aggregator.pk, ])
def test_get(self):
response = self.client.get(self.aggregator.get_absolute_url())
self.assertContains(response, self.aggregator.name)
def test_contains_edit_link(self):
response = self.client.get(self.aggregator.get_absolute_url())
self.assertContains(
response, self.aggregator.get_absolute_url() + 'edit/'
)
def test_contains_archiveitems(self):
item1 = ArchiveItemFactory()
item2 = ArchiveItemFactory()
for item in (item1, item2):
AggregatorArchiveItem.objects.create(
aggregator=self.aggregator,
archiveitem=item
)
response = self.client.get(self.aggregator.get_absolute_url())
self.assertContains(response, item1.get_absolute_url())
self.assertContains(response, item2.get_absolute_url())
def test_contains_rule(self):
self.aggregator.silk_rule = 'tanto gentile e tanto onesta pare'
self.aggregator.save()
response = self.client.get(self.aggregator.get_absolute_url())
self.assertContains(response, self.aggregator.silk_rule)
def test_contains_schedulers(self):
response = self.client.get(self.aggregator.get_absolute_url())
self.assertContains(response, 'No scheduler found')
scheduler = AggregatorSchedulerFactory(object_id=self.aggregator.pk)
response = self.client.get(self.aggregator.get_absolute_url())
self.assertNotContains(response, 'No scheduler found')
self.assertContains(response, scheduler.get_absolute_url())
def test_contains_silk_link(self):
response = self.client.get(self.aggregator.get_absolute_url())
silk_url = 'http://{}:{}/workbench/'.format(
settings.SILK_EXTERNAL_HOST, settings.SILK_EXTERNAL_PORT
)
self.assertContains(response, silk_url)
def test_can_download_silk_project_file(self):
self.client_login('admin')
response = self.client.get(self.aggregator.get_absolute_url())
self.assertContains(response, self.export_url + '?download')
response = self.client.get(self.export_url + '?download')
self.assertEqual(response['Content-Type'], 'text/xml; charset=utf-8')
self.assertTrue(response.has_header('Content-Disposition'))
self.assertNotEqual(response.content.strip(), '')
def test_can_run_workflow(self):
self.client_login('admin')
Scheduler.objects.all().delete()
response = self.client.get(self.aggregator.get_absolute_url())
self.assertContains(response, self.workflow_url)
response = self.client.post(self.workflow_url)
self.assertEqual(response.status_code, 302)
self.assertTrue(
response['Location'].startswith('http://testserver/s/task/')
)
self.assertEqual(Scheduler.objects.count(), 1)
def test_can_view_silk_project_file_without_downloading(self):
self.client_login('admin')
response = self.client.get(self.export_url)
self.assertEqual(response['Content-Type'], 'text/xml; charset=utf-8')
self.assertFalse(response.has_header('Content-Disposition'))
self.assertNotEqual(response.content.strip(), '')
def test_silk_project_file_is_valid(self):
import xml.etree.ElementTree as ET
self.client_login('admin')
item1 = ArchiveItemFactory()
item2 = ArchiveItemFactory()
for item in (item1, item2):
AggregatorArchiveItem.objects.create(
aggregator=self.aggregator,
archiveitem=item
)
response = self.client.get(self.export_url)
tree = ET.fromstring(response.content)
self.assertIn(
(settings.TRIPLE_DATABASE['PREFIXES']['sdv1'], 'sd'),
[(x.get('namespace'), x.get('id'))
for x in tree.findall('.//Prefix')]
)
# check datasources
datasources = tree.findall('.//DataSource')
self.assertEqual(len(datasources), 3)
self.assertEqual(datasources[0].get('id'), 'master-graph')
mastergraph = datasources[0]
datasources = datasources[1:]
# check datasources endpoints
self.assertEqual(
mastergraph.find('Param[@name="host"]').get('value'),
settings.TRIPLE_DATABASE_MASTER['HOST']
)
self.assertEqual(
[get_virtuoso_endpoint()] * 2,
[x.find('Param[@name="endpointURI"]').get("value")
for x in datasources]
)
# check datasources graph names
self.assertEqual(
mastergraph.find('Param[@name="graph"]').get('value'),
settings.TRIPLE_DATABASE_MASTER["KWARGS"]["graph"]
)
self.assertEqual(
[item1.datagraph_mapped_name, item2.datagraph_mapped_name],
[x.find('Param[@name="graph"]').get("value")
for x in datasources]
)
# check tasks
datasource_ids = [x.get('id') for x in datasources]
tasks = tree.findall('.//LinkingTask')
self.assertEqual(len(tasks), 2)
self.assertEqual(
datasource_ids,
[x.find('.//Interlink').get('id') for x in tasks]
)
# check task parameters
for datasource_id, task in zip(datasource_ids, tasks):
self.assertEqual(
task.find('.//SourceDataset').get('dataSource'),
datasource_id
)
self.assertEqual(
task.find('.//TargetDataset').get('dataSource'),
'master-graph'
)
self.assertEqual(
task.find('.//SourceDataset').find('RestrictTo').text.strip(),
'?a rdf:type <{}> .'.format(self.aggregator.entity_type)
)
self.assertEqual(
task.find('.//TargetDataset').find('RestrictTo').text.strip(),
'b -> {}'.format(self.aggregator.vertex_selector)
)
self.assertIsNone(task.find('.//LinkageRule').text)
self.assertIsNone(task.find('.//Filter').text)
self.assertIsNone(task.find('.//Outputs').text)
self.assertIsNone(task.find('.//PositiveEntities').text)
self.assertIsNone(task.find('.//NegativeEntities').text)
self.assertIsNone(
task.find('.//Alignment/')
.find('{}Alignment'.format('{http://knowledgeweb.'
'semanticweb.org'
'/heterogeneity/alignment#}')
).text
)
class SilkRuleXMLTestCase(TestCase):
def setUp(self):
self.aggregator = AggregatorFactory()
def test_can_silk_rules_file_is_valid(self):
import xml.etree.ElementTree as ET
from django.template.loader import render_to_string
archive_item = ArchiveItemFactory()
AggregatorArchiveItem.objects.create(
aggregator=self.aggregator,
archiveitem=archive_item
)
self.aggregator.silk_rule = \
'<LinkageRule><smart data="now" /></LinkageRule>'
self.aggregator.save()
output_filename = 'a_really_cool_filename.thm'
context = {
'aggregator': self.aggregator,
'sd_prefix': settings.TRIPLE_DATABASE['PREFIXES']['sdv1'],
'sparql_endpoint': get_virtuoso_endpoint(),
'archive_item': archive_item,
'output_filename': output_filename,
'mastergraph_host': settings.TRIPLE_DATABASE_MASTER['HOST'],
'mastergraph_port':
settings.TRIPLE_DATABASE_MASTER['KWARGS']['rexpro_port'],
'mastergraph_graphname':
settings.TRIPLE_DATABASE_MASTER['KWARGS']['graph'],
'resource_namespace':
settings.TRIPLE_DATABASE_MASTER['PREFIXES']['sdres'],
}
tree = ET.fromstring(render_to_string(
'controller/aggregator/silk_rules.xml', context
))
self.assertIn(
(settings.TRIPLE_DATABASE['PREFIXES']['sdv1'], 'sd'),
[(x.get('namespace'), x.get('id'))
for x in tree.findall('.//Prefix')]
)
# check datasources
datasources_dom = tree.findall('.//DataSource')
self.assertEqual(len(datasources_dom), 2)
self.assertEqual(datasources_dom[0].get('id'), 'master-graph')
mastergraph, datasource = datasources_dom
# check datasource endpoints
self.assertEqual(
get_virtuoso_endpoint(),
datasource.find('Param[@name="endpointURI"]').get("value"),
)
# check datasources graph names
self.assertEqual(
mastergraph.find('Param[@name="graph"]').get('value'),
settings.TRIPLE_DATABASE_MASTER["KWARGS"]["graph"]
)
self.assertEqual(
archive_item.datagraph_mapped_name,
datasource.find('Param[@name="graph"]').get("value")
)
# check tasks
datasource_id = datasource.get('id')
rules = tree.findall('.//Interlink')
self.assertEqual(len(rules), 1)
self.assertEqual(datasource_id, rules[0].get('id'))
# check rules parameters
rule = rules[0]
self.assertEqual(
rule.find('.//SourceDataset').get('dataSource'),
datasource_id
)
self.assertEqual(
rule.find('.//TargetDataset').get('dataSource'),
'master-graph'
)
self.assertEqual(
ET.tostring(rule.find('.//LinkageRule')).strip(),
self.aggregator.silk_rule
)
self.assertEqual(
rule.find('.//SourceDataset').find('RestrictTo').text.strip(),
'?a rdf:type <{}> .'.format(self.aggregator.entity_type)
)
self.assertEqual(
rule.find('.//TargetDataset').find('RestrictTo').text.strip(),
'b -> {}'.format(self.aggregator.vertex_selector)
)
self.assertIsNone(rule.find('.//Filter').text)
output = rule.find('.//Outputs').find('Output')
self.assertEqual(output.get('type'), 'file')
self.assertEqual(output.findall('Param')[0].get('name'), 'file')
self.assertEqual(
output.findall('Param')[0].get('value'), output_filename)
self.assertEqual(output.findall('Param')[1].get('name'), 'format')
self.assertEqual(output.findall('Param')[1].get('value'), 'ntriples')
