def dump_as_rdf(g: Dataset, table_name: str) -> bool:
"""
Dump the contents of Graph g in RDF turtle
:param g: Dataset to dump
:param table_name: name of the base table
:return: success indicator
"""
# Propagate the mapped concepts up the tree
def add_to_ancestors(s: URIRef, vm: URIRef):
g.add((s, ISO['enumeratedConceptualDomain.hasMember'], vm))
for parent in g.objects(s, SKOS.broader):
add_to_ancestors(parent, vm)
if COMPUTE_MEMBERS and EXPLICIT_MEMBERS:
for subj, obj in g.subject_objects(SKOS.exactMatch):
add_to_ancestors(subj, obj)
# TODO: this gives us a list of all concepts in the scheme... useful?
for scheme, tc in g.subject_objects(SKOS.hasTopConcept):
for member in g.objects(
tc, ISO['enumeratedConceptualDomain.hasMember']):
g.add((scheme, ISO['enumeratedConceptualDomain.hasMember'],
member))
for name, ns in namespaces.items():
g.bind(name.lower(), ns)
outfile = os.path.join(DATA_DIR, table_name + '.ttl')
print(f"Saving output to {outfile}")
g.serialize(outfile, format='turtle')
print(f"{len(g)} triples written")
return True
class DatasetTestCase(unittest.TestCase):
store = 'default'
slow = True
tmppath = None
def setUp(self):
try:
self.graph = Dataset(store=self.store)
except ImportError:
raise SkipTest("Dependencies for store '%s' not available!" %
self.store)
if self.store == "SQLite":
_, self.tmppath = mkstemp(prefix='test',
dir='/tmp',
suffix='.sqlite')
elif self.store == "SPARQLUpdateStore":
root = "http://localhost:3030/ukpp/"
self.graph.open((root + "sparql", root + "update"))
else:
self.tmppath = mkdtemp()
if self.store != "SPARQLUpdateStore":
self.graph.open(self.tmppath, create=True)
self.michel = URIRef(u'urn:michel')
self.tarek = URIRef(u'urn:tarek')
self.bob = URIRef(u'urn:bob')
self.likes = URIRef(u'urn:likes')
self.hates = URIRef(u'urn:hates')
self.pizza = URIRef(u'urn:pizza')
self.cheese = URIRef(u'urn:cheese')
# Use regular URIs because SPARQL endpoints like Fuseki alter short names
self.c1 = URIRef(u'urn:context-1')
self.c2 = URIRef(u'urn:context-2')
# delete the graph for each test!
self.graph.remove((None, None, None))
for c in self.graph.contexts():
c.remove((None, None, None))
assert len(c) == 0
self.graph.remove_graph(c)
def tearDown(self):
self.graph.close()
if self.store == "SPARQLUpdateStore":
pass
else:
if os.path.isdir(self.tmppath):
shutil.rmtree(self.tmppath)
else:
os.remove(self.tmppath)
def testGraphAware(self):
if not self.graph.store.graph_aware: return
g = self.graph
g1 = g.graph(self.c1)
# Some SPARQL endpoint backends (e.g. TDB) do not consider
# empty named graphs
if self.store != "SPARQLUpdateStore":
# added graph exists
self.assertEquals(set(x.identifier for x in self.graph.contexts()),
set([self.c1, DATASET_DEFAULT_GRAPH_ID]))
# added graph is empty
self.assertEquals(len(g1), 0)
g1.add((self.tarek, self.likes, self.pizza))
# added graph still exists
self.assertEquals(set(x.identifier for x in self.graph.contexts()),
set([self.c1, DATASET_DEFAULT_GRAPH_ID]))
# added graph contains one triple
self.assertEquals(len(g1), 1)
g1.remove((self.tarek, self.likes, self.pizza))
# added graph is empty
self.assertEquals(len(g1), 0)
# Some SPARQL endpoint backends (e.g. TDB) do not consider
# empty named graphs
if self.store != "SPARQLUpdateStore":
# graph still exists, although empty
self.assertEquals(set(x.identifier for x in self.graph.contexts()),
set([self.c1, DATASET_DEFAULT_GRAPH_ID]))
g.remove_graph(self.c1)
# graph is gone
self.assertEquals(set(x.identifier for x in self.graph.contexts()),
set([DATASET_DEFAULT_GRAPH_ID]))
def testDefaultGraph(self):
# Something the default graph is read-only (e.g. TDB in union mode)
if self.store == "SPARQLUpdateStore":
print "Please make sure updating the default graph " \
"is supported by your SPARQL endpoint"
self.graph.add((self.tarek, self.likes, self.pizza))
self.assertEquals(len(self.graph), 1)
# only default exists
self.assertEquals(set(x.identifier for x in self.graph.contexts()),
set([DATASET_DEFAULT_GRAPH_ID]))
# removing default graph removes triples but not actual graph
self.graph.remove_graph(DATASET_DEFAULT_GRAPH_ID)
self.assertEquals(len(self.graph), 0)
# default still exists
self.assertEquals(set(x.identifier for x in self.graph.contexts()),
set([DATASET_DEFAULT_GRAPH_ID]))
def testNotUnion(self):
# Union depends on the SPARQL endpoint configuration
if self.store == "SPARQLUpdateStore":
print "Please make sure your SPARQL endpoint has not configured " \
"its default graph as the union of the named graphs"
g1 = self.graph.graph(self.c1)
g1.add((self.tarek, self.likes, self.pizza))
self.assertEqual(list(self.graph.objects(self.tarek, None)), [])
self.assertEqual(list(g1.objects(self.tarek, None)), [self.pizza])
class DatasetTestCase(unittest.TestCase):
store = 'default'
slow = True
tmppath = None
def setUp(self):
try:
self.graph = Dataset(store=self.store)
except ImportError:
raise SkipTest(
"Dependencies for store '%s' not available!" % self.store)
if self.store == "SQLite":
_, self.tmppath = mkstemp(
prefix='test', dir='/tmp', suffix='.sqlite')
else:
self.tmppath = mkdtemp()
self.graph.open(self.tmppath, create=True)
self.michel = URIRef(u'michel')
self.tarek = URIRef(u'tarek')
self.bob = URIRef(u'bob')
self.likes = URIRef(u'likes')
self.hates = URIRef(u'hates')
self.pizza = URIRef(u'pizza')
self.cheese = URIRef(u'cheese')
self.c1 = URIRef(u'context-1')
self.c2 = URIRef(u'context-2')
# delete the graph for each test!
self.graph.remove((None, None, None))
def tearDown(self):
self.graph.close()
if os.path.isdir(self.tmppath):
shutil.rmtree(self.tmppath)
else:
os.remove(self.tmppath)
def testGraphAware(self):
if not self.graph.store.graph_aware: return
g = self.graph
g1 = g.graph(self.c1)
# added graph exists
self.assertEquals(set(x.identifier for x in self.graph.contexts()),
set([self.c1, DATASET_DEFAULT_GRAPH_ID]))
# added graph is empty
self.assertEquals(len(g1), 0)
g1.add( (self.tarek, self.likes, self.pizza) )
# added graph still exists
self.assertEquals(set(x.identifier for x in self.graph.contexts()),
set([self.c1, DATASET_DEFAULT_GRAPH_ID]))
# added graph contains one triple
self.assertEquals(len(g1), 1)
g1.remove( (self.tarek, self.likes, self.pizza) )
# added graph is empty
self.assertEquals(len(g1), 0)
# graph still exists, although empty
self.assertEquals(set(x.identifier for x in self.graph.contexts()),
set([self.c1, DATASET_DEFAULT_GRAPH_ID]))
g.remove_graph(self.c1)
# graph is gone
self.assertEquals(set(x.identifier for x in self.graph.contexts()),
set([DATASET_DEFAULT_GRAPH_ID]))
def testDefaultGraph(self):
self.graph.add(( self.tarek, self.likes, self.pizza))
self.assertEquals(len(self.graph), 1)
# only default exists
self.assertEquals(set(x.identifier for x in self.graph.contexts()),
set([DATASET_DEFAULT_GRAPH_ID]))
# removing default graph removes triples but not actual graph
self.graph.remove_graph(DATASET_DEFAULT_GRAPH_ID)
self.assertEquals(len(self.graph), 0)
# default still exists
self.assertEquals(set(x.identifier for x in self.graph.contexts()),
set([DATASET_DEFAULT_GRAPH_ID]))
def testNotUnion(self):
g1 = self.graph.graph(self.c1)
g1.add((self.tarek, self.likes, self.pizza))
self.assertEqual(list(self.graph.objects(self.tarek, None)),
[])
self.assertEqual(list(g1.objects(self.tarek, None)), [self.pizza])
class DatasetTestCase(unittest.TestCase):
store = 'default'
slow = True
tmppath = None
def setUp(self):
try:
self.graph = Dataset(store=self.store)
except ImportError:
raise SkipTest(
"Dependencies for store '%s' not available!" % self.store)
if self.store == "SQLite":
_, self.tmppath = mkstemp(
prefix='test', dir='/tmp', suffix='.sqlite')
elif self.store == "SPARQLUpdateStore":
root = HOST + DB
self.graph.open((root + "sparql", root + "update"))
else:
self.tmppath = mkdtemp()
if self.store != "SPARQLUpdateStore":
self.graph.open(self.tmppath, create=True)
self.michel = URIRef(u'urn:michel')
self.tarek = URIRef(u'urn:tarek')
self.bob = URIRef(u'urn:bob')
self.likes = URIRef(u'urn:likes')
self.hates = URIRef(u'urn:hates')
self.pizza = URIRef(u'urn:pizza')
self.cheese = URIRef(u'urn:cheese')
# Use regular URIs because SPARQL endpoints like Fuseki alter short names
self.c1 = URIRef(u'urn:context-1')
self.c2 = URIRef(u'urn:context-2')
# delete the graph for each test!
self.graph.remove((None, None, None))
for c in self.graph.contexts():
c.remove((None, None, None))
assert len(c) == 0
self.graph.remove_graph(c)
def tearDown(self):
self.graph.close()
if self.store == "SPARQLUpdateStore":
pass
else:
if os.path.isdir(self.tmppath):
shutil.rmtree(self.tmppath)
else:
os.remove(self.tmppath)
def testGraphAware(self):
if not self.graph.store.graph_aware:
return
g = self.graph
g1 = g.graph(self.c1)
# Some SPARQL endpoint backends (e.g. TDB) do not consider
# empty named graphs
if self.store != "SPARQLUpdateStore":
# added graph exists
self.assertEqual(set(x.identifier for x in self.graph.contexts()),
set([self.c1, DATASET_DEFAULT_GRAPH_ID]))
# added graph is empty
self.assertEqual(len(g1), 0)
g1.add((self.tarek, self.likes, self.pizza))
# added graph still exists
self.assertEqual(set(x.identifier for x in self.graph.contexts()),
set([self.c1, DATASET_DEFAULT_GRAPH_ID]))
# added graph contains one triple
self.assertEqual(len(g1), 1)
g1.remove((self.tarek, self.likes, self.pizza))
# added graph is empty
self.assertEqual(len(g1), 0)
# Some SPARQL endpoint backends (e.g. TDB) do not consider
# empty named graphs
if self.store != "SPARQLUpdateStore":
# graph still exists, although empty
self.assertEqual(set(x.identifier for x in self.graph.contexts()),
set([self.c1, DATASET_DEFAULT_GRAPH_ID]))
g.remove_graph(self.c1)
# graph is gone
self.assertEqual(set(x.identifier for x in self.graph.contexts()),
set([DATASET_DEFAULT_GRAPH_ID]))
def testDefaultGraph(self):
# Something the default graph is read-only (e.g. TDB in union mode)
if self.store == "SPARQLUpdateStore":
print("Please make sure updating the default graph "
"is supported by your SPARQL endpoint")
self.graph.add((self.tarek, self.likes, self.pizza))
self.assertEqual(len(self.graph), 1)
# only default exists
self.assertEqual(set(x.identifier for x in self.graph.contexts()),
set([DATASET_DEFAULT_GRAPH_ID]))
# removing default graph removes triples but not actual graph
self.graph.remove_graph(DATASET_DEFAULT_GRAPH_ID)
self.assertEqual(len(self.graph), 0)
# default still exists
self.assertEqual(set(x.identifier for x in self.graph.contexts()),
set([DATASET_DEFAULT_GRAPH_ID]))
def testNotUnion(self):
# Union depends on the SPARQL endpoint configuration
if self.store == "SPARQLUpdateStore":
print("Please make sure your SPARQL endpoint has not configured "
"its default graph as the union of the named graphs")
g1 = self.graph.graph(self.c1)
g1.add((self.tarek, self.likes, self.pizza))
self.assertEqual(list(self.graph.objects(self.tarek, None)),
[])
self.assertEqual(list(g1.objects(self.tarek, None)), [self.pizza])
class DatasetTestCase(unittest.TestCase):
store = 'default'
slow = True
tmppath = None
def setUp(self):
try:
self.graph = Dataset(store=self.store)
except ImportError:
raise SkipTest("Dependencies for store '%s' not available!" %
self.store)
if self.store == "SQLite":
_, self.tmppath = mkstemp(prefix='test',
dir='/tmp',
suffix='.sqlite')
else:
self.tmppath = mkdtemp()
self.graph.open(self.tmppath, create=True)
self.michel = URIRef(u'michel')
self.tarek = URIRef(u'tarek')
self.bob = URIRef(u'bob')
self.likes = URIRef(u'likes')
self.hates = URIRef(u'hates')
self.pizza = URIRef(u'pizza')
self.cheese = URIRef(u'cheese')
self.c1 = URIRef(u'context-1')
self.c2 = URIRef(u'context-2')
# delete the graph for each test!
self.graph.remove((None, None, None))
def tearDown(self):
self.graph.close()
if os.path.isdir(self.tmppath):
shutil.rmtree(self.tmppath)
else:
os.remove(self.tmppath)
def testGraphAware(self):
if not self.graph.store.graph_aware: return
g = self.graph
g1 = g.graph(self.c1)
# added graph exists
self.assertEquals(set(x.identifier for x in self.graph.contexts()),
set([self.c1, DATASET_DEFAULT_GRAPH_ID]))
# added graph is empty
self.assertEquals(len(g1), 0)
g1.add((self.tarek, self.likes, self.pizza))
# added graph still exists
self.assertEquals(set(x.identifier for x in self.graph.contexts()),
set([self.c1, DATASET_DEFAULT_GRAPH_ID]))
# added graph contains one triple
self.assertEquals(len(g1), 1)
g1.remove((self.tarek, self.likes, self.pizza))
# added graph is empty
self.assertEquals(len(g1), 0)
# graph still exists, although empty
self.assertEquals(set(x.identifier for x in self.graph.contexts()),
set([self.c1, DATASET_DEFAULT_GRAPH_ID]))
g.remove_graph(self.c1)
# graph is gone
self.assertEquals(set(x.identifier for x in self.graph.contexts()),
set([DATASET_DEFAULT_GRAPH_ID]))
def testDefaultGraph(self):
self.graph.add((self.tarek, self.likes, self.pizza))
self.assertEquals(len(self.graph), 1)
# only default exists
self.assertEquals(set(x.identifier for x in self.graph.contexts()),
set([DATASET_DEFAULT_GRAPH_ID]))
# removing default graph removes triples but not actual graph
self.graph.remove_graph(DATASET_DEFAULT_GRAPH_ID)
self.assertEquals(len(self.graph), 0)
# default still exists
self.assertEquals(set(x.identifier for x in self.graph.contexts()),
set([DATASET_DEFAULT_GRAPH_ID]))
def testNotUnion(self):
g1 = self.graph.graph(self.c1)
g1.add((self.tarek, self.likes, self.pizza))
self.assertEqual(list(self.graph.objects(self.tarek, None)), [])
self.assertEqual(list(g1.objects(self.tarek, None)), [self.pizza])
class DatasetTestCase(unittest.TestCase):
store = "default"
slow = True
tmppath = None
def setUp(self):
try:
self.graph = Dataset(store=self.store)
except ImportError:
raise SkipTest("Dependencies for store '%s' not available!" %
self.store)
if self.store == "SQLite":
_, self.tmppath = mkstemp(prefix="test",
dir="/tmp",
suffix=".sqlite")
elif self.store == "SPARQLUpdateStore":
root = HOST + DB
self.graph.open((root + "sparql", root + "update"))
else:
self.tmppath = mkdtemp()
if self.store != "SPARQLUpdateStore":
self.graph.open(self.tmppath, create=True)
self.michel = URIRef("urn:michel")
self.tarek = URIRef("urn:tarek")
self.bob = URIRef("urn:bob")
self.likes = URIRef("urn:likes")
self.hates = URIRef("urn:hates")
self.pizza = URIRef("urn:pizza")
self.cheese = URIRef("urn:cheese")
# Use regular URIs because SPARQL endpoints like Fuseki alter short names
self.c1 = URIRef("urn:context-1")
self.c2 = URIRef("urn:context-2")
# delete the graph for each test!
self.graph.remove((None, None, None))
for c in self.graph.contexts():
c.remove((None, None, None))
assert len(c) == 0
self.graph.remove_graph(c)
def tearDown(self):
self.graph.close()
if self.store == "SPARQLUpdateStore":
pass
else:
if os.path.isdir(self.tmppath):
shutil.rmtree(self.tmppath)
else:
os.remove(self.tmppath)
def testGraphAware(self):
if not self.graph.store.graph_aware:
return
g = self.graph
g1 = g.graph(self.c1)
# Some SPARQL endpoint backends (e.g. TDB) do not consider
# empty named graphs
if self.store != "SPARQLUpdateStore":
# added graph exists
self.assertEqual(
set(x.identifier for x in self.graph.contexts()),
set([self.c1, DATASET_DEFAULT_GRAPH_ID]),
)
# added graph is empty
self.assertEqual(len(g1), 0)
g1.add((self.tarek, self.likes, self.pizza))
# added graph still exists
self.assertEqual(
set(x.identifier for x in self.graph.contexts()),
set([self.c1, DATASET_DEFAULT_GRAPH_ID]),
)
# added graph contains one triple
self.assertEqual(len(g1), 1)
g1.remove((self.tarek, self.likes, self.pizza))
# added graph is empty
self.assertEqual(len(g1), 0)
# Some SPARQL endpoint backends (e.g. TDB) do not consider
# empty named graphs
if self.store != "SPARQLUpdateStore":
# graph still exists, although empty
self.assertEqual(
set(x.identifier for x in self.graph.contexts()),
set([self.c1, DATASET_DEFAULT_GRAPH_ID]),
)
g.remove_graph(self.c1)
# graph is gone
self.assertEqual(
set(x.identifier for x in self.graph.contexts()),
set([DATASET_DEFAULT_GRAPH_ID]),
)
def testDefaultGraph(self):
# Something the default graph is read-only (e.g. TDB in union mode)
if self.store == "SPARQLUpdateStore":
print("Please make sure updating the default graph "
"is supported by your SPARQL endpoint")
self.graph.add((self.tarek, self.likes, self.pizza))
self.assertEqual(len(self.graph), 1)
# only default exists
self.assertEqual(
set(x.identifier for x in self.graph.contexts()),
set([DATASET_DEFAULT_GRAPH_ID]),
)
# removing default graph removes triples but not actual graph
self.graph.remove_graph(DATASET_DEFAULT_GRAPH_ID)
self.assertEqual(len(self.graph), 0)
# default still exists
self.assertEqual(
set(x.identifier for x in self.graph.contexts()),
set([DATASET_DEFAULT_GRAPH_ID]),
)
def testNotUnion(self):
# Union depends on the SPARQL endpoint configuration
if self.store == "SPARQLUpdateStore":
print("Please make sure your SPARQL endpoint has not configured "
"its default graph as the union of the named graphs")
g1 = self.graph.graph(self.c1)
g1.add((self.tarek, self.likes, self.pizza))
self.assertEqual(list(self.graph.objects(self.tarek, None)), [])
self.assertEqual(list(g1.objects(self.tarek, None)), [self.pizza])
def testIter(self):
"""PR 1382: adds __iter__ to Dataset"""
d = Dataset()
uri_a = URIRef("https://example.com/a")
uri_b = URIRef("https://example.com/b")
uri_c = URIRef("https://example.com/c")
uri_d = URIRef("https://example.com/d")
d.add_graph(URIRef("https://example.com/g1"))
d.add((uri_a, uri_b, uri_c, URIRef("https://example.com/g1")))
d.add((uri_a, uri_b, uri_c, URIRef("https://example.com/g1")
)) # pointless addition: duplicates above
d.add_graph(URIRef("https://example.com/g2"))
d.add((uri_a, uri_b, uri_c, URIRef("https://example.com/g2")))
d.add((uri_a, uri_b, uri_d,
URIRef("https://example.com/g1"))) # new, uri_d
# traditional iterator
i_trad = 0
for t in d.quads((None, None, None)):
i_trad += 1
# new Dataset.__iter__ iterator
i_new = 0
for t in d:
i_new += 1
self.assertEqual(i_new, i_trad) # both should be 3
