def test_sparql_query(self):
results = sparqlquery(u'http://dbpedia.org/sparql',
u'''SELECT DISTINCT ?uri ?designer
WHERE {
?uri rdf:type <http://dbpedia.org/ontology/ProgrammingLanguage> ;
rdfs:label ?label ;
dbpedia-owl:designer ?designer .
FILTER(regex(?label, "^Python"))
}''')
self.assertEqual(results, [['http://dbpedia.org/resource/Python_(programming_language)', 'http://dbpedia.org/resource/Guido_van_Rossum'],
['http://dbpedia.org/resource/Python_for_S60', 'http://dbpedia.org/resource/Guido_van_Rossum']])
def test_sparql_no_autocast(self):
alignset = sparqlquery('http://dbpedia.inria.fr/sparql',
'prefix db-owl: <http://dbpedia.org/ontology/>'
'prefix db-prop: <http://fr.dbpedia.org/property/>'
'select ?ville, ?name, ?long, ?lat where {'
' ?ville db-owl:country <http://fr.dbpedia.org/resource/France> .'
' ?ville rdf:type db-owl:PopulatedPlace .'
' ?ville db-owl:populationTotal ?population .'
' ?ville foaf:name ?name .'
' ?ville db-prop:longitude ?long .'
' ?ville db-prop:latitude ?lat .'
' FILTER (?population > 1000)'
'} LIMIT 100', indexes=[0, 1, (2, 3)], autocast_data=False)
self.assertEqual(len(alignset), 100)
self.assertFalse(isinstance(alignset[0][2][0], float))
def __call__(self, named_entities):
filtered_named_entities = []
seen_uris = {}
for uri, p, t in named_entities:
if uri in seen_uris:
if seen_uris[uri]:
filtered_named_entities.append((uri, p, t))
else:
results = sparqlquery(self.endpoint, self.query % {'uri': uri})
types = set([r[0] for r in results])
if not len(types.intersection(self.accepted_types)):
seen_uris[uri] = False
else:
seen_uris[uri] = True
filtered_named_entities.append((uri, p, t))
return filtered_named_entities
def query_word(self, word):
""" Query a word for a Named Entities Recognition process
"""
return [r[0] for r in sparqlquery(self.endpoint, self.query % {'word': word})]
