def fetch(self, entity_name):
u = self._get_access_url(entity_name)
requests_session = requests.session()
requests_session.mount('file://', LocalFileAdapter())
requests_session.mount('file:///', LocalFileAdapter())
r = requests_session.get(u,
headers=self.headers,
allow_redirects=True,
stream=True)
np = nanopub.Nanopublication()
if 'content-disposition' in r.headers:
d = r.headers['content-disposition']
fname = re.findall("filename=(.+)", d)
else:
fname = entity_name.split('/')[-1]
content_type = r.headers.get('content-type')
if self.file_types is not None:
for file_type in file_types:
np.assertion.add((entity_name, rdflib.RDF.type, file_type))
f = FileStorage(FileLikeFromIter(r.iter_content()),
fname,
content_type=content_type)
old_nanopubs = self.app.add_file(f, entity_name, np)
np.assertion.add(
(entity_name, self.app.NS.RDF.type, self.app.NS.pv.File))
for old_np, old_np_assertion in old_nanopubs:
np.pubinfo.add((np.assertion.identifier,
self.app.NS.prov.wasRevisionOf, old_np_assertion))
return np
def test_L102_S3_Hu_2007(self):
self.login(*self.create_user("*****@*****.**", "password"))
text = "Hello, World!"
b64text = b64encode(text)
nanopub = files['L102_S3_Hu_2007']
response = self.client.post("/pub",
data=nanopub,
content_type="application/ld+json",
follow_redirects=True)
self.assertEquals(response.status, '201 CREATED')
content = self.client.get(
"/about",
query_string={"uri": "http://example.com/testdatab64"},
follow_redirects=True)
self.assertEquals(content.mimetype, "text/plain")
self.assertEquals(content.data, text)
np = nanopub.Nanopublication()
np.assertion.parse(data=open('../setl/xml_ingest.setl.ttl'),
format="turtle")
setlmaker = autonomic.SETLMaker()
results = self.run_agent(setlmaker, nanopublication=np)
# confirm this is creating a SETL script for the XML file.
setlr = autonomic.SETLr()
for nanopub in results:
setlr_results = self.run_agent(setlr, nanopublication=nanopub)
def test_hasco_import(self):
np = nanopub.Nanopublication()
np.assertion.parse(data='''{
"@id": "http://example.com/testonto",
"@type" : "http://www.w3.org/2002/07/owl#Ontology",
"http://www.w3.org/2002/07/owl#imports":{"@id":"http://hadatac.org/ont/hasco/"}
}''',
format="json-ld")
agent = autonomic.OntologyImporter()
results = self.run_agent(agent, nanopublication=np)
self.assertEquals(len(results), 1)
self.assertTrue(results[0].resource(
URIRef('http://hadatac.org/ont/hasco/'))[RDF.type:OWL.Ontology])
def test_dc_terms_import(self):
np = nanopub.Nanopublication()
np.assertion.parse(data='''{
"@id": "http://example.com/testonto",
"@type" : "http://www.w3.org/2002/07/owl#Ontology",
"http://www.w3.org/2002/07/owl#imports":{"@id":"http://purl.org/dc/terms/"}
}''',
format="json-ld")
agent = autonomic.OntologyImporter()
results = self.run_agent(agent, nanopublication=np)
self.assertEquals(len(results), 1)
print results[0].serialize(format="trig")
self.assertTrue(results[0].resource(
URIRef('http://purl.org/dc/terms/created'))[RDF.type:RDF.Property])
def test_dc_terms_import(self):
np = nanopub.Nanopublication()
np.assertion.parse(data=str(
'''<http://example.com/testonto> a <http://www.w3.org/2002/07/owl#Ontology>;
<http://www.w3.org/2002/07/owl#imports> <http://purl.org/dc/terms/>.'''
),
format="turtle")
#print(np.serialize(format="trig"))
agent = autonomic.OntologyImporter()
results = self.run_agent(agent, nanopublication=np)
self.assertEquals(len(results), 1)
#print(results[0].serialize(format="trig"))
self.assertTrue(results[0].resource(
URIRef('http://purl.org/dc/terms/created'))[RDF.type:RDF.Property])
def test_prov_import(self):
np = nanopub.Nanopublication()
np.assertion.parse(data='''{
"@id": "http://example.com/testonto",
"@type" : "http://www.w3.org/2002/07/owl#Ontology",
"http://www.w3.org/2002/07/owl#imports":{"@id":"http://www.w3.org/ns/prov#"}
}''',
format="json-ld")
#print(np.serialize(format="trig"))
agent = autonomic.OntologyImporter()
results = self.run_agent(agent, nanopublication=np)
self.assertEquals(len(results), 1)
self.assertTrue(len(results[0]) > 0)
self.assertTrue(results[0].resource(
URIRef('http://www.w3.org/ns/prov#'))[RDF.type:OWL.Ontology])
def process(self, i, o):
document_count = float(self.document_count)
query = """select distinct ?concept (count(distinct ?othernode) as ?count) ?assertion where {
?node sio:hasPart [ a sio:Term; prov:specializationOf ?concept].
?othernode sio:hasPart [ a sio:Term; prov:specializationOf ?concept].
optional {
graph ?assertion {
?concept sio:InverseDocumentFrequency ?idf.
}
}
} group by ?concept ?assertion"""
for concept, count, assertion in self.app.db.query(query, initBindings=dict(node=i.identifier)):
idf = log10(old_div(document_count,count.value))
npub = nanopub.Nanopublication(store=o.graph.store)
if assertion is not None:
npub.pubinfo.add((npub.assertion.identifier, prov.wasRevisionOf, assertion))
npub.assertion.add((concept, sio.InverseDocumentFrequency, Literal(idf)))
