def test_parser_load_none(self):
parser = PGCParser()
pg_corpus = parser.parse("data/corpus-2.pgc", graph_loading=LOAD_NONE)
for graph_pair in pg_corpus:
for graph in graph_pair._graphs:
self.assertTrue(isinstance(graph, GraphStub))
for bank in graph_pair._banks:
self.assertEqual(bank.__class__, SparseGraphBank)
self.assertEqual(len(bank), 3)
def test_parser_load_none(self):
parser = PGCParser()
pg_corpus = parser.parse("data/corpus-2.pgc",
graph_loading=LOAD_NONE)
for graph_pair in pg_corpus:
for graph in graph_pair._graphs:
self.assertTrue(isinstance(graph, GraphStub))
for bank in graph_pair._banks:
self.assertEqual(bank.__class__, SparseGraphBank)
self.assertEqual(len(bank), 3)
def test_merge_2(self):
"""
merging a corpus with another corpus should change the number of
graphbanks
"""
parser = PGCParser()
pg_corpus2 = parser.parse("data/corpus-2.pgc")
self.pg_corpus.extend(pg_corpus2)
self.assertEqual(len(self.pg_corpus), 6)
tree = self.generator.generate(self.pg_corpus, outf=self.tmpfn,
pprint=True, abs_path=True)
gb_elem = tree.find("//graphbanks")
self.assertEqual(len(gb_elem), 4)
self.assertTrue(self._can_be_parsed(self.tmpfn))
def test_merge_2(self):
"""
merging a corpus with another corpus should change the number of
graphbanks
"""
parser = PGCParser()
pg_corpus2 = parser.parse("data/corpus-2.pgc")
self.pg_corpus.extend(pg_corpus2)
self.assertEqual(len(self.pg_corpus), 6)
tree = self.generator.generate(self.pg_corpus,
outf=self.tmpfn,
pprint=True,
abs_path=True)
gb_elem = tree.find("//graphbanks")
self.assertEqual(len(gb_elem), 4)
self.assertTrue(self._can_be_parsed(self.tmpfn))
def test_parser_node_pairs(self):
"""
check if all node_pair are correctly read
"""
parser = PGCParser()
pg_corpus = parser.parse("data/corpus-2.pgc")
true_align = [(Pair("4", "4"), "equals"), (Pair("8", "11"), "equals"),
(Pair("5", "5"), "equals"),
(Pair("11", "10"), "intersects"),
(Pair("19", "8"), "intersects"),
(Pair("1", "1"), "restates"), (Pair("0",
"0"), "restates")]
read_align = pg_corpus[1].alignments()
self.assertEqual(len(read_align), len(true_align))
for e in read_align:
true_align.remove(e)
self.assertFalse(true_align)
def test_parser_node_pairs(self):
"""
check if all node_pair are correctly read
"""
parser = PGCParser()
pg_corpus = parser.parse("data/corpus-2.pgc")
true_align = [ (Pair("4","4"), "equals"),
(Pair("8","11"), "equals"),
(Pair("5","5"), "equals"),
(Pair("11","10"), "intersects"),
(Pair("19","8"), "intersects"),
(Pair("1","1"), "restates"),
(Pair("0","0"), "restates") ]
read_align = pg_corpus[1].alignments()
self.assertEqual(len(read_align), len(true_align))
for e in read_align:
true_align.remove(e)
self.assertFalse(true_align)
def _can_be_parsed(self, corpus_filename):
parser = PGCParser()
corpus = parser.parse(corpus_filename)
return len(corpus)
def setUp(self):
parser = PGCParser()
self.pg_corpus = parser.parse("data/corpus-1.pgc")
self.generator = PGCGenerator()
self.tmpfn = tempfile.NamedTemporaryFile().name
def _can_be_parsed(self, corpus_filename):
parser = PGCParser()
corpus = parser.parse(corpus_filename)
return len(corpus)
def setUp(self):
parser = PGCParser()
self.pg_corpus = parser.parse("data/corpus-1.pgc")
self.generator = PGCGenerator()
self.tmpfn = tempfile.NamedTemporaryFile().name