def test_extpos():
sr1 = parser.SentRep(['record'])
print 'Unconstrained'
display_parses(parser.parse(sr1, thread_slot))
print 'NN'
ext_pos1 = parser.ExtPos()
ext_pos1.addTagConstraints(parser.VectorString(['NN']))
display_parses(parser.parse(sr1, ext_pos1, thread_slot))
print 'VB'
ext_pos2 = parser.ExtPos()
ext_pos2.addTagConstraints(parser.VectorString(['VB']))
display_parses(parser.parse(sr1, ext_pos2, thread_slot))
def test_multiword_extpos():
sr1 = parser.SentRep('British left waffles on Falklands .'.split())
print 'waffles = [anything]:'
display_parses(parser.parse(sr1, thread_slot))
if 1:
print 'waffles = VBZ/VBD/VB:'
ext_pos = parser.ExtPos()
ext_pos.addTagConstraints(parser.VectorString([]))
ext_pos.addTagConstraints(parser.VectorString([]))
ext_pos.addTagConstraints(parser.VectorString(['VBZ', 'VBD', 'VB']))
ext_pos.addTagConstraints(parser.VectorString([]))
ext_pos.addTagConstraints(parser.VectorString([]))
ext_pos.addTagConstraints(parser.VectorString([]))
display_parses(parser.parse(sr1, ext_pos, thread_slot))
print 'waffles = NNS:'
ext_pos = parser.ExtPos()
ext_pos.addTagConstraints(parser.VectorString([]))
ext_pos.addTagConstraints(parser.VectorString([]))
ext_pos.addTagConstraints(parser.VectorString(['NNS']))
ext_pos.addTagConstraints(parser.VectorString([]))
ext_pos.addTagConstraints(parser.VectorString([]))
ext_pos.addTagConstraints(parser.VectorString([]))
display_parses(parser.parse(sr1, ext_pos, thread_slot))
print 'waffles = NN/NNS:'
ext_pos = parser.ExtPos()
ext_pos.addTagConstraints(parser.VectorString([]))
ext_pos.addTagConstraints(parser.VectorString([]))
ext_pos.addTagConstraints(parser.VectorString(['NN', 'NNS']))
ext_pos.addTagConstraints(parser.VectorString([]))
ext_pos.addTagConstraints(parser.VectorString([]))
ext_pos.addTagConstraints(parser.VectorString([]))
display_parses(parser.parse(sr1, ext_pos, thread_slot))
def parse_tagged(self, tokens, possible_tags, rerank=True):
"""Parse some pre-tagged, pre-tokenized text. tokens is a
sequence of strings. possible_tags is map from token indices
to possible POS tags. Tokens without an entry in possible_tags
will be unconstrained by POS. If rerank is True, we will
rerank the n-best list."""
assert self._parser_model_loaded
ext_pos = parser.ExtPos()
for index in range(len(tokens)):
tags = possible_tags.get(index, [])
if isinstance(tags, basestring):
tags = [tags]
ext_pos.addTagConstraints(parser.VectorString(tags))
sentence = Sentence(tokens)
parses = parser.parse(sentence.sentrep, ext_pos,
self._parser_thread_slot)
nbest_list = NBestList(sentence, parses)
if rerank:
self.rerank(nbest_list)
return nbest_list
