def test_filter_insignificant(self):
chunk = self.extractor._parse_sentence(self.sentence)
tags = [tag for word, tag in chunk.leaves()]
assert_true('DT' in tags)
filtered = filter_insignificant(chunk.leaves())
tags = [tag for word, tag in filtered]
assert_true("DT" not in tags)
def extract(self, text):
'''Return a list of noun phrases (strings) for body of text.'''
sentences = nltk.tokenize.sent_tokenize(text)
noun_phrases = []
for sentence in sentences:
parsed = self._parse_sentence(sentence)
# Get the string representation of each subtree that is a
# noun phrase tree
phrases = [_normalize_tags(filter_insignificant(each,
self.INSIGNIFICANT_SUFFIXES)) for each in parsed
if isinstance(each, nltk.tree.Tree) and each.label()
== 'NP' and len(filter_insignificant(each)) >= 1
and _is_match(each, cfg=self.CFG)]
nps = [tree2str(phrase) for phrase in phrases]
noun_phrases.extend(nps)
return noun_phrases
