mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 04:08:09 +03:00
58 lines
1.7 KiB
Python
58 lines
1.7 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...symbols import NOUN, PROPN, PRON, VERB, AUX
|
|
|
|
|
|
def noun_chunks(obj):
|
|
doc = obj.doc
|
|
if not len(doc):
|
|
return
|
|
np_label = doc.vocab.strings.add('NP')
|
|
left_labels = ['det', 'fixed', 'neg'] #['nunmod', 'det', 'appos', 'fixed']
|
|
right_labels = ['flat', 'fixed', 'compound', 'neg']
|
|
stop_labels = ['punct']
|
|
np_left_deps = [doc.vocab.strings.add(label) for label in left_labels]
|
|
np_right_deps = [doc.vocab.strings.add(label) for label in right_labels]
|
|
stop_deps = [doc.vocab.strings.add(label) for label in stop_labels]
|
|
token = doc[0]
|
|
while token and token.i < len(doc):
|
|
if token.pos in [PROPN, NOUN, PRON]:
|
|
left, right = noun_bounds(doc, token, np_left_deps, np_right_deps, stop_deps)
|
|
yield left.i, right.i+1, np_label
|
|
token = right
|
|
token = next_token(token)
|
|
|
|
|
|
def is_verb_token(token):
|
|
return token.pos in [VERB, AUX]
|
|
|
|
|
|
def next_token(token):
|
|
try:
|
|
return token.nbor()
|
|
except:
|
|
return None
|
|
|
|
|
|
def noun_bounds(doc, root, np_left_deps, np_right_deps, stop_deps):
|
|
left_bound = root
|
|
for token in reversed(list(root.lefts)):
|
|
if token.dep in np_left_deps:
|
|
left_bound = token
|
|
right_bound = root
|
|
for token in root.rights:
|
|
if (token.dep in np_right_deps):
|
|
left, right = noun_bounds(doc, token, np_left_deps, np_right_deps, stop_deps)
|
|
if list(filter(lambda t: is_verb_token(t) or t.dep in stop_deps,
|
|
doc[left_bound.i: right.i])):
|
|
break
|
|
else:
|
|
right_bound = right
|
|
return left_bound, right_bound
|
|
|
|
|
|
SYNTAX_ITERATORS = {
|
|
'noun_chunks': noun_chunks
|
|
}
|