explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-02-09 16:10:33 +03:00
Code Issues Packages Projects Releases Wiki Activity

fix unbound vars in es.syntax_iterators

Browse Source
This commit is contained in:
Feng Niu 2018-02-21 13:11:17 -08:00
parent a5981914a6
commit 8df75b229c
1 changed files with 7 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
spacy/lang/es/syntax_iterators.py
View File

@ -6,17 +6,17 @@ from ...symbols import NOUN, PROPN, PRON, VERB, AUX
def noun_chunks(obj): def noun_chunks(obj):
doc = obj.doc doc = obj.doc
np_label = doc.vocab.strings['NP'] np_label = doc.vocab.strings.add('NP')
left_labels = ['det', 'fixed', 'neg'] #['nunmod', 'det', 'appos', 'fixed'] left_labels = ['det', 'fixed', 'neg'] #['nunmod', 'det', 'appos', 'fixed']
right_labels = ['flat', 'fixed', 'compound', 'neg'] right_labels = ['flat', 'fixed', 'compound', 'neg']
stop_labels = ['punct'] stop_labels = ['punct']
np_left_deps = [doc.vocab.strings[label] for label in left_labels] np_left_deps = [doc.vocab.strings.add(label) for label in left_labels]
np_right_deps = [doc.vocab.strings[label] for label in right_labels] np_right_deps = [doc.vocab.strings.add(label) for label in right_labels]
stop_deps = [doc.vocab.strings[label] for label in stop_labels] stop_deps = [doc.vocab.strings.add(label) for label in stop_labels]
token = doc[0] token = doc[0]
while token and token.i < len(doc): while token and token.i < len(doc):
if token.pos in [PROPN, NOUN, PRON]: if token.pos in [PROPN, NOUN, PRON]:
left, right = noun_bounds(token) left, right = noun_bounds(token, np_left_deps, np_right_deps, stop_deps)
yield left.i, right.i+1, np_label yield left.i, right.i+1, np_label
token = right token = right
token = next_token(token) token = next_token(token)
@ -33,7 +33,7 @@ def next_token(token):
return None return None
def noun_bounds(root): def noun_bounds(root, np_left_deps, np_right_deps, stop_deps):
left_bound = root left_bound = root
for token in reversed(list(root.lefts)): for token in reversed(list(root.lefts)):
if token.dep in np_left_deps: if token.dep in np_left_deps:
@ -41,7 +41,7 @@ def noun_bounds(root):
right_bound = root right_bound = root
for token in root.rights: for token in root.rights:
if (token.dep in np_right_deps): if (token.dep in np_right_deps):
left, right = noun_bounds(token) left, right = noun_bounds(token, np_left_deps, np_right_deps, stop_deps)
if list(filter(lambda t: is_verb_token(t) or t.dep in stop_deps, if list(filter(lambda t: is_verb_token(t) or t.dep in stop_deps,
doc[left_bound.i: right.i])): doc[left_bound.i: right.i])):
break break