mirror of https://github.com/explosion/spaCy.git
make the code less cryptic
This commit is contained in:
parent
a06fca9fdf
commit
5bf2fd1f78
|
@ -32,9 +32,10 @@ def german_noun_chunks(doc):
|
||||||
np_deps = set(doc.vocab.strings[label] for label in labels)
|
np_deps = set(doc.vocab.strings[label] for label in labels)
|
||||||
close_app = doc.vocab.strings['nk']
|
close_app = doc.vocab.strings['nk']
|
||||||
|
|
||||||
i = 0
|
rbracket = 0
|
||||||
while i < len(doc):
|
for i, word in enumerate(doc):
|
||||||
word = doc[i]
|
if i < rbracket:
|
||||||
|
continue
|
||||||
if word.pos == NOUN and word.dep in np_deps:
|
if word.pos == NOUN and word.dep in np_deps:
|
||||||
rbracket = word.i+1
|
rbracket = word.i+1
|
||||||
# try to extend the span to the right
|
# try to extend the span to the right
|
||||||
|
@ -42,9 +43,6 @@ def german_noun_chunks(doc):
|
||||||
for rdep in doc[word.i].rights:
|
for rdep in doc[word.i].rights:
|
||||||
if rdep.pos == NOUN and rdep.dep == close_app:
|
if rdep.pos == NOUN and rdep.dep == close_app:
|
||||||
rbracket = rdep.i+1
|
rbracket = rdep.i+1
|
||||||
yield word.left_edge.i, rbracket, np_label
|
yield word.left_edge.i, rbracket, np_label
|
||||||
i = rbracket
|
|
||||||
continue
|
|
||||||
i += 1
|
|
||||||
|
|
||||||
CHUNKERS = {'en': english_noun_chunks, 'de': german_noun_chunks}
|
CHUNKERS = {'en': english_noun_chunks, 'de': german_noun_chunks}
|
||||||
|
|
Loading…
Reference in New Issue