make the code less cryptic

This commit is contained in:
Wolfgang Seeker 2016-05-03 17:19:05 +02:00
parent a06fca9fdf
commit 5bf2fd1f78
1 changed files with 5 additions and 7 deletions

View File

@ -32,9 +32,10 @@ def german_noun_chunks(doc):
np_deps = set(doc.vocab.strings[label] for label in labels)
close_app = doc.vocab.strings['nk']
i = 0
while i < len(doc):
word = doc[i]
rbracket = 0
for i, word in enumerate(doc):
if i < rbracket:
continue
if word.pos == NOUN and word.dep in np_deps:
rbracket = word.i+1
# try to extend the span to the right
@ -42,9 +43,6 @@ def german_noun_chunks(doc):
for rdep in doc[word.i].rights:
if rdep.pos == NOUN and rdep.dep == close_app:
rbracket = rdep.i+1
yield word.left_edge.i, rbracket, np_label
i = rbracket
continue
i += 1
yield word.left_edge.i, rbracket, np_label
CHUNKERS = {'en': english_noun_chunks, 'de': german_noun_chunks}