spaCy/spacy/zh/__init__.py

12 lines
276 B
Python
Raw Normal View History

2016-11-02 21:57:38 +03:00
from ..language import Language
from ..tokens import Doc
class Chinese(Language):
lang = u'zh'
2016-05-05 12:39:12 +03:00
2016-11-02 21:57:38 +03:00
def make_doc(self, text):
2016-11-03 01:49:19 +03:00
import jieba
2016-11-02 21:57:38 +03:00
words = list(jieba.cut(text, cut_all=True))
return Doc(self.vocab, words=words, spaces=[False]*len(words))