2017-05-08 13:54:36 +00:00
|
|
|
# coding: utf8
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
2016-11-02 18:57:38 +00:00
|
|
|
from ..language import Language
|
|
|
|
from ..tokens import Doc
|
2016-04-24 16:44:24 +00:00
|
|
|
|
|
|
|
|
|
|
|
class Chinese(Language):
|
2017-05-08 13:54:36 +00:00
|
|
|
lang = 'zh'
|
2016-05-05 09:39:12 +00:00
|
|
|
|
2016-11-02 18:57:38 +00:00
|
|
|
def make_doc(self, text):
|
2017-05-08 13:54:36 +00:00
|
|
|
try:
|
|
|
|
from jieba
|
|
|
|
except ImportError:
|
|
|
|
raise ImportError("The Chinese tokenizer requires the Jieba library: "
|
|
|
|
"https://github.com/fxsjy/jieba")
|
2016-11-02 18:57:38 +00:00
|
|
|
words = list(jieba.cut(text, cut_all=True))
|
|
|
|
return Doc(self.vocab, words=words, spaces=[False]*len(words))
|
2017-05-03 09:01:42 +00:00
|
|
|
|
|
|
|
|
2017-05-08 13:54:36 +00:00
|
|
|
__all__ = ['Chinese']
|