Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Reorganise Chinese language data

This commit is contained in:
ines 2017-05-08 15:54:36 +02:00
parent 7b86ee093a
commit a627d3e3b0
1 changed files with 10 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
spacy/zh/__init__.py
View File

@ -1,14 +1,21 @@
# coding: utf8
from __future__ import unicode_literals
from ..language import Language from ..language import Language
from ..tokens import Doc from ..tokens import Doc
class Chinese(Language): class Chinese(Language):
lang = u'zh' lang = 'zh'
def make_doc(self, text): def make_doc(self, text):
import jieba try:
from jieba
except ImportError:
raise ImportError("The Chinese tokenizer requires the Jieba library: "
"https://github.com/fxsjy/jieba")
words = list(jieba.cut(text, cut_all=True)) words = list(jieba.cut(text, cut_all=True))
return Doc(self.vocab, words=words, spaces=[False]*len(words)) return Doc(self.vocab, words=words, spaces=[False]*len(words))
EXPORT = Chinese __all__ = ['Chinese']