explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-02-26 08:30:48 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update __init__.py

Browse Source 
remove the empty string return from jieba.cut,this will cause the list of tokens cant be pushed assert error
This commit is contained in:
gispk47 2017-07-01 13:12:00 +08:00 committed by GitHub
parent f69ff15089
commit 669bd14213
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
spacy/zh/__init__.py
View File

@ -8,4 +8,5 @@ class Chinese(Language):
def make_doc(self, text): def make_doc(self, text):
import jieba import jieba
words = list(jieba.cut(text, cut_all=True)) words = list(jieba.cut(text, cut_all=True))
words=[x for x in words if x]
return Doc(self.vocab, words=words, spaces=[False]*len(words)) return Doc(self.vocab, words=words, spaces=[False]*len(words))