Port over changes from #1168

2017-07-01 11:43:54 +02:00 · 2017-07-01 11:43:54 +02:00 · c91642efd5
parent e265e34e18
commit c91642efd5
1 changed files with 1 additions and 0 deletions
--- a/spacy/lang/zh/init.py
+++ b/spacy/lang/zh/init.py
@ -15,6 +15,7 @@ class Chinese(Language):
            raise ImportError("The Chinese tokenizer requires the Jieba library: "
                              "https://github.com/fxsjy/jieba")
        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))