third_codes/jieba
1
0
Fork 0
mirror of https://github.com/fxsjy/jieba.git synced 2025-07-24 00:00:05 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add re.U flag to re variable.

Browse Source
This commit is contained in:
Richard Wong 2013-07-10 16:22:17 +08:00
parent fbfaac2eaa
commit 99d2492d67
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
jieba/__init__.py
View File

@ -212,9 +212,9 @@ def cut(sentence,cut_all=False):
sentence = sentence.decode('utf-8')
except UnicodeDecodeError:
sentence = sentence.decode('gbk','ignore')
re_han, re_skip = re.compile(ur"([\u4E00-\u9FA5a-zA-Z0-9+#&\._]+)"), re.compile(ur"(\s+)")
re_han, re_skip = re.compile(ur"([\u4E00-\u9FA5a-zA-Z0-9+#&\._]+)", re.U), re.compile(ur"(\s+)", re.U)
if cut_all:
re_han, re_skip = re.compile(ur"([\u4E00-\u9FA5]+)"), re.compile(ur"[^a-zA-Z0-9+#\n]")
re_han, re_skip = re.compile(ur"([\u4E00-\u9FA5]+)", re.U), re.compile(ur"[^a-zA-Z0-9+#\n]", re.U)
blocks = re_han.split(sentence)
cut_block = __cut_DAG
if cut_all: