third_codes/jieba
1
0
Fork 0
mirror of https://github.com/fxsjy/jieba.git synced 2025-07-10 00:01:33 +08:00
Code Issues Packages Projects Releases Wiki Activity

support decimal point

Browse Source
This commit is contained in:
Sun Junyi 2013-04-08 09:40:32 +08:00
parent a383f035ba
commit 72fff6c8e2
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
jieba/posseg/__init__.py
View File

@ -65,7 +65,7 @@ def __cut(sentence):
yield pair(sentence[next:], pos_list[next][1] ) yield pair(sentence[next:], pos_list[next][1] )
def __cut_detail(sentence): def __cut_detail(sentence):
re_han, re_skip = re.compile(ur"([\u4E00-\u9FA5]+)"), re.compile(ur"([a-zA-Z0-9]+)") re_han, re_skip = re.compile(ur"([\u4E00-\u9FA5]+)"), re.compile(ur"([\.0-9]+|[a-zA-Z0-9]+)")
re_eng,re_num = re.compile(ur"[a-zA-Z+#]+"), re.compile(ur"[0-9]+") re_eng,re_num = re.compile(ur"[a-zA-Z+#]+"), re.compile(ur"[0-9]+")
blocks = re_han.split(sentence) blocks = re_han.split(sentence)
for blk in blocks: for blk in blocks: