From 72fff6c8e2e2cefea4e6f02b6cbd7e23ab800a27 Mon Sep 17 00:00:00 2001 From: Sun Junyi Date: Mon, 8 Apr 2013 09:40:32 +0800 Subject: [PATCH] support decimal point --- jieba/posseg/__init__.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/jieba/posseg/__init__.py b/jieba/posseg/__init__.py index affeac1..982c132 100644 --- a/jieba/posseg/__init__.py +++ b/jieba/posseg/__init__.py @@ -65,7 +65,7 @@ def __cut(sentence): yield pair(sentence[next:], pos_list[next][1] ) 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]+") blocks = re_han.split(sentence) for blk in blocks: