1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
|
From: CY Wang <a0953218488@gmail.com>
Date: Mon, 27 Aug 2018 17:05:46 +0800
Subject: Fix __init__ "-" symbol issue
MIME-Version: 1.0
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: 8bit
Applied-Upstream: https://github.com/fxsjy/jieba/commit/36a27302ce345a1866d125a9e59bd8611cf06813
Solving "-" symbol can't be analyze issue .
For example,
In keyword , chap-EX喬沛詩 , SK-II ...etc
the present version will show "chap", "-", "EX喬沛詩" , "SK", "-", "II"
After the modify,
The new version will show "chap-EX","喬沛詩" , "SK-II"
ps: I have used the jieba.load_userdict() , and added "chap-EX" , "喬沛詩", "SK-II" in the userdict.txt.
---
jieba/__init__.py | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/jieba/__init__.py b/jieba/__init__.py
index 62183a9..45dc908 100644
--- a/jieba/__init__.py
+++ b/jieba/__init__.py
@@ -40,7 +40,10 @@ re_eng = re.compile('[a-zA-Z0-9]', re.U)
# \u4E00-\u9FD5a-zA-Z0-9+#&\._ : All non-space characters. Will be handled with re_han
# \r\n|\s : whitespace characters. Will not be handled.
-re_han_default = re.compile("([\u4E00-\u9FD5a-zA-Z0-9+#&\._%]+)", re.U)
+# re_han_default = re.compile("([\u4E00-\u9FD5a-zA-Z0-9+#&\._%]+)", re.U)
+# Adding "-" symbol in re_han_default
+re_han_default = re.compile("([\u4E00-\u9FD5a-zA-Z0-9+#&\._%\-]+)", re.U)
+
re_skip_default = re.compile("(\r\n|\s)", re.U)
re_han_cut_all = re.compile("([\u4E00-\u9FD5]+)", re.U)
re_skip_cut_all = re.compile("[^a-zA-Z0-9+#\n]", re.U)
|
