From 45591bb9ab484f8e8fb1e047f0b17f4d538ab1ee Mon Sep 17 00:00:00 2001
From: fxsjy <ccnusjy@gmail.com>
Date: Fri, 12 Apr 2013 21:53:03 +0800
Subject: [PATCH 1/3] support flag '_'; ignore white space

---
 jieba/__init__.py        |  5 +++--
 jieba/posseg/__init__.py |  2 +-
 test/test_userdict.py    | 10 ++++++++++
 test/userdict.txt        |  6 ++++--
 4 files changed, 18 insertions(+), 5 deletions(-)

diff --git a/jieba/__init__.py b/jieba/__init__.py
index 9aaccd7..faf52a4 100644
--- a/jieba/__init__.py
+++ b/jieba/__init__.py
@@ -153,7 +153,7 @@ def cut(sentence,cut_all=False):
 			sentence = sentence.decode('utf-8')
 		except:
 			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.compile(ur"(\s+)")
 	if cut_all:
 		re_han, re_skip = re.compile(ur"([\u4E00-\u9FA5]+)"), re.compile(ur"[^a-zA-Z0-9+#\n]")
 	blocks = re_han.split(sentence)
@@ -169,7 +169,8 @@ def cut(sentence,cut_all=False):
 			tmp = re_skip.split(blk)
 			for x in tmp:
 				if re_skip.match(x):
-					yield x
+					if x!=' ':
+						yield x
 				else:
 					for xx in x:
 						yield xx
diff --git a/jieba/posseg/__init__.py b/jieba/posseg/__init__.py
index 09df9e4..48b0488 100644
--- a/jieba/posseg/__init__.py
+++ b/jieba/posseg/__init__.py
@@ -125,7 +125,7 @@ def cut(sentence):
 			sentence = sentence.decode('utf-8')
 		except:
 			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.compile(ur"(\s+)")
 	re_eng,re_num = re.compile(ur"[a-zA-Z0-9]+"), re.compile(ur"[\.0-9]+")
 	blocks = re_han.split(sentence)
 	for blk in blocks:
diff --git a/test/test_userdict.py b/test/test_userdict.py
index aac4730..4b62d42 100644
--- a/test/test_userdict.py
+++ b/test/test_userdict.py
@@ -14,3 +14,13 @@ result = pseg.cut(test_sent)
 
 for w in result:
 	print w.word, "/", w.flag, ", ",  
+
+print "\n========"
+
+terms = jieba.cut('easy_install is great')
+for t in terms:
+    print t
+print '-------------------------'
+terms = jieba.cut('python 的正则表达式是好用的')
+for t in terms:
+    print t
diff --git a/test/userdict.txt b/test/userdict.txt
index 56e1f3d..4632566 100644
--- a/test/userdict.txt
+++ b/test/userdict.txt
@@ -1,3 +1,5 @@
-云计算 5
+云计算 5
 李小福 2 nr
-创新办 3 i
\ No newline at end of file
+创新办 3 i
+easy_install 3 eng
+好用 300
\ No newline at end of file

From 012fddf13f69a1546747e5c5f345a7bd29150841 Mon Sep 17 00:00:00 2001
From: Sun Junyi <ccnusjy@gmail.com>
Date: Fri, 12 Apr 2013 22:37:53 +0800
Subject: [PATCH 2/3] ignore white space

---
 jieba/__init__.py        | 2 +-
 jieba/posseg/__init__.py | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/jieba/__init__.py b/jieba/__init__.py
index faf52a4..5a17d5b 100644
--- a/jieba/__init__.py
+++ b/jieba/__init__.py
@@ -169,7 +169,7 @@ def cut(sentence,cut_all=False):
 			tmp = re_skip.split(blk)
 			for x in tmp:
 				if re_skip.match(x):
-					if x!=' ':
+					if x.strip(' ')!='':
 						yield x
 				else:
 					for xx in x:
diff --git a/jieba/posseg/__init__.py b/jieba/posseg/__init__.py
index 48b0488..fbc791e 100644
--- a/jieba/posseg/__init__.py
+++ b/jieba/posseg/__init__.py
@@ -136,7 +136,8 @@ def cut(sentence):
 			tmp = re_skip.split(blk)
 			for x in tmp:
 				if re_skip.match(x):
-					yield pair(x,'')
+					if x.strip(' ')!='':
+						yield pair(x,'')
 				else:
 					for xx in x:
 						if re_num.match(xx):

From 8d89e8afda4bd1d547f5bf6202c09fe6c500658b Mon Sep 17 00:00:00 2001
From: Sun Junyi <ccnusjy@gmail.com>
Date: Fri, 19 Apr 2013 10:02:33 +0800
Subject: [PATCH 3/3] =?UTF-8?q?handle=20=E7=9A=84?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 jieba/dict.txt   | 5 +++--
 test/test.py     | 3 ++-
 test/test_pos.py | 3 ++-
 3 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/jieba/dict.txt b/jieba/dict.txt
index f4b81ef..3fbcb4a 100644
--- a/jieba/dict.txt
+++ b/jieba/dict.txt
@@ -245161,10 +245161,9 @@
 皂隶 96 n
 皂靴 10 n
 皂鞋 3 n
-的 3188252 uj
+的 318825 uj
 的一确二 3 l
 的士高 3 n
-的歌者 3 n
 的的确确 64 d
 的确 2135 d
 的确如此 31 l
@@ -245174,6 +245173,8 @@
 的里雅斯特 23 ns
 的里雅斯特市 3 ns
 的黎波里 62 ns
+的哥 63 n
+的士 20 n
 皆 7511 d
 皆佳 3 nrt
 皆准 3 i
diff --git a/test/test.py b/test/test.py
index ea8595f..86ade7d 100644
--- a/test/test.py
+++ b/test/test.py
@@ -93,4 +93,5 @@ if __name__ == "__main__":
 	cuttest('我是中华人民共和国公民;我爸爸是共和党党员; 地铁和平门站')
 	cuttest('张晓梅去人民医院做了个B超然后去买了件T恤')
 	cuttest('AT&T是一件不错的公司，给你发offer了吗？')
-	cuttest('C++和c#是什么关系？11+122=133，是吗？PI=3.14159')
\ No newline at end of file
+	cuttest('C++和c#是什么关系？11+122=133，是吗？PI=3.14159')
+	cuttest('你认识那个和主席握手的的哥吗？他开一辆黑色的士。')
\ No newline at end of file
diff --git a/test/test_pos.py b/test/test_pos.py
index 5e2862f..7f6a7f3 100644
--- a/test/test_pos.py
+++ b/test/test_pos.py
@@ -93,4 +93,5 @@ if __name__ == "__main__":
 	cuttest('我是中华人民共和国公民;我爸爸是共和党党员; 地铁和平门站')
 	cuttest('张晓梅去人民医院做了个B超然后去买了件T恤')
 	cuttest('AT&T是一件不错的公司，给你发offer了吗？')
-	cuttest('C++和c#是什么关系？11+122=133，是吗？PI=3.14159')
\ No newline at end of file
+	cuttest('C++和c#是什么关系？11+122=133，是吗？PI=3.14159')
+	cuttest('你认识那个和主席握手的的哥吗？他开一辆黑色的士。')
\ No newline at end of file