support decimal point: example PI=3.141569 = > PI / = / 3.14159

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)

jieba/finalseg/__init__.py

@@ -59,7 +59,7 @@ def cut(sentence):
 			sentence = sentence.decode('utf-8')
 		except:
 			sentence = sentence.decode('gbk','ignore')
-	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]+)")
 	blocks = re_han.split(sentence)
 	for blk in blocks:
 		if re_han.match(blk):

test/test.py

@@ -93,4 +93,4 @@ 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？')
+	cuttest('C++和c#是什么关系？11+122=133，是吗？PI=3.14159')