merge change from master

.gitignore

@@ -162,4 +162,5 @@ pip-log.txt
 # Mac crap
 .DS_Store
 *.log
+test/tmp/*
 

jieba/__init__.py

@@ -1,7 +1,9 @@
 from __future__ import with_statement
 import re
+
 import math
-import os,sys
+import os
+import sys
 import pprint
 from . import finalseg
 import time
@@ -112,8 +114,10 @@ def require_initialized(fn):
         else:
             initialize(DICTIONARY)
             return fn(*args, **kwargs)
+
     return wrapped
 
+
 def __cut_all(sentence):
     dag = get_DAG(sentence)
     old_j = -1
@@ -212,7 +216,8 @@ def cut(sentence,cut_all=False):
         except UnicodeDecodeError:
             sentence = sentence.decode('gbk','ignore')
 
-    re_han, re_skip = re.compile("([\u4E00-\u9FA5a-zA-Z0-9+#&\._]+)"), re.compile("(\s+)")
+
+    re_han, re_skip = re.compile("([\u4E00-\u9FA5a-zA-Z0-9+#&\._]+)"), re.compile("(\r\n|\s)")
 
     if cut_all:
         re_han, re_skip = re.compile("([\u4E00-\u9FA5]+)"), re.compile("[^a-zA-Z0-9+#\n]")

jieba/analyse/__init__.py

@@ -1,6 +1,11 @@
 import jieba
 import os
 
+try:
+	from analyzer import ChineseAnalyzer
+except ImportError:
+	pass
+
 _curpath=os.path.normpath( os.path.join( os.getcwd(), os.path.dirname(__file__) )  )
 f_name = os.path.join(_curpath,"idf.txt")
 content = open(f_name,'rb').read().decode('utf-8')

jieba/finalseg/__init__.py

@@ -59,7 +59,7 @@ def cut(sentence):
         except:
             sentence = sentence.decode('gbk','ignore')
 
-    re_han, re_skip = re.compile("([\u4E00-\u9FA5]+)"), re.compile("([\.0-9]+|[a-zA-Z0-9]+)")
+    re_han, re_skip = re.compile("([\u4E00-\u9FA5]+)"), re.compile("(\d+\.\d+|[a-zA-Z0-9]+)")
 
     blocks = re_han.split(sentence)
     for blk in blocks:

jieba/posseg/__init__.py

@@ -135,7 +135,7 @@ def __cut_internal(sentence):
         except:
             sentence = sentence.decode('gbk','ignore')
 
-    re_han, re_skip = re.compile("([\u4E00-\u9FA5a-zA-Z0-9+#&\._]+)"), re.compile("(\s+)")
+    re_han, re_skip = re.compile("([\u4E00-\u9FA5a-zA-Z0-9+#&\._]+)"), re.compile("(\r\n|\s)")
     re_eng,re_num = re.compile("[a-zA-Z0-9]+"), re.compile("[\.0-9]+")
 
     blocks = re_han.split(sentence)

test/test.py

@@ -96,4 +96,4 @@ if __name__ == "__main__":
     cuttest('枪杆子中出政权')
     cuttest('张三风同学走上了不归路')
     cuttest('阿Q腰间挂着BB机手里拿着大哥大，说：我一般吃饭不AA制的。')
-    cuttest('在1号店能买到小S和大S八卦的书。')
+    cuttest('在1号店能买到小S和大S八卦的书，还有3D电视。')

test/test_whoosh.py

@@ -1,5 +1,5 @@
 # -*- coding: UTF-8 -*-
-import sys
+import sys,os
 sys.path.append("../")
 from whoosh.index import create_in,open_dir
 from whoosh.fields import *
@@ -10,6 +10,9 @@ from jieba.analyse.analyzer import ChineseAnalyzer
 analyzer = ChineseAnalyzer()
 
 schema = Schema(title=TEXT(stored=True), path=ID(stored=True), content=TEXT(stored=True, analyzer=analyzer))
+if not os.path.exists("tmp"):
+    os.mkdir("tmp")
+
 ix = create_in("tmp", schema) # for create new index
 #ix = open_dir("tmp", schema=schema) # for read only
 writer = ix.writer()

test/test_whoosh_flie.py

@@ -1,5 +1,6 @@
 # -*- coding: UTF-8 -*-
 import sys
+import os
 sys.path.append("../")
 from whoosh.index import create_in
 from whoosh.fields import *
@@ -10,6 +11,8 @@ from jieba.analyse import ChineseAnalyzer
 analyzer = ChineseAnalyzer()
 
 schema = Schema(title=TEXT(stored=True), path=ID(stored=True), content=TEXT(stored=True, analyzer=analyzer))
+if not os.path.exists("tmp"):
+    os.mkdir("tmp")
 ix = create_in("tmp", schema)
 writer = ix.writer()
 

test/test_whoosh_flie_read.py

@@ -0,0 +1,27 @@
+# -*- coding: UTF-8 -*-
+import sys
+import os
+sys.path.append("../")
+from whoosh.index import create_in,open_dir
+from whoosh.fields import *
+from whoosh.qparser import QueryParser
+
+from jieba.analyse import ChineseAnalyzer 
+
+analyzer = ChineseAnalyzer()
+
+schema = Schema(title=TEXT(stored=True), path=ID(stored=True), content=TEXT(stored=True, analyzer=analyzer))
+if not os.path.exists("tmp"):
+    os.mkdir("tmp")
+ix = open_dir("tmp")
+
+searcher = ix.searcher()
+parser = QueryParser("content", schema=ix.schema)
+
+for keyword in (u"水果小姐",u"你",u"first",u"中文",u"交换机",u"交换",u"少林",u"乔峰"):
+    print "result of ",keyword
+    q = parser.parse(keyword)
+    results = searcher.search(q)
+    for hit in results:  
+        print hit.highlights("content")
+    print "="*10