third_codes/jieba
1
0
Fork 0
mirror of https://github.com/fxsjy/jieba.git synced 2025-07-24 00:00:05 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix a bug of cxfree support

Browse Source
This commit is contained in:
fxsjy 2013-06-23 12:50:28 +08:00
parent a9f53e9c85
commit e1afafe353
2 changed files with 8 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
jieba/__init__.py
View File

@ -324,3 +324,8 @@ def set_dictionary(dictionary_path):
raise Exception("path does not exists:" + abs_path) raise Exception("path does not exists:" + abs_path)
DICTIONARY = abs_path DICTIONARY = abs_path
initialized = False initialized = False
def get_abs_path_dict():
_curpath=os.path.normpath( os.path.join( os.getcwd(), os.path.dirname(__file__) ) )
abs_path = os.path.join(_curpath,DICTIONARY)
return abs_path

6
jieba/posseg/__init__.py
View File

@ -17,14 +17,14 @@ def load_model(f_name):
return eval(open(prob_p_path,"rb").read()) return eval(open(prob_p_path,"rb").read())
else: else:
result = {} result = {}
for line in open(prob_p_path,"rb"): for line in open(f_name,"rb"):
line = line.strip() line = line.strip()
if line=="":continue if line=="":continue
word, _, tag = line.split(' ') word, _, tag = line.split(' ')
result[word.decode('utf-8')]=tag result[word.decode('utf-8')]=tag
return result return result
word_tag_tab = load_model("../dict.txt") word_tag_tab = load_model(jieba.get_abs_path_dict())
if jieba.user_word_tag_tab: if jieba.user_word_tag_tab:
word_tag_tab.update(jieba.user_word_tag_tab) word_tag_tab.update(jieba.user_word_tag_tab)
@ -142,7 +142,7 @@ def __cut_internal(sentence):
tmp = re_skip.split(blk) tmp = re_skip.split(blk)
for x in tmp: for x in tmp:
if re_skip.match(x): if re_skip.match(x):
yield pair(x,'') yield pair(x,'x')
else: else:
for xx in x: for xx in x:
if re_num.match(xx): if re_num.match(xx):