Created
September 6, 2014 06:30
-
-
Save xingkaixin/77c69d0be06e1dac51d9 to your computer and use it in GitHub Desktop.
Chinese words segementation uitlities
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding:utf-8 -*- | |
import jieba | |
import sys | |
reload(sys) | |
sys.setdefaultencoding( "utf-8" ) | |
def trim(mystr): | |
x='' | |
for str in mystr: | |
if str==' ': | |
continue | |
else : | |
x=x+str | |
return x | |
text = ''' | |
Dear Kevin, | |
请提供一下科目的清单 223023 translation date 2013011 | |
''' | |
default_mode = jieba.cut(text) | |
#ull_mode = jieba.cut(text,cut_all=True) | |
#search_mode = jieba.cut_for_search(text) | |
#print "精确模式:","/".join(default_mode) | |
#print "全模式:","/".join(full_mode) | |
#print "搜索引擎模式:","/".join(search_mode) | |
words = [] | |
for n in default_mode: | |
word = trim(n).replace('\n','').replace('\t','') | |
if len(word) < 1: | |
pass | |
else: | |
words.append(word) | |
print words | |
for word in words: | |
print word.decode('utf-8') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment