比较两文件的相似度（比较中文），文件中文,#!/usr/bin/e

比较两文件的相似度（比较中文），文件中文,#!/usr/bin/e

#!/usr/bin/env python# -*- coding: utf-8 -*import refrom math import sqrtdef file_reader(filename,filename2):    file_words = {}    ignore_list = [u'的',u'了',u'和',u'呢',u'啊',u'哦',u'恩',u'嗯',u'吧'];    #ignore_list = [];    accepted_chars = re.compile(ur"[\\u4E00-\\u9FA5]+")    file_object = open(filename)    try:        all_the_text = file_object.read()        for s in all_the_text.decode('gb2312'):            if accepted_chars.match(s) and s not in ignore_list:                if s not in file_words.keys():                    file_words[s] = [1,0]                else:                    file_words[s][0] += 1    finally:        file_object.close()    file_object2 = open(filename2)    try:        all_the_text = file_object2.read()        for s in all_the_text.decode('gb2312'):            if accepted_chars.match(s) and s not in ignore_list:                if s not in file_words.keys():                    file_words[s] = [0,1]                else:                    file_words[s][1] += 1    finally:        file_object2.close()    sum_2 = 0    sum_file1 = 0    sum_file2 = 0    for word in file_words.values():        sum_2 += word[0]*word[1]        sum_file1 += word[0]**2        sum_file2 += word[1]**2    rate = sum_2/(sqrt(sum_file1*sum_file2))    print 'rate: '    print ratefile_reader('thefile.txt','thefile2.txt')#该片段来自于http://byrx.net