#coding:gbk
'''
Created on 2012-2-3
从文件中读取文本，并判断文本中形如“message0”、“message123”这样的消息有多少条是重复的
@author: Administrator
'''
import re
if __name__ == '__main__':
 pattern = u"(message((\d)+))"
 prog = re.compile(pattern)
 # read text from file
 f = open("1003.txt","r")
 text = unicode(f.read())
 f.close()
 result = prog.findall(text)
 message_map = dict()
 redupicate_count = 0
 for message in result:
  if message_map.has_key(message[0]) == True:
   print message[0], "is reduplicate"
   redupicate_count += 1
  else :
   message_map[message[0]] = 1;
 print "total reduplicate message is ", redupicate_count