汉字按照拼音排序

```
# -*- coding: utf-8 -*-

import os
import codecs
import math
import operator
import re
from xpinyin import Pinyin
pin = Pinyin()


patent_file = "in.txt"
corpus = {}
f = open(patent_file, 'r', encoding='utf-8')   
for line in f.readlines():
   match = re.match("(\d+):(.+)",line)
   if match == None:
      print(line)
   else:
      ID = match.group(1)
      content = str(line)
      corpus[ID] = content
f.close()

cmpDict = {}
f = open(patent_file, 'r', encoding='utf-8')   
for line in f.readlines():
   match = re.match("(\d+):.*(.)\[得像\]",line)
   if match == None:
      print("search 2",line)
   else:
      ID = match.group(1)
      cmp = match.group(2)
      cmpDict[ID] = pin.get_pinyin(cmp)
      #cmpDict[ID] = cmp.encode("GBK")             
f.close()

mylist = sorted(cmpDict.items(),key=lambda item:item[1])
print(mylist)
f = open("out.txt", 'w', encoding='utf-8')   
for ID,w in mylist:           
   f.write(str(corpus[ID]))
f.close()


```