#!/usr/bin/python
# -*- coding: utf-8 -*-

import re
import random

dictee_file = open("dictee-2005.txt", "r")

dictee_text = dictee_file.read()
dictee_genetic = dictee_text
# print(dictee_text)

dictee_text_clean = re.sub('\n+', ' ', dictee_text)
dictee_text_clean = re.sub(r'\(.+\)', '', dictee_text_clean)
# print(dictee_text_clean)

words = dictee_text_clean.split(' ')
# print(words)

clean_words = []
for word in words:
   clean_word = re.sub(r'[^\w\s]', '', word)
   if len(clean_word) :
      clean_words.append(clean_word)

# print(clean_words)

genetic_words = {}
for word in clean_words:
   # print(word)
   genetic_words[word] = []
   for c in word:
      # print(ord(c))
      genetic_words[word].append(ord(c))

print(genetic_words)

for g_word in genetic_words:
   # print(g_word)
   # print("len",len(genetic_words[g_word]))
   l = random.randint(0, len(genetic_words[g_word])-1)
   # print("l", l)
   genetic_words[g_word][l] = genetic_words[g_word][l]+1

print(genetic_words)


for g_word in genetic_words:
   print(g_word)
   word = ""
   for c in genetic_words[g_word]:
      print(c)
      word+=chr(c)
   print(word)
   dictee_genetic = dictee_genetic.replace(g_word, word)

print(dictee_genetic)


with open('export.txt', 'w') as f:
   f.write(dictee_genetic)