make-cracking-dictionary.py

   1 import language_models
   2
   3 american = set(open('/usr/share/dict/american-english', 'r').readlines())
   4 british = set(open('/usr/share/dict/british-english', 'r').readlines())
   5 cracklib = set(open('/usr/share/dict/cracklib-small', 'r').readlines())
   6
   7 words = american | british | cracklib
   8
   9 # sanitised_words = set()
  10
  11 # for w in words:
  12     # sanitised_words.add(language_models.sanitise(w))
  13
  14 sanitised_words = set(language_models.sanitise(w) for w in words)
  15
  16 sanitised_words.discard('')
  17
  18 with open('words.txt', 'w') as f:
  19     f.write('\n'.join(sorted(sanitised_words, key=lambda w: (len(w), w))))