lib/crapto/english_utils.nit

   1 # This file is part of NIT ( http://www.nitlanguage.org ).
   2 #
   3 # Copyright 2016 Philippe Pépos Petitclerc <ppeposp@gmail.com>
   4 #
   5 # Licensed under the Apache License, Version 2.0 (the "License");
   6 # you may not use this file except in compliance with the License.
   7 # You may obtain a copy of the License at
   8 #
   9 #     http://www.apache.org/licenses/LICENSE-2.0
  10 #
  11 # Unless required by applicable law or agreed to in writing, software
  12 # distributed under the License is distributed on an "AS IS" BASIS,
  13 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  14 # See the License for the specific language governing permissions and
  15 # limitations under the License.
  16
  17 # English language utilities for cryptographic purposes.
  18 module english_utils
  19
  20 redef class Sys
  21         # English letter frequency map
  22         var english_freqs: HashMap[Char, Float] is lazy do
  23                 var freqs = new HashMap[Char, Float]
  24
  25                 freqs['a'] = 0.0651738
  26                 freqs['b'] = 0.0124248
  27                 freqs['c'] = 0.0217339
  28                 freqs['d'] = 0.0349835
  29                 freqs['e'] = 0.1041442
  30                 freqs['f'] = 0.0197881
  31                 freqs['g'] = 0.0158610
  32                 freqs['h'] = 0.0492888
  33                 freqs['i'] = 0.0558094
  34                 freqs['j'] = 0.0009033
  35                 freqs['k'] = 0.0050529
  36                 freqs['l'] = 0.0331490
  37                 freqs['m'] = 0.0202124
  38                 freqs['n'] = 0.0564513
  39                 freqs['o'] = 0.0596302
  40                 freqs['p'] = 0.0137645
  41                 freqs['q'] = 0.0008606
  42                 freqs['r'] = 0.0497563
  43                 freqs['s'] = 0.0515760
  44                 freqs['t'] = 0.0729357
  45                 freqs['u'] = 0.0225134
  46                 freqs['v'] = 0.0082903
  47                 freqs['w'] = 0.0171272
  48                 freqs['x'] = 0.0013692
  49                 freqs['y'] = 0.0145984
  50                 freqs['z'] = 0.0007836
  51                 freqs[' '] = 0.1918182
  52
  53                 return freqs
  54         end
  55 end
  56
  57 redef class Text
  58
  59         # Score `self` according to english's letter frequency.
  60         # This function is useful mainly for cryptography but could happen to be helpful
  61         # elsewhere.
  62         #
  63         #     assert "aaaa".english_scoring > "bbbb".english_scoring
  64         fun english_scoring: Float do
  65
  66                 var freqs = english_freqs
  67                 var score = 0.0
  68
  69                 for c in self do
  70                         c = c.to_lower
  71                         var points = freqs.get_or_null(c)
  72                         if points != null then
  73                                 score += points
  74                         end
  75                 end
  76
  77                 return score
  78
  79         end
  80 end