07-word-chains/build-word-lists.ipynb

   1 {
   2  "cells": [
   3   {
   4    "cell_type": "code",
   5    "execution_count": 3,
   6    "metadata": {
   7     "collapsed": true
   8    },
   9    "outputs": [],
  10    "source": [
  11     "import unicodedata\n",
  12     "import string"
  13    ]
  14   },
  15   {
  16    "cell_type": "code",
  17    "execution_count": 4,
  18    "metadata": {
  19     "collapsed": true
  20    },
  21    "outputs": [],
  22    "source": [
  23     "unaccent_specials = ''.maketrans({\"’\": \"'\", '“': '\"', '”': '\"'})"
  24    ]
  25   },
  26   {
  27    "cell_type": "code",
  28    "execution_count": 5,
  29    "metadata": {
  30     "collapsed": true
  31    },
  32    "outputs": [],
  33    "source": [
  34     "def unaccent(text):\n",
  35     "    translated_text = text.translate(unaccent_specials)\n",
  36     "    return unicodedata.normalize('NFKD', translated_text).\\\n",
  37     "        encode('ascii', 'ignore').\\\n",
  38     "        decode('utf-8')"
  39    ]
  40   },
  41   {
  42    "cell_type": "code",
  43    "execution_count": 6,
  44    "metadata": {
  45     "collapsed": true
  46    },
  47    "outputs": [],
  48    "source": [
  49     "def only_lower(text):\n",
  50     "    return all((c in string.ascii_lowercase) for c in text)"
  51    ]
  52   },
  53   {
  54    "cell_type": "code",
  55    "execution_count": 7,
  56    "metadata": {},
  57    "outputs": [
  58     {
  59      "name": "stdout",
  60      "output_type": "stream",
  61      "text": [
  62       "/usr/share/dict/british-english\n",
  63       "find: ‘/usr/share/doc/google-chrome-stable’: Permission denied\n",
  64       "/usr/share/man/man5/british-english.5.gz\n"
  65      ]
  66     }
  67    ],
  68    "source": [
  69     "# !find /usr -type f -iname 'british-english*'"
  70    ]
  71   },
  72   {
  73    "cell_type": "code",
  74    "execution_count": 8,
  75    "metadata": {},
  76    "outputs": [
  77     {
  78      "name": "stdout",
  79      "output_type": "stream",
  80      "text": [
  81       "total 2.3M\r\n",
  82       "drwxr-xr-x   2 root root 4.0K Dec 29 12:37 .\r\n",
  83       "drwxr-xr-x 640 root root  20K Apr 13 17:05 ..\r\n",
  84       "-rw-r--r--   1 root root 917K Oct 23  2011 american-english\r\n",
  85       "-rw-r--r--   1 root root 917K Oct 23  2011 british-english\r\n",
  86       "-rw-r--r--   1 root root 467K Aug 25  2016 cracklib-small\r\n",
  87       "-rw-r--r--   1 root root  199 Aug 29  2016 README.select-wordlist\r\n",
  88       "lrwxrwxrwx   1 root root   30 Nov 10  2014 words -> /etc/dictionaries-common/words\r\n",
  89       "lrwxrwxrwx   1 root root   16 Jun 18  2014 words.pre-dictionaries-common -> american-english\r\n"
  90      ]
  91     }
  92    ],
  93    "source": [
  94     "# !ls -lah /usr/share/dict"
  95    ]
  96   },
  97   {
  98    "cell_type": "code",
  99    "execution_count": 17,
 100    "metadata": {
 101     "collapsed": true
 102    },
 103    "outputs": [],
 104    "source": [
 105     "def rude(word):\n",
 106     "    return any(w in word \n",
 107     "               for w in 'piss shit cunt fuck arse crap fart jizz whore bitch'.split())"
 108    ]
 109   },
 110   {
 111    "cell_type": "code",
 112    "execution_count": 18,
 113    "metadata": {},
 114    "outputs": [
 115     {
 116      "data": {
 117       "text/plain": [
 118        "True"
 119       ]
 120      },
 121      "execution_count": 18,
 122      "metadata": {},
 123      "output_type": "execute_result"
 124     }
 125    ],
 126    "source": [
 127     "rude('fucks')"
 128    ]
 129   },
 130   {
 131    "cell_type": "code",
 132    "execution_count": 19,
 133    "metadata": {
 134     "collapsed": true
 135    },
 136    "outputs": [],
 137    "source": [
 138     "def words_with_len(n):\n",
 139     "    return [unaccent(w.strip()) for w in open('/usr/share/dict/british-english').readlines()\n",
 140     "               if only_lower(unaccent(w.strip()))\n",
 141     "               if len(unaccent(w.strip())) == n\n",
 142     "               if not rude(unaccent(w.strip()))]"
 143    ]
 144   },
 145   {
 146    "cell_type": "code",
 147    "execution_count": 20,
 148    "metadata": {},
 149    "outputs": [
 150     {
 151      "name": "stdout",
 152      "output_type": "stream",
 153      "text": [
 154       "2336 4-letter words\n",
 155       "4566 5-letter words\n",
 156       "7223 6-letter words\n"
 157      ]
 158     }
 159    ],
 160    "source": [
 161     "dicts = {}\n",
 162     "\n",
 163     "for n in [4, 5, 6]:\n",
 164     "    dicts[n] = words_with_len(n)\n",
 165     "    print('{} {}-letter words'.format(len(dicts[n]), n))\n",
 166     "    with open('words{}.txt'.format(n), 'w') as f:\n",
 167     "        f.write('\\n'.join(sorted(set(dicts[n]))))\n"
 168    ]
 169   },
 170   {
 171    "cell_type": "code",
 172    "execution_count": null,
 173    "metadata": {
 174     "collapsed": true
 175    },
 176    "outputs": [],
 177    "source": []
 178   }
 179  ],
 180  "metadata": {
 181   "kernelspec": {
 182    "display_name": "Python 3",
 183    "language": "python",
 184    "name": "python3"
 185   },
 186   "language_info": {
 187    "codemirror_mode": {
 188     "name": "ipython",
 189     "version": 3
 190    },
 191    "file_extension": ".py",
 192    "mimetype": "text/x-python",
 193    "name": "python",
 194    "nbconvert_exporter": "python",
 195    "pygments_lexer": "ipython3",
 196    "version": "3.5.2+"
 197   }
 198  },
 199  "nbformat": 4,
 200  "nbformat_minor": 2
 201 }