{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import unicodedata\n",
    "import string"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "unaccent_specials = ''.maketrans({\"’\": \"'\", '“': '\"', '”': '\"'})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def unaccent(text):\n",
    "    translated_text = text.translate(unaccent_specials)\n",
    "    return unicodedata.normalize('NFKD', translated_text).\\\n",
    "        encode('ascii', 'ignore').\\\n",
    "        decode('utf-8')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def only_lower(text):\n",
    "    return all((c in string.ascii_lowercase) for c in text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# !find /usr -type f -iname 'british-english*'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "# !ls -lah /usr/share/dict"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def rude(word):\n",
    "    return any(w in word \n",
    "               for w in 'piss shit cunt fuck arse crap fart jizz whore bitch'.split())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rude('fucks')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "def valid_words():\n",
    "    return [unaccent(w.strip()) for w in open('/usr/share/dict/british-english').readlines()\n",
    "               if only_lower(unaccent(w.strip()))\n",
    "               if not rude(unaccent(w.strip()))]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def words_with_len(n):\n",
    "    return [unaccent(w.strip()) for w in open('/usr/share/dict/british-english').readlines()\n",
    "               if only_lower(unaccent(w.strip()))\n",
    "               if len(unaccent(w.strip())) == n\n",
    "               if not rude(unaccent(w.strip()))]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "62863 words\n"
     ]
    }
   ],
   "source": [
    "words = valid_words()\n",
    "print('{} words'.format(len(words)))\n",
    "with open('words.txt', 'w') as f:\n",
    "    f.write('\\n'.join(words))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.2+"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}