RandomKerningText.ipynb

{
 "metadata": {
  "name": ""
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "This notebook creates random text that covers as many of the letter digraphs as possible for usage in font kerning. The approach used here is rather pedestrian, but it works fairly well if you are OK with random text."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import random\n",
      "from IPython.utils.text import wrap_paragraphs"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 64
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "alpha = 'abcdefghijklmnopqrstuvwxyz'.upper()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 98
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "def random_word(size):\n",
      "    \"\"\"Generate a random word of size.\"\"\"\n",
      "    return ''.join(random.sample(alpha, size))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 99
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "def random_text(nwords, min_size=2, max_size=15, ncols=80):\n",
      "    \"\"\"Generate random text with n words of length (min_size, max_size).\"\"\"\n",
      "    words = []\n",
      "    for i in range(nwords):\n",
      "        size = random.randint(min_size,max_size)\n",
      "        word = random_word(size)\n",
      "        words.append(word)\n",
      "    return wrap_paragraphs(' '.join(words), ncols=ncols)[0]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 100
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "def count_digraphs(text):\n",
      "    \"\"\"Count the total number of unique digraphs in a text.\"\"\"\n",
      "    digraphs = set()\n",
      "    words = text.split(' ')\n",
      "    for word in words:\n",
      "        for i in range(len(word)-1):\n",
      "            digraphs.add(word[i:i+2])\n",
      "    return len(digraphs)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 101
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "text = random_text(200)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 102
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "print text"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "BOLMCX GM FGJLNVCWYR ER GRVBQMZPTLI XQ IV OA ACBJUKRFYZDVTNP CQM MGFIYPK\n",
        "XCVBGDOSNAE MNHLOYBESID KDHEJCPA HISNFCQA XRHYDGM KNXIT XEIMTQRGHJYO\n",
        "THQEYJOPRLUFS UCFIBSWVNMZ SATXWUGLEPQN KJMVWNECSHGIP KAQDJEXUT TDYJGC\n",
        "XGDPRHSLYVAOEB VTZBPLNRFK ZHAGVMUNIJBK ZPLDWOXEQIAH HEBUSTIQPGDWZJA RYZPWCJ\n",
        "BCWEUXPJYSLT ASCKL CJUSVQTRGMFIOLN IQTX LQCEHAYF WZIAGVPXENR VLSKCFGAB VQIR\n",
        "XYQGLKR WHGJCRDFY QTM FJPW ONZJITHC NDCQLKSJEFTX PDTHISXZEN MJ SLRZYIDPFMEWNCO\n",
        "ZQLUCIRXJMADTK BKYGEP CVSN DYJMWGEV QUHMF BWCZTGIKNSHJ EFIVW QPKSVINJDOU\n",
        "ISQBAGLWHZUK NR RG IWHPBXMNAYTKC YRQZFGKMCWLP XI DIRYSLVXH PXWUENBRIVTJZ FWJMKY\n",
        "XMLEKDTF YKM QK SMCBPVXNOAH VGUJWCAINETRZ HCQPNAWM KZE GVYXRDLCQEJI XOUTSZD\n",
        "KNCESXRQ QMYABHOJE IPM PBNGJMSZXRLHC TPDLIUVZ PO QMDXSBNTCPG HVQJYWNRBEMD VM\n",
        "OPYSWMTFQZJG PU OHAZ FKNZTBGXRPJ RMBDCNGW DR KMYIWJHAFCSBET NDYGJUMKHFSPBC\n",
        "LUWTYVBPIAXE UPIOGK SDGX HJGPWQZBKENX CALSDRHIOB VEAPOXLUWQ JL KEUQWRAFTXB\n",
        "LJZHNUQCMBXW RECHY AJVP QLK IRQLYGZSHD AJIGKBF QHEAFDSXLZTCG ZWCUEY FHJAPNWV\n",
        "GMXVZ ROP QBK WAGLUH WQM TXPLNBYU DMB PR FJ IJDLZUHMG AOIHFYWXPGE LMSQRAPDWBT\n",
        "LDYCN OQDAREN DREVLQKIYJT VHSIMAORTG EQCOJPLFIKVMGZT OQZFEJRLIAWVXP VBIMF IUQ\n",
        "GOJ QDE IHR JMXNZ AEX IRQKCON UBYMNTQELWRIJFG XRLNMGAQSCTW RWPKYLOFVTAMG\n",
        "VTHKSAZYPGBU DOA MNBKG ZECYOFJVD QO FXPJ SKYLC ZOQEU ZKRINBOPDXGHJAS\n",
        "HLEBKRGODJUXSWN GMS NWUDJQR HNWOUKJ EHSCZKTFOU YGW VLPMNTFQA QUJEMZCRXNDFBKT\n",
        "ISEVGNYOHWUJ RL ZSBIEJFXKO JNQZUYLPAVCS QAM FBRKJY TLGJUXSFHMZV XKVFDZI RQH\n",
        "ALUFZCDI WLCMSDTV HIFGYXCRMBO PDX IAVPFMHSXQNGBTZ JZVEDT OKAXQCEPGYVDZT\n",
        "OBNQVRLXTDSW OUWFCSQLPR XUPAQYC TUZIDVWFKSPAMRC ULVPBOAEMWTY NR ARVLUMKJT\n",
        "PGQJZDE MYIPOFEVNQJBRTC IXQ JDVFZPWIX WZINDK LWJXABQYHPGTK PVGLUHCKRWN FJWZ\n",
        "UTIZVJSBCLNG CYPGAVTIUF ILB UVSJIBNTKHDEX FVKULXIJZYPQRD VRNIBHUGZAKYLP UCNQIS\n",
        "ZAJUC PXEHNT VGKAOQJUFBP JPGCYUO DPSI YGZVOQM DFVJXAMZURNSLP DHGOYBQWZSAF\n",
        "VCWXFPYTABLSK\n"
       ]
      }
     ],
     "prompt_number": 103
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "This sample has a good fraction of the total number of digraphs:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "count = count_digraphs(text); count"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 116,
       "text": [
        "611"
       ]
      }
     ],
     "prompt_number": 116
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "total = 26.0**2; total"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 117,
       "text": [
        "676.0"
       ]
      }
     ],
     "prompt_number": 117
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "fraction = count/total; fraction"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 119,
       "text": [
        "0.9038461538461539"
       ]
      }
     ],
     "prompt_number": 119
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "len(text)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 97,
       "text": [
        "1833"
       ]
      }
     ],
     "prompt_number": 97
    }
   ],
   "metadata": {}
  }
 ]
}