chunkify.ipynb

{
 "metadata": {
  "name": "",
  "signature": "sha256:09f3b9ebabdf3f7b528062fa19c3e10f88aa13691f2fa7380879c197ced7eb72"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from itertools import islice\n",
      "\n",
      "\n",
      "class ChunkingError(Exception):\n",
      "    pass\n",
      "\n",
      "\n",
      "def chunkify(things, this_chunk, chunks):\n",
      "    if this_chunk > chunks:\n",
      "        raise ChunkingError(\"this_chunk is greater than total chunks\")\n",
      "\n",
      "    size = len(things) / chunks\n",
      "    big_chunks = len(things) % chunks\n",
      "    start = size * (this_chunk-1)\n",
      "    if big_chunks:\n",
      "        start += (min(big_chunks, this_chunk)-1)\n",
      "        if this_chunk <= big_chunks:\n",
      "            size += 1\n",
      "        elif this_chunk == big_chunks+1:\n",
      "            start += 1\n",
      "        else:\n",
      "            start += this_chunk-big_chunks-1\n",
      "\n",
      "    end = start + size\n",
      "    try:\n",
      "        return things[start:end]\n",
      "    except TypeError:\n",
      "        return islice(things, start, end)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "changesets = \"\"\"ach 658769a76613\n",
      "af 431e02c10881\n",
      "an fe436c75f71d\n",
      "ar bbcf06888dc5\n",
      "as 8313f975ae77\n",
      "ast 0300b60cd340\n",
      "az fd96727d2a26\n",
      "be b72077740aac\n",
      "bg 9f7507dd2b92\n",
      "bn-BD fe0a6bb82a2d\n",
      "bn-IN a2ea6b87d80d\n",
      "br 95b028350e29\n",
      "bs cfee6f5b1e50\n",
      "ca e8ca2d46b4a8\n",
      "cs ed6004b91b51\n",
      "cy 5bbcbba9b054\n",
      "da 324fe068c0b9\n",
      "de 217ff3f0054a\n",
      "dsb 7cdfb5d9dc5d\n",
      "el 22b959c9a739\n",
      "en-GB 36012ab486ad\n",
      "en-ZA 1c91f05aae5a\n",
      "eo 049c1b065f4c\n",
      "es-AR b3647b1d5927\n",
      "es-CL e45186f983b9\n",
      "es-ES 6fe131a8b07f\n",
      "es-MX 4cd511663283\n",
      "et ecae9df9c92a\n",
      "eu 1a65e2c03dda\n",
      "fa e5993d9fb76e\n",
      "ff 8373353b43c4\n",
      "fi 9382e9e4eb2b\n",
      "fr 7d0bb8edc149\n",
      "fy-NL 02ee99ad3f83\n",
      "ga-IE 713ecb614f77\n",
      "\"\"\""
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 7
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "locales = [l.split()[0] for l in changesets.splitlines()]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 12
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "locales "
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 13,
       "text": [
        "['ach',\n",
        " 'af',\n",
        " 'an',\n",
        " 'ar',\n",
        " 'as',\n",
        " 'ast',\n",
        " 'az',\n",
        " 'be',\n",
        " 'bg',\n",
        " 'bn-BD',\n",
        " 'bn-IN',\n",
        " 'br',\n",
        " 'bs',\n",
        " 'ca',\n",
        " 'cs',\n",
        " 'cy',\n",
        " 'da',\n",
        " 'de',\n",
        " 'dsb',\n",
        " 'el',\n",
        " 'en-GB',\n",
        " 'en-ZA',\n",
        " 'eo',\n",
        " 'es-AR',\n",
        " 'es-CL',\n",
        " 'es-ES',\n",
        " 'es-MX',\n",
        " 'et',\n",
        " 'eu',\n",
        " 'fa',\n",
        " 'ff',\n",
        " 'fi',\n",
        " 'fr',\n",
        " 'fy-NL',\n",
        " 'ga-IE']"
       ]
      }
     ],
     "prompt_number": 13
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "chunkify(locales, 1, 10)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 14,
       "text": [
        "['ach', 'af', 'an', 'ar']"
       ]
      }
     ],
     "prompt_number": 14
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "chunkify(locales, 10, 10)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 15,
       "text": [
        "[]"
       ]
      }
     ],
     "prompt_number": 15
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "chunkify(locales, 9, 10)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 16,
       "text": [
        "['fi', 'fr', 'fy-NL']"
       ]
      }
     ],
     "prompt_number": 16
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": []
    }
   ],
   "metadata": {}
  }
 ]
}