{
 "metadata": {
  "name": "",
  "signature": "sha256:91e28abc35e42fd71d64d3d474aeb54e4b38e4f01ace5d68ed314731bd5fc976"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import re\n",
      "\n",
      "\n",
      "PATTERN = r\"Wally\"\n",
      "COMPILED = re.compile(PATTERN)\n",
      "STRING = \"We are looking for Wally right now!\"\n",
      "DATA_SEED = [STRING]\n",
      "\n",
      "\n",
      "def simple(string):\n",
      "    return re.search(PATTERN, string)\n",
      "\n",
      "\n",
      "def compiled(string):\n",
      "    return COMPILED.search(string)\n",
      "\n",
      "\n",
      "def bench_loop(lines, check_fn):\n",
      "    good_strings = 0\n",
      "    for line in lines:\n",
      "        re._cache.pop((str, PATTERN, 0), None)\n",
      "        if check_fn(line):\n",
      "            good_strings += 1\n",
      "        re._cache[(str, PATTERN, 0)] = COMPILED\n",
      "    return good_strings\n",
      "\n",
      "\n",
      "lines = DATA_SEED * 10**4"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%timeit bench_loop(lines, simple)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "1 loops, best of 3: 602 ms per loop\n"
       ]
      }
     ],
     "prompt_number": 2
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%timeit bench_loop(lines, compiled)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "100 loops, best of 3: 14.2 ms per loop\n"
       ]
      }
     ],
     "prompt_number": 3
    }
   ],
   "metadata": {}
  }
 ]
}