src/task5/task5-re.ipynb

   1 {
   2  "cells": [
   3   {
   4    "cell_type": "code",
   5    "execution_count": 1,
   6    "metadata": {},
   7    "outputs": [],
   8    "source": [
   9     "import re\n",
  10     "import string"
  11    ]
  12   },
  13   {
  14    "cell_type": "code",
  15    "execution_count": 2,
  16    "metadata": {},
  17    "outputs": [],
  18    "source": [
  19     "comment_mark = re.compile('<[^>]*>') # A < followed by some things that aren't > followed by >\n",
  20     "expand_mark = re.compile(':(\\d+):(\\d+):') # A : followed by some digits, followed by another :, then some more digits, then a final :"
  21    ]
  22   },
  23   {
  24    "cell_type": "code",
  25    "execution_count": 3,
  26    "metadata": {},
  27    "outputs": [],
  28    "source": [
  29     "def decomment(text):\n",
  30     "    m = comment_mark.search(text)\n",
  31     "    while m:\n",
  32     "        s = m.start()\n",
  33     "        e = m.end()\n",
  34     "        text = text[:s] + text[e:]\n",
  35     "        m = comment_mark.search(text)\n",
  36     "    return text"
  37    ]
  38   },
  39   {
  40    "cell_type": "code",
  41    "execution_count": 4,
  42    "metadata": {},
  43    "outputs": [],
  44    "source": [
  45     "def expand(text, expansion_limit=None):\n",
  46     "    i = 1\n",
  47     "    m = expand_mark.search(text)\n",
  48     "    while m and (expansion_limit is None or (expansion_limit is not None and i <= expansion_limit)):\n",
  49     "        l = int(m.group(1))\n",
  50     "        n = int(m.group(2))\n",
  51     "        s = m.start()\n",
  52     "        e = m.end()\n",
  53     "        if l > s:\n",
  54     "            l = s\n",
  55     "        text = text[:s-l] + text[s-l:s] * n + text[e:]\n",
  56     "        m = expand_mark.search(text)\n",
  57     "        i += 1\n",
  58     "    return text"
  59    ]
  60   },
  61   {
  62    "cell_type": "code",
  63    "execution_count": 5,
  64    "metadata": {},
  65    "outputs": [],
  66    "source": [
  67     "data_p_t = [l.strip() for l in open('../../data/05-instructions.txt')]"
  68    ]
  69   },
  70   {
  71    "cell_type": "code",
  72    "execution_count": 6,
  73    "metadata": {},
  74    "outputs": [],
  75    "source": [
  76     "data_p = [decomment(l) for l in data_p_t]\n",
  77     "data = [expand(l) for l in data_p]"
  78    ]
  79   },
  80   {
  81    "cell_type": "code",
  82    "execution_count": 7,
  83    "metadata": {},
  84    "outputs": [
  85     {
  86      "data": {
  87       "text/plain": [
  88        "149043"
  89       ]
  90      },
  91      "execution_count": 7,
  92      "metadata": {},
  93      "output_type": "execute_result"
  94     }
  95    ],
  96    "source": [
  97     "len([c for c in ''.join(data_p) if c not in string.whitespace])"
  98    ]
  99   },
 100   {
 101    "cell_type": "code",
 102    "execution_count": 8,
 103    "metadata": {},
 104    "outputs": [
 105     {
 106      "data": {
 107       "text/plain": [
 108        "302266"
 109       ]
 110      },
 111      "execution_count": 8,
 112      "metadata": {},
 113      "output_type": "execute_result"
 114     }
 115    ],
 116    "source": [
 117     "len([c for c in ''.join(data) if c not in string.whitespace])"
 118    ]
 119   },
 120   {
 121    "cell_type": "code",
 122    "execution_count": 9,
 123    "metadata": {},
 124    "outputs": [],
 125    "source": [
 126     "data_s_p_t = open('../../data/05-instructions.txt').read()\n",
 127     "data_s_p = decomment(data_s_p_t)\n",
 128     "data_s = expand(data_s_p)"
 129    ]
 130   },
 131   {
 132    "cell_type": "code",
 133    "execution_count": 10,
 134    "metadata": {},
 135    "outputs": [
 136     {
 137      "data": {
 138       "text/plain": [
 139        "149043"
 140       ]
 141      },
 142      "execution_count": 10,
 143      "metadata": {},
 144      "output_type": "execute_result"
 145     }
 146    ],
 147    "source": [
 148     "sum(1 for c in data_s_p if c not in string.whitespace)"
 149    ]
 150   },
 151   {
 152    "cell_type": "code",
 153    "execution_count": 11,
 154    "metadata": {},
 155    "outputs": [
 156     {
 157      "data": {
 158       "text/plain": [
 159        "302266"
 160       ]
 161      },
 162      "execution_count": 11,
 163      "metadata": {},
 164      "output_type": "execute_result"
 165     }
 166    ],
 167    "source": [
 168     "sum(1 for c in data_s if c not in string.whitespace)"
 169    ]
 170   },
 171   {
 172    "cell_type": "code",
 173    "execution_count": 12,
 174    "metadata": {},
 175    "outputs": [
 176     {
 177      "name": "stdout",
 178      "output_type": "stream",
 179      "text": [
 180       "27.7 ms ± 908 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)\n"
 181      ]
 182     }
 183    ],
 184    "source": [
 185     "%%timeit\n",
 186     "data_p = [decomment(l) for l in data_p_t]\n",
 187     "data = [expand(l) for l in data_p]"
 188    ]
 189   },
 190   {
 191    "cell_type": "code",
 192    "execution_count": 13,
 193    "metadata": {},
 194    "outputs": [
 195     {
 196      "name": "stdout",
 197      "output_type": "stream",
 198      "text": [
 199       "861 ms ± 7.25 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
 200      ]
 201     }
 202    ],
 203    "source": [
 204     "%%timeit\n",
 205     "data_s_p = decomment(data_s_p_t)\n",
 206     "data_s = expand(data_s_p)"
 207    ]
 208   },
 209   {
 210    "cell_type": "code",
 211    "execution_count": null,
 212    "metadata": {},
 213    "outputs": [],
 214    "source": []
 215   }
 216  ],
 217  "metadata": {
 218   "kernelspec": {
 219    "display_name": "Python 3",
 220    "language": "python",
 221    "name": "python3"
 222   },
 223   "language_info": {
 224    "codemirror_mode": {
 225     "name": "ipython",
 226     "version": 3
 227    },
 228    "file_extension": ".py",
 229    "mimetype": "text/x-python",
 230    "name": "python",
 231    "nbconvert_exporter": "python",
 232    "pygments_lexer": "ipython3",
 233    "version": "3.6.6"
 234   }
 235  },
 236  "nbformat": 4,
 237  "nbformat_minor": 2
 238 }