word_pos_to_char_pos.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from __future__ import unicode_literals\n",
    "from pprint import pformat"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "words = '當時 只有 一 個 念頭 ： 人類 的 末日 已經 來臨 ！'.split()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[2, 2, 1, 1, 2, 1, 2, 1, 2, 2, 2, 1]"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "word_lens = map(len, words)\n",
    "word_lens"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0, 2, 4, 5, 6, 8, 9, 11, 12, 14, 16, 18, 19]"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "word_lens_sums = reduce(lambda  s, l: s + [s[-1]+l], word_lens, [0])\n",
    "word_lens_sums"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{u'一': (4,),\n",
      " u'人類': (9, 10),\n",
      " u'來臨': (16, 17),\n",
      " u'個': (5,),\n",
      " u'只有': (2, 3),\n",
      " u'已經': (14, 15),\n",
      " u'念頭': (6, 7),\n",
      " u'末日': (12, 13),\n",
      " u'當時': (0, 1),\n",
      " u'的': (11,),\n",
      " u'！': (18,),\n",
      " u'：': (8,)}\n"
     ]
    }
   ],
   "source": [
    "# 每個詞對應的 char 位置\n",
    "print pformat({word: tuple(range(start, end))\n",
    "    for word, start, end in zip(words, word_lens_sums, word_lens_sums[1:])}).decode('unicode-escape')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "https://gist.github.com/7e2f03d9c4e6fc78ca58\r\n"
     ]
    }
   ],
   "source": [
    "!gist  -u  https://gist.github.com/7e2f03d9c4e6fc78ca58 word_pos_to_char_pos.ipynb"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}