{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The type is <class 'list'>\n",
      "['\\n\\nhi', 'everyon', 'if', 'you', 'can', 'read', 'this', 'messag', 'your', 'proper', 'use', 'parseouttext', 'pleas', 'proceed', 'to', 'the', 'next', 'part', 'of', 'the', 'project\\n']\n"
     ]
    }
   ],
   "source": [
    "#!/usr/bin/python\n",
    "\n",
    "from nltk.stem.snowball import SnowballStemmer\n",
    "import string\n",
    "\n",
    "def parseOutText(f):\n",
    "    \"\"\" given an opened email file f, parse out all text below the\n",
    "        metadata block at the top\n",
    "        (in Part 2, you will also add stemming capabilities)\n",
    "        and return a string that contains all the words\n",
    "        in the email (space-separated) \n",
    "        \n",
    "        example use case:\n",
    "        f = open(\"email_file_name.txt\", \"r\")\n",
    "        text = parseOutText(f)\n",
    "        \n",
    "        \"\"\"\n",
    "\n",
    "\n",
    "    f.seek(0)  ### go back to beginning of file (annoying)\n",
    "    all_text = f.read()\n",
    "\n",
    "    ### split off metadata\n",
    "    content = all_text.split(\"X-FileName:\")\n",
    "    words = \"\"\n",
    "    if len(content) > 1:\n",
    "        ### remove punctuation\n",
    "        text_string = content[1].translate(str.maketrans(\"\", \"\", string.punctuation))\n",
    "\n",
    "        ### project part 2: comment out the line below\n",
    "        #words = text_string\n",
    "\n",
    "        ### split the text string into individual words, stem each word,\n",
    "        ### and append the stemmed word to words (make sure there's a single\n",
    "        ### space between each stemmed word)\n",
    "    str_list = text_string.split(\" \")\n",
    "    #print(str_list)\n",
    "    #不知道为什么会有空的元素夹杂在里边，所以写个循环删掉空的元素\n",
    "    for txt in str_list:\n",
    "        if txt == \"\":\n",
    "            str_list.remove(\"\")\n",
    "    \n",
    "    stemmer = SnowballStemmer(\"english\")\n",
    "    for x in range(0,len(str_list)):\n",
    "        str_list[x] = stemmer.stem(str_list[x])\n",
    "        \n",
    "    # 将一个列表转换为字符串并且用空格隔开\n",
    "    #words = \" \".join(str_list)\n",
    "    words = str_list\n",
    "    print(\"The type is\", type(str_list))\n",
    "    \n",
    "    return words\n",
    "\n",
    "    \n",
    "\n",
    "def main():\n",
    "    ff = open(\"../text_learning/test_email.txt\", \"r\")\n",
    "    text = parseOutText(ff)\n",
    "    print(text)\n",
    "\n",
    "\n",
    "\n",
    "if __name__ == '__main__':\n",
    "    main()\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}