{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from pymongo import MongoClient\n",
    "import pandas as pd\n",
    "import json\n",
    "from bson.json_util import dumps\n",
    "from pandas.io.json import json_normalize"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "ip = '127.0.0.1'\n",
    "port = 27017\n",
    "client = MongoClient(ip, port)\n",
    "db = client['Vulnerabilities']\n",
    "vulnerabilities = db['Vulnerabilities']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def getLayerAndSubsystem():\n",
    "            return vulnerabilities.aggregate([\n",
    "\n",
    "                { \"$match\" : {\"high-level\":{\"$ne\":\"Unclear\"} }},\n",
    "                { \"$group\": {\n",
    "                    \"_id\": {\n",
    "                    \"layer\": \"$high-level\",\n",
    "                    \"subsystem\": \"$subsystem\"\n",
    "                },\n",
    "                \"value\": { \"$sum\": 1 }\n",
    "                }},\n",
    "                {\"$sort\":{\"_id.layer\":1}}\n",
    "            ])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "MongoResponse = getLayerAndSubsystem()\n",
    "dataFromMongoResponse = json.loads(dumps(MongoResponse))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "myList = []\n",
    "for element in dataFromMongoResponse:\n",
    "    myList.append([\"Android Subsystems.\"+element[\"_id\"][\"layer\"].encode(\"utf-8\")+\".\"+element[\"_id\"][\"subsystem\"].replace(\",\", \" \").replace(\".\", \" \").encode(\"utf-8\"),element[\"value\"]])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "df = pd.DataFrame(myList, columns=['id','value'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "df = df[~df['id'].str.contains(\",\")]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#Dataframe created and appended due visualizations reasons\n",
    "dataTemp = {'id': ['Android Subsystems', 'Android Subsystems.HAL', 'Android Subsystems.Native Libraries', 'Android Subsystems.Android Framework', 'Android Subsystems.Kernel', 'Android Subsystems.Application', 'Android Subsystems.Android Runtime'], 'value': ['','','','','','','']}\n",
    "dfTemp = pd.DataFrame(data=dataTemp)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "df = df.append(dfTemp, ignore_index=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "df.to_csv(path_or_buf=\"sabsvEMSE.csv\", index=False)"
   ]
  }
 ],
 "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": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}