{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Final Project"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Log analysis using regular expressions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "grep \"ERROR\" syslog.log\n",
    "grep \"ERROR Tried to add information to closed ticket\" syslog.log"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import re\n",
    "line = \"May 27 11:45:40 ubuntu.local ticky: INFO: Created ticket [#1234] (username)\"\n",
    "re.search(r\"ticky: INFO: ([\\w ]*) \", line)\n",
    "# <re.Match object; span=(29, 56), match='ticky: INFO Created ticket '>\n",
    "line = \"May 27 11:45:40 ubuntu.local ticky: ERROR Error creating ticket [#1234] (username)\"\n",
    "re.search(r\"ticky: ERROR ([\\w ]*) \", line)\n",
    "# <re.Match object; span=(29, 64), match='ticky: ERROR Error creating ticket '>\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "fruit = {\"oranges\": 3, \"apples\": 5, \"bananas\": 7, \"pears\": 2}\n",
    "sorted(fruit.items())\n",
    "# [('apples', 5), ('bananas', 7), ('oranges', 3), ('pears', 2)]\n",
    "\n",
    "import operator\n",
    "sorted(fruit.items(), key=operator.itemgetter(0))\n",
    "# [('apples', 5), ('bananas', 7), ('oranges', 3), ('pears', 2)]\n",
    "\n",
    "sorted(fruit.items(), key=operator.itemgetter(1))\n",
    "# [('pears', 2), ('oranges', 3), ('apples', 5), ('bananas', 7)]\n",
    "\n",
    "sorted(fruit.items(), key = operator.itemgetter(1), reverse=True)\n",
    "# [('bananas', 7), ('apples', 5), ('oranges', 3), ('pears', 2)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#!/usr/bin/env python3\n",
    "import sys\n",
    "import re\n",
    "import operator\n",
    "import csv\n",
    "\n",
    "# Dict: Count number of entries for each user\n",
    "per_user = {}  # Splitting between INFO and ERROR\n",
    "# Dict: Number of different error messages\n",
    "errors = {}\n",
    "\n",
    "# * Read file and create dictionaries\n",
    "with open('syslog.log') as file:\n",
    "    # read each line\n",
    "    for line in file.readlines():\n",
    "        # regex search\n",
    "        # * Sample Line of log file\n",
    "        # \"May 27 11:45:40 ubuntu.local ticky: INFO: Created ticket [#1234] (username)\"\n",
    "        match = re.search(\n",
    "            r\"ticky: ([\\w+]*):? ([\\w' ]*)[\\[[#0-9]*\\]?]? ?\\((.*)\\)$\", line)\n",
    "        code, error_msg, user = match.group(1), match.group(2), match.group(3)\n",
    "\n",
    "        # Populates error dict with ERROR messages from log file\n",
    "        if error_msg not in errors.keys():\n",
    "            errors[error_msg] = 1\n",
    "        else:\n",
    "            errors[error_msg] += 1\n",
    "        # Populates per_user dict with users and default values\n",
    "        if user not in per_user.keys():\n",
    "            per_user[user] = {}\n",
    "            per_user[user]['INFO'] = 0\n",
    "            per_user[user]['ERROR'] = 0\n",
    "        # Populates per_user dict with users logs entry\n",
    "        if code == 'INFO':\n",
    "            if user not in per_user.keys():\n",
    "                per_user[user] = {}\n",
    "                per_user[user]['INFO'] = 0\n",
    "            else:\n",
    "                per_user[user][\"INFO\"] += 1\n",
    "        elif code == 'ERROR':\n",
    "            if user not in per_user.keys():\n",
    "                per_user[user] = {}\n",
    "                per_user[user]['INFO'] = 0\n",
    "            else:\n",
    "                per_user[user]['ERROR'] += 1\n",
    "\n",
    "# Sorted by VALUE (Most common to least common)\n",
    "errors_list = sorted(errors.items(), key=operator.itemgetter(1), reverse=True)\n",
    "# Sorted by USERNAME\n",
    "per_user_list = sorted(per_user.items(), key=operator.itemgetter(0))\n",
    "\n",
    "file.close()\n",
    "# Insert at the beginning of the list\n",
    "errors_list.insert(0, ('Error', 'Count'))\n",
    "# * Create CSV file user_statistics\n",
    "with open('user_statistics.csv', 'w', newline='') as user_csv:\n",
    "    for key, value in per_user_list:\n",
    "        user_csv.write(str(key) + ',' +\n",
    "                       str(value['INFO']) + ',' + str(value['ERROR'])+'\\n')\n",
    "# * Create CSV error_message\n",
    "with open('error_message.csv', 'w', newline='') as error_csv:\n",
    "    for key, value in errors_list:\n",
    "        error_csv.write(str(key) + ' ' + str(value))"
   ]
  }
 ],
 "metadata": {
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}