{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "filename = \"_chat.txt\"\n",
    "pattern = \"^\\[\\d{2}\\.\\d{2}\\.\\d{2},\\s\\d{2}:\\d{2}:\\d{2}\\].[^:]*:\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "messages = []\n",
    "with open(filename,'r', encoding=\"utf8\") as f:\n",
    "    for line in f:\n",
    "        match = re.search(pattern,line)\n",
    "        #print(line)\n",
    "        #print(match)\n",
    "        if match:\n",
    "            #print(match)\n",
    "            content = re.sub(pattern,'',line)\n",
    "            messages.append(content)\n",
    "        else:\n",
    "            messages[-1] += line"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "questions = [msg.replace('\\n', '') for msg in messages if \"?\" in msg]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "with open(\"questions\", \"wb\") as fp:\n",
    "    pickle.dump(questions, fp)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1821"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(questions)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "import keyboard\n",
    "with open(\"questions\", \"rb\") as fp:\n",
    "    questions = pickle.load(fp)\n",
    "try:\n",
    "    with open(\"remaining\", \"rb\") as fp2:\n",
    "        remaining = pickle.load(fp2)\n",
    "except:\n",
    "    remaining = []\n",
    "for idx, question in enumerate(questions):\n",
    "    try:\n",
    "        print(question)\n",
    "        command = input()\n",
    "        if command == \"d\":\n",
    "            continue\n",
    "        elif command == \"s\":\n",
    "            remaining.append(question)\n",
    "        elif command == \"m\":\n",
    "            modified = input(\"Enter new modified sentence\")\n",
    "            remaining.append(modified)\n",
    "    except:\n",
    "        print(f\"Canceled at question {idx}\")\n",
    "        questions = questions[idx:]\n",
    "        break\n",
    "with open(\"questions\", \"wb\") as fp:\n",
    "    pickle.dump(questions, fp)\n",
    "with open(\"remaining\", \"wb\") as fp:\n",
    "    pickle.dump(remaining, fp)\n",
    "        "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "with open(\"./remaining\", \"rb\") as fp:\n",
    "    remaining = pickle.load(fp)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "list"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(remaining)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "df = pd.DataFrame(data={\"question\": remaining})\n",
    "df.to_csv(\"./questions.csv\", sep=',',index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.7.9 64-bit",
   "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": "3.7.9"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "999ea782e2d719ec62688e738a2ff20f2535cd73f1388dd13a2d835295a4fc1a"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}