{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "首行题目数量:  21\n",
      "剩余题目数量:  21\n"
     ]
    }
   ],
   "source": [
    "import os,re,json\n",
    "\n",
    "\"\"\"---设置题号列表所在文件, 仅第一行有用---\"\"\"\n",
    "id_list_file = \"文本文件/题号筛选.txt\"\n",
    "\"\"\"---设置题号列表文件结束---\"\"\"\n",
    "\n",
    "\"\"\"---设置要排除的题号所在的绝对路径---\"\"\"\n",
    "mainpath = r\"C:/Users/Weiye/Documents/wwy sync/23届/\"\n",
    "\n",
    "used_path_list = [\n",
    "mainpath + \"第一轮复习讲义/\",\n",
    "mainpath + \"上学期测验卷/\",\n",
    "mainpath + \"上学期周末卷/\",\n",
    "mainpath + \"赋能/\",\n",
    "mainpath + \"寒假作业/\",\n",
    "mainpath + \"下学期测验卷/\",\n",
    "mainpath + \"下学期周末卷/\",\n",
    "mainpath + \"第二轮复习讲义/\",\n",
    "# mainpath + \"简单题/\",\n",
    "]\n",
    "\"\"\"---路径设置完毕---\"\"\"\n",
    "\n",
    "# 从字符串中获取题号列表\n",
    "def extract_idlist(string):\n",
    "    idlist = re.findall(r\"\\(([\\d]{6})\\)\",string)\n",
    "    return idlist\n",
    "\n",
    "# 生成题号列表\n",
    "def generate_number_set(string,dict):\n",
    "    string = re.sub(r\"[\\n\\s]\",\"\",string)\n",
    "    string_list = string.split(\",\")\n",
    "    numbers_list = []\n",
    "    for s in string_list:\n",
    "        if not \":\" in s:\n",
    "            numbers_list.append(s.zfill(6))\n",
    "        else:\n",
    "            start,end = s.split(\":\")\n",
    "            for ind in range(int(start),int(end)+1):\n",
    "                numbers_list.append(str(ind).zfill(6))\n",
    "    return numbers_list\n",
    "\n",
    "#读取题库json文件并转化为字典\n",
    "with open(r\"../题库0.3/Problems.json\",\"r\",encoding = \"utf8\") as f:\n",
    "    database = f.read()\n",
    "pro_dict = json.loads(database)\n",
    "\n",
    "# 生成首行题号列表并输出数量\n",
    "with open(id_list_file,\"r\",encoding = \"utf8\") as f:\n",
    "    data = f.read() + \"\\n\"\n",
    "\n",
    "# id_list = re.findall(r\"^([^\\n]*)\\n\",data)[0].split(\",\")\n",
    "id_list = generate_number_set(data,pro_dict)\n",
    "print(\"首行题目数量: \",len(id_list))\n",
    "\n",
    "# 生成已使用题号列表\n",
    "used_id_list = []\n",
    "\n",
    "for path in used_path_list:\n",
    "    filelist = [f for f in os.listdir(path) if \".tex\" in f]\n",
    "    for f in filelist:\n",
    "        with open(path+f,\"r\",encoding = \"utf8\") as texfile:\n",
    "            texdata = texfile.read()\n",
    "        used_id_list += extract_idlist(texdata)\n",
    "\n",
    "# 去除已使用题号\n",
    "checked_id_list = []\n",
    "ripped_id_list = []\n",
    "for id in id_list:\n",
    "    if not id in used_id_list:\n",
    "        checked_id_list.append(id)\n",
    "    else:\n",
    "        ripped_id_list.append(id)\n",
    "\n",
    "print(\"剩余题目数量: \",len(checked_id_list))\n",
    "\n",
    "# 写入文件\n",
    "with open(id_list_file,\"a\",encoding = \"utf8\") as f:\n",
    "    f.write(\"\\n\\n\")\n",
    "    f.write(\"未使用题号:\\n\")\n",
    "    f.write(\",\".join(checked_id_list))\n",
    "    f.write(\"\\n\\n已使用题号:\\n\")\n",
    "    f.write(\",\".join(ripped_id_list))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "mathdept",
   "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": "3.9.15"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "ff3c292c316ba85de6f1ad75f19c731e79d694e741b6f515ec18f14996fe48dc"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}