{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os,re,json\n",
    "\n",
    "def form_decimals(string):\n",
    "    string = re.sub(r\"[\\s]+\",r\"\\t\",string)\n",
    "    numerals_list = [n for n in string.split(\"\\t\") if len(n)>0]\n",
    "    for i in range(len(numerals_list)):\n",
    "        numeral = numerals_list[i]\n",
    "        str_numeral = \"%.3f\" %float(numeral)\n",
    "        numerals_list[i] = str_numeral\n",
    "    return \"\\t\".join(numerals_list)\n",
    "\n",
    "with open(\"文本文件/手动统计结果.txt\",\"r\",encoding = \"utf8\") as f:\n",
    "    data = f.read()\n",
    "\n",
    "blocks = re.findall(r\"\\[BEGIN\\]([\\s\\S]*?)\\[END\\]\",data)\n",
    "\n",
    "results_dict = {}\n",
    "for block in blocks:\n",
    "    temp_list = [l.strip() for l in block.split(\"\\n\") if l.strip() != \"\"]    \n",
    "    for line in temp_list:\n",
    "        if line[:2] == \"##\":\n",
    "            date = line[2:].strip()\n",
    "        elif line[:2] == \"**\":\n",
    "            current_class = line[2:].strip()\n",
    "        else:\n",
    "            separating_pos = re.search(\"\\s\",line).span(0)[0]\n",
    "            if not line[:separating_pos].zfill(6) in results_dict:\n",
    "                results_dict[line[:separating_pos].zfill(6)] = [date + \"\\t\" + current_class + \"\\t\" + form_decimals(re.sub(\"\\s+?\",\"\\t\",line[separating_pos:])).strip()]\n",
    "            else:\n",
    "                results_dict[line[:separating_pos].zfill(6)].append(date + \"\\t\" + current_class + \"\\t\" + form_decimals(re.sub(\"\\s+?\",\"\\t\",line[separating_pos:])).strip())\n",
    "\n",
    "output_data = \"usages\\n\"\n",
    "for id in results_dict:\n",
    "    output_data += id + \"\\n\"\n",
    "    output_data += \"\\n\".join(results_dict[id])\n",
    "    output_data += \"\\n\\n\"\n",
    "\n",
    "with open(\"文本文件/metadata.txt\",\"w\",encoding = \"utf8\") as f:\n",
    "    f.write(output_data)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.9.15 ('pythontest')",
   "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": "91219a98e0e9be72efb992f647fe78b593124968b75db0b865552d6787c8db93"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}