md2hatena.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b3b9bf4d",
   "metadata": {},
   "outputs": [],
   "source": [
    "import re\n",
    "import sys\n",
    "import os\n",
    "\n",
    "def work(name):\n",
    "    with open(name, encoding='UTF-8') as f:\n",
    "        lines = f.read()\n",
    "        \n",
    "    result = lines\n",
    "    \n",
    "    # コードブロックは処理をしないためコードブロックを除いた文字列を作成\n",
    "    resultNocode = re.sub(r'```.+?```', '', result, flags=re.DOTALL)\n",
    "    \n",
    "    words = re.findall(r'\\$.+?\\$', resultNocode)#, flags=re.DOTALL)\n",
    "#     print(words)\n",
    "    \n",
    "    for rin in words:\n",
    "        rout = rin\n",
    "        rout = re.sub(r'_', r'\\\\_' , rout)\n",
    "        rout = re.sub(r'\\^', r'\\\\^', rout)\n",
    "        rout = re.sub(r'\\*', r'\\*' , rout)\n",
    "        \n",
    "        rout = re.sub(r'^\\$', r'[tex:', rout)\n",
    "        rout = re.sub(r'\\$$', r']', rout)\n",
    "        \n",
    "        result = result.replace(rin, rout)\n",
    "        \n",
    "    # align環境の処理\n",
    "    words = re.findall(r'\\$\\$\\n\\\\begin{align}\\n.+?\\\\end{align}\\n\\$\\$\\n',resultNocode, flags=re.DOTALL)\n",
    "    \n",
    "    for rin in words:\n",
    "        rout = rin\n",
    "        for wesc in [r'\\[',r'\\]']:\n",
    "            rout = re.sub(wesc, wesc, rout)\n",
    "        \n",
    "        rout = re.sub(r'^\\$\\$\\n\\\\begin{align}\\n', r'<div align=\"center\">[tex:\\\\begin{align}\\n', rout)\n",
    "        rout = re.sub(r'\\\\end{align}\\n\\$\\$\\n$', r'\\\\end{align}]</div>\\n', rout)\n",
    "            \n",
    "        result = result.replace(rin, rout)\n",
    "    \n",
    "    \n",
    "    sname = os.path.splitext(name)\n",
    "    oname = sname[0] + '_output' + sname[-1]\n",
    "    with open(oname, mode=\"w\", encoding=\"UTF-8\") as f:\n",
    "        f.write(result)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ef58c556",
   "metadata": {},
   "outputs": [],
   "source": [
    "print(sys.argv)\n",
    "d = work(sys.argv[1])"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.12"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}