markdown-pandoc.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pathlib import Path as P\n",
    "import pypandoc\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# https://stackoverflow.com/a/67029719\n",
    "\n",
    "from IPython import get_ipython\n",
    "from IPython.core.magic import register_cell_magic\n",
    "\n",
    "ipython = get_ipython()\n",
    "\n",
    "@register_cell_magic\n",
    "def pybash(line, cell):\n",
    "    ipython.run_cell_magic('bash', '', cell.format(**globals()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "import subprocess\n",
    "\n",
    "def run_cmd(*args, shell=True, cwd=None):\n",
    "    r = subprocess.run(*args, shell=shell, capture_output=True, cwd=cwd)\n",
    "    return r\n",
    "\n",
    "\n",
    "def pandoc_formats():\n",
    "\n",
    "    cmd = 'pandoc --list-input-formats'\n",
    "    r = run_cmd(cmd, shell=True, cwd=P.cwd())\n",
    "    input_formats = set (r.stdout.decode('utf-8').split('\\n'))\n",
    "\n",
    "    cmd = 'pandoc --list-output-formats'\n",
    "    r = run_cmd(cmd, shell=True, cwd=P.cwd())\n",
    "    output_formats = set (r.stdout.decode('utf-8').split('\\n'))\n",
    "\n",
    "    return {'input': input_formats, 'output': output_formats}\n",
    "\n",
    "\n",
    "def extensions_for_format(fmt):\n",
    "    cmd = f'pandoc --list-extensions {fmt}'\n",
    "    r = run_cmd(cmd, shell=True, cwd=P.cwd())\n",
    "    # partition the extensions into two sets based by default enabling or disabling\n",
    "    enabled = set()\n",
    "    disabled = set()\n",
    "    for e in r.stdout.decode('utf-8').split('\\n'):\n",
    "        if e.startswith('+'):\n",
    "            enabled.add(e[1:])\n",
    "        elif e.startswith('-'):\n",
    "            disabled.add(e[1:])\n",
    "    return {'enabled': enabled, 'disabled': disabled, 'all': enabled.union(disabled)}\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'enabled': {'all_symbols_escapable',\n",
       "  'auto_identifiers',\n",
       "  'backtick_code_blocks',\n",
       "  'blank_before_blockquote',\n",
       "  'blank_before_header',\n",
       "  'bracketed_spans',\n",
       "  'citations',\n",
       "  'definition_lists',\n",
       "  'escaped_line_breaks',\n",
       "  'example_lists',\n",
       "  'fancy_lists',\n",
       "  'fenced_code_attributes',\n",
       "  'fenced_code_blocks',\n",
       "  'fenced_divs',\n",
       "  'footnotes',\n",
       "  'grid_tables',\n",
       "  'header_attributes',\n",
       "  'implicit_figures',\n",
       "  'implicit_header_references',\n",
       "  'inline_code_attributes',\n",
       "  'inline_notes',\n",
       "  'intraword_underscores',\n",
       "  'latex_macros',\n",
       "  'line_blocks',\n",
       "  'link_attributes',\n",
       "  'markdown_in_html_blocks',\n",
       "  'multiline_tables',\n",
       "  'native_divs',\n",
       "  'native_spans',\n",
       "  'pandoc_title_block',\n",
       "  'pipe_tables',\n",
       "  'raw_attribute',\n",
       "  'raw_html',\n",
       "  'raw_tex',\n",
       "  'shortcut_reference_links',\n",
       "  'simple_tables',\n",
       "  'smart',\n",
       "  'space_in_atx_header',\n",
       "  'startnum',\n",
       "  'strikeout',\n",
       "  'subscript',\n",
       "  'superscript',\n",
       "  'table_captions',\n",
       "  'task_lists',\n",
       "  'tex_math_dollars',\n",
       "  'yaml_metadata_block'},\n",
       " 'disabled': {'abbreviations',\n",
       "  'angle_brackets_escapable',\n",
       "  'ascii_identifiers',\n",
       "  'autolink_bare_uris',\n",
       "  'compact_definition_lists',\n",
       "  'east_asian_line_breaks',\n",
       "  'emoji',\n",
       "  'four_space_rule',\n",
       "  'gfm_auto_identifiers',\n",
       "  'gutenberg',\n",
       "  'hard_line_breaks',\n",
       "  'ignore_line_breaks',\n",
       "  'lists_without_preceding_blankline',\n",
       "  'literate_haskell',\n",
       "  'mark',\n",
       "  'markdown_attribute',\n",
       "  'mmd_header_identifiers',\n",
       "  'mmd_link_attributes',\n",
       "  'mmd_title_block',\n",
       "  'old_dashes',\n",
       "  'rebase_relative_paths',\n",
       "  'short_subsuperscripts',\n",
       "  'spaced_reference_links',\n",
       "  'tex_math_double_backslash',\n",
       "  'tex_math_single_backslash',\n",
       "  'wikilinks_title_after_pipe',\n",
       "  'wikilinks_title_before_pipe'},\n",
       " 'all': {'abbreviations',\n",
       "  'all_symbols_escapable',\n",
       "  'angle_brackets_escapable',\n",
       "  'ascii_identifiers',\n",
       "  'auto_identifiers',\n",
       "  'autolink_bare_uris',\n",
       "  'backtick_code_blocks',\n",
       "  'blank_before_blockquote',\n",
       "  'blank_before_header',\n",
       "  'bracketed_spans',\n",
       "  'citations',\n",
       "  'compact_definition_lists',\n",
       "  'definition_lists',\n",
       "  'east_asian_line_breaks',\n",
       "  'emoji',\n",
       "  'escaped_line_breaks',\n",
       "  'example_lists',\n",
       "  'fancy_lists',\n",
       "  'fenced_code_attributes',\n",
       "  'fenced_code_blocks',\n",
       "  'fenced_divs',\n",
       "  'footnotes',\n",
       "  'four_space_rule',\n",
       "  'gfm_auto_identifiers',\n",
       "  'grid_tables',\n",
       "  'gutenberg',\n",
       "  'hard_line_breaks',\n",
       "  'header_attributes',\n",
       "  'ignore_line_breaks',\n",
       "  'implicit_figures',\n",
       "  'implicit_header_references',\n",
       "  'inline_code_attributes',\n",
       "  'inline_notes',\n",
       "  'intraword_underscores',\n",
       "  'latex_macros',\n",
       "  'line_blocks',\n",
       "  'link_attributes',\n",
       "  'lists_without_preceding_blankline',\n",
       "  'literate_haskell',\n",
       "  'mark',\n",
       "  'markdown_attribute',\n",
       "  'markdown_in_html_blocks',\n",
       "  'mmd_header_identifiers',\n",
       "  'mmd_link_attributes',\n",
       "  'mmd_title_block',\n",
       "  'multiline_tables',\n",
       "  'native_divs',\n",
       "  'native_spans',\n",
       "  'old_dashes',\n",
       "  'pandoc_title_block',\n",
       "  'pipe_tables',\n",
       "  'raw_attribute',\n",
       "  'raw_html',\n",
       "  'raw_tex',\n",
       "  'rebase_relative_paths',\n",
       "  'short_subsuperscripts',\n",
       "  'shortcut_reference_links',\n",
       "  'simple_tables',\n",
       "  'smart',\n",
       "  'space_in_atx_header',\n",
       "  'spaced_reference_links',\n",
       "  'startnum',\n",
       "  'strikeout',\n",
       "  'subscript',\n",
       "  'superscript',\n",
       "  'table_captions',\n",
       "  'task_lists',\n",
       "  'tex_math_dollars',\n",
       "  'tex_math_double_backslash',\n",
       "  'tex_math_single_backslash',\n",
       "  'wikilinks_title_after_pipe',\n",
       "  'wikilinks_title_before_pipe',\n",
       "  'yaml_metadata_block'}}"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "extensions_for_format('markdown')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "md_showcase =P(\"/Users/raymondyee/obsidian/MainRY/Obsidian markdown showcase.md\")\n",
    "md_showcase.exists()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "%%pybash\n",
    "\n",
    "# pandoc -f markdown+task_lists+backtick_code_blocks -t html \"{md_showcase}\"\n",
    "pandoc -f markdown+wikilinks_title_after_pipe+mark+lists_without_preceding_blankline+task_lists+backtick_code_blocks -t html \"{md_showcase}\" > /tmp/obsidian.html\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "biblatex\n",
      "bibtex\n",
      "commonmark\n",
      "commonmark_x\n",
      "creole\n",
      "csljson\n",
      "csv\n",
      "docbook\n",
      "docx\n",
      "dokuwiki\n",
      "endnotexml\n",
      "epub\n",
      "fb2\n",
      "gfm\n",
      "haddock\n",
      "html\n",
      "ipynb\n",
      "jats\n",
      "jira\n",
      "json\n",
      "latex\n",
      "man\n",
      "markdown\n",
      "markdown_github\n",
      "markdown_mmd\n",
      "markdown_phpextra\n",
      "markdown_strict\n",
      "mediawiki\n",
      "muse\n",
      "native\n",
      "odt\n",
      "opml\n",
      "org\n",
      "ris\n",
      "rst\n",
      "rtf\n",
      "t2t\n",
      "textile\n",
      "tikiwiki\n",
      "tsv\n",
      "twiki\n",
      "typst\n",
      "vimwiki\n"
     ]
    }
   ],
   "source": [
    "%%pybash\n",
    "\n",
    "pandoc --list-input-formats"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "-abbreviations\n",
      "+all_symbols_escapable\n",
      "-angle_brackets_escapable\n",
      "-ascii_identifiers\n",
      "+auto_identifiers\n",
      "-autolink_bare_uris\n",
      "+backtick_code_blocks\n",
      "+blank_before_blockquote\n",
      "+blank_before_header\n",
      "+bracketed_spans\n",
      "+citations\n",
      "-compact_definition_lists\n",
      "+definition_lists\n",
      "-east_asian_line_breaks\n",
      "-emoji\n",
      "+escaped_line_breaks\n",
      "+example_lists\n",
      "+fancy_lists\n",
      "+fenced_code_attributes\n",
      "+fenced_code_blocks\n",
      "+fenced_divs\n",
      "+footnotes\n",
      "-four_space_rule\n",
      "-gfm_auto_identifiers\n",
      "+grid_tables\n",
      "-gutenberg\n",
      "-hard_line_breaks\n",
      "+header_attributes\n",
      "-ignore_line_breaks\n",
      "+implicit_figures\n",
      "+implicit_header_references\n",
      "+inline_code_attributes\n",
      "+inline_notes\n",
      "+intraword_underscores\n",
      "+latex_macros\n",
      "+line_blocks\n",
      "+link_attributes\n",
      "-lists_without_preceding_blankline\n",
      "-literate_haskell\n",
      "-mark\n",
      "-markdown_attribute\n",
      "+markdown_in_html_blocks\n",
      "-mmd_header_identifiers\n",
      "-mmd_link_attributes\n",
      "-mmd_title_block\n",
      "+multiline_tables\n",
      "+native_divs\n",
      "+native_spans\n",
      "-old_dashes\n",
      "+pandoc_title_block\n",
      "+pipe_tables\n",
      "+raw_attribute\n",
      "+raw_html\n",
      "+raw_tex\n",
      "-rebase_relative_paths\n",
      "-short_subsuperscripts\n",
      "+shortcut_reference_links\n",
      "+simple_tables\n",
      "+smart\n",
      "+space_in_atx_header\n",
      "-spaced_reference_links\n",
      "+startnum\n",
      "+strikeout\n",
      "+subscript\n",
      "+superscript\n",
      "+task_lists\n",
      "+table_captions\n",
      "+tex_math_dollars\n",
      "-tex_math_double_backslash\n",
      "-tex_math_single_backslash\n",
      "-wikilinks_title_after_pipe\n",
      "-wikilinks_title_before_pipe\n",
      "+yaml_metadata_block\n"
     ]
    }
   ],
   "source": [
    "%%pybash\n",
    "\n",
    "pandoc --list-extensions markdown"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "myenv-3.11.3",
   "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": "3.11.3"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}