DEV Community

Casualwriter
Casualwriter

Posted on • Updated on

A simple markdown parser in 55 lines of js

Working on a document framework, and would like to have a simple markdown parser.

However, some are too heavy and some not support IE11. Just write a simple one using RegExp.

  • support basic markdown syntax only
  • not perfect but hope to be good enough for basic usage
  • 55 lines of pure JavaScript, without dependance.
//=== simple markdown parser
function simpleMarkdown(mdText) {

  // first, handle syntax for code-block
  mdText = mdText.replace(/\r\n/g, '\n')
  mdText = mdText.replace(/\n~~~ *(.*?)\n([\s\S]*?)\n

~~~/g, '<pre><code title="$1">$2</code></pre>' )
  mdText = mdText.replace(/\n``` *(.*?)\n([\s\S]*?)\n```/g, '<pre><code title="$1">$2</code></pre>' )

  // split by "pre>", skip for code-block and process normal text
  var mdHTML = ''
  var mdCode = mdText.split( 'pre>')

  for (var i=0; i<mdCode.length; i++) {
    if ( mdCode[i].substr(-2) == '</' ) {
      mdHTML += '<pre>' + mdCode[i] + 'pre>'
    } else {
      mdHTML += mdCode[i].replace(/(.*)<$/, '$1')
        .replace(/^##### (.*?)\s*#*$/gm, '<h5>$1</h5>')
        .replace(/^#### (.*?)\s*#*$/gm, '<h4 id="$1">$1</h4>')
        .replace(/^### (.*?)\s*#*$/gm, '<h3 id="$1">$1</h3>')
        .replace(/^## (.*?)\s*#*$/gm, '<h2 id="$1">$1</h2>')
        .replace(/^# (.*?)\s*#*$/gm, '<h1 id="$1">$1</h1>')    
        .replace(/^-{3,}|^\_{3,}|^\*{3,}/gm, '<hr/>')    
        .replace(/``(.*?)``/gm, '<code>$1</code>' )
        .replace(/`(.*?)`/gm, '<code>$1</code>' )
        .replace(/^\>> (.*$)/gm, '<blockquote><blockquote>$1</blockquote></blockquote>')
        .replace(/^\> (.*$)/gm, '<blockquote>$1</blockquote>')
        .replace(/<\/blockquote\>\n<blockquote\>/g, '\n<br>' )
        .replace(/<\/blockquote\>\n<br\><blockquote\>/g, '\n<br>' )
        .replace(/!\[(.*?)\]\((.*?) "(.*?)"\)/gm, '<img alt="$1" src="$2" $3 />')
        .replace(/!\[(.*?)\]\((.*?)\)/gm, '<img alt="$1" src="$2" />')
        .replace(/\[(.*?)\]\((.*?) "(.*?)"\)/gm, '<a href="$2" title="$3">$1</a>')
        .replace(/<http(.*?)\>/gm, '<a href="http$1">http$1</a>')
        .replace(/\[(.*?)\]\(\)/gm, '<a href="$1">$1</a>')
        .replace(/\[(.*?)\]\((.*?)\)/gm, '<a href="$2">$1</a>')
        .replace(/^[\*|+|-][ |.](.*)/gm, '<ul><li>$1</li></ul>' ).replace(/<\/ul\>\n<ul\>/g, '\n' )
        .replace(/^\d[ |.](.*)/gm, '<ol><li>$1</li></ol>' ).replace(/<\/ol\>\n<ol\>/g, '\n' )
        .replace(/\*\*\*(.*)\*\*\*/gm, '<b><em>$1</em></b>')
        .replace(/\*\*(.*)\*\*/gm, '<b>$1</b>')
        .replace(/\*([\w \d]*)\*/gm, '<em>$1</em>')
        .replace(/___(.*)___/gm, '<b><em>$1</em></b>')
        .replace(/__(.*)__/gm, '<u>$1</u>')
        .replace(/_([\w \d]*)_/gm, '<em>$1</em>')
        .replace(/~~(.*)~~/gm, '<del>$1</del>')
        .replace(/\^\^(.*)\^\^/gm, '<ins>$1</ins>')
        .replace(/ +\n/g, '\n<br/>')
        .replace(/\n\s*\n/g, '\n<p>\n')
        .replace(/^ {4,10}(.*)/gm, '<pre><code>$1</code></pre>' )
        .replace(/^\t(.*)/gm, '<pre><code>$1</code></pre>' )
        .replace(/<\/code\><\/pre\>\n<pre\><code\>/g, '\n' )
        .replace(/\\([`_\\\*\+\-\.\(\)\[\]\{\}])/gm, '$1' )
    }  
  }

  return mdHTML.trim()
}
Enter fullscreen mode Exit fullscreen mode

Sorry for not good coding style! still working on more syntax.

Enjoy,

Top comments (0)