showdownjs/src/subParsers/hashHTMLBlocks.js

showdown.subParser('hashHTMLBlocks', function (text, options, globals) {
  'use strict';

  // attacklab: Double up blank lines to reduce lookaround
  text = text.replace(/\n/g, '\n\n');

  // Hashify HTML blocks:
  // We only want to do this for block-level HTML tags, such as headers,
  // lists, and tables. That's because we still want to wrap <p>s around
  // "paragraphs" that are wrapped in non-block-level tags, such as anchors,
  // phrase emphasis, and spans. The list of tags we're looking for is
  // hard-coded:
  //var block_tags_a =
  // 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|script|noscript|form|fieldset|iframe|math|ins|del|style|section|header|footer|nav|article|aside';
  // var block_tags_b =
  // 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|script|noscript|form|fieldset|iframe|math|style|section|header|footer|nav|article|aside';

  // First, look for nested blocks, e.g.:
  //   <div>
  //     <div>
  //     tags for inner block must be indented.
  //     </div>
  //   </div>
  //
  // The outermost tags must start at the left margin for this to match, and
  // the inner nested divs must be indented.
  // We need to do this before the next, more liberal match, because the next
  // match will start at the first `<div>` and stop at the first `</div>`.

  // attacklab: This regex can be expensive when it fails.
  /*
   var text = text.replace(/
   (						// save in $1
   ^					// start of line  (with /m)
   <($block_tags_a)	// start tag = $2
   \b					// word break
   // attacklab: hack around khtml/pcre bug...
   [^\r]*?\n			// any number of lines, minimally matching
   </\2>				// the matching end tag
   [ \t]*				// trailing spaces/tabs
   (?=\n+)				// followed by a newline
   )						// attacklab: there are sentinel newlines at end of document
   /gm,function(){...}};
   */
  text = text.replace(/^(<(p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|script|noscript|form|fieldset|iframe|math|ins|del)\b[^\r]*?\n<\/\2>[ \t]*(?=\n+))/gm,
                      showdown.subParser('hashElement')(text, options, globals));

  //
  // Now match more liberally, simply from `\n<tag>` to `</tag>\n`
  //

  /*
   var text = text.replace(/
   (						// save in $1
   ^					// start of line  (with /m)
   <($block_tags_b)	// start tag = $2
   \b					// word break
   // attacklab: hack around khtml/pcre bug...
   [^\r]*?				// any number of lines, minimally matching
   </\2>				// the matching end tag
   [ \t]*				// trailing spaces/tabs
   (?=\n+)				// followed by a newline
   )						// attacklab: there are sentinel newlines at end of document
   /gm,function(){...}};
   */
  text = text.replace(/^(<(p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|script|noscript|form|fieldset|iframe|math|style|section|header|footer|nav|article|aside|address|audio|canvas|figure|hgroup|output|video)\b[^\r]*?<\/\2>[ \t]*(?=\n+)\n)/gm,
                      showdown.subParser('hashElement')(text, options, globals));

  // Special case just for <hr />. It was easier to make a special case than
  // to make the other regex more complicated.

  /*
   text = text.replace(/
   (						// save in $1
   \n\n				// Starting after a blank line
   [ ]{0,3}
   (<(hr)				// start tag = $2
   \b					// word break
   ([^<>])*?			//
   \/?>)				// the matching end tag
   [ \t]*
   (?=\n{2,})			// followed by a blank line
   )
   /g,showdown.subParser('hashElement')(text, options, globals));
   */
  text = text.replace(/(\n[ ]{0,3}(<(hr)\b([^<>])*?\/?>)[ \t]*(?=\n{2,}))/g,
                      showdown.subParser('hashElement')(text, options, globals));

  // Special case for standalone HTML comments:

  /*
   text = text.replace(/
   (						// save in $1
   \n\n				// Starting after a blank line
   [ ]{0,3}			// attacklab: g_tab_width - 1
   <!
   (--[^\r]*?--\s*)+
   >
   [ \t]*
   (?=\n{2,})			// followed by a blank line
   )
   /g,showdown.subParser('hashElement')(text, options, globals));
   */
  text = text.replace(/(\n\n[ ]{0,3}<!(--[^\r]*?--\s*)+>[ \t]*(?=\n{2,}))/g,
                      showdown.subParser('hashElement')(text, options, globals));

  // PHP and ASP-style processor instructions (<?...?> and <%...%>)

  /*
   text = text.replace(/
   (?:
   \n\n				// Starting after a blank line
   )
   (						// save in $1
   [ ]{0,3}			// attacklab: g_tab_width - 1
   (?:
   <([?%])			// $2
   [^\r]*?
   \2>
   )
   [ \t]*
   (?=\n{2,})			// followed by a blank line
   )
   /g,showdown.subParser('hashElement')(text, options, globals));
   */
  text = text.replace(/(?:\n\n)([ ]{0,3}(?:<([?%])[^\r]*?\2>)[ \t]*(?=\n{2,}))/g,
                      showdown.subParser('hashElement')(text, options, globals));

  // attacklab: Undo double lines (see comment at top of this function)
  text = text.replace(/\n\n/g, '\n');
  return text;

});