showdown.js.svn-base

mooltools源码很不错的源码

//
// showdown.js -- A javascript port of Markdown.
//
// Copyright (c) 2007 John Fraser.
//
// Original Markdown Copyright (c) 2004-2005 John Gruber
//   <http://daringfireball.net/projects/markdown/>
//
// Redistributable under a BSD-style open source license.
// See license.txt for more information.
//
// The full source distribution is at:
//
//				A A L
//				T C A
//				T K B
//
//   <http://www.attacklab.net/>
//

//
// Wherever possible, Showdown is a straight, line-by-line port
// of the Perl version of Markdown.
//
// This is not a normal parser design; it's basically just a
// series of string substitutions.  It's hard to read and
// maintain this way,  but keeping Showdown close to the original
// design makes it easier to port new features.
//
// More importantly, Showdown behaves like markdown.pl in most
// edge cases.  So web applications can do client-side preview
// in Javascript, and then build identical HTML on the server.
//
// This port needs the new RegExp functionality of ECMA 262,
// 3rd Edition (i.e. Javascript 1.5).  Most modern web browsers
// should do fine.  Even with the new regular expression features,
// We do a lot of work to emulate Perl's regex functionality.
// The tricky changes in this file mostly have the "attacklab:"
// label.  Major or self-explanatory changes don't.
//
// Smart diff tools like Araxis Merge will be able to match up
// this file with markdown.pl in a useful way.  A little tweaking
// helps: in a copy of markdown.pl, replace "#" with "//" and
// replace "$text" with "text".  Be sure to ignore whitespace
// and line endings.
//


//
// Showdown usage:
//
//   var text = "Markdown *rocks*.";
//
//   var converter = new Showdown.converter();
//   var html = converter.makeHtml(text);
//
//   alert(html);
//
// Note: move the sample code to the bottom of this
// file before uncommenting it.
//


//
// Showdown namespace
//
var Showdown = {};

//
// converter
//
// Wraps all "globals" so that the only thing
// exposed is makeHtml().
//
Showdown.converter = function() {

//
// Globals:
//

// Global hashes, used by various utility routines
var g_urls;
var g_titles;
var g_html_blocks;

// Used to track when we're inside an ordered or unordered list
// (see _ProcessListItems() for details):
var g_list_level = 0;


this.makeHtml = function(text) {
//
// Main function. The order in which other subs are called here is
// essential. Link and image substitutions need to happen before
// _EscapeSpecialCharsWithinTagAttributes(), so that any *'s or _'s in the <a>
// and <img> tags get encoded.
//

	// Clear the global hashes. If we don't clear these, you get conflicts
	// from other articles when generating a page which contains more than
	// one article (e.g. an index page that shows the N most recent
	// articles):
	g_urls = new Array();
	g_titles = new Array();
	g_html_blocks = new Array();

	// attacklab: Replace ~ with ~T
	// This lets us use tilde as an escape char to avoid md5 hashes
	// The choice of character is arbitray; anything that isn't
    // magic in Markdown will work.
	text = text.replace(/~/g,"~T");

	// attacklab: Replace $ with ~D
	// RegExp interprets $ as a special character
	// when it's in a replacement string
	text = text.replace(/\$/g,"~D");

	// Standardize line endings
	text = text.replace(/\r\n/g,"\n"); // DOS to Unix
	text = text.replace(/\r/g,"\n"); // Mac to Unix

	// Make sure text begins and ends with a couple of newlines:
	text = "\n\n" + text + "\n\n";

	// Convert all tabs to spaces.
	text = _Detab(text);

	// Strip any lines consisting only of spaces and tabs.
	// This makes subsequent regexen easier to write, because we can
	// match consecutive blank lines with /\n+/ instead of something
	// contorted like /[ \t]*\n+/ .
	text = text.replace(/^[ \t]+$/mg,"");

	// Turn block-level HTML blocks into hash entries
	text = _HashHTMLBlocks(text);

	// Strip link definitions, store in hashes.
	text = _StripLinkDefinitions(text);

	text = _RunBlockGamut(text);

	text = _UnescapeSpecialChars(text);

	// attacklab: Restore dollar signs
	text = text.replace(/~D/g,"$$");

	// attacklab: Restore tildes
	text = text.replace(/~T/g,"~");

	return text;
}


var _StripLinkDefinitions = function(text) {
//
// Strips link definitions from text, stores the URLs and titles in
// hash references.
//

	// Link defs are in the form: ^[id]: url "optional title"

	/*
		var text = text.replace(/
				^[ ]{0,3}\[(.+)\]:  // id = $1  attacklab: g_tab_width - 1
				  [ \t]*
				  \n?				// maybe *one* newline
				  [ \t]*
				<?(\S+?)>?			// url = $2
				  [ \t]*
				  \n?				// maybe one newline
				  [ \t]*
				(?:
				  (\n*)				// any lines skipped = $3 attacklab: lookbehind removed
				  ["(]
				  (.+?)				// title = $4
				  [")]
				  [ \t]*
				)?					// title is optional
				(?:\n+|$)
			  /gm,
			  function(){...});
	*/
	text = text.replace(/^[ ]{0,3}\[(.+)\]:[ \t]*\n?[ \t]*<?(\S+?)>?[ \t]*\n?[ \t]*(?:(\n*)["(](.+?)[")][ \t]*)?(?:\n+|\Z)/gm,
		function (wholeMatch,m1,m2,m3,m4) {
			m1 = m1.toLowerCase();
			g_urls[m1] = _EncodeAmpsAndAngles(m2);  // Link IDs are case-insensitive
			if (m3) {
				// Oops, found blank lines, so it's not a title.
				// Put back the parenthetical statement we stole.
				return m3+m4;
			} else if (m4) {
				g_titles[m1] = m4.replace(/"/g,"&quot;");
			}

			// Completely remove the definition from the text
			return "";
		}
	);

	return text;
}


var _HashHTMLBlocks = function(text) {
	// 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"
	var block_tags_b = "p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|script|noscript|form|fieldset|iframe|math"

	// 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,hashElement);

	//
	// 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)\b[^\r]*?.*<\/\2>[ \t]*(?=\n+)\n)/gm,hashElement);

	// 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,hashElement);
	*/
	text = text.replace(/(\n[ ]{0,3}(<(hr)\b([^<>])*?\/?>)[ \t]*(?=\n{2,}))/g,hashElement);

	// 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,hashElement);
	*/
	text = text.replace(/(\n\n[ ]{0,3}<!(--[^\r]*?--\s*)+>[ \t]*(?=\n{2,}))/g,hashElement);

	// 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,hashElement);
	*/
	text = text.replace(/(?:\n\n)([ ]{0,3}(?:<([?%])[^\r]*?\2>)[ \t]*(?=\n{2,}))/g,hashElement);

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

var hashElement = function(wholeMatch,m1) {
	var blockText = m1;

	// Undo double lines
	blockText = blockText.replace(/\n\n/g,"\n");
	blockText = blockText.replace(/^\n/,"");

	// strip trailing blank lines
	blockText = blockText.replace(/\n+$/g,"");

	// Replace the element text with a marker ("~KxK" where x is its key)
	blockText = "\n\n~K" + (g_html_blocks.push(blockText)-1) + "K\n\n";

	return blockText;
};

var _RunBlockGamut = function(text) {
//
// These are all the transformations that form block-level
// tags like paragraphs, headers, and list items.
//
	text = _DoHeaders(text);

	// Do Horizontal Rules:
	var key = hashBlock("<hr />");
	text = text.replace(/^[ ]{0,2}([ ]?\*[ ]?){3,}[ \t]*$/gm,key);
	text = text.replace(/^[ ]{0,2}([ ]?\-[ ]?){3,}[ \t]*$/gm,key);
	text = text.replace(/^[ ]{0,2}([ ]?\_[ ]?){3,}[ \t]*$/gm,key);

	text = _DoLists(text);
	text = _DoCodeBlocks(text);
	text = _DoBlockQuotes(text);

	// We already ran _HashHTMLBlocks() before, in Markdown(), but that
	// was to escape raw HTML in the original Markdown source. This time,
	// we're escaping the markup we've just created, so that we don't wrap
	// <p> tags around block-level tags.
	text = _HashHTMLBlocks(text);
	text = _FormParagraphs(text);

	return text;
}


var _RunSpanGamut = function(text) {
//
// These are all the transformations that occur *within* block-level
// tags like paragraphs, headers, and list items.
//

	text = _DoCodeSpans(text);
	text = _EscapeSpecialCharsWithinTagAttributes(text);
	text = _EncodeBackslashEscapes(text);

	// Process anchor and image tags. Images must come first,
	// because ![foo][f] looks like an anchor.
	text = _DoImages(text);
	text = _DoAnchors(text);

	// Make links out of things like `<http://example.com/>`
	// Must come after _DoAnchors(), because you can use < and >
	// delimiters in inline links like [this](<url>).
	text = _DoAutoLinks(text);
	text = _EncodeAmpsAndAngles(text);
	text = _DoItalicsAndBold(text);

	// Do hard breaks:
	text = text.replace(/  +\n/g," <br />\n");

	return text;
}

var _EscapeSpecialCharsWithinTagAttributes = function(text) {
//
// Within tags -- meaning between < and > -- encode [\ ` * _] so they
// don't conflict with their use in Markdown for code, italics and strong.
//

	// Build a regex to find HTML tags and comments.  See Friedl's 
	// "Mastering Regular Expressions", 2nd Ed., pp. 200-201.
	var regex = /(<[a-z\/!$]("[^"]*"|'[^']*'|[^'">])*>|<!(--.*?--\s*)+>)/gi;

	text = text.replace(regex, function(wholeMatch) {
		var tag = wholeMatch.replace(/(.)<\/?code>(?=.)/g,"$1`");
		tag = escapeCharacters(tag,"\\`*_");
		return tag;
	});

	return text;
}

var _DoAnchors = function(text) {
//
// Turn Markdown link shortcuts into XHTML <a> tags.
//
	//
	// First, handle reference-style links: [link text] [id]
	//

	/*
		text = text.replace(/
		(							// wrap whole match in $1
			\[
			(
				(?: