showdown.js.svn-base

mooltools源码很不错的源码

	text += "~0";

	text = text.replace(/(?:\n\n|^)((?:(?:[ ]{4}|\t).*\n+)+)(\n*[ ]{0,3}[^ \t\n]|(?=~0))/g,
		function(wholeMatch,m1,m2) {
			var codeblock = m1;
			var nextChar = m2;

			codeblock = _EncodeCode( _Outdent(codeblock));
			codeblock = _Detab(codeblock);
			codeblock = codeblock.replace(/^\n+/g,""); // trim leading newlines
			codeblock = codeblock.replace(/\n+$/g,""); // trim trailing whitespace

			codeblock = "<pre><code>" + codeblock + "\n</code></pre>";

			return hashBlock(codeblock) + nextChar;
		}
	);

	// attacklab: strip sentinel
	text = text.replace(/~0/,"");

	return text;
}

var hashBlock = function(text) {
	text = text.replace(/(^\n+|\n+$)/g,"");
	return "\n\n~K" + (g_html_blocks.push(text)-1) + "K\n\n";
}


var _DoCodeSpans = function(text) {
//
//   *  Backtick quotes are used for <code></code> spans.
// 
//   *  You can use multiple backticks as the delimiters if you want to
//	 include literal backticks in the code span. So, this input:
//	 
//		 Just type ``foo `bar` baz`` at the prompt.
//	 
//	   Will translate to:
//	 
//		 <p>Just type <code>foo `bar` baz</code> at the prompt.</p>
//	 
//	There's no arbitrary limit to the number of backticks you
//	can use as delimters. If you need three consecutive backticks
//	in your code, use four for delimiters, etc.
//
//  *  You can use spaces to get literal backticks at the edges:
//	 
//		 ... type `` `bar` `` ...
//	 
//	   Turns to:
//	 
//		 ... type <code>`bar`</code> ...
//

	/*
		text = text.replace(/
			(^|[^\\])					// Character before opening ` can't be a backslash
			(`+)						// $2 = Opening run of `
			(							// $3 = The code block
				[^\r]*?
				[^`]					// attacklab: work around lack of lookbehind
			)
			\2							// Matching closer
			(?!`)
		/gm, function(){...});
	*/

	text = text.replace(/(^|[^\\])(`+)([^\r]*?[^`])\2(?!`)/gm,
		function(wholeMatch,m1,m2,m3,m4) {
			var c = m3;
			c = c.replace(/^([ \t]*)/g,"");	// leading whitespace
			c = c.replace(/[ \t]*$/g,"");	// trailing whitespace
			c = _EncodeCode(c);
			return m1+"<code>"+c+"</code>";
		});

	return text;
}


var _EncodeCode = function(text) {
//
// Encode/escape certain characters inside Markdown code runs.
// The point is that in code, these characters are literals,
// and lose their special Markdown meanings.
//
	// Encode all ampersands; HTML entities are not
	// entities within a Markdown code span.
	text = text.replace(/&/g,"&amp;");

	// Do the angle bracket song and dance:
	text = text.replace(/</g,"&lt;");
	text = text.replace(/>/g,"&gt;");

	// Now, escape characters that are magic in Markdown:
	text = escapeCharacters(text,"\*_{}[]\\",false);

// jj the line above breaks this:
//---

//* Item

//   1. Subitem

//            special char: *
//---

	return text;
}


var _DoItalicsAndBold = function(text) {

	// <strong> must go first:
	text = text.replace(/(\*\*|__)(?=\S)([^\r]*?\S[*_]*)\1/g,
		"<strong>$2</strong>");

	text = text.replace(/(\*|_)(?=\S)([^\r]*?\S)\1/g,
		"<em>$2</em>");

	return text;
}


var _DoBlockQuotes = function(text) {

	/*
		text = text.replace(/
		(								// Wrap whole match in $1
			(
				^[ \t]*>[ \t]?			// '>' at the start of a line
				.+\n					// rest of the first line
				(.+\n)*					// subsequent consecutive lines
				\n*						// blanks
			)+
		)
		/gm, function(){...});
	*/

	text = text.replace(/((^[ \t]*>[ \t]?.+\n(.+\n)*\n*)+)/gm,
		function(wholeMatch,m1) {
			var bq = m1;

			// attacklab: hack around Konqueror 3.5.4 bug:
			// "----------bug".replace(/^-/g,"") == "bug"

			bq = bq.replace(/^[ \t]*>[ \t]?/gm,"~0");	// trim one level of quoting

			// attacklab: clean up hack
			bq = bq.replace(/~0/g,"");

			bq = bq.replace(/^[ \t]+$/gm,"");		// trim whitespace-only lines
			bq = _RunBlockGamut(bq);				// recurse

			bq = bq.replace(/(^|\n)/g,"$1  ");
			// These leading spaces screw with <pre> content, so we need to fix that:
			bq = bq.replace(
					/(\s*<pre>[^\r]+?<\/pre>)/gm,
				function(wholeMatch,m1) {
					var pre = m1;
					// attacklab: hack around Konqueror 3.5.4 bug:
					pre = pre.replace(/^  /mg,"~0");
					pre = pre.replace(/~0/g,"");
					return pre;
				});

			return hashBlock("<blockquote>\n" + bq + "\n</blockquote>");
		});
	return text;
}


var _FormParagraphs = function(text) {
//
//  Params:
//    $text - string to process with html <p> tags
//

	// Strip leading and trailing lines:
	text = text.replace(/^\n+/g,"");
	text = text.replace(/\n+$/g,"");

	var grafs = text.split(/\n{2,}/g);
	var grafsOut = new Array();

	//
	// Wrap <p> tags.
	//
	var end = grafs.length;
	for (var i=0; i<end; i++) {
		var str = grafs[i];

		// if this is an HTML marker, copy it
		if (str.search(/~K(\d+)K/g) >= 0) {
			grafsOut.push(str);
		}
		else if (str.search(/\S/) >= 0) {
			str = _RunSpanGamut(str);
			str = str.replace(/^([ \t]*)/g,"<p>");
			str += "</p>"
			grafsOut.push(str);
		}

	}

	//
	// Unhashify HTML blocks
	//
	end = grafsOut.length;
	for (var i=0; i<end; i++) {
		// if this is a marker for an html block...
		while (grafsOut[i].search(/~K(\d+)K/) >= 0) {
			var blockText = g_html_blocks[RegExp.$1];
			blockText = blockText.replace(/\$/g,"$$$$"); // Escape any dollar signs
			grafsOut[i] = grafsOut[i].replace(/~K\d+K/,blockText);
		}
	}

	return grafsOut.join("\n\n");
}


var _EncodeAmpsAndAngles = function(text) {
// Smart processing for ampersands and angle brackets that need to be encoded.

	// Ampersand-encoding based entirely on Nat Irons's Amputator MT plugin:
	//   http://bumppo.net/projects/amputator/
	text = text.replace(/&(?!#?[xX]?(?:[0-9a-fA-F]+|\w+);)/g,"&amp;");

	// Encode naked <'s
	text = text.replace(/<(?![a-z\/?\$!])/gi,"&lt;");

	return text;
}


var _EncodeBackslashEscapes = function(text) {
//
//   Parameter:  String.
//   Returns:	The string, with after processing the following backslash
//			   escape sequences.
//

	// attacklab: The polite way to do this is with the new
	// escapeCharacters() function:
	//
	// 	text = escapeCharacters(text,"\\",true);
	// 	text = escapeCharacters(text,"`*_{}[]()>#+-.!",true);
	//
	// ...but we're sidestepping its use of the (slow) RegExp constructor
	// as an optimization for Firefox.  This function gets called a LOT.

	text = text.replace(/\\(\\)/g,escapeCharacters_callback);
	text = text.replace(/\\([`*_{}\[\]()>#+-.!])/g,escapeCharacters_callback);
	return text;
}


var _DoAutoLinks = function(text) {

	text = text.replace(/<((https?|ftp|dict):[^'">\s]+)>/gi,"<a href=\"$1\">$1</a>");

	// Email addresses: <[e-mail]>

	/*
		text = text.replace(/
			<
			(?:mailto:)?
			(
				[-.\w]+
				\@
				[-a-z0-9]+(\.[-a-z0-9]+)*\.[a-z]+
			)
			>
		/gi, _DoAutoLinks_callback());
	*/
	text = text.replace(/<(?:mailto:)?([-.\w]+\@[-a-z0-9]+(\.[-a-z0-9]+)*\.[a-z]+)>/gi,
		function(wholeMatch,m1) {
			return _EncodeEmailAddress( _UnescapeSpecialChars(m1) );
		}
	);

	return text;
}


var _EncodeEmailAddress = function(addr) {
//
//  Input: an email address, e.g. "[e-mail]"
//
//  Output: the email address as a mailto link, with each character
//	of the address encoded as either a decimal or hex entity, in
//	the hopes of foiling most address harvesting spam bots. E.g.:
//
//	<a href="&#x6D;&#97;&#105;&#108;&#x74;&#111;:&#102;&#111;&#111;&#64;&#101;
//	   x&#x61;&#109;&#x70;&#108;&#x65;&#x2E;&#99;&#111;&#109;">&#102;&#111;&#111;
//	   &#64;&#101;x&#x61;&#109;&#x70;&#108;&#x65;&#x2E;&#99;&#111;&#109;</a>
//
//  Based on a filter by Matthew Wickline, posted to the BBEdit-Talk
//  mailing list: <http://tinyurl.com/yu7ue>
//

	// attacklab: why can't javascript speak hex?
	function char2hex(ch) {
		var hexDigits = '0123456789ABCDEF';
		var dec = ch.charCodeAt(0);
		return(hexDigits.charAt(dec>>4) + hexDigits.charAt(dec&15));
	}

	var encode = [
		function(ch){return "&#"+ch.charCodeAt(0)+";";},
		function(ch){return "&#x"+char2hex(ch)+";";},
		function(ch){return ch;}
	];

	addr = "mailto:" + addr;

	addr = addr.replace(/./g, function(ch) {
		if (ch == "@") {
		   	// this *must* be encoded. I insist.
			ch = encode[Math.floor(Math.random()*2)](ch);
		} else if (ch !=":") {
			// leave ':' alone (to spot mailto: later)
			var r = Math.random();
			// roughly 10% raw, 45% hex, 45% dec
			ch =  (
					r > .9  ?	encode[2](ch)   :
					r > .45 ?	encode[1](ch)   :
								encode[0](ch)
				);
		}
		return ch;
	});

	addr = "<a href=\"" + addr + "\">" + addr + "</a>";
	addr = addr.replace(/">.+:/g,"\">"); // strip the mailto: from the visible part

	return addr;
}


var _UnescapeSpecialChars = function(text) {
//
// Swap back in all the special characters we've hidden.
//
	text = text.replace(/~E(\d+)E/g,
		function(wholeMatch,m1) {
			var charCodeToReplace = parseInt(m1);
			return String.fromCharCode(charCodeToReplace);
		}
	);
	return text;
}


var _Outdent = function(text) {
//
// Remove one level of line-leading tabs or spaces
//

	// attacklab: hack around Konqueror 3.5.4 bug:
	// "----------bug".replace(/^-/g,"") == "bug"

	text = text.replace(/^(\t|[ ]{1,4})/gm,"~0"); // attacklab: g_tab_width

	// attacklab: clean up hack
	text = text.replace(/~0/g,"")

	return text;
}

var _Detab = function(text) {
// attacklab: Detab's completely rewritten for speed.
// In perl we could fix it by anchoring the regexp with \G.
// In javascript we're less fortunate.

	// expand first n-1 tabs
	text = text.replace(/\t(?=\t)/g,"    "); // attacklab: g_tab_width

	// replace the nth with two sentinels
	text = text.replace(/\t/g,"~A~B");

	// use the sentinel to anchor our regex so it doesn't explode
	text = text.replace(/~B(.+?)~A/g,
		function(wholeMatch,m1,m2) {
			var leadingText = m1;
			var numSpaces = 4 - leadingText.length % 4;  // attacklab: g_tab_width

			// there *must* be a better way to do this:
			for (var i=0; i<numSpaces; i++) leadingText+=" ";

			return leadingText;
		}
	);

	// clean up sentinels
	text = text.replace(/~A/g,"    ");  // attacklab: g_tab_width
	text = text.replace(/~B/g,"");

	return text;
}


//
//  attacklab: Utility functions
//


var escapeCharacters = function(text, charsToEscape, afterBackslash) {
	// First we have to escape the escape characters so that
	// we can build a character class out of them
	var regexString = "([" + charsToEscape.replace(/([\[\]\\])/g,"\\$1") + "])";

	if (afterBackslash) {
		regexString = "\\\\" + regexString;
	}

	var regex = new RegExp(regexString,"g");
	text = text.replace(regex,escapeCharacters_callback);

	return text;
}


var escapeCharacters_callback = function(wholeMatch,m1) {
	var charCodeToEscape = m1.charCodeAt(0);
	return "~E"+charCodeToEscape+"E";
}

} // end of Showdown.converter