X-Git-Url: http://git.osdn.jp/view?a=blobdiff_plain;f=0.6.x%2Fjs%2F02_dom%2F09_XDomParser.js;fp=0.6.x%2Fjs%2F02_dom%2F09_XDomParser.js;h=648de81b528ba3b0b40f3a8f7cb5e1e825661e63;hb=541618cd9485cb041f46177d6869cc6d618ed1da;hp=0000000000000000000000000000000000000000;hpb=c54d46848e396b9208daa4d4cb535b4b461cb019;p=pettanr%2FclientJs.git

diff --git a/0.6.x/js/02_dom/09_XDomParser.js b/0.6.x/js/02_dom/09_XDomParser.js
new file mode 100644
index 0000000..648de81
--- /dev/null
+++ b/0.6.x/js/02_dom/09_XDomParser.js
@@ -0,0 +1,396 @@
+
+/*
+ * Original code by Erik John Resig (ejohn.org)
+ * http://ejohn.org/blog/pure-javascript-html-parser/
+ *
+ */
+
+X_Dom_Parser = {
+	CHARS : {
+		A:1,B:1,C:1,D:1,E:1,F:1,G:1,H:1,I:1,J:1,K:1,L:1,M:1,N:1,O:1,P:1,Q:1,R:1,S:1,T:1,U:1,V:1,W:1,X:1,Y:1,Z:1,
+		a:2,b:2,c:2,d:2,e:2,f:2,g:2,h:2,i:2,j:2,k:2,l:2,m:2,n:2,o:2,p:2,q:2,r:2,s:2,t:2,u:2,v:2,w:2,x:2,y:2,z:2,
+		'0' : 4, '1' : 4, '2' : 4, '3' : 4, '4' : 4, '5' : 4, '6' : 4, '7' : 4, '8' : 4, '9' : 4,
+		
+		'\t' : 16, '\r\n' : 16, '\r' : 16, '\n' : 16, '\f' : 16, '\b' : 16, ' ' : 16
+	},
+	alphabets  : 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz',
+	whiteSpace : '\t\r\n\f\b ',
+
+	// Empty Elements - HTML 4.01
+	empty : X.Dom.DTD.EMPTY,
+
+	// Block Elements - HTML 4.01
+	block : {ADDRESS:1,APPLET:1,BLOCKQUOTE:1,BUTTON:1,CENTER:1,DD:1,DEL:1,DIR:1,DIV:1,DL:1,DT:1,FIELDSET:1,FORM:1,FRAMESET:1,HR:1,IFRAME:1,INS:1,
+		ISINDEX:1,LI:1,MAP:1,MENU:1,NOFRAMES:1,NOSCRIPT:1,OBJECT:1,OL:1,P:1,PRE:1,SCRIPT:1,TABLE:1,TBODY:1,TD:1,TFOOT:1,TH:1,THEAD:1,TR:1,UL:1 },
+	// Inline Elements - HTML 4.01
+	inline : {A:1,ABBR:1,ACRONYM:1,APPLET:1,B:1,BASEFONT:1,BDO:1,BIG:1,BR:1,BUTTON:1,CITE:1,CODE:1,DEL:1,DFN:1,EM:1,FONT:1,I:1,IFRAME:1,IMG:1,
+		INPUT:1,INS:1,KBD:1,LABEL:1,MAP:1,OBJECT:1,Q:1,S:1,SAMP:1,SCRIPT:1,SELECT:1,SMALL:1,SPAN:1,STRIKE:1,STRONG:1,SUB:1,SUP:1,TEXTAREA:1,TT:1,U:1,VAR:1},
+	// Elements that you can, intentionally, leave open
+	// (and which close themselves)
+	closeSelf : {OLGROUP:1,DD:1,DT:1,LI:1,OPTIONS:1,P:1,TBODY:1,TD:1,TFOOT:1,TH:1,THEAD:1,TR:1}, // add tbody
+
+	sisters : {
+		TH : { TD : 1 },
+		TD : { TH : 1 },
+		DT : { DD : 1 },
+		DD : { DT : 1 },
+		COLGROUP : { CAPTION : 1 },
+		THEAD    : { CAPTION : 1, COLGROUP : 1 },
+		TFOOT    : { CAPTION : 1, COLGROUP : 1, THEAD : 1, TBODY : 1 },
+		TBODY    : { CAPTION : 1, COLGROUP : 1, THEAD : 1, TFOOT : 1 }
+	},
+	/*
+	 * http://www.tohoho-web.com/html/tbody.htm
+	 * HTML4.01では、ヘッダとフッタを先読みして表示するために、<tbody> よりも <tfoot> の方を先に記述しなくてはならないと定義されています。
+	 * IE5.0 などでは HEAD → BODY → FOOT の順に表示するのですが、
+	 * <tfoot> に未対応の古いブラウザでは、HEAD → FOOT → BODY の順に表示されてしまいます。
+	 * また、HTML5 では、<tfoot> と <tbody> の順番はどちらでもよいことになりました。
+	 */
+
+	// Attributes that have their values filled in disabled="disabled"
+	fillAttrs : X.Dom.Attr.noValue, //{checked:1,compact:1,declare:1,defer:1,disabled:1,ismap:1,multiple:1,nohref:1,noresize:1,noshade:1,nowrap:1,readonly:1,selected:1};
+
+	// Special Elements (can contain anything)
+	special : { SCRIPT : 1, STYLE : 1, PLAINTEXT : 1, XMP : 1, TEXTAREA : 1 },
+	
+	exec : function( html, handler, async ){
+		var special        = X_Dom_Parser.special,
+			//plainText      = X_Dom_Parser.plainText,
+			startTime      = async && X.getTime(),
+			_parseStartTag = X_Dom_Parser._parseStartTag,
+			_parseEndTag   = X_Dom_Parser._parseEndTag,
+			stack          = async ? async[ 1 ] : [],
+			lastHtml       = html,
+			chars, last, text, index;
+
+		while ( html ) {
+			chars = true;
+			last  = stack[ stack.length - 1 ];
+			
+			// Make sure we're not in a script or style element
+			if ( last && special[ last ] === 1 ) {
+				if( 0 <= ( index = html.toUpperCase().indexOf( '</' + last ) ) ){
+					handler.chars( html.substring( 0, index ) );
+					if( index = _parseEndTag( stack, handler, html ) ){
+						html = html.substring( index );
+					} else {
+						handler.chars( html );
+						html = '';
+					};
+				} else {
+					handler.chars( html );
+					html = '';
+				};
+			} else {
+				// Comment
+				if ( html.indexOf("<!--") === 0 ) {
+					if ( 0 < ( index = html.indexOf("-->") ) ) {
+						handler.comment( html.substring( 4, index ) );
+						html = html.substring( index + 3 );
+						chars = false;
+					};
+	
+				// end tag
+				} else if ( html.indexOf("</") === 0 ) {
+					if ( 2 < ( index = _parseEndTag( stack, handler, html ) ) ) {
+						html = html.substring( index );
+						chars = false;
+					};
+	
+				// start tag
+				} else if ( html.indexOf("<") === 0 ) {
+					if( index = _parseStartTag( stack, last, handler, html ) ){
+						html  = html.substring( index );
+						chars = false;
+					} else
+					if( index === false ){
+						return;
+					};
+				};
+
+				if ( chars ) {
+					index = html.indexOf("<");
+					
+					text = index < 0 ? html : html.substring( 0, index );
+					html = index < 0 ? '' : html.substring( index );
+					
+					handler.chars( text );
+				};
+
+			};
+
+			if( html === lastHtml ){
+				handler.err( html );
+				return;
+			};
+			
+			if( async && startTime + 15 <= X.getTime() && html ){
+				handler.progress( 1 - html.length / async[ 0 ] );
+				X.Timer.once( 0, X_Dom_Parser.exec, [ html, handler, async ] );
+				return;
+			};
+			
+			lastHtml = html;
+		};
+		
+		// Clean up any remaining tags
+		X_Dom_Parser.parseEndTag( stack, handler );
+		
+		async && handler.complete();
+	},
+
+	_parseStartTag : function( stack, last, handler, html ){
+		var alphabets = X_Dom_Parser.CHARS,
+			whiteSpace = X_Dom_Parser.CHARS,
+			saveAttr = X_Dom_Parser.saveAttr,
+			uri   = X.Dom.DTD.ATTR_VAL_IS_URI,
+			phase = 0,
+			l     = html.length,
+			i     = 0,
+			attrs = [],
+			tagName, empty = false,
+			chr, start, attrName, quot, escape;
+		
+		while( i < l && phase < 9 ){
+			chr = html.charAt( i );
+			switch( phase ){
+				case 0 :
+					chr === '<' && ( ++phase );
+					break;
+				case 1 : // タグ名の開始を待つ
+					( alphabets[ chr ] & 3 ) && ( ++phase && ( start = i ) );
+					break;
+				case 2 : // タグ名の終わりの空白文字を待つ
+					( whiteSpace[ chr ] & 16 ) ?
+						( ++phase && ( tagName = html.substring( start, i ) ) ) :
+					( chr === '>' || ( empty = html.substr( i, 2 ) === '/>' ) ) &&
+						( ( tagName = html.substring( start, i ) ) && ( phase = 9 ) );
+					break;
+				case 3 : // 属性名の開始を待つ
+					( alphabets[ chr ] & 3 ) ?
+						( ++phase && ( start = i ) ) :
+					( chr === '>' || ( empty = html.substr( i, 2 ) === '/>' ) ) &&
+						( phase = 9 );
+					break;
+				case 4 : // 属性名の終わりを待つ
+					chr === '=' ?
+						( ( phase = 6 ) && ( attrName = html.substring( start, i ) ) ) :
+					( whiteSpace[ chr ] & 16 ) &&
+						( ( phase = 5 ) && ( attrName = html.substring( start, i ) ) );
+					break;
+				case 5 : // 属性の = または次の属性または htmlタグの閉じ
+					( whiteSpace[ chr ] & 16 ) ?// ie4 未対応の属性には cite = http:// となる
+						1 :
+					( alphabets[ chr ] & 3 ) ?
+						( ( phase = 4 ) && ( attrs[ attrs.length ] = attrName ) && ( start = i ) ) :
+					chr === '=' ?
+						( phase = 6 ) :
+					( chr === '>' || ( empty = html.substr( i, 2 ) === '/>' ) ) &&
+						( ( phase = 9 ) && ( attrs[ attrs.length ] = attrName ) );
+					break;
+				case 6 : // 属性値の開始 quot を待つ
+					( chr === '"' || chr === "'" ) ?
+						( ( phase = 7 ) && ( quot = chr ) && ( start = i + 1 ) ):
+					!( whiteSpace[ chr ] & 16 ) &&
+						( ( phase = 8 ) && ( start = i ) ); // no quot
+					break;
+				case 7 : //属性値の閉じ quot を待つ
+					!escape && ( chr === quot ) && ( phase = 3 ) && saveAttr( attrs, attrName, html.substring( start, i ) );
+					break;
+				case 8 : //閉じ quot のない属性の値
+					( whiteSpace[ chr ] & 16 ) ?
+						( ( phase = 3 ) && saveAttr( attrs, attrName, html.substring( start, i ) ) ) :
+					( chr === '>' ) ?
+						( ( phase = 9 ) && saveAttr( attrs, attrName, html.substring( start, i ) ) ) :
+					!escape && !uri[ attrName ] && ( empty = html.substr( i, 2 ) === '/>' ) && // attr の val が uri で / で終わりかつ、未対応属性の場合
+						( phase = 9 );
+					break;
+			};
+			escape = chr === '\\' && !escape; // \\\\ is not escape for "
+			++i;
+		};
+		if( phase === 9 ){
+			if( empty ) ++i;
+			if( X_Dom_Parser.parseStartTag( stack, last, handler, tagName.toUpperCase(), attrs, empty, i ) === false ) return false;
+			return i;
+		};
+		return 0; // error
+	},
+
+	_parseEndTag : function( stack, handler, html ){
+		var alphabets = X_Dom_Parser.CHARS,
+			whiteSpace = X_Dom_Parser.CHARS,
+			phase = 0,
+			l     = html.length,
+			i     = 0,
+			tagName,
+			chr, start;
+		
+		while( i < l && phase < 9 ){
+			chr = html.charAt( i );
+			switch( phase ){
+				case 0 :
+					html.substr( i, 2 ) === '</' && ( ++phase && ++i );
+					break;
+				case 1 : // タグ名の開始を待つ
+					( alphabets[ chr ] & 3 ) && ( ++phase && ( start = i ) );
+					break;
+				case 2 : // タグ名の終わりの空白文字を待つ
+					( whiteSpace[ chr ] & 16 ) && ( ++phase );
+					( chr === '>' ) && ( phase = 9 );
+					( phase !== 2 ) && ( tagName = html.substring( start, i ) );
+					break;
+				case 3 : // タグの終了を待つ
+					chr === '>' && ( phase = 9 );
+					break;
+			};
+			++i;
+		};
+		if( phase === 9 ){
+			X_Dom_Parser.parseEndTag( stack, handler, tagName.toUpperCase() );
+			return i;
+		};
+		return 0; // error
+	},
+
+	saveAttr : function( attrs, name, value ){
+		name  = name.toLowerCase();
+		value = X_Dom_Parser.fillAttrs[ name ] === 1 ? name : value;
+		attrs[ attrs.length ] = {
+			name    : name,
+			value   : value,
+			escaped :
+				value.indexOf( '"' ) !== -1 ?
+					value.split( '"' ).join( '\\"' ).split( '\\\\"' ).join( '\\"' ) :
+					value
+		};
+	},
+
+	parseStartTag : function( stack, last, handler, tagName, attrs, unary, index ) {
+		var inline   = X_Dom_Parser.inline,
+			parseEndTag = X_Dom_Parser.parseEndTag,
+			sisters  = X_Dom_Parser.sisters;
+		if ( X_Dom_Parser.block[ tagName ] === 1 ) {
+			while ( last && inline[ last ] === 1 ) {
+				parseEndTag( stack, handler, last );
+				last = stack[ stack.length - 1 ];
+			};
+		};
+		last && X_Dom_Parser.closeSelf[ tagName ] === 1 && ( last === tagName || ( sisters[ tagName ] && sisters[ tagName ][ last ] === 1 ) ) && parseEndTag( stack, handler, last );
+		unary = unary || X_Dom_Parser.empty[ tagName ];
+		!unary && ( stack[ stack.length ] = tagName );
+		
+		return handler.start( tagName, attrs, unary, index );
+	},
+
+	parseEndTag : function( stack, handler, tagName ) {
+		var pos = 0, i = stack.length;
+		// If no tag name is provided, clean shop
+		
+		// Find the closest opened tag of the same type
+		if ( tagName )
+			for ( pos = i; 0 <= pos; )
+				if ( stack[ --pos ] === tagName )
+					break;
+		
+		if ( 0 <= pos ) {
+			// Close all the open elements, up the stack
+			for ( ; pos < i; )
+				handler.end( stack[ --i ] );
+			
+			// Remove the open elements from the stack
+			stack.length = pos;
+		};
+	}
+	
+};
+
+X.Dom._htmlStringToXNode = {
+	flat : null,
+	nest : [],
+	err : function( html ){
+		X.Dom._htmlStringToXNode.flat.length = 0;
+		X.Dom._htmlStringToXNode.ignoreError !== true && X.Logger.warn( 'X_Dom_Parser() error ' + html );
+	},
+	start : function( tagName, attrs, noChild, length ){
+		var xnode,
+			nest   = X.Dom._htmlStringToXNode.nest,
+			flat   = X.Dom._htmlStringToXNode.flat,
+			l      = nest.length,
+			attr, name, i, _attrs; //, toIndex;
+		if( l ){
+			xnode = nest[ l - 1 ].create( tagName );
+		} else {
+			xnode = flat[ flat.length ] = X.Dom.Node.create( tagName );
+		};
+		if( !noChild ) nest[ l ] = xnode;
+		if( i = attrs.length ){
+			_attrs = {};
+			for( ; i; ){
+				if( attr = attrs[ --i ] ){
+					if( typeof attr === 'string' ){
+						name = attr;
+						_attrs[ name ] = true;
+					} else {
+						name = attr.name;
+						_attrs[ name ] = attr.escaped;
+					};
+				};
+			};
+			xnode.attr( _attrs );
+		};
+	},
+	end : function(){
+		0 < X.Dom._htmlStringToXNode.nest.length && ( --X.Dom._htmlStringToXNode.nest.length );
+	},
+	chars : function( text ){
+		if( X.Dom._htmlStringToXNode.nest.length ){
+			X.Dom._htmlStringToXNode.nest[ X.Dom._htmlStringToXNode.nest.length - 1 ].createText( text );
+		} else {
+			X.Dom._htmlStringToXNode.flat[ X.Dom._htmlStringToXNode.flat.length ] = X.Dom.Node.createText( text );
+		};
+	},
+	comment : X.emptyFunction
+};
+
+X.Dom.parse = function( html, ignoreError ){
+	var worker = X.Dom._htmlStringToXNode, ret;
+	worker.flat = [];
+	worker.nest.length = 0;
+	worker.ignoreError = ignoreError;
+	X_Dom_Parser.exec( html, worker );
+	ret = worker.flat;
+	delete worker.flat;
+	return ret;
+};
+
+X.Dom._asyncHtmlStringToXNode = {
+	err : function( html ){
+		X.Dom._htmlStringToXNode.err( html );
+		this.asyncDispatch( 0, { type : X.Event.ERROR } );
+	},
+	start   : X.Dom._htmlStringToXNode.start,
+	end     : X.Dom._htmlStringToXNode.end,
+	chars   : X.Dom._htmlStringToXNode.chars,
+	comment : X.emptyFunction,
+	
+	progress : function( pct ){
+		this.asyncDispatch( 0, { type : X.Event.PROGRESS, percent : pct } );
+	},
+	complete : function(){
+		var ret = X.Dom._htmlStringToXNode.flat;
+		delete X.Dom._htmlStringToXNode.flat;
+		this.asyncDispatch( 0, { type : X.Event.SUCCESS, xnodes : ret } );
+	}
+};
+
+X.Dom.asyncParse = function( html, ignoreError ){
+	var dispatcher = X.Class._override( new X.EventDispatcher(), X.Dom._asyncHtmlStringToXNode ),
+		worker = X.Dom._htmlStringToXNode;
+	dispatcher.listenOnce( X.Event.SUCCESS, dispatcher, dispatcher.kill );
+	worker.flat = [];
+	worker.nest.length = 0;
+	worker.ignoreError = ignoreError;
+	X_Dom_Parser.exec( html, dispatcher, [ html.length, [] ] );
+	return dispatcher;
+};