htmlparser.js 10.7 KB
Newer Older
txy committed
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367
/*
 * HTML5 Parser By Sam Blowes
 *
 * Designed for HTML5 documents
 *
 * Original code by John Resig (ejohn.org)
 * http://ejohn.org/blog/pure-javascript-html-parser/
 * Original code by Erik Arvidsson, Mozilla Public License
 * http://erik.eae.net/simplehtmlparser/simplehtmlparser.js
 *
 * ----------------------------------------------------------------------------
 * License
 * ----------------------------------------------------------------------------
 *
 * This code is triple licensed using Apache Software License 2.0,
 * Mozilla Public License or GNU Public License
 * 
 * ////////////////////////////////////////////////////////////////////////////
 * 
 * Licensed under the Apache License, Version 2.0 (the "License"); you may not
 * use this file except in compliance with the License.  You may obtain a copy
 * of the License at http://www.apache.org/licenses/LICENSE-2.0
 * 
 * ////////////////////////////////////////////////////////////////////////////
 * 
 * The contents of this file are subject to the Mozilla Public License
 * Version 1.1 (the "License"); you may not use this file except in
 * compliance with the License. You may obtain a copy of the License at
 * http://www.mozilla.org/MPL/
 * 
 * Software distributed under the License is distributed on an "AS IS"
 * basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
 * License for the specific language governing rights and limitations
 * under the License.
 * 
 * The Original Code is Simple HTML Parser.
 * 
 * The Initial Developer of the Original Code is Erik Arvidsson.
 * Portions created by Erik Arvidssson are Copyright (C) 2004. All Rights
 * Reserved.
 * 
 * ////////////////////////////////////////////////////////////////////////////
 * 
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version 2
 * of the License, or (at your option) any later version.
 * 
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 * 
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
 *
 * ----------------------------------------------------------------------------
 * Usage
 * ----------------------------------------------------------------------------
 *
 * // Use like so:
 * HTMLParser(htmlString, {
 *     start: function(tag, attrs, unary) {},
 *     end: function(tag) {},
 *     chars: function(text) {},
 *     comment: function(text) {}
 * });
 *
 * // or to get an XML string:
 * HTMLtoXML(htmlString);
 *
 * // or to get an XML DOM Document
 * HTMLtoDOM(htmlString);
 *
 * // or to inject into an existing document/DOM node
 * HTMLtoDOM(htmlString, document);
 * HTMLtoDOM(htmlString, document.body);
 *
 */

(function () {

	// Regular Expressions for parsing tags and attributes
	var startTag = /^<([-A-Za-z0-9_]+)((?:\s+[a-zA-Z_:][-a-zA-Z0-9_:.]*(?:\s*=\s*(?:(?:"[^"]*")|(?:'[^']*')|[^>\s]+))?)*)\s*(\/?)>/,
		endTag = /^<\/([-A-Za-z0-9_]+)[^>]*>/,
		attr = /([a-zA-Z_:][-a-zA-Z0-9_:.]*)(?:\s*=\s*(?:(?:"((?:\\.|[^"])*)")|(?:'((?:\\.|[^'])*)')|([^>\s]+)))?/g;

	// Empty Elements - HTML 5
	var empty = makeMap("area,base,basefont,br,col,frame,hr,img,input,link,meta,param,embed,command,keygen,source,track,wbr");

	// Block Elements - HTML 5
	var block = makeMap("a,address,article,applet,aside,audio,blockquote,button,canvas,center,dd,del,dir,div,dl,dt,fieldset,figcaption,figure,footer,form,frameset,h1,h2,h3,h4,h5,h6,header,hgroup,hr,iframe,ins,isindex,li,map,menu,noframes,noscript,object,ol,output,p,pre,section,script,table,tbody,td,tfoot,th,thead,tr,ul,video");

	// Inline Elements - HTML 5
	var inline = makeMap("abbr,acronym,applet,b,basefont,bdo,big,br,button,cite,code,del,dfn,em,font,i,iframe,img,input,ins,kbd,label,map,object,q,s,samp,script,select,small,span,strike,strong,sub,sup,textarea,tt,u,var");

	// Elements that you can, intentionally, leave open
	// (and which close themselves)
	var closeSelf = makeMap("colgroup,dd,dt,li,options,p,td,tfoot,th,thead,tr");

	// Attributes that have their values filled in disabled="disabled"
	var fillAttrs = makeMap("checked,compact,declare,defer,disabled,ismap,multiple,nohref,noresize,noshade,nowrap,readonly,selected");

	// Special Elements (can contain anything)
	var special = makeMap("script,style");

	var HTMLParser = this.HTMLParser = function (html, handler) {
		var index, chars, match, stack = [], last = html;
		stack.last = function () {
			return this[this.length - 1];
		};

		while (html) {
			chars = true;

			// Make sure we're not in a script or style element
			if (!stack.last() || !special[stack.last()]) {

				// Comment
				if (html.indexOf("<!--") == 0) {
					index = html.indexOf("-->");

					if (index >= 0) {
						if (handler.comment)
							handler.comment(html.substring(4, index));
						html = html.substring(index + 3);
						chars = false;
					}

					// end tag
				} else if (html.indexOf("</") == 0) {
					match = html.match(endTag);

					if (match) {
						html = html.substring(match[0].length);
						match[0].replace(endTag, parseEndTag);
						chars = false;
					}

					// start tag
				} else if (html.indexOf("<") == 0) {
					match = html.match(startTag);

					if (match) {
						html = html.substring(match[0].length);
						match[0].replace(startTag, parseStartTag);
						chars = false;
					}
				}

				if (chars) {
					index = html.indexOf("<");

					var text = index < 0 ? html : html.substring(0, index);
					html = index < 0 ? "" : html.substring(index);

					if (handler.chars)
						handler.chars(text);
				}

			} else {
				html = html.replace(new RegExp("([\\s\\S]*?)<\/" + stack.last() + "[^>]*>"), function (all, text) {
					text = text.replace(/<!--([\s\S]*?)-->|<!\[CDATA\[([\s\S]*?)]]>/g, "$1$2");
					if (handler.chars)
						handler.chars(text);

					return "";
				});

				parseEndTag("", stack.last());
			}

			if (html == last)
				throw "Parse Error: " + html;
			last = html;
		}

		// Clean up any remaining tags
		parseEndTag();

		function parseStartTag(tag, tagName, rest, unary) {
			tagName = tagName.toLowerCase();

			if (block[tagName]) {
				while (stack.last() && inline[stack.last()]) {
					parseEndTag("", stack.last());
				}
			}

			if (closeSelf[tagName] && stack.last() == tagName) {
				parseEndTag("", tagName);
			}

			unary = empty[tagName] || !!unary;

			if (!unary)
				stack.push(tagName);

			if (handler.start) {
				var attrs = [];

				rest.replace(attr, function (match, name) {
					var value = arguments[2] ? arguments[2] :
						arguments[3] ? arguments[3] :
						arguments[4] ? arguments[4] :
						fillAttrs[name] ? name : "";

					attrs.push({
						name: name,
						value: value,
						escaped: value.replace(/(^|[^\\])"/g, '$1\\\"') //"
					});
				});

				if (handler.start)
					handler.start(tagName, attrs, unary);
			}
		}

		function parseEndTag(tag, tagName) {
			// If no tag name is provided, clean shop
			if (!tagName)
				var pos = 0;

				// Find the closest opened tag of the same type
			else
				for (var pos = stack.length - 1; pos >= 0; pos--)
					if (stack[pos] == tagName)
						break;

			if (pos >= 0) {
				// Close all the open elements, up the stack
				for (var i = stack.length - 1; i >= pos; i--)
					if (handler.end)
						handler.end(stack[i]);

				// Remove the open elements from the stack
				stack.length = pos;
			}
		}
	};

	this.HTMLtoXML = function (html) {
		var results = "";

		HTMLParser(html, {
			start: function (tag, attrs, unary) {
				results += "<" + tag;

				for (var i = 0; i < attrs.length; i++)
					results += " " + attrs[i].name + '="' + attrs[i].escaped + '"';
				results += ">";
			},
			end: function (tag) {
				results += "</" + tag + ">";
			},
			chars: function (text) {
				results += text;
			},
			comment: function (text) {
				results += "<!--" + text + "-->";
			}
		});

		return results;
	};

	this.HTMLtoDOM = function (html, doc) {
		// There can be only one of these elements
		var one = makeMap("html,head,body,title");

		// Enforce a structure for the document
		var structure = {
			link: "head",
			base: "head"
		};

		if (!doc) {
			if (typeof DOMDocument != "undefined")
				doc = new DOMDocument();
			else if (typeof document != "undefined" && document.implementation && document.implementation.createDocument)
				doc = document.implementation.createDocument("", "", null);
			else if (typeof ActiveX != "undefined")
				doc = new ActiveXObject("Msxml.DOMDocument");

		} else
			doc = doc.ownerDocument ||
				doc.getOwnerDocument && doc.getOwnerDocument() ||
				doc;

		var elems = [],
			documentElement = doc.documentElement ||
				doc.getDocumentElement && doc.getDocumentElement();

		// If we're dealing with an empty document then we
		// need to pre-populate it with the HTML document structure
		if (!documentElement && doc.createElement) (function () {
			var html = doc.createElement("html");
			var head = doc.createElement("head");
			head.appendChild(doc.createElement("title"));
			html.appendChild(head);
			html.appendChild(doc.createElement("body"));
			doc.appendChild(html);
		})();

		// Find all the unique elements
		if (doc.getElementsByTagName)
			for (var i in one)
				one[i] = doc.getElementsByTagName(i)[0];

		// If we're working with a document, inject contents into
		// the body element
		var curParentNode = one.body;

		HTMLParser(html, {
			start: function (tagName, attrs, unary) {
				// If it's a pre-built element, then we can ignore
				// its construction
				if (one[tagName]) {
					curParentNode = one[tagName];
					if (!unary) {
						elems.push(curParentNode);
					}
					return;
				}

				var elem = doc.createElement(tagName);

				for (var attr in attrs)
					elem.setAttribute(attrs[attr].name, attrs[attr].value);

				if (structure[tagName] && typeof one[structure[tagName]] != "boolean")
					one[structure[tagName]].appendChild(elem);

				else if (curParentNode && curParentNode.appendChild)
					curParentNode.appendChild(elem);

				if (!unary) {
					elems.push(elem);
					curParentNode = elem;
				}
			},
			end: function (tag) {
				elems.length -= 1;

				// Init the new parentNode
				curParentNode = elems[elems.length - 1];
			},
			chars: function (text) {
				curParentNode.appendChild(doc.createTextNode(text));
			},
			comment: function (text) {
				// create comment node
			}
		});

		return doc;
	};

	function makeMap(str) {
		var obj = {}, items = str.split(",");
		for (var i = 0; i < items.length; i++)
			obj[items[i]] = true;
		return obj;
	}
})();