| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182 | /** * author: Di (微信小程序开发工程师) * organization: WeAppDev(微信小程序开发论坛)(http://weappdev.com) *               垂直微信小程序开发交流社区 *  * github地址: https://github.com/icindy/wxParse *  * for: 微信小程序富文本解析 * detail : http://weappdev.com/t/wxparse-alpha0-1-html-markdown/184 */// Regular Expressions for parsing tags and attributesvar 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 5var empty = makeMap("area,base,basefont,br,col,frame,hr,img,input,link,meta,param,embed,command,keygen,source,track,wbr");// Block Elements - HTML 5var block = makeMap("a,address,code,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 5var inline = makeMap("abbr,acronym,applet,b,basefont,bdo,big,br,button,cite,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("wxxxcode-style,script,style,view,scroll-view,block");function HTMLParser(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;		}	}};function makeMap(str) {	var obj = {}, items = str.split(",");	for (var i = 0; i < items.length; i++)		obj[items[i]] = true;	return obj;}module.exports = HTMLParser;
 |