微信小程序/bml/wxParse/htmlparser.js

这里只显示每个文件的开头 60 行。登录后可以解锁完整代码。

微信扫码关注公众号，代码整理好后第一时间通知你。

/**
 * 
 * htmlParser改造自: https://github.com/blowsie/Pure-JavaScript-HTML5-Parser
 * 
 * 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 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,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 5
var 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;
				}