"use strict"; var startTag = /^<([-A-Za-z0-9_]+)((?:\s+[a-zA-Z_:][-a-zA-Z0-9_:.]*(?:\s*=\s*(?:(?:"[^"]*")|(?:'[^']*')|[^>\s]+))?)*)\s*(\/?)>/; var endTag = /^<\/([-A-Za-z0-9_]+)[^>]*>/; var attr = /([a-zA-Z_:][-a-zA-Z0-9_:.]*)(?:\s*=\s*(?:(?:"((?:\\.|[^"])*)")|(?:'((?:\\.|[^'])*)')|([^>\s]+)))?/g; var empty = makeMap("area,base,basefont,br,col,frame,hr,img,input,link,meta,param,embed,command,keygen,source,track,wbr"); 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,isindex,li,map,menu,noframes,noscript,object,ol,output,p,pre,section,script,table,tbody,td,tfoot,th,thead,tr,ul,video"); 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"); var closeSelf = makeMap("colgroup,dd,dt,li,options,p,td,tfoot,th,thead,tr"); var fillAttrs = makeMap("checked,compact,declare,defer,disabled,ismap,multiple,nohref,noresize,noshade,nowrap,readonly,selected"); var special = makeMap("script,style"); function HTMLParser(html, handler) { var index; var chars; var match; var stack = []; var last = html; stack.last = function() { return this[this.length - 1]; }; while (html) { chars = true; if (!stack.last() || !special[stack.last()]) { if (html.indexOf(""); if (index >= 0) { if (handler.comment) { handler.comment(html.substring(4, index)); } html = html.substring(index + 3); chars = false; } } else if (html.indexOf("]*>"), function(all, text2) { text2 = text2.replace(/|/g, "$1$2"); if (handler.chars) { handler.chars(text2); } return ""; }); parseEndTag("", stack.last()); } if (html == last) { throw "Parse Error: " + html; } last = html; } 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(match2, name) { var value = arguments[2] ? arguments[2] : arguments[3] ? arguments[3] : arguments[4] ? arguments[4] : fillAttrs[name] ? name : ""; attrs.push({ name, value, escaped: value.replace(/(^|[^\\])"/g, '$1\\"') // " }); }); if (handler.start) { handler.start(tagName, attrs, unary); } } } function parseEndTag(tag, tagName) { if (!tagName) { var pos = 0; } else { for (var pos = stack.length - 1; pos >= 0; pos--) { if (stack[pos] == tagName) { break; } } } if (pos >= 0) { for (var i = stack.length - 1; i >= pos; i--) { if (handler.end) { handler.end(stack[i]); } } stack.length = pos; } } } function makeMap(str) { var obj = {}; var items = str.split(","); for (var i = 0; i < items.length; i++) { obj[items[i]] = true; } return obj; } function removeDOCTYPE(html) { return html.replace(/<\?xml.*\?>\n/, "").replace(/\n/, "").replace(/\n/, ""); } function parseAttrs(attrs) { return attrs.reduce(function(pre, attr2) { var value = attr2.value; var name = attr2.name; if (pre[name]) { pre[name] = pre[name] + " " + value; } else { pre[name] = value; } return pre; }, {}); } function parseHtml(html) { html = removeDOCTYPE(html); var stacks = []; var results = { node: "root", children: [] }; HTMLParser(html, { start: function start(tag, attrs, unary) { var node = { name: tag }; if (attrs.length !== 0) { node.attrs = parseAttrs(attrs); } if (unary) { var parent = stacks[0] || results; if (!parent.children) { parent.children = []; } parent.children.push(node); } else { stacks.unshift(node); } }, end: function end(tag) { var node = stacks.shift(); if (node.name !== tag) console.error("invalid state: mismatch end tag"); if (stacks.length === 0) { results.children.push(node); } else { var parent = stacks[0]; if (!parent.children) { parent.children = []; } parent.children.push(node); } }, chars: function chars(text) { var node = { type: "text", text }; if (stacks.length === 0) { results.children.push(node); } else { var parent = stacks[0]; if (!parent.children) { parent.children = []; } parent.children.push(node); } }, comment: function comment(text) { var node = { node: "comment", text }; var parent = stacks[0]; if (!parent.children) { parent.children = []; } parent.children.push(node); } }); return results.children; } exports.parseHtml = parseHtml;