123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289 |
- 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('<!--') == 0) {
- index = 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('</') == 0) {
- match = html.match(endTag);
- if (match) {
- html = html.substring(match[0].length);
- match[0].replace(endTag, parseEndTag);
- chars = false;
- }
- } 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;
- }
- 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 (!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(/<!doctype.*>\n/, '').replace(/<!DOCTYPE.*>\n/, '');
- }
- function parseAttrs(attrs) {
- return attrs.reduce(function (pre, attr) {
- var value = attr.value;
- var name = attr.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 str = text
- var textArray = []
- for(let i=0;i<str.length;i++){
- let msg = {
- name: 'text',
- type: 'text',
- text: str[i]
- }
- textArray.push(msg);
- }
-
-
-
-
-
-
- if (stacks.length === 0) {
- for(let i=0;i<textArray.length;i++){
- results.children.push(textArray[i]);
- }
-
- } else {
- var parent = stacks[0];
- if (!parent.children) {
- parent.children = [];
- }
- for(let i=0;i<textArray.length;i++){
- parent.children.push(textArray[i]);
- }
-
- }
- },
- comment: function comment(text) {
- var node = {
- node: 'comment',
- text: text
- };
- var parent = stacks[0];
- if (!parent.children) {
- parent.children = [];
- }
- parent.children.push(node);
- }
- });
- return results.children;
- }
- export default parseHtml;
|