anmo-master/package/components/u-parse/libs/htmlparser.js

/**
 *
 * 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

const startTag = /^<([-A-Za-z0-9_]+)((?:\s+[a-zA-Z0-9_:][-a-zA-Z0-9_:.]*(?:\s*=\s*(?:(?:"[^"]*")|(?:'[^']*')|[^>\s]+))?)*)\s*(\/?)>/;
const endTag = /^<\/([-A-Za-z0-9_]+)[^>]*>/;
const attr = /([a-zA-Z0-9_:][-a-zA-Z0-9_:.]*)(?:\s*=\s*(?:(?:"((?:\\.|[^"])*)")|(?:'((?:\\.|[^'])*)')|([^>\s]+)))?/g;

function makeMap(str) {
  const obj = {};
  const items = str.split(',');
  for (let i = 0; i < items.length; i += 1) obj[items[i]] = true;
  return obj;
}

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

// Block Elements - HTML 5
const block = makeMap('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
const inline = makeMap('a,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)
const closeSelf = makeMap('colgroup,dd,dt,li,options,p,td,tfoot,th,thead,tr');

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

function HTMLParser(html, handler) {
  let index;
  let chars;
  let match;
  let last = html;
  const stack = [];

  stack.last = () => stack[stack.length - 1];

  function parseEndTag(tag, tagName) {
    // If no tag name is provided, clean shop
    let pos;
    if (!tagName) {
      pos = 0;
    } else {
      // Find the closest opened tag of the same type
      tagName = tagName.toLowerCase();
      for (pos = stack.length - 1; pos >= 0; pos -= 1) {
        if (stack[pos] === tagName) break;
      }
    }
    if (pos >= 0) {
      // Close all the open elements, up the stack
      for (let i = stack.length - 1; i >= pos; i -= 1) {
        if (handler.end) handler.end(stack[i]);
      }

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

  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) {
      const attrs = [];

      rest.replace(attr, function genAttr(matches, name) {
        const value = arguments[2] || arguments[3] || arguments[4] || (fillAttrs[name] ? name : '');

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

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

  while (html) {
    chars = true;

    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('<');
      let text = '';
      while (index === 0) {
        text += '<';
        html = html.substring(1);
        index = html.indexOf('<');
      }
      text += index < 0 ? html : html.substring(0, index);
      html = index < 0 ? '' : html.substring(index);

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

    if (html === last) throw new Error(`Parse Error: ${html}`);
    last = html;
  }

  // Clean up any remaining tags
  parseEndTag();
}

export default HTMLParser;