all files / src/ fixedReadTokenFactory.js

83.05% Statements 49/59
72.22% Branches 26/36
91.67% Functions 11/12
82.76% Lines 48/58
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149                                    98× 38× 38×   98×                   50× 50× 50× 50×                                   12×   12× 30×     12× 14× 14×       12×                 12×                         12×   12×   19×   19×     19×               19× 19×         16× 16× 14×                 50× 50× 35×       12× 48× 48×        
/**
 * Empty Elements - HTML 4.01
 *
 * @type {RegExp}
 */
const EMPTY = /^(AREA|BASE|BASEFONT|BR|COL|FRAME|HR|IMG|INPUT|ISINDEX|LINK|META|PARAM|EMBED)$/i;
 
/**
 * Elements that you can intentionally leave open (and which close themselves)
 *
 * @type {RegExp}
 */
const CLOSESELF = /^(COLGROUP|DD|DT|LI|OPTIONS|P|TD|TFOOT|TH|THEAD|TR)$/i;
 
/**
 * Corrects a token.
 *
 * @param {Token} tok The token to correct
 * @returns {Token} The corrected token
 */
function correct(tok) {
  if (tok && tok.type === 'startTag') {
    tok.unary = EMPTY.test(tok.tagName) || tok.unary;
    tok.html5Unary = !(/\/>$/).test(tok.text);
  }
  return tok;
}
 
/**
 * Peeks at the next token in the parser.
 *
 * @param {HtmlParser} parser The parser
 * @param {Function} readTokenImpl The underlying readToken implementation
 * @returns {Token} The next token
 */
function peekToken(parser, readTokenImpl) {
  const tmp = parser.stream;
  const tok = correct(readTokenImpl());
  parser.stream = tmp;
  return tok;
}
 
/**
 * Closes the last token.
 *
 * @param {HtmlParser} parser The parser
 * @param {Array<Token>} stack The stack
 */
function closeLast(parser, stack) {
  const tok = stack.pop();
 
  // prepend close tag to stream.
  parser.prepend(`</${tok.tagName}>`);
}
 
/**
 * Create a new token stack.
 *
 * @returns {Array<Token>}
 */
function newStack() {
  const stack = [];
 
  stack.last = function() {
    return this[this.length - 1];
  };
 
  stack.lastTagNameEq = function(tagName) {
    const last = this.last();
    return last && last.tagName &&
      last.tagName.toUpperCase() === tagName.toUpperCase();
  };
 
  stack.containsTagName = function(tagName) {
    for (let i = 0, tok; (tok = this[i]); i++) {
      if (tok.tagName === tagName) {
        return true;
      }
    }
    return false;
  };
 
  return stack;
}
 
/**
 * Return a readToken implementation that fixes input.
 *
 * @param {HtmlParser} parser The parser
 * @param {Object} options Options for fixing
 * @param {boolean} options.tagSoupFix True to fix tag soup scenarios
 * @param {boolean} options.selfCloseFix True to fix self-closing tags
 * @param {Function} readTokenImpl The underlying readToken implementation
 * @returns {Function}
 */
export default function fixedReadTokenFactory(parser, options, readTokenImpl) {
  const stack = newStack();
 
  const handlers = {
    startTag(tok) {
      const tagName = tok.tagName;
 
      Iif (tagName.toUpperCase() === 'TR' && stack.lastTagNameEq('TABLE')) {
        parser.prepend('<TBODY>');
        prepareNextToken();
      } else Iif (options.selfCloseFix && CLOSESELF.test(tagName) &&
          stack.containsTagName(tagName)) {
        if (stack.lastTagNameEq(tagName)) {
          closeLast(parser, stack);
        } else {
          parser.prepend(`</${tok.tagName}>`);
          prepareNextToken();
        }
      } else Eif (!tok.unary) {
        stack.push(tok);
      }
    },
 
    endTag(tok) {
      const last = stack.last();
      if (last) {
        if (options.tagSoupFix && !stack.lastTagNameEq(tok.tagName)) {
          // cleanup tag soup
          closeLast(parser, stack);
        } else {
          stack.pop();
        }
      } else Eif (options.tagSoupFix) {
        // cleanup tag soup part 2: skip this token
        readTokenImpl();
        prepareNextToken();
      }
    }
  };
 
  function prepareNextToken() {
    const tok = peekToken(parser, readTokenImpl);
    if (tok && handlers[tok.type]) {
      handlers[tok.type](tok);
    }
  }
 
  return function fixedReadToken() {
    prepareNextToken();
    return correct(readTokenImpl());
  };
}