xml.js

module.exports = function(hljs) {
  var XML_IDENT_RE = '[A-Za-z0-9\\._:-]+';
  var TAG_INTERNALS = {
    endsWithParent: true,
    relevance: 0,
    contains: [
      {
        className: 'attribute',
        begin: XML_IDENT_RE,
        relevance: 0
      },
      {
        begin: '="', returnBegin: true, end: '"',
        contains: [{
            className: 'value',
            begin: '"', endsWithParent: true
        }]
      },
      {
        begin: '=\'', returnBegin: true, end: '\'',
        contains: [{
          className: 'value',
          begin: '\'', endsWithParent: true
        }]
      },
      {
        begin: '=',
        contains: [{
          className: 'value',
          begin: '[^\\s/>]+'
        }]
      }
    ]
  };
  return {
    case_insensitive: true,
    contains: [
      {
        className: 'pi',
        begin: '<\\?', end: '\\?>',
        relevance: 10
      },
      {
        className: 'doctype',
        begin: '<!DOCTYPE', end: '>',
        relevance: 10,
        contains: [{begin: '\\[', end: '\\]'}]
      },
      {
        className: 'comment',
        begin: '<!--', end: '-->',
        relevance: 10
      },
      {
        className: 'cdata',
        begin: '<\\!\\[CDATA\\[', end: '\\]\\]>',
        relevance: 10
      },
      {
        className: 'tag',
        /*
        The lookahead pattern (?=...) ensures that 'begin' only matches
        '<style' as a single word, followed by a whitespace or an
        ending braket. The '$' is needed for the lexem to be recognized
        by hljs.subMode() that tests lexems outside the stream.
        */
        begin: '<style(?=\\s|>|$)', end: '>',
        keywords: {title: 'style'},
        contains: [TAG_INTERNALS],
        starts: {
          end: '</style>', returnEnd: true,
          subLanguage: 'css'
        }
      },
      {
        className: 'tag',
        // See the comment in the <style tag about the lookahead pattern
        begin: '<script(?=\\s|>|$)', end: '>',
        keywords: {title: 'script'},
        contains: [TAG_INTERNALS],
        starts: {
          end: '</script>', returnEnd: true,
          subLanguage: 'javascript'
        }
      },
      {
        begin: '<%', end: '%>',
        subLanguage: 'vbscript'
      },
      {
        className: 'tag',
        begin: '</?', end: '/?>',
        relevance: 0,
        contains: [
          {
            className: 'title', begin: '[^ /><]+'
          },
          TAG_INTERNALS
        ]
      }
    ]
  };
};