function extractTags()

in myfaces-html5-demo/src/main/webapp/resources/script/google-code-prettify/prettify.js [660:720]


  function extractTags(s) {
    // since the pattern has the 'g' modifier and defines no capturing groups,
    // this will return a list of all chunks which we then classify and wrap as
    // PR_Tokens
    var matches = s.match(pr_chunkPattern);
    var sourceBuf = [];
    var sourceBufLen = 0;
    var extractedTags = [];
    if (matches) {
      for (var i = 0, n = matches.length; i < n; ++i) {
        var match = matches[i];
        if (match.length > 1 && match.charAt(0) === '<') {
          if (pr_commentPrefix.test(match)) { continue; }
          if (pr_cdataPrefix.test(match)) {
            // strip CDATA prefix and suffix.  Don't unescape since it's CDATA
            sourceBuf.push(match.substring(9, match.length - 3));
            sourceBufLen += match.length - 12;
          } else if (pr_brPrefix.test(match)) {
            // <br> tags are lexically significant so convert them to text.
            // This is undone later.
            sourceBuf.push('\n');
            ++sourceBufLen;
          } else {
            if (match.indexOf(PR_NOCODE) >= 0 && isNoCodeTag(match)) {
              // A <span class="nocode"> will start a section that should be
              // ignored.  Continue walking the list until we see a matching end
              // tag.
              var name = match.match(pr_tagNameRe)[2];
              var depth = 1;
              var j;
              end_tag_loop:
              for (j = i + 1; j < n; ++j) {
                var name2 = matches[j].match(pr_tagNameRe);
                if (name2 && name2[2] === name) {
                  if (name2[1] === '/') {
                    if (--depth === 0) { break end_tag_loop; }
                  } else {
                    ++depth;
                  }
                }
              }
              if (j < n) {
                extractedTags.push(
                    sourceBufLen, matches.slice(i, j + 1).join(''));
                i = j;
              } else {  // Ignore unclosed sections.
                extractedTags.push(sourceBufLen, match);
              }
            } else {
              extractedTags.push(sourceBufLen, match);
            }
          }
        } else {
          var literalText = htmlToText(match);
          sourceBuf.push(literalText);
          sourceBufLen += literalText.length;
        }
      }
    }
    return { source: sourceBuf.join(''), tags: extractedTags };
  }