showdownjs/src/subParsers/lists.js

/**
 * Form HTML ordered (numbered) and unordered (bulleted) lists.
 */
showdown.subParser('lists', function (text, options, globals) {
  'use strict';

  text = globals.converter._dispatch('lists.before', text, options);
  /**
   * Process the contents of a single ordered or unordered list, splitting it
   * into individual list items.
   * @param {string} listStr
   * @param {boolean} trimTrailing
   * @returns {string}
   */
  function processListItems (listStr, trimTrailing) {
    // The $g_list_level global keeps track of when we're inside a list.
    // Each time we enter a list, we increment it; when we leave a list,
    // we decrement. If it's zero, we're not in a list anymore.
    //
    // We do this because when we're not inside a list, we want to treat
    // something like this:
    //
    //    I recommend upgrading to version
    //    8. Oops, now this line is treated
    //    as a sub-list.
    //
    // As a single paragraph, despite the fact that the second line starts
    // with a digit-period-space sequence.
    //
    // Whereas when we're inside a list (or sub-list), that line will be
    // treated as the start of a sub-list. What a kludge, huh? This is
    // an aspect of Markdown's syntax that's hard to parse perfectly
    // without resorting to mind-reading. Perhaps the solution is to
    // change the syntax rules such that sub-lists must start with a
    // starting cardinal number; e.g. "1." or "a.".
    globals.gListLevel++;

    // trim trailing blank lines:
    listStr = listStr.replace(/\n{2,}$/, '\n');

    // attacklab: add sentinel to emulate \z
    listStr += '~0';

    var rgx = /(\n)?(^[ \t]*)([*+-]|\d+[.])[ \t]+((\[(x| )?])?[ \t]*[^\r]+?(\n{1,2}))(?=\n*(~0|\2([*+-]|\d+[.])[ \t]+))/gm,
        isParagraphed = (/\n[ \t]*\n(?!~0)/.test(listStr));

    listStr = listStr.replace(rgx, function (wholeMatch, m1, m2, m3, m4, taskbtn, checked) {
      checked = (checked && checked.trim() !== '');
      var item = showdown.subParser('outdent')(m4, options, globals),
          bulletStyle = '';

      // Support for github tasklists
      if (taskbtn && options.tasklists) {
        bulletStyle = ' class="task-list-item" style="list-style-type: none;"';
        item = item.replace(/^[ \t]*\[(x| )?]/m, function () {
          var otp = '<input type="checkbox" disabled style="margin: 0px 0.35em 0.25em -1.6em; vertical-align: middle;"';
          if (checked) {
            otp += ' checked';
          }
          otp += '>';
          return otp;
        });
      }
      // m1 - Leading line or
      // Has a double return (multi paragraph) or
      // Has sublist
      if (m1 || (item.search(/\n{2,}/) > -1)) {
        item = showdown.subParser('githubCodeBlocks')(item, options, globals);
        item = showdown.subParser('blockGamut')(item, options, globals);
      } else {
        // Recursion for sub-lists:
        item = showdown.subParser('lists')(item, options, globals);
        item = item.replace(/\n$/, ''); // chomp(item)
        if (isParagraphed) {
          item = showdown.subParser('paragraphs')(item, options, globals);
        } else {
          item = showdown.subParser('spanGamut')(item, options, globals);
        }
      }
      item =  '\n<li' + bulletStyle + '>' + item + '</li>\n';
      return item;
    });

    // attacklab: strip sentinel
    listStr = listStr.replace(/~0/g, '');

    globals.gListLevel--;

    if (trimTrailing) {
      listStr = listStr.replace(/\s+$/, '');
    }

    return listStr;
  }

  /**
   * Check and parse consecutive lists (better fix for issue #142)
   * @param {string} list
   * @param {string} listType
   * @param {boolean} trimTrailing
   * @returns {string}
   */
  function parseConsecutiveLists(list, listType, trimTrailing) {
    // check if we caught 2 or more consecutive lists by mistake
    // we use the counterRgx, meaning if listType is UL we look for UL and vice versa
    var counterRxg = (listType === 'ul') ? /^ {0,2}\d+\.[ \t]/gm : /^ {0,2}[*+-][ \t]/gm,
      subLists = [],
      result = '';

    if (list.search(counterRxg) !== -1) {
      (function parseCL(txt) {
        var pos = txt.search(counterRxg);
        if (pos !== -1) {
          // slice
          result += '\n\n<' + listType + '>' + processListItems(txt.slice(0, pos), !!trimTrailing) + '</' + listType + '>\n\n';

          // invert counterType and listType
          listType = (listType === 'ul') ? 'ol' : 'ul';
          counterRxg = (listType === 'ul') ? /^ {0,2}\d+\.[ \t]/gm : /^ {0,2}[*+-][ \t]/gm;

          //recurse
          parseCL(txt.slice(pos));
        } else {
          result += '\n\n<' + listType + '>' + processListItems(txt, !!trimTrailing) + '</' + listType + '>\n\n';
        }
      })(list);
      for (var i = 0; i < subLists.length; ++i) {

      }
    } else {
      result = '\n\n<' + listType + '>' + processListItems(list, !!trimTrailing) + '</' + listType + '>\n\n';
    }

    return result;
  }

  // attacklab: add sentinel to hack around khtml/safari bug:
  // http://bugs.webkit.org/show_bug.cgi?id=11231
  text += '~0';

  // Re-usable pattern to match any entire ul or ol list:
  var wholeList = /^(([ ]{0,3}([*+-]|\d+[.])[ \t]+)[^\r]+?(~0|\n{2,}(?=\S)(?![ \t]*(?:[*+-]|\d+[.])[ \t]+)))/gm;

  if (globals.gListLevel) {
    text = text.replace(wholeList, function (wholeMatch, list, m2) {
      var listType = (m2.search(/[*+-]/g) > -1) ? 'ul' : 'ol';
      return parseConsecutiveLists(list, listType, true);
    });
  } else {
    wholeList = /(\n\n|^\n?)(([ ]{0,3}([*+-]|\d+[.])[ \t]+)[^\r]+?(~0|\n{2,}(?=\S)(?![ \t]*(?:[*+-]|\d+[.])[ \t]+)))/gm;
    //wholeList = /(\n\n|^\n?)( {0,3}([*+-]|\d+\.)[ \t]+[\s\S]+?)(?=(~0)|(\n\n(?!\t| {2,}| {0,3}([*+-]|\d+\.)[ \t])))/g;
    text = text.replace(wholeList, function (wholeMatch, m1, list, m3) {

      var listType = (m3.search(/[*+-]/g) > -1) ? 'ul' : 'ol';
      return parseConsecutiveLists(list, listType);
    });
  }

  // attacklab: strip sentinel
  text = text.replace(/~0/, '');

  text = globals.converter._dispatch('lists.after', text, options);
  return text;
});