MarkLogic / JavaScript: Unserializing output from PHP's serialize()

unserialize.js

/**
 * Unserialize data taken from PHP's serialize() output
 *
 * Taken from https://github.com/kvz/phpjs/blob/master/functions/var/unserialize.js
 * Fixed window reference to make it nodejs-compatible
 *
 * @param string serialized data
 * @return unserialized data
 * @throws
 */
function unserialize (data) {
  // http://kevin.vanzonneveld.net
  // +     original by: Arpad Ray (mailto:[email protected])
  // +     improved by: Pedro Tainha (http://www.pedrotainha.com)
  // +     bugfixed by: dptr1988
  // +      revised by: d3x
  // +     improved by: Kevin van Zonneveld (http://kevin.vanzonneveld.net)
  // +        input by: Brett Zamir (http://brett-zamir.me)
  // +     improved by: Kevin van Zonneveld (http://kevin.vanzonneveld.net)
  // +     improved by: Chris
  // +     improved by: James
  // +        input by: Martin (http://www.erlenwiese.de/)
  // +     bugfixed by: Kevin van Zonneveld (http://kevin.vanzonneveld.net)
  // +     improved by: Le Torbi
  // +     input by: kilops
  // +     bugfixed by: Brett Zamir (http://brett-zamir.me)
  // +      input by: Jaroslaw Czarniak
  // %            note: We feel the main purpose of this function should be to ease the transport of data between php & js
  // %            note: Aiming for PHP-compatibility, we have to translate objects to arrays
  // *       example 1: unserialize('a:3:{i:0;s:5:"Kevin";i:1;s:3:"van";i:2;s:9:"Zonneveld";}');
  // *       returns 1: ['Kevin', 'van', 'Zonneveld']
  // *       example 2: unserialize('a:3:{s:9:"firstName";s:5:"Kevin";s:7:"midName";s:3:"van";s:7:"surName";s:9:"Zonneveld";}');
  // *       returns 2: {firstName: 'Kevin', midName: 'van', surName: 'Zonneveld'}
  var that = this,
    utf8Overhead = function (chr) {
      // http://phpjs.org/functions/unserialize:571#comment_95906
      var code = chr.charCodeAt(0);
      if (code < 0x0080) {
        return 0;
      }
      if (code < 0x0800) {
        return 1;
      }
      return 2;
    },
    error = function (type, msg, filename, line) {
      throw new window[type](msg, filename, line);
    },
    read_until = function (data, offset, stopchr) {
      var i = 2, buf = [], chr = data.slice(offset, offset + 1);

      while (chr != stopchr) {
        if ((i + offset) > data.length) {
          error('Error', 'Invalid');
        }
        buf.push(chr);
        chr = data.slice(offset + (i - 1), offset + i);
        i += 1;
      }
      return [buf.length, buf.join('')];
    },
    read_chrs = function (data, offset, length) {
      var i, chr, buf;

      buf = [];
      for (i = 0; i < length; i++) {
        chr = data.slice(offset + (i - 1), offset + i);
        buf.push(chr);
        length -= utf8Overhead(chr);
      }
      return [buf.length, buf.join('')];
    },
    _unserialize = function (data, offset) {
      var dtype, dataoffset, keyandchrs, keys,
        readdata, readData, ccount, stringlength,
        i, key, kprops, kchrs, vprops, vchrs, value,
        chrs = 0,
        typeconvert = function (x) {
          return x;
        };

      if (!offset) {
        offset = 0;
      }
      dtype = (data.slice(offset, offset + 1)).toLowerCase();

      dataoffset = offset + 2;

      switch (dtype) {
        case 'i':
          typeconvert = function (x) {
            return parseInt(x, 10);
          };
          readData = read_until(data, dataoffset, ';');
          chrs = readData[0];
          readdata = readData[1];
          dataoffset += chrs + 1;
          break;
        case 'b':
          typeconvert = function (x) {
            return parseInt(x, 10) !== 0;
          };
          readData = read_until(data, dataoffset, ';');
          chrs = readData[0];
          readdata = readData[1];
          dataoffset += chrs + 1;
          break;
        case 'd':
          typeconvert = function (x) {
            return parseFloat(x);
          };
          readData = read_until(data, dataoffset, ';');
          chrs = readData[0];
          readdata = readData[1];
          dataoffset += chrs + 1;
          break;
        case 'n':
          readdata = null;
          break;
        case 's':
          ccount = read_until(data, dataoffset, ':');
          chrs = ccount[0];
          stringlength = ccount[1];
          dataoffset += chrs + 2;

          readData = read_chrs(data, dataoffset + 1, parseInt(stringlength, 10));
          chrs = readData[0];
          readdata = readData[1];
          dataoffset += chrs + 2;
          if (chrs != parseInt(stringlength, 10) && chrs != readdata.length) {
            error('SyntaxError', 'String length mismatch');
          }
          break;
        case 'a':
          readdata = {};

          keyandchrs = read_until(data, dataoffset, ':');
          chrs = keyandchrs[0];
          keys = keyandchrs[1];
          dataoffset += chrs + 2;

          for (i = 0; i < parseInt(keys, 10); i++) {
            kprops = _unserialize(data, dataoffset);
            kchrs = kprops[1];
            key = kprops[2];
            dataoffset += kchrs;

            vprops = _unserialize(data, dataoffset);
            vchrs = vprops[1];
            value = vprops[2];
            dataoffset += vchrs;

            readdata[key] = value;
          }

          dataoffset += 1;
          break;
        default:
          error('SyntaxError', 'Unknown / Unhandled data type(s): ' + dtype);
          break;
      }
      return [dtype, dataoffset - offset, typeconvert(readdata)];
    }
  ;

  return _unserialize((data + ''), 0)[2];
}

unserialize('a:5:{s:5:"width";i:665;s:6:"height";i:210;s:4:"file";s:42:"2015/06/Screenshot-2015-04-27-16.40.11.png";s:5:"sizes";a:3:{s:9:"thumbnail";a:4:{s:4:"file";s:42:"Screenshot-2015-04-27-16.40.11-150x150.png";s:5:"width";i:150;s:6:"height";i:150;s:9:"mime-type";s:9:"image/png";}s:6:"medium";a:4:{s:4:"file";s:41:"Screenshot-2015-04-27-16.40.11-300x95.png";s:5:"width";i:300;s:6:"height";i:95;s:9:"mime-type";s:9:"image/png";}s:14:"post-thumbnail";a:4:{s:4:"file";s:42:"Screenshot-2015-04-27-16.40.11-665x198.png";s:5:"width";i:665;s:6:"height";i:198;s:9:"mime-type";s:9:"image/png";}}s:10:"image_meta";a:11:{s:8:"aperture";i:0;s:6:"credit";s:0:"";s:6:"camera";s:0:"";s:7:"caption";s:0:"";s:17:"created_timestamp";i:0;s:9:"copyright";s:0:"";s:12:"focal_length";i:0;s:3:"iso";i:0;s:13:"shutter_speed";i:0;s:5:"title";s:0:"";s:11:"orientation";i:0;}}')