Question

I’m trying to process a json document in javascript. The critical part is that the Json document has a section carrying base64 encoded xml data.
if I take the base64 encoded data and try to decode them I’ll see that the xml tags are trimmed away.

For example:

I have this base64 string in the json content section

Jmx0O3RhZyZndDtjb250ZW50Jmx0Oy90YWcmZ3Q7

If you try to decode it with every base64 tool you’ll get

<tag>content</tag>

Instead, I only get

content

loosing the information from the xml tags. I really need them, any advice?

EDIT: you can see the javascript code below:

    var requestUrl = span.html();
    var data = JSON.parse(doAjaxGet(requestUrl));   //I get the json document
    if(data!=null)
    {
        var envelope = data.document.envelope[0]; 
        if(envelope!=null)
        {           
            if(envelope!=null)
            {
                var data = envelope.node.applicationData;
                if(data!=null)
                {
                    var li_d = ul.find('#data');
                    encodedData = data.value;
                    li_d.find('span').html(base64.decode(encodedData)); //here the encodeddata are decoded and the Xml tags are trimmed
                    li_d.show();
                }

and here’s the Json

    {
       "document":{
          "envelope":[
             {
                "node":{
                   "applicationData":{
                      "value":"PGJpekxvY2F0aW9uPml0LnVuaWZpLmRldC50ZWxlbWF0LmVwY2lzLmRvY3VtZW50LklkZW50aWZpZXJANmRlZWE5NmM8L2JpekxvY2F0aW9uPg=="
                   }
                }
             }
          ]
       }
    }

in the following I’ll include the the library I use to encode/decode, but I think it isn’t helpful because if I do the steps:

1. copy the base64 payload form the json
2. paste it in the same js file I use to process the document as follows

base64.decode('PGJpekxvY2F0aW9uPml0LnVuaWZpLmRldC50ZWxlbWF0LmVwY2lzLmRvY3VtZW50LklkZW50aWZpZXJANmRlZWE5NmM8L2JpekxvY2F0aW9uPg==')

the output is correct i.e. I have the xml tag included in the decoded string. So I argue that the problems is related to the fact that I’m decoding something inside a json document.

By the way, here’s the library

base64 = {

        // private property
        _keyStr : "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/=",

        // public method for encoding
        encode : function (input) {
            var output = "";
            var chr1, chr2, chr3, enc1, enc2, enc3, enc4;
            var i = 0;

            input = base64._utf8_encode(input);

            while (i < input.length) {

                chr1 = input.charCodeAt(i++);
                chr2 = input.charCodeAt(i++);
                chr3 = input.charCodeAt(i++);

                enc1 = chr1 >> 2;
                enc2 = ((chr1 & 3) << 4) | (chr2 >> 4);
                enc3 = ((chr2 & 15) << 2) | (chr3 >> 6);
                enc4 = chr3 & 63;

                if (isNaN(chr2)) {
                    enc3 = enc4 = 64;
                } else if (isNaN(chr3)) {
                    enc4 = 64;
                }

                output = output +
                this._keyStr.charAt(enc1) + this._keyStr.charAt(enc2) +
                this._keyStr.charAt(enc3) + this._keyStr.charAt(enc4);

            }

            return output;
        },

        // public method for decoding
        decode : function (input) {
            var output = "";
            var chr1, chr2, chr3;
            var enc1, enc2, enc3, enc4;
            var i = 0;

            input = input.replace(/[^A-Za-z0-9\+\/\=]/g, "");

            while (i < input.length) {

                enc1 = this._keyStr.indexOf(input.charAt(i++));
                enc2 = this._keyStr.indexOf(input.charAt(i++));
                enc3 = this._keyStr.indexOf(input.charAt(i++));
                enc4 = this._keyStr.indexOf(input.charAt(i++));

                chr1 = (enc1 << 2) | (enc2 >> 4);
                chr2 = ((enc2 & 15) << 4) | (enc3 >> 2);
                chr3 = ((enc3 & 3) << 6) | enc4;

                output = output + String.fromCharCode(chr1);

                if (enc3 != 64) {
                    output = output + String.fromCharCode(chr2);
                }
                if (enc4 != 64) {
                    output = output + String.fromCharCode(chr3);
                }

            }

            output = base64._utf8_decode(output);

            return output;

        },

        // private method for UTF-8 encoding
        _utf8_encode : function (string) {
            string = string.replace(/\r\n/g,"\n");
            var utftext = "";

            for (var n = 0; n < string.length; n++) {

                var c = string.charCodeAt(n);

                if (c < 128) {
                    utftext += String.fromCharCode(c);
                }
                else if((c > 127) && (c < 2048)) {
                    utftext += String.fromCharCode((c >> 6) | 192);
                    utftext += String.fromCharCode((c & 63) | 128);
                }
                else {
                    utftext += String.fromCharCode((c >> 12) | 224);
                    utftext += String.fromCharCode(((c >> 6) & 63) | 128);
                    utftext += String.fromCharCode((c & 63) | 128);
                }

            }

            return utftext;
        },

        // private method for UTF-8 decoding
        _utf8_decode : function (utftext) {
            var string = "";
            var i = 0;
            var c = c1 = c2 = 0;

            while ( i < utftext.length ) {

                c = utftext.charCodeAt(i);

                if (c < 128) {
                    string += String.fromCharCode(c);
                    i++;
                }
                else if((c > 191) && (c < 224)) {
                    c2 = utftext.charCodeAt(i+1);
                    string += String.fromCharCode(((c & 31) << 6) | (c2 & 63));
                    i += 2;
                }
                else {
                    c2 = utftext.charCodeAt(i+1);
                    c3 = utftext.charCodeAt(i+2);
                    string += String.fromCharCode(((c & 15) << 12) | ((c2 & 63) << 6) | (c3 & 63));
                    i += 3;
                }

            }

            return string;
        }

    }

Answer 1

I’m jumping the gun a little on my answer here. But, under the assumption that your answer to my last question is yes …

Create or find a simple html escaping function and run the decoded data through it before dropping it on the page. For your purposes, I think it can be pretty simple.

var escapeTags = function(s) {
  return s.replace(/</g, "&lt;").replace(/>/g, "&gt");
} // escapeTags()

Dropping it on the page doesn’t change much:

li_d.find('span').html(escapeTags(base64.decode(encodedData)));