how parse utf-8 json in jquery
Asked Answered
C

2

6

I have encode a Persian name in php file . before encoding it is displayed correct and after encoding it converts to utf-8 characters. and i am receiving it in java Script (jQuery) By Ajax.

sample.php :

json_encode('نام خانوادگی ');

//after encode: "\u06a9\u0627\u0638\u0645\u06a9\u06cc"

Js:
JSON.parse(response)
// it is still in this form: \u06a9\u0627\u0638\u0645 \u06a9\u06cc

how do I parse this json so that i can have it in its original form?

Chelonian answered 14/9, 2015 at 17:3 Comment(3)
try displaying it somewhere, it will probably be outputted as you expect.Liberticide
@Liberticide it is displayed with those codes both in console.log and also in html displayChelonian
@mohammadeslahisani I added the fiddle to my answer so you can test how it works.Yan
P
1

This has nothing to do with UTF-8, but with Unicode. The difference is:

var original = "\u06a9\u0627\u0638\u0645\u06a9\u06cc"
var encoded = "\\u06a9\\u0627\\u0638\\u0645\\u06a9\\u06cc"

You have to convert the string representing the Unicode notation back to the original string. Use this:

var r = encoded.replace(/\\u(....)/gi, function(m,v){
    return String.fromCharCode(parseInt(v,16))
})
alert(r)
Potash answered 14/9, 2015 at 18:34 Comment(0)
Y
1

Try to convert your data to Base64 string and back to normal string:

Here is the fiddle that you can try the code

use this:

var Base64 = {


    _keyStr: "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/=",


    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;
    },


    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;

    },

    _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;
    },

    _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;
    }

}

the you can use like:

Base64.encode(yourString);
Base64.decode(returnValue);
Yan answered 14/9, 2015 at 17:42 Comment(0)
P
1

This has nothing to do with UTF-8, but with Unicode. The difference is:

var original = "\u06a9\u0627\u0638\u0645\u06a9\u06cc"
var encoded = "\\u06a9\\u0627\\u0638\\u0645\\u06a9\\u06cc"

You have to convert the string representing the Unicode notation back to the original string. Use this:

var r = encoded.replace(/\\u(....)/gi, function(m,v){
    return String.fromCharCode(parseInt(v,16))
})
alert(r)
Potash answered 14/9, 2015 at 18:34 Comment(0)

© 2022 - 2024 — McMap. All rights reserved.