Javascript: Unicode string to hex

Question

I'm trying to convert a unicode string to a hexadecimal representation in javascript.

This is what I have:

function convertFromHex(hex) {
    var hex = hex.toString();//force conversion
    var str = '';
    for (var i = 0; i < hex.length; i += 2)
        str += String.fromCharCode(parseInt(hex.substr(i, 2), 16));
    return str;
}

function convertToHex(str) {
    var hex = '';
    for(var i=0;i<str.length;i++) {
        hex += ''+str.charCodeAt(i).toString(16);
    }
    return hex;
}

But if fails on unicode characters, like chinese;

Input: 漢字

Output: ªo"[W

Any ideas? Can this be done in javascript?

Answer 1

Remember that a JavaScript code unit is 16 bits wide. Therefore the hex string form will be 4 digits per code unit.

usage:

var str = "\u6f22\u5b57"; // "\u6f22\u5b57" === "漢字"
alert(str.hexEncode().hexDecode());

String to hex form:

String.prototype.hexEncode = function(){
    var hex, i;

    var result = "";
    for (i=0; i<this.length; i++) {
        hex = this.charCodeAt(i).toString(16);
        result += ("000"+hex).slice(-4);
    }

    return result
}

Back again:

String.prototype.hexDecode = function(){
    var j;
    var hexes = this.match(/.{1,4}/g) || [];
    var back = "";
    for(j = 0; j<hexes.length; j++) {
        back += String.fromCharCode(parseInt(hexes[j], 16));
    }

    return back;
}