utf8.js

/**
    Code Point (Base 16)  Code Unit (Base 2)                        Code Unit (Base 16)
    0x000000 - 0x00007F   0xxx xxxx                                 0x00
    0x000080 - 0x0007FF   110x xxxx 10xx xxxx                       0xC0 0x80
    0x000800 - 0x00FFFF   1110 xxxx 10xx xxxx 10xx xxxx             0xE0 0x80 0x80
    0x010000 - 0x10FFFF   1111 0xxx 10xx xxxx 10xx xxxx 10xx xxxx   0xF0 0x80 0x80 0x80

    Encoding a UTF-8 character:
    1. Determine the Code Unit required using the Code Point.
    2. Push in the bits marked x from the bits of the Code Point.

    Decoding a UTF-8 character:
    1. Determine the Code Unit size from its high-order bits.
    3. Pull out the bits marked x from the bits of the Code Unit.
**/
function Utf8 () {
    return this;
}

Utf8.encode = function () {
    var unit = '';
    arguments = Array.isArray(arguments[0]) ? arguments[0] : arguments;
    for (var code in arguments) {
        code = arguments[code];
        if (typeof code === 'number' && code >= 0) {
            if (code <= 0x7F) {
                code = [ 0x00 | code ];
            } else if (code <= 0x0007FF) {
                code = [ 0xC0 | code >>> 06, 0x80 | code & 0x3F ];
            } else if (code <= 0x00FFFF) {
                code = [ 0xE0 | code >>> 12, 0x80 | code >>> 06 & 0x3F, 0x80 | code & 0x3F ];
            } else if (code <= 0x10FFFF) {
                code = [ 0xF0 | code >>> 18, 0x80 | code >>> 12 & 0x3F, 0x80 | code >>> 06 & 0x3F, 0x80 | code & 0x3F ];
            } else {
                code = [];
            }
            unit += String.fromCharCode.apply(null, code);
        }
    }
    return unit;
};