Counterpart to Python's chr() in JavaScript

Question

The JavaScript method String.fromCharCode() behaves equivalently to Python's unichar() in the following sense:

print unichr(213) # prints Õ on the console 
console.log(String.fromCharCode(213)); // prints Õ on the console as well

For my purposes, however, I need a JavaScript equivalent to the Python function chr(). Is there such a JavaScript function or a way to make String.fromCharCode() behave like chr()?

That is, I need something in JavaScript that mimics

print chr(213) # prints � on the console

Answer 1

So turns out you just want to work with raw bytes in node.js, there's a module for that. If you are a real wizard, you can get this stuff to work with javascript strings alone but it's harder and far less efficient.

var b = new Buffer(1);
b[0] = 213;

console.log(b.toString()); //�


var b = new Buffer(3);
b[0] = 0xE2;
b[1] = 0x98;
b[2] = 0x85;

console.log(b.toString()); //★

---

print chr(213) # prints � on the console

So this prints a raw byte (0xD5), that is interpreted in UTF-8 (most likely) which is not valid UTF-8 byte sequence and thus is displayed as the replacement character (�).

The interpretation as UTF-8 is not relevant here, you most likely just want raw bytes.

To create raw bytes in javascript you could use UInt8Array.

var a = new Uint8Array(1);
a[0] = 213;

You could optionally then interpret the raw bytes as utf-8:

console.log( utf8decode(a)); // "�"

//Not recommended for production use ;D
//Doesn't handle > BMP to keep the answer shorter
function utf8decode(uint8array) {
    var codePoints = [],
        i = 0,
        byte, codePoint, len = uint8array.length;
    for (i = 0; i < len; ++i) {
        byte = uint8array[i];

        if ((byte & 0xF8) === 0xF0 && len > i + 3) {

            codePoint = ((byte & 0x7) << 18) | ((uint8array[++i] & 0x3F) << 12) | ((uint8array[++i] & 0x3F) << 6) | (uint8array[++i] & 0x3F);
            if (!(0xFFFF < codePoint && codePoint <= 0x10FFFF)) {
                codePoints.push(0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD);
            } else {
                codePoints.push(codePoint);
            }
        } else if ((byte & 0xF0) === 0xE0 && len > i + 2) {

            codePoint = ((byte & 0xF) << 12) | ((uint8array[++i] & 0x3F) << 6) | (uint8array[++i] & 0x3F);
            if (!(0x7FF < codePoint && codePoint <= 0xFFFF)) {
                codePoints.push(0xFFFD, 0xFFFD, 0xFFFD);
            } else {
                codePoints.push(codePoint);
            }
        } else if ((byte & 0xE0) === 0xC0  && len > i + 1) {

            codePoint = ((byte & 0x1F) << 6) | ((uint8array[++i] & 0x3F));
            if (!(0x7F < codePoint && codePoint <= 0x7FF)) {
                codePoints.push(0xFFFD, 0xFFFD);
            } else {
                codePoints.push(codePoint);
            }
        } else if ((byte & 0x80) === 0x00) {
            codePoints.push(byte & 0x7F);
        } else {
            codePoints.push(0xFFFD);
        }
    }
    return String.fromCharCode.apply(String, codePoints);
}

What you are most likely trying to do has nothing to do with trying to interpret the bytes as utf8 though.

Another example:

//UTF-8 For the black star U+2605 ★:
var a = new Uint8Array(3);
a[0] = 0xE2;
a[1] = 0x98;
a[2] = 0x85;
utf8decode(a) === String.fromCharCode(0x2605) //True
utf8decode(a) // ★

In python 2.7 (Ubuntu):

print chr(0xE2) + chr(0x98) + chr(0x85)
#prints ★