Converting byte array to string in javascript

Question

How do I convert a byte array into a string?

I have found these functions that do the reverse:

function string2Bin(s) {
    var b = new Array();
    var last = s.length;
    
    for (var i = 0; i < last; i++) {
        var d = s.charCodeAt(i);
        if (d < 128)
            b[i] = dec2Bin(d);
        else {
            var c = s.charAt(i);
            alert(c + ' is NOT an ASCII character');
            b[i] = -1;
        }
    }
    return b;
}

function dec2Bin(d) {
    var b = '';
    
    for (var i = 0; i < 8; i++) {
        b = (d%2) + b;
        d = Math.floor(d/2);
    }
    
    return b;
}

But how do I get the functions working the other way?

Answer 1

You need to parse each octet back to number, and use that value to get a character, something like this:

function bin2String(array) {
  var result = "";
  for (var i = 0; i < array.length; i++) {
    result += String.fromCharCode(parseInt(array[i], 2));
  }
  return result;
}

bin2String(["01100110", "01101111", "01101111"]); // "foo"

// Using your string2Bin function to test:
bin2String(string2Bin("hello world")) === "hello world";

Edit: Yes, your current string2Bin can be written more shortly:

function string2Bin(str) {
  var result = [];
  for (var i = 0; i < str.length; i++) {
    result.push(str.charCodeAt(i).toString(2));
  }
  return result;
}

But by looking at the documentation you linked, I think that the setBytesParameter method expects that the blob array contains the decimal numbers, not a bit string, so you could write something like this:

function string2Bin(str) {
  var result = [];
  for (var i = 0; i < str.length; i++) {
    result.push(str.charCodeAt(i));
  }
  return result;
}

function bin2String(array) {
  return String.fromCharCode.apply(String, array);
}

string2Bin('foo'); // [102, 111, 111]
bin2String(string2Bin('foo')) === 'foo'; // true

Answer 2

ES6 update

Now, string 'foo' also equals String.fromCharCode(...[102, 111, 111])

Original answer

Simply apply your byte array to String.fromCharCode. For example

String.fromCharCode.apply(null, [102, 111, 111]) equals 'foo'.

MDN docs here.

Caveat: works for arrays shorter than 65535 - MDN docs here.

Answer 3

Try the new Text Encoding API:

// create an array view of some valid bytes
let bytesView = new Uint8Array([104, 101, 108, 108, 111]);

console.log(bytesView);

// convert bytes to string
// encoding can be specfied, defaults to utf-8
let str = new TextDecoder().decode(bytesView); 

console.log(str);

// convert string to bytes
// encoding can be specfied, defaults to utf-8
let bytes2 = new TextEncoder().encode(str);

// look, they're the same!
console.log(bytes2);
console.log(bytesView);

Answer 4

This should work:

String.fromCharCode(...array);

Or

String.fromCodePoint(...array)

Answer 5

That string2Bin can be written even more succinctly, and without any loops, to boot!

function string2Bin ( str ) {
    return str.split("").map( function( val ) { 
        return val.charCodeAt( 0 ); 
    } );
}

Answer 6

String to byte array: "FooBar".split('').map(c => c.charCodeAt(0));

Byte array to string: [102, 111, 111, 98, 97, 114].map(c => String.fromCharCode(c)).join('');

Answer 7

I think this would be more efficient:

function toBinString (arr) {
    var uarr = new Uint8Array(arr.map(function(x){return parseInt(x,2)}));
    var strings = [], chunksize = 0xffff;
    // There is a maximum stack size. We cannot call String.fromCharCode with as many arguments as we want
    for (var i=0; i*chunksize < uarr.length; i++){
        strings.push(String.fromCharCode.apply(null, uarr.subarray(i*chunksize, (i+1)*chunksize)));
    }
    return strings.join('');
}

Answer 8

Even if I'm a bit late, I thought it would be interesting for future users to share some one-liners implementations I did using ES6.

One thing that I consider important depending on your environment or/and what you will do with with the data is to preserve the full byte value. For example, (5).toString(2) will give you 101, but the complete binary conversion is in reality 00000101, and that's why you might need to create a leftPad implementation to fill the string byte with leading zeros. But you may not need it at all, like other answers demonstrated.

If you run the below code snippet, you'll see the first output being the conversion of the abc string to a byte array and right after that the re-transformation of said array to it's corresponding string.

// For each byte in our array, retrieve the char code value of the binary value
const binArrayToString = array => array.map(byte => String.fromCharCode(parseInt(byte, 2))).join('')

// Basic left pad implementation to ensure string is on 8 bits
const leftPad = str => str.length < 8 ? (Array(8).join('0') + str).slice(-8) : str

// For each char of the string, get the int code and convert it to binary. Ensure 8 bits.
const stringToBinArray = str => str.split('').map(c => leftPad(c.charCodeAt().toString(2)))

const array = stringToBinArray('abc')

console.log(array)
console.log(binArrayToString(array))

Answer 9

If your array is encoded in UTF-8 and you can't use the TextDecoder API because it is not supported on IE:

1. You can use the FastestSmallestTextEncoderDecoder polyfill recommended by the Mozilla Developer Network website;
2. You can use this function also provided at the MDN website:

function utf8ArrayToString(aBytes) {
    var sView = "";
    
    for (var nPart, nLen = aBytes.length, nIdx = 0; nIdx < nLen; nIdx++) {
        nPart = aBytes[nIdx];
        
        sView += String.fromCharCode(
            nPart > 251 && nPart < 254 && nIdx + 5 < nLen ? /* six bytes */
                /* (nPart - 252 << 30) may be not so safe in ECMAScript! So...: */
                (nPart - 252) * 1073741824 + (aBytes[++nIdx] - 128 << 24) + (aBytes[++nIdx] - 128 << 18) + (aBytes[++nIdx] - 128 << 12) + (aBytes[++nIdx] - 128 << 6) + aBytes[++nIdx] - 128
            : nPart > 247 && nPart < 252 && nIdx + 4 < nLen ? /* five bytes */
                (nPart - 248 << 24) + (aBytes[++nIdx] - 128 << 18) + (aBytes[++nIdx] - 128 << 12) + (aBytes[++nIdx] - 128 << 6) + aBytes[++nIdx] - 128
            : nPart > 239 && nPart < 248 && nIdx + 3 < nLen ? /* four bytes */
                (nPart - 240 << 18) + (aBytes[++nIdx] - 128 << 12) + (aBytes[++nIdx] - 128 << 6) + aBytes[++nIdx] - 128
            : nPart > 223 && nPart < 240 && nIdx + 2 < nLen ? /* three bytes */
                (nPart - 224 << 12) + (aBytes[++nIdx] - 128 << 6) + aBytes[++nIdx] - 128
            : nPart > 191 && nPart < 224 && nIdx + 1 < nLen ? /* two bytes */
                (nPart - 192 << 6) + aBytes[++nIdx] - 128
            : /* nPart < 127 ? */ /* one byte */
                nPart
        );
    }
    
    return sView;
}

let str = utf8ArrayToString([50,72,226,130,130,32,43,32,79,226,130,130,32,226,135,140,32,50,72,226,130,130,79]);

// Must show 2H₂ + O₂ ⇌ 2H₂O
console.log(str);

Answer 10

If you are using node.js you can do this:

yourByteArray.toString('base64');

Answer 11

Too late to answer but if your input is in form of ASCII bytes, then you could try this solution:

function convertArrToString(rArr){
 //Step 1: Convert each element to character
 let tmpArr = new Array();
 rArr.forEach(function(element,index){
    tmpArr.push(String.fromCharCode(element));
});
//Step 2: Return the string by joining the elements
return(tmpArr.join(""));
}

function convertArrToHexNumber(rArr){
  return(parseInt(convertArrToString(rArr),16));
}

Answer 12

UPDATE

@rosberg-linhares posted best solution so far to handle UTF8.

---

Didn't find any solution that would work with UTF-8 characters. String.fromCharCode is good until you meet 2 byte character.

For example word Hüser can come over the wire in form of arraybuffer as [0x48,0xc3,0xbc,0x73,0x65,0x72] (e.g. through websocket connection)

But if you go through it with String.fromCharCode you will have Hüser as each byte will be converted to a char separately, and letter ü is encoded in two bytes.

Solution

Currently I'm using following solution:

function pad(n) { return (n.length < 2 ? '0' + n : n); }
function decodeUtf8(data) {
  return decodeURIComponent(
    data.map(byte => ('%' + pad(byte.toString(16)))).join('')
  );
}

Answer 13

I had some decrypted byte arrays with padding characters and other stuff I didn't need, so I did this (probably not perfect, but it works for my limited use)

var junk = String.fromCharCode.apply(null, res).split('').map(char => char.charCodeAt(0) <= 127 && char.charCodeAt(0) >= 32 ? char : '').join('');

Answer 14

> const stringToBin = (str) => [...str].map(item=>item.charCodeAt())
> undefined
> stringToBin('hello')
> (5) [104, 101, 108, 108, 111]
> const binToString = (array) => String.fromCharCode(...array) 
> undefined
> binToString(stringToBin('hello'))
> 'hello'

Answer 15

What you are looking for is String.fromCharCode

What you want to do is loop through the array of bytes (represented as integers), create the string equivalent and add it to the result:

function bin2String(array) {
  var result = "";
  for (const char of array) {
    result += String.fromCharCode(char);
  }
  return result;
}

console.log(bin2String([116, 104, 101, 32, 114, 101, 115, 117, 108, 116]));

You can also use the Array.Map function to convert the array of bytes into an array of strings, then join them all.

function string2Bin(array) {
  return array.map(byte => String.fromCharCode(byte)).join("");
}

console.log(string2Bin([116, 104, 101, 32, 114, 101, 115, 117, 108, 116]));

Answer 16

The simplest solution I've found is:

var text = atob(byteArray);