Convert base64 string to ArrayBuffer

Question

I need to convert a base64 encode string into an ArrayBuffer. The base64 strings are user input, they will be copy and pasted from an email, so they're not there when the page is loaded. I would like to do this in javascript without making an ajax call to the server if possible.

I found those links interesting, but they didt'n help me:

ArrayBuffer to base64 encoded string

this is about the opposite conversion, from ArrayBuffer to base64, not the other way round

http://jsperf.com/json-vs-base64/2

this looks good but i can't figure out how to use the code.

Is there an easy (maybe native) way to do the conversion? thanks

Answer 1

function base64ToArrayBuffer(base64) {
    var binaryString = atob(base64);
    var bytes = new Uint8Array(binaryString.length);
    for (var i = 0; i < binaryString.length; i++) {
        bytes[i] = binaryString.charCodeAt(i);
    }
    return bytes.buffer;
}

Answer 2

Using TypedArray.from:

Uint8Array.from(atob(base64_string), c => c.charCodeAt(0))

Performance to be compared with the for loop version of Goran.it answer.

Answer 3

For Node.js users:

const myBuffer = Buffer.from(someBase64String, 'base64');

myBuffer will be of type Buffer which is a subclass of Uint8Array. Unfortunately, Uint8Array is NOT an ArrayBuffer as the OP was asking for. But when manipulating an ArrayBuffer I almost always wrap it with Uint8Array or something similar, so it should be close to what's being asked for.

Answer 4

Goran.it's answer does not work because of unicode problem in javascript - https://developer.mozilla.org/en-US/docs/Web/API/WindowBase64/Base64_encoding_and_decoding.

I ended up using the function given on Daniel Guerrero's blog: http://blog.danguer.com/2011/10/24/base64-binary-decoding-in-javascript/

Function is listed on github link: https://github.com/danguer/blog-examples/blob/master/js/base64-binary.js

Use these lines

var uintArray = Base64Binary.decode(base64_string);  
var byteArray = Base64Binary.decodeArrayBuffer(base64_string); 

Answer 5

Async solution, it's better when the data is big:

// base64 to buffer
function base64ToBufferAsync(base64) {
  var dataUrl = "data:application/octet-binary;base64," + base64;

  fetch(dataUrl)
    .then(res => res.arrayBuffer())
    .then(buffer => {
      console.log("base64 to buffer: " + new Uint8Array(buffer));
    })
}

// buffer to base64
function bufferToBase64Async( buffer ) {
    var blob = new Blob([buffer], {type:'application/octet-binary'});    
    console.log("buffer to blob:" + blob)

    var fileReader = new FileReader();
    fileReader.onload = function() {
      var dataUrl = fileReader.result;
      console.log("blob to dataUrl: " + dataUrl);

      var base64 = dataUrl.substr(dataUrl.indexOf(',')+1)      
      console.log("dataUrl to base64: " + base64);
    };
    fileReader.readAsDataURL(blob);
}

Answer 6

Javascript is a fine development environment so it seems odd than it doesn't provide a solution to this small problem. The solutions offered elsewhere on this page are potentially slow. Here is my solution. It employs the inbuilt functionality that decodes base64 image and sound data urls.

var req = new XMLHttpRequest;
req.open('GET', "data:application/octet;base64," + base64Data);
req.responseType = 'arraybuffer';
req.onload = function fileLoaded(e)
{
   var byteArray = new Uint8Array(e.target.response);
   // var shortArray = new Int16Array(e.target.response);
   // var unsignedShortArray = new Int16Array(e.target.response);
   // etc.
}
req.send();

The send request fails if the base 64 string is badly formed.

The mime type (application/octet) is probably unnecessary.

Tested in chrome. Should work in other browsers.

Answer 7

Pure JS - no string middlestep (no atob)

I write following function which convert base64 in direct way (without conversion to string at the middlestep). IDEA

• get 4 base64 characters chunk
• find index of each character in base64 alphabet
• convert index to 6-bit number (binary string)
• join four 6 bit numbers which gives 24-bit numer (stored as binary string)
• split 24-bit string to three 8-bit and covert each to number and store them in output array
• corner case: if input base64 string ends with one/two = char, remove one/two numbers from output array

Below solution allows to process large input base64 strings. Similar function for convert bytes to base64 without btoa is HERE

function base64ToBytesArr(str) {
  const abc = [..."ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"]; // base64 alphabet
  let result = [];

  for(let i=0; i<str.length/4; i++) {
    let chunk = [...str.slice(4*i,4*i+4)]
    let bin = chunk.map(x=> abc.indexOf(x).toString(2).padStart(6,0)).join(''); 
    let bytes = bin.match(/.{1,8}/g).map(x=> +('0b'+x));
    result.push(...bytes.slice(0,3 - (str[4*i+2]=="=") - (str[4*i+3]=="=")));
  }
  return result;
}


// --------
// TEST
// --------


let test = "Alice's Adventure in Wonderland.";  

console.log('test string:', test.length, test);
let b64_btoa = btoa(test);
console.log('encoded string:', b64_btoa);

let decodedBytes = base64ToBytesArr(b64_btoa); // decode base64 to array of bytes
console.log('decoded bytes:', JSON.stringify(decodedBytes));
let decodedTest = decodedBytes.map(b => String.fromCharCode(b) ).join``;
console.log('Uint8Array', JSON.stringify(new Uint8Array(decodedBytes)));
console.log('decoded string:', decodedTest.length, decodedTest);

Caution!

If you want to decode base64 to STRING (not bytes array) and you know that result contains utf8 characters then atob will fail in general e.g. for character the atob("8J+SqQ==") will give wrong result . In this case you can use above solution and convert result bytes array to string in proper way e.g. :

function base64ToBytesArr(str) {
  const abc = [..."ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"]; // base64 alphabet
  let result = [];

  for(let i=0; i<str.length/4; i++) {
    let chunk = [...str.slice(4*i,4*i+4)]
    let bin = chunk.map(x=> abc.indexOf(x).toString(2).padStart(6,0)).join(''); 
    let bytes = bin.match(/.{1,8}/g).map(x=> +('0b'+x));
    result.push(...bytes.slice(0,3 - (str[4*i+2]=="=") - (str[4*i+3]=="=")));
  }
  return result;
}


// --------
// TEST
// --------


let testB64 = "8J+SqQ==";   // for string: "";  
console.log('input base64            :', testB64);

let decodedBytes = base64ToBytesArr(testB64); // decode base64 to array of bytes
console.log('decoded bytes           :', JSON.stringify(decodedBytes));

let result = new TextDecoder("utf-8").decode(new Uint8Array(decodedBytes));
console.log('properly decoded string :', result);

let result_atob = atob(testB64);
console.log('decoded by atob         :', result_atob);

Snippets tested 2022-08-04 on: chrome 103.0.5060.134 (arm64), safari 15.2, firefox 103.0.1 (64 bit), edge 103.0.1264.77 (arm64), and node-js v12.16.1

Answer 8

I would strongly suggest using an npm package implementing correctly the base64 specification.

The best one I know is rfc4648

The problem is that btoa and atob use binary strings instead of Uint8Array and trying to convert to and from it is cumbersome. Also there is a lot of bad packages in npm for that. I lose a lot of time before finding that one.

The creators of that specific package did a simple thing: they took the specification of Base64 (which is here by the way) and implemented it correctly from the beginning to the end. (Including other formats in the specification that are also useful like Base64-url, Base32, etc ...) That doesn't seem a lot but apparently that was too much to ask to the bunch of other libraries.

So yeah, I know I'm doing a bit of proselytism but if you want to avoid losing your time too just use rfc4648.

Answer 9

I used the accepted answer to this question to create base64Url string <-> arrayBuffer conversions in the realm of base64Url data transmitted via ASCII-cookie [atob, btoa are base64[with +/]<->js binary string], so I decided to post the code.

Many of us may want both conversions and client-server communication may use the base64Url version (though a cookie may contain +/ as well as -_ characters if I understand well, only ",;\ characters and some wicked characters from the 128 ASCII are disallowed). But a url cannot contain / character, hence the wider use of b64 url version which of course not what atob-btoa supports...

Seeing other comments, I would like to stress that my use case here is base64Url data transmission via url/cookie and trying to use this crypto data with the js crypto api (2017) hence the need for ArrayBuffer representation and b64u <-> arrBuff conversions... if array buffers represent other than base64 (part of ascii) this conversion wont work since atob, btoa is limited to ascii(128). Check out an appropriate converter like below:

The buff -> b64u version is from a tweet from Mathias Bynens, thanks for that one (too)! He also wrote a base64 encoder/decoder: https://github.com/mathiasbynens/base64

Coming from java, it may help when trying to understand the code that java byte[] is practically js Int8Array (signed int) but we use here the unsigned version Uint8Array since js conversions work with them. They are both 256bit, so we call it byte[] in js now...

The code is from a module class, that is why static.

//utility

/**
 * Array buffer to base64Url string
 * - arrBuff->byte[]->biStr->b64->b64u
 * @param arrayBuffer
 * @returns {string}
 * @private
 */
static _arrayBufferToBase64Url(arrayBuffer) {
    console.log('base64Url from array buffer:', arrayBuffer);

    let base64Url = window.btoa(String.fromCodePoint(...new Uint8Array(arrayBuffer)));
    base64Url = base64Url.replaceAll('+', '-');
    base64Url = base64Url.replaceAll('/', '_');

    console.log('base64Url:', base64Url);
    return base64Url;
}

/**
 * Base64Url string to array buffer
 * - b64u->b64->biStr->byte[]->arrBuff
 * @param base64Url
 * @returns {ArrayBufferLike}
 * @private
 */
static _base64UrlToArrayBuffer(base64Url) {
    console.log('array buffer from base64Url:', base64Url);

    let base64 = base64Url.replaceAll('-', '+');
    base64 = base64.replaceAll('_', '/');
    const binaryString = window.atob(base64);
    const length = binaryString.length;
    const bytes = new Uint8Array(length);
    for (let i = 0; i < length; i++) {
        bytes[i] = binaryString.charCodeAt(i);
    }

    console.log('array buffer:', bytes.buffer);
    return bytes.buffer;
}

Answer 10

Solution without atob

I've seen many people complaining about using atob and btoa in the replies. There are some issues to take into account when using them.

There's a solution without using them in the MDN page about Base64. Below you can find the code to convert a base64 string into a Uint8Array copied from the docs.

Note that the function below returns a Uint8Array. To get the ArrayBuffer version you just need to do uintArray.buffer.

function b64ToUint6(nChr) {
  return nChr > 64 && nChr < 91
    ? nChr - 65
    : nChr > 96 && nChr < 123
    ? nChr - 71
    : nChr > 47 && nChr < 58
    ? nChr + 4
    : nChr === 43
    ? 62
    : nChr === 47
    ? 63
    : 0;
}

function base64DecToArr(sBase64, nBlocksSize) {
  const sB64Enc = sBase64.replace(/[^A-Za-z0-9+/]/g, "");
  const nInLen = sB64Enc.length;
  const nOutLen = nBlocksSize
    ? Math.ceil(((nInLen * 3 + 1) >> 2) / nBlocksSize) * nBlocksSize
    : (nInLen * 3 + 1) >> 2;
  const taBytes = new Uint8Array(nOutLen);

  let nMod3;
  let nMod4;
  let nUint24 = 0;
  let nOutIdx = 0;
  for (let nInIdx = 0; nInIdx < nInLen; nInIdx++) {
    nMod4 = nInIdx & 3;
    nUint24 |= b64ToUint6(sB64Enc.charCodeAt(nInIdx)) << (6 * (3 - nMod4));
    if (nMod4 === 3 || nInLen - nInIdx === 1) {
      nMod3 = 0;
      while (nMod3 < 3 && nOutIdx < nOutLen) {
        taBytes[nOutIdx] = (nUint24 >>> ((16 >>> nMod3) & 24)) & 255;
        nMod3++;
        nOutIdx++;
      }
      nUint24 = 0;
    }
  }

  return taBytes;
}

If you're interested in the reverse operation, ArrayBuffer to base64, you can find how to do it in the same link.