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
Try this:
function _base64ToArrayBuffer(base64) {
var binary_string = window.atob(base64);
var len = binary_string.length;
var bytes = new Uint8Array(len);
for (var i = 0; i < len; i++) {
bytes[i] = binary_string.charCodeAt(i);
}
return bytes.buffer;
}
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.
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.
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);
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);
}
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.
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
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.
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;
}
made a ArrayBuffer from a base64:
function base64ToArrayBuffer(base64) {
var binary_string = window.atob(base64);
var len = binary_string.length;
var bytes = new Uint8Array(len);
for (var i = 0; i < len; i++) {
bytes[i] = binary_string.charCodeAt(i);
}
return bytes.buffer;
}
I was trying to use above code and It's working fine.
The result of atob is a string that is separated with some comma
,
A simpler way is to convert this string to a json array string and after that parse it to a byteArray
below code can simply be used to convert base64 to an array of number
let byteArray = JSON.parse('['+atob(base64)+']');
let buffer = new Uint8Array(byteArray);
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.
I have this GZIPed string: H4sIAAAAAAAA//NIzcnJVyguSUzOzi9LLUrLyS/XUSjJSMzLLlZIyy9SSMwpT6wsVshIzSnIzEtXBACs78K6LwAAAA==
I created that with this website: http://www.txtwizard.net/compression
I have tried using pako to ungzip it.
import { ungzip } from 'pako';
const textEncoder = new TextEncoder();
const gzipedData = textEncoder.encode("H4sIAAAAAAAA//NIzcnJVyguSUzOzi9LLUrLyS/XUSjJSMzLLlZIyy9SSMwpT6wsVshIzSnIzEtXBACs78K6LwAAAA==");
console.log('gzipeddata', gzipedData);
const ungzipedData = ungzip(gzipedData);
console.log('ungziped data', ungzipedData);
The issue is that Pako throws the error: incorrect header check
What am I missing here?
A JSbin
The "H4sIAAAAAAAA//NIzcnJVyguSUzOzi9LLUrLyS/XUSjJSMzLLlZIyy9SSMwpT6wsVshIzSnIzEtXBACs78K6LwAAAA==" is a base64 encoded string, you first need to decode that into a buffer.
textEncoder.encode just encodes that base64 encoded string into a byte stream.
How to do that depend on whether you are in a browser or on nodejs.
node.js version
To convert the unzipped data to a string you further have use new TextDecoder().decode()
For node you will use Buffer.from(string, 'base64') to decode the base64 encoded string:
import { ungzip } from 'pako';
// decode the base64 encoded data
const gzipedData = Buffer.from("H4sIAAAAAAAA//NIzcnJVyguSUzOzi9LLUrLyS/XUSjJSMzLLlZIyy9SSMwpT6wsVshIzSnIzEtXBACs78K6LwAAAA==", "base64");
console.log('gzipeddata', gzipedData);
const ungzipedData = ungzip(gzipedData);
console.log('ungziped data', new TextDecoder().decode(ungzipedData));
browser version
In the browser, you have to use atob, and you need to convert the decoded data to an Uint8Array using e.g. Uint8Array.from.
The conversion I used was taken from Convert base64 string to ArrayBuffer, you might need to verify if that really works in all cases.
// decode the base64 encoded data
const gezipedData = atob("H4sIAAAAAAAA//NIzcnJVyguSUzOzi9LLUrLyS/XUSjJSMzLLlZIyy9SSMwpT6wsVshIzSnIzEtXBACs78K6LwAAAA==")
const gzipedDataArray = Uint8Array.from(gezipedData, c => c.charCodeAt(0))
console.log('gzipeddata', gzipedDataArray);
const ungzipedData = pako.ungzip(gzipedDataArray);
console.log('ungziped data', new TextDecoder().decode(ungzipedData));
<script src="https://cdnjs.cloudflare.com/ajax/libs/pako/2.0.4/pako.min.js"></script>
This string is base64-encoded.
You first need to decode it to a buffer:
const gzippedString = 'H4sIAAAAAAAA//NIzcnJVyguSUzOzi9LLUrLyS/XUSjJSMzLLlZIyy9SSMwpT6wsVshIzSnIzEtXBACs78K6LwAAAA==';
const gzippedBuffer = new Buffer(gzippedString, 'base64');
Then you can un(g)zip it:
const unzippedBuffer = ungzip(gzippedBuffer);
The result on ungzip is a Unit8Array. If you want to convert it back to a string you'll need to decode it again:
const unzippedString = new TextDecoder('utf8').decode(unzipped);
I'm trying to create SHA-1 hash on the client-side. I'm trying to do this with Web Crypto API but when I'm comparing the output to what various online tools give me, the result is completely different. I think the problem is in ArrayBuffer to Hex conversion. Here is my code:
function generateHash() {
var value = "mypassword";
var crypto = window.crypto;
var buffer = new ArrayBuffer(value);
var hash_bytes = crypto.subtle.digest("SHA-1", buffer);
hash_bytes.then(value => document.write([...new Uint8Array(value)].map(x => x.toString(16).padStart(2, '0')).join('')));
}
Output of document.write should be:
91dfd9ddb4198affc5c194cd8ce6d338fde470e2
But it's not, I get a completely different hash of different length (should be 40). Could I have some advise on the problem? Thanks.
The problem seems to be more the input conversion from a string to an ArrayBuffer. E.g. with str2ab() the code works:
generateHash();
function generateHash() {
var value = "mypassword";
var crypto = window.crypto;
var buffer = str2ab(value); // Fix
var hash_bytes = crypto.subtle.digest("SHA-1", buffer);
hash_bytes.then(value => document.write([...new Uint8Array(value)].map(x => x.toString(16).padStart(2, '0')).join('')));
}
// https://stackoverflow.com/a/11058858
function str2ab(str) {
const buf = new ArrayBuffer(str.length);
const bufView = new Uint8Array(buf);
for (let i = 0, strLen = str.length; i < strLen; i++) {
bufView[i] = str.charCodeAt(i);
}
return buf;
}
with the expected output:
91dfd9ddb4198affc5c194cd8ce6d338fde470e2
Using the debugger, it looks like var buffer = new ArrayBuffer(value); results in buffer being an empty ArrayBuffer. The text string stored in value must be utf-8 encoded in order to be correctly converted to bytes, which can then by passed as an input to the crypto.subtle.digest() function.
Try changing:
var buffer = new ArrayBuffer(value);
to:
var buffer = new TextEncoder("utf-8").encode(value);
This creates a Uint8Array (as expected by crypto.subtle.digest()) consisting of the bytes resulting from utf-8 encoding the text string in 'value'. This should solve the problem and produce the result that you are expecting.
I have some large data sets which I would like to compress before I send to my client. The compression works.
Utilizing this bit of code which turns my data into a nice, small base64String:
Example: string mytest = "This is some test text.";
public static string Compress(string mytest)
{
byte[] buffer = System.Text.Encoding.UTF8.GetBytes(text);
MemoryStream ms = new MemoryStream();
using (GZipStream zip = new GZipStream(ms, CompressionMode.Compress, true))
{
zip.Write(buffer, 0, buffer.Length);
}
ms.Position = 0;
MemoryStream outStream = new MemoryStream();
byte[] compressed = new byte[ms.Length];
ms.Read(compressed, 0, compressed.Length);
byte[] gzBuffer = new byte[compressed.Length + 4];
System.Buffer.BlockCopy(compressed, 0, gzBuffer, 4, compressed.Length);
System.Buffer.BlockCopy(BitConverter.GetBytes(buffer.Length), 0, gzBuffer, 0, 4);
return Convert.ToBase64String(gzBuffer);
}
On the client side, I need to walk this whole thing backwards.
I can convert the base64string back to a byte array using (library):
var byteArray = Base64Binary.decodeArrayBuffer(source);
Then using pako.js I can deflate the gzip compressed content:
var deflate = new pako.Deflate({ level: 1 });
deflate.push(uintArray, true);
if (deflate.err) { throw new Error(deflate.err); }
Finally, I should be able to convert this back to my text:
var encodedString = String.fromCharCode.apply(null, deflate.result)
var decodedString = decodeURIComponent(encodedString);
Problem is that while I get no errors, I don't get expected results, which should be the the original string - "This is some test text."
Output is like this (can't paste it all):
xg``ïæ
Any thought on what am I missing?
You need to use pako.Inflate in your frontend.
Additionally you need to remove the 4 bytes size you added to the front of the gzBuffer in the frontend before decoding.
Something like this should work:
// "cookies rule the world" compressed with your c# code
let sample = "FgAAAB+LCAAAAAAABABLzs/PzkwtVigqzUlVKMlIVSjPL8pJAQBkkN7rFgAAAA==";
// decode base64 & convert to Uint8 Array
let binary = atob(sample);
let bytes = Uint8Array.from(binary, c => c.charCodeAt(0));
// You appended the length at the start of gzBuffer, so you need to remove those bytes
bytes = bytes.slice(4);
// inflate the message & convert it to a string
let inflated = pako.inflate(bytes);
let message = String.fromCharCode.apply(null, inflated);
console.log(message);
<script src="https://raw.githubusercontent.com/danguer/blog-examples/master/js/base64-binary.js"></script>
<script src="https://unpkg.com/pako#1.0.10/dist/pako.min.js"></script>
the question says it all, im receiving a base64 encoded ZIPFILE from the server, which I first want to decode to a ZIPFILE in memory and then get the ZIPFILES content, which is a json-file.
I tried to use JSZIP but im totally lost in this case ... the base64 string is received with javascript by a promise.
So my question in short is: How can I convert a base64 encoded ZIPFILE to a ZIPFILE in memory to get its contents.
BASE64 -> ZIPFILE -> CONTENT
I use this complicated process to save much space on my database. And I dont want to handle this process on server-side, but on clientside with JS.
Thanks in advance!
If anyone is interested in my solution to this problem read my answer right here:
I received the data in a base64-string format, then converted the string to a blob. Then I used the blob-handle to load the zipfile with the JSZip-Library. After that I could just grab the contents of the zipfile. Code is below:
function base64ToBlob(base64) {
let binaryString = window.atob(base64);
let binaryLen = binaryString.length;
let ab = new ArrayBuffer(binaryLen);
let ia = new Uint8Array(ab);
for (let i = 0; i < binaryLen; i++) {
ia[i] = binaryString.charCodeAt(i);
}
let bb = new Blob([ab]);
bb.lastModifiedDate = new Date();
bb.name = "archive.zip";
bb.type = "zip";
return bb;
}
To get the contents of the zipfile:
let blob = base64ToBlob(resolved);
let zip = new JSZip();
zip.loadAsync(blob).then(function(zip) {
zip.file("archived.json").async("string").then(function (content) {
console.log(content);
// content is the file as a string
});
}).catch((e) => {
});
As you can see, first the blob is created from the base64-string. Then the handle is given over to the JSZip loadAsync method. After that you have to set the name of the file which you want to retrieve from the zipfile. In this case it is the file called "archived.json". Now because of the async("string") function the file (file contents) are returned as a string. To further use the extracted string, just work with the content variable.