Conversion between UTF-8 ArrayBuffer and String

Solution 1:

Using TextEncoder and TextDecoder

var uint8array = new TextEncoder("utf-8").encode("Plain Text");
var string = new TextDecoder().decode(uint8array);
console.log(uint8array ,string )

Solution 2:

function stringToUint(string) {
    var string = btoa(unescape(encodeURIComponent(string))),
        charList = string.split(''),
        uintArray = [];
    for (var i = 0; i < charList.length; i++) {
        uintArray.push(charList[i].charCodeAt(0));
    }
    return new Uint8Array(uintArray);
}

function uintToString(uintArray) {
    var encodedString = String.fromCharCode.apply(null, uintArray),
        decodedString = decodeURIComponent(escape(atob(encodedString)));
    return decodedString;
}

I have done, with some help from the internet, these little functions, they should solve your problems! Here is the working JSFiddle.

EDIT:

Since the source of the Uint8Array is external and you can't use atob you just need to remove it(working fiddle):

function uintToString(uintArray) {
    var encodedString = String.fromCharCode.apply(null, uintArray),
        decodedString = decodeURIComponent(escape(encodedString));
    return decodedString;
}

Warning: escape and unescape is removed from web standards. See this.

Solution 3:

This should work:

// http://www.onicos.com/staff/iz/amuse/javascript/expert/utf.txt

/* utf.js - UTF-8 <=> UTF-16 convertion
 *
 * Copyright (C) 1999 Masanao Izumo <[email protected]>
 * Version: 1.0
 * LastModified: Dec 25 1999
 * This library is free.  You can redistribute it and/or modify it.
 */

function Utf8ArrayToStr(array) {
  var out, i, len, c;
  var char2, char3;

  out = "";
  len = array.length;
  i = 0;
  while (i < len) {
    c = array[i++];
    switch (c >> 4)
    { 
      case 0: case 1: case 2: case 3: case 4: case 5: case 6: case 7:
        // 0xxxxxxx
        out += String.fromCharCode(c);
        break;
      case 12: case 13:
        // 110x xxxx   10xx xxxx
        char2 = array[i++];
        out += String.fromCharCode(((c & 0x1F) << 6) | (char2 & 0x3F));
        break;
      case 14:
        // 1110 xxxx  10xx xxxx  10xx xxxx
        char2 = array[i++];
        char3 = array[i++];
        out += String.fromCharCode(((c & 0x0F) << 12) |
                                   ((char2 & 0x3F) << 6) |
                                   ((char3 & 0x3F) << 0));
        break;
    }
  }    
  return out;
}

It's somewhat cleaner as the other solutions because it doesn't use any hacks nor depends on Browser JS functions, e.g. works also in other JS environments.

Check out the JSFiddle demo.

Also see the related questions: here, here

Solution 4:

There's a polyfill for Encoding over on Github: text-encoding. It's easy for Node or the browser, and the Readme advises the following:

var uint8array = TextEncoder(encoding).encode(string);
var string = TextDecoder(encoding).decode(uint8array);

If I recall, 'utf-8' is the encoding you need, and of course you'll need to wrap your buffer:

var uint8array = new Uint8Array(utf8buffer);

Hope it works as well for you as it has for me.