Javascript: UTF8 ↔ String & UTF8 ↔ base64

Fucntion to convert to UTF8 byte array:

function toUTF8Array(str) {
var utf8 = [];
for (var i=0; i < str.length; i++) {
var charcode = str.charCodeAt(i);
if (charcode < 0x80) utf8.push(charcode);
else if (charcode < 0x800) {
utf8.push(0xc0 | (charcode >> 6),
0x80 | (charcode & 0x3f));
}
else if (charcode < 0xd800 || charcode >= 0xe000) {
utf8.push(0xe0 | (charcode >> 12),
0x80 | ((charcode>>6) & 0x3f),
0x80 | (charcode & 0x3f));
}
// surrogate pair
else {
i++;
// UTF-16 encodes 0x10000-0x10FFFF by
// subtracting 0x10000 and splitting the
// 20 bits of 0x0-0xFFFFF into two halves
charcode = 0x10000 + (((charcode & 0x3ff)<<10)
| (str.charCodeAt(i) & 0x3ff))
utf8.push(0xf0 | (charcode >>18),
0x80 | ((charcode>>12) & 0x3f),
0x80 | ((charcode>>6) & 0x3f),
0x80 | (charcode & 0x3f));
}
}
return utf8;
}

view raw
toUTF8Array.js
hosted with ❤ by GitHub

 

Function to convert from UTF8 byte array to String:

JavaScript: Correctly Converting a Byte Array to a UTF-8 String

 

 

For base64:

https://stackoverflow.com/questions/30106476/using-javascripts-atob-to-decode-base64-doesnt-properly-decode-utf-8-strings

 

 

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

Powered by WordPress.com.

Up ↑

%d bloggers like this: