Last active
April 25, 2018 22:52
-
-
Save panzi/f338e83e128736b5aaac2b5a0816f530 to your computer and use it in GitHub Desktop.
Truncate a string at a given length in UTF-8 encoded bytes with JavaScript. Many APIs have lengths limitations given in these kind of numbers.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
// Truncate a string at a given length in UTF-8 encoded bytes. | |
// Many APIs have lengths limitations given in these kind of numbers. | |
function truncateUtf8Bytes(string, byteLength) { | |
const charLength = string.length; | |
let curByteLength = 0; | |
for (let i = 0; i < charLength; ++ i) { | |
const start = i; | |
const w1 = string.charCodeAt(i); | |
let cp = w1; | |
if ((w1 & 0xfc00) === 0xd800) { | |
const w2 = string.charCodeAt(i + 1); | |
if ((w2 & 0xfc00) === 0xdc00) { | |
const hi = w1 & 0x3ff; | |
const lo = w2 & 0x3ff; | |
cp = (hi << 10) | lo | 0x10000; | |
++ i; | |
} | |
} | |
curByteLength += ( | |
cp >= 0x10000 ? 4 : | |
cp >= 0x800 ? 3 : | |
cp >= 0x80 ? 2 : | |
1); | |
if (curByteLength === byteLength) { | |
return string.slice(0, i + 1); | |
} | |
else if (curByteLength > byteLength) { | |
return string.slice(0, start + 1); | |
} | |
} | |
return string; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment