Last active
July 1, 2021 12:22
-
-
Save camas/80113751bcdbb7c8b284d505efacf8d4 to your computer and use it in GitHub Desktop.
Read a single utf8 char using rust
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
// See: https://en.wikipedia.org/wiki/UTF-8#Encoding | |
fn read_char<T: Read>(data: &mut T) -> char { | |
let b = read_u8(data); | |
let value; | |
if (b & 0b1111_1000) == 0b1111_0000 { | |
value = (((b & 0b0000_0111) as u32) << 18) | |
+ (((read_u8(data) & 0b0011_1111) as u32) << 12) | |
+ (((read_u8(data) & 0b0011_1111) as u32) << 6) | |
+ ((read_u8(data) & 0b0011_1111) as u32); | |
} else if (b & 0b1111_0000) == 0b1110_0000 { | |
value = (((b & 0b0000_1111) as u32) << 12) | |
+ (((read_u8(data) & 0b0011_1111) as u32) << 6) | |
+ ((read_u8(data) & 0b0011_1111) as u32); | |
} else if (b & 0b1110_0000) == 0b1100_0000 { | |
value = (((b & 0b0001_1111) as u32) << 6) + ((read_u8(data) & 0b0011_1111) as u32); | |
} else { | |
value = b as u32; | |
} | |
char::from_u32(value).unwrap() | |
} | |
fn read_u8<T: Read>(data: &mut T) -> u8 { | |
let mut buf = [0; 1]; | |
data.read_exact(&mut buf).unwrap(); | |
buf[0] | |
} | |
#[cfg(test)] | |
mod tests { | |
use super::*; | |
#[test] | |
fn test_char() { | |
let data = vec![0xF0, 0x9F, 0x99, 0x82]; | |
assert_eq!(read_char(&mut &data[..]), '🙂'); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment