Compiler Explorer

Source code

#![feature(core_intrinsics)]
#![feature(iter_advance_by)]
#![feature(unchecked_math)]

use std::num::NonZeroUsize;

pub fn advance_by<'a>(s: &mut core::slice::Iter<'a, u8>, mut remainder: usize) -> Result<(), NonZeroUsize> {
    while (remainder > 0) && (s.len() > 0) {
        remainder -= 1;
        let b = s.as_slice()[0];
        let slurp = utf8_char_width(b);
        unsafe { s.advance_by(slurp).unwrap_unchecked() };
    }

NonZeroUsize::new(remainder).map_or(Ok(()), Err)
}

pub fn advance<'a>(s: &mut core::slice::Iter<'a, u8>) -> Result<(), NonZeroUsize> {
    advance_by(s, 1)
}

pub fn std_advance(s: &mut std::str::Chars)  -> Result<(), NonZeroUsize> {
    s.advance_by(1)
}

pub fn std_advance_by(s: &mut std::str::Chars, by: usize)  -> Result<(), NonZeroUsize> {
    s.advance_by(by)
}

#[inline]
const fn utf8_is_cont_byte(byte: u8) -> bool {
    (byte as i8) < -64
}

const UTF8_CHAR_WIDTH: &[u8; 256] = &[
    // 1  2  3  4  5  6  7  8  9  A  B  C  D  E  F
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 0
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 1
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 2
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 3
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 4
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 5
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 6
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 7
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 8
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 9
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // A
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // B
    0, 0, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, // C
    2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, // D
    3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, // E
    4, 4, 4, 4, 4, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // F
];

/// Given a first byte, determines how many bytes are in this UTF-8 character.
#[inline]
pub const fn utf8_char_width(b: u8) -> usize {
    UTF8_CHAR_WIDTH[b as usize] as usize
}