Function next_code_point_reverse

crates/sre_engine/src/string.rs:274–309

(ptr: &mut *const u8)

/// `bytes` must produce a valid UTF-8-like (UTF-8 or WTF-8) string
#[inline]
const unsafe fn next_code_point_reverse(ptr: &mut *const u8) -> u32 {
    // Decode UTF-8
    *ptr = unsafe { ptr.offset(-1) };
    let w = match unsafe { **ptr } {
        next_byte if next_byte < 128 => return next_byte as u32,
        back_byte => back_byte,
    };

    // Multibyte case follows
    // Decode from a byte combination out of: [x [y [z w]]]
    let mut ch;
    // SAFETY: `bytes` produces an UTF-8-like string,
    // so the iterator must produce a value here.
    *ptr = unsafe { ptr.offset(-1) };
    let z = unsafe { **ptr };
    ch = utf8_first_byte(z, 2);
    if utf8_is_cont_byte(z) {
        // SAFETY: `bytes` produces an UTF-8-like string,
        // so the iterator must produce a value here.
        *ptr = unsafe { ptr.offset(-1) };
        let y = unsafe { **ptr };
        ch = utf8_first_byte(y, 3);
        if utf8_is_cont_byte(y) {
            // SAFETY: `bytes` produces an UTF-8-like string,
            // so the iterator must produce a value here.
            *ptr = unsafe { ptr.offset(-1) };
            let x = unsafe { **ptr };
            ch = utf8_first_byte(x, 4);
            ch = utf8_acc_cont_byte(ch, y);
        }
        ch = utf8_acc_cont_byte(ch, z);
    }
    ch = utf8_acc_cont_byte(ch, w);

    ch
}

/// Returns the initial codepoint accumulator for the first byte.
/// The first byte is special, only want bottom 5 bits for width 2, 4 bits