gcc/testsuite/rust/compile/issues/3898.rs

// { dg-additional-options "-frust-compile-until=lowering" }
#![feature(no_core)]
#![no_core]

#![feature(lang_items)]

#[lang = "sized"]
trait Sized {}

enum Result<T, E> {
    Ok(T),
    Err(E),
}

use Result::{Err, Ok};

struct Utf8Error;

const CONT_MASK: u8 = 15;
const TAG_CONT_U8: u8 = 15;

#[inline(always)]
pub fn run_utf8_validation(v: &[u8]) -> Result<(), Utf8Error> {
    let mut index = 0;
    let len = 64;

    let usize_bytes = 8;
    let ascii_block_size = 2 * usize_bytes;
    let blocks_end = if len >= ascii_block_size {
        len - ascii_block_size + 1
    } else {
        0
    };

    while index < len {
        let old_offset = index;
        macro_rules! err {
            ($error_len: expr) => {
                return Err(Utf8Error)
            };
        }

        macro_rules! next {
            () => {{
                index += 1;
                // we needed data, but there was none: error!
                if index >= len {
                    err!(None)
                }
                v[index]
            }};
        }

        let first = v[index];
        if first >= 128 {
            let w = 15;
            // 2-byte encoding is for codepoints  \u{0080} to  \u{07ff}
            //        first  C2 80        last DF BF
            // 3-byte encoding is for codepoints  \u{0800} to  \u{ffff}
            //        first  E0 A0 80     last EF BF BF
            //   excluding surrogates codepoints  \u{d800} to  \u{dfff}
            //               ED A0 80 to       ED BF BF
            // 4-byte encoding is for codepoints \u{1000}0 to \u{10ff}ff
            //        first  F0 90 80 80  last F4 8F BF BF
            //
            // Use the UTF-8 syntax from the RFC
            //
            // https://tools.ietf.org/html/rfc3629
            // UTF8-1      = %x00-7F
            // UTF8-2      = %xC2-DF UTF8-tail
            // UTF8-3      = %xE0 %xA0-BF UTF8-tail / %xE1-EC 2( UTF8-tail ) /
            //               %xED %x80-9F UTF8-tail / %xEE-EF 2( UTF8-tail )
            // UTF8-4      = %xF0 %x90-BF 2( UTF8-tail ) / %xF1-F3 3( UTF8-tail ) /
            //               %xF4 %x80-8F 2( UTF8-tail )
            match w {
                2 => {
                    if next!() & !CONT_MASK != TAG_CONT_U8 {
                        err!(Some(1))
                    }
                }
                3 => {
                    match (first, next!()) {
                        (0xE0, 0xA0..=0xBF)
                        | (0xE1..=0xEC, 0x80..=0xBF)
                        | (0xED, 0x80..=0x9F)
                        | (0xEE..=0xEF, 0x80..=0xBF) => {}
                        _ => err!(Some(1)),
                    }
                    if next!() & !CONT_MASK != TAG_CONT_U8 {
                        err!(Some(2))
                    }
                }
                4 => {
                    match (first, next!()) {
                        (0xF0, 0x90..=0xBF) | (0xF1..=0xF3, 0x80..=0xBF) | (0xF4, 0x80..=0x8F) => {}
                        _ => err!(Some(1)),
                    }
                    if next!() & !CONT_MASK != TAG_CONT_U8 {
                        err!(Some(2))
                    }
                    if next!() & !CONT_MASK != TAG_CONT_U8 {
                        err!(Some(3))
                    }
                }
                _ => err!(Some(1)),
            }
            index += 1;
        } else {
            index += 1;
        }
    }

    Ok(())
}

fn main() {}