utf8.rs

// Copyright (c) 2008-2010 Bjoern Hoehrmann <[email protected]>
// See http://bjoern.hoehrmann.de/utf-8/decoder/dfa/ for details.

use std::{error::Error, fmt::Display};

#[derive(Debug)]
pub struct Utf8Error;

impl Display for Utf8Error {
    fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
        write!(f, "invalid utf-8")
    }
}

impl Error for Utf8Error {}

const ACCEPT: u8 = 0;
const REJECT: u8 = 12;

#[rustfmt::skip]
const UTF8D: [u8; 364] = [
  // The first part of the table maps bytes to character classes that
  // to reduce the size of the transition table and create bitmasks.
  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,  9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,
  7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,  7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,
  8,8,2,2,2,2,2,2,2,2,2,2,2,2,2,2,  2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
 10,3,3,3,3,3,3,3,3,3,3,3,3,4,3,3, 11,6,6,6,5,8,8,8,8,8,8,8,8,8,8,8,

 // The second part is a transition table that maps a combination
 // of a state of the automaton and a character class to a state.
  0,12,24,36,60,96,84,12,12,12,48,72, 12,12,12,12,12,12,12,12,12,12,12,12,
 12, 0,12,12,12,12,12, 0,12, 0,12,12, 12,24,12,12,12,12,12,24,12,24,12,12,
 12,12,12,12,12,12,12,24,12,12,12,12, 12,24,12,12,12,12,12,12,12,24,12,12,
 12,12,12,12,12,12,12,36,12,36,12,12, 12,36,12,12,12,12,12,36,12,36,12,12,
 12,36,12,12,12,12,12,12,12,12,12,12,
];

pub struct Utf8Decoder {
    codep: u32,
    state: u8,
}

impl Utf8Decoder {
    pub fn new() -> Self {
        Utf8Decoder {
            state: ACCEPT,
            codep: 0,
        }
    }

    #[inline]
    pub fn decode(&mut self, byte: u8) -> Result<Option<char>, Utf8Error> {
        let byte = byte as u32;
        let typ = UTF8D[byte as usize] as u32;

        self.codep = if self.state != ACCEPT {
            (byte & 0x3f) | (self.codep << 6)
        } else {
            (0xff >> typ) & byte
        };

        self.state = UTF8D[256 + self.state as usize + typ as usize];

        match self.state {
            ACCEPT => unsafe { Ok(Some(char::from_u32_unchecked(self.codep))) },
            REJECT => Err(Utf8Error),
            _ => Ok(None),
        }
    }

    #[inline]
    pub fn valid(&self) -> bool {
        self.state == ACCEPT
    }

    #[inline]
    pub fn invalid(&self) -> bool {
        self.state == REJECT
    }
}