sj/parser/unicode_char.rs
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150
/*
==--==--==--==--==--==--==--==--==--==--==--==--==--==--==--==--
SJ
Copyright (C) 2019-2024 Anonymous
There are several releases over multiple years,
they are listed as ranges, such as: "2019-2024".
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program. If not, see <https://www.gnu.org/licenses/>.
::--::--::--::--::--::--::--::--::--::--::--::--::--::--::--::--
*/
//! # Unicode character
//!
//! ## References
//!
//! - <https://en.wikipedia.org/wiki/UTF-8>
use {
alloc::vec::Vec,
crate::Result,
};
/// # Unicode character
#[derive(Debug)]
pub (super) struct UnicodeChar {
bytes: [u8; 4],
idx: usize,
}
impl UnicodeChar {
/// # Makes new instance
pub fn new() -> Self {
Self {
bytes: [0; 4],
idx: 0,
}
}
/// # Adds new byte written as a hexadecimal
pub fn add_hex(&mut self, hex: &u8) -> Result<()> {
match self.bytes.get_mut(self.idx) {
Some(item) => {
let byte = match hex {
b'0'..=b'9' => hex - b'0',
b'a'..=b'f' => hex - b'a' + 10,
b'A'..=b'F' => hex - b'A' + 10,
_ => return Err(err!("Not a hexadecimal: {:?}", char::from(*hex))),
};
match self.idx % 2 {
0 => *item = byte * 16,
_ => *item = byte,
};
self.idx += 1;
Ok(())
},
None => return Err(e!("Bytes are full")),
}
}
/// # Checks if data is full
pub fn is_full(&self) -> bool {
self.idx >= self.bytes.len()
}
/// # Encodes as UTF-8 bytes
pub fn encode_as_utf8_bytes(self, out: &mut Vec<u8>) -> Result<()> {
const MARKER: u8 = 0b_1000_0000;
if self.is_full() {
let first = self.bytes[0] + self.bytes[1];
let last = self.bytes[2] + self.bytes[3];
let byte_count = match first {
0x00 => match last {
0x00..=0x7f => ByteCount::One,
_ => ByteCount::Two,
},
0x01..=0x07 => ByteCount::Two,
_ => ByteCount::Three,
};
match byte_count {
ByteCount::One => out.push(last),
ByteCount::Two => {
const HEADER_OF_TWO: u8 = 0b_1100_0000;
out.push(HEADER_OF_TWO | (first << 5 >> 3) | (last >> 6));
out.push(MARKER | (last << 2 >> 2));
},
ByteCount::Three => {
const HEADER_OF_THREE: u8 = 0b_1110_0000;
out.push(HEADER_OF_THREE | (first >> 4));
out.push(MARKER | (first << 4 >> 2) | (last >> 6));
out.push(MARKER | (last << 2 >> 2));
},
};
return Ok(());
}
Err(e!("Bytes are not full"))
}
}
/// # Byte count
#[derive(Debug)]
enum ByteCount {
One,
Two,
Three,
}
#[test]
fn tests() -> Result<()> {
for (hex, chr) in &[
("0024", '\u{0024}'), ("00A2", '\u{00a2}'),
("07fF", '\u{07ff}'),
("0939", '\u{0939}'), ("20AC", '\u{20AC}'), ("d55c", '\u{d55c}'), ("1d2D", '\u{1d2d}'), ("0800", '\u{0800}'), ("fFFf", '\u{FFff}'),
] {
let mut buf = [0; 4];
chr.encode_utf8(&mut buf);
let buf = &buf[..chr.len_utf8()];
let mut uc = UnicodeChar::new();
for b in hex.as_bytes() {
uc.add_hex(b)?;
}
let mut out = Vec::with_capacity(4);
uc.encode_as_utf8_bytes(&mut out)?;
assert_eq!(out, buf);
}
Ok(())
}