| 1 |
// Copyright 2012-2016 The Rust Project Developers. See the COPYRIGHT |
| 2 |
// file at the top-level directory of this distribution and at |
| 3 |
// http://rust-lang.org/COPYRIGHT. |
| 4 |
// |
| 5 |
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or |
| 6 |
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license |
| 7 |
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your |
| 8 |
// option. This file may not be copied, modified, or distributed |
| 9 |
// except according to those terms. |
| 10 |
// |
| 11 |
// Original authors: alexchrichton, bluss |
| 12 |
|
| 13 |
// UTF-8 ranges and tags for encoding characters |
| 14 |
const TAG_CONT: u8 = 0b1000_0000; |
| 15 |
const TAG_TWO_B: u8 = 0b1100_0000; |
| 16 |
const TAG_THREE_B: u8 = 0b1110_0000; |
| 17 |
const TAG_FOUR_B: u8 = 0b1111_0000; |
| 18 |
const MAX_ONE_B: u32 = 0x80; |
| 19 |
const MAX_TWO_B: u32 = 0x800; |
| 20 |
const MAX_THREE_B: u32 = 0x10000; |
| 21 |
|
| 22 |
/// Placeholder |
| 23 |
pub struct EncodeUtf8Error; |
| 24 |
|
| 25 |
/// Encode a char into buf using UTF-8. |
| 26 |
/// |
| 27 |
/// On success, return the byte length of the encoding (1, 2, 3 or 4).<br> |
| 28 |
/// On error, return `EncodeUtf8Error` if the buffer was too short for the char. |
| 29 |
/// |
| 30 |
/// Safety: `ptr` must be writable for `len` bytes. |
| 31 |
#[inline] |
| 32 |
pub unsafe fn encode_utf8(ch: char, ptr: *mut u8, len: usize) -> Result<usize, EncodeUtf8Error> |
| 33 |
{ |
| 34 |
let code = ch as u32; |
| 35 |
if code < MAX_ONE_B && len >= 1 { |
| 36 |
ptr.add(0).write(code as u8); |
| 37 |
return Ok(1); |
| 38 |
} else if code < MAX_TWO_B && len >= 2 { |
| 39 |
ptr.add(0).write((code >> 6 & 0x1F) as u8 | TAG_TWO_B); |
| 40 |
ptr.add(1).write((code & 0x3F) as u8 | TAG_CONT); |
| 41 |
return Ok(2); |
| 42 |
} else if code < MAX_THREE_B && len >= 3 { |
| 43 |
ptr.add(0).write((code >> 12 & 0x0F) as u8 | TAG_THREE_B); |
| 44 |
ptr.add(1).write((code >> 6 & 0x3F) as u8 | TAG_CONT); |
| 45 |
ptr.add(2).write((code & 0x3F) as u8 | TAG_CONT); |
| 46 |
return Ok(3); |
| 47 |
} else if len >= 4 { |
| 48 |
ptr.add(0).write((code >> 18 & 0x07) as u8 | TAG_FOUR_B); |
| 49 |
ptr.add(1).write((code >> 12 & 0x3F) as u8 | TAG_CONT); |
| 50 |
ptr.add(2).write((code >> 6 & 0x3F) as u8 | TAG_CONT); |
| 51 |
ptr.add(3).write((code & 0x3F) as u8 | TAG_CONT); |
| 52 |
return Ok(4); |
| 53 |
}; |
| 54 |
Err(EncodeUtf8Error) |
| 55 |
} |
| 56 |
|
| 57 |
|
| 58 |
#[test] |
| 59 |
#[cfg_attr(miri, ignore)] // Miri is too slow |
| 60 |
fn test_encode_utf8() { |
| 61 |
// Test that all codepoints are encoded correctly |
| 62 |
let mut data = [0u8; 16]; |
| 63 |
for codepoint in 0..=(std::char::MAX as u32) { |
| 64 |
if let Some(ch) = std::char::from_u32(codepoint) { |
| 65 |
for elt in &mut data { *elt = 0; } |
| 66 |
let ptr = data.as_mut_ptr(); |
| 67 |
let len = data.len(); |
| 68 |
unsafe { |
| 69 |
let res = encode_utf8(ch, ptr, len).ok().unwrap(); |
| 70 |
assert_eq!(res, ch.len_utf8()); |
| 71 |
} |
| 72 |
let string = std::str::from_utf8(&data).unwrap(); |
| 73 |
assert_eq!(string.chars().next(), Some(ch)); |
| 74 |
} |
| 75 |
} |
| 76 |
} |
| 77 |
|
| 78 |
#[test] |
| 79 |
fn test_encode_utf8_oob() { |
| 80 |
// test that we report oob if the buffer is too short |
| 81 |
let mut data = [0u8; 16]; |
| 82 |
let chars = ['a', 'α', '�', '𐍈']; |
| 83 |
for (len, &ch) in (1..=4).zip(&chars) { |
| 84 |
assert_eq!(len, ch.len_utf8(), "Len of ch={}", ch); |
| 85 |
let ptr = data.as_mut_ptr(); |
| 86 |
unsafe { |
| 87 |
assert!(matches::matches!(encode_utf8(ch, ptr, len - 1), Err(_))); |
| 88 |
assert!(matches::matches!(encode_utf8(ch, ptr, len), Ok(_))); |
| 89 |
} |
| 90 |
} |
| 91 |
} |
| 92 |
|