-
Notifications
You must be signed in to change notification settings - Fork 235
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
feat(Rust): Implement utf16 to utf8 conversion algorithm (#1730)
## What does this PR do? Implement an util function converting utf16 encoded string to utf8 string in Rust. ## Related issues #1547 ## Does this PR introduce any user-facing change? - [x] Does this PR introduce any public API change? - [ ] Does this PR introduce any binary protocol compatibility change? ## Benchmark
- Loading branch information
Showing
3 changed files
with
228 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,113 @@ | ||
// Licensed to the Apache Software Foundation (ASF) under one | ||
// or more contributor license agreements. See the NOTICE file | ||
// distributed with this work for additional information | ||
// regarding copyright ownership. The ASF licenses this file | ||
// to you under the Apache License, Version 2.0 (the | ||
// "License"); you may not use this file except in compliance | ||
// with the License. You may obtain a copy of the License at | ||
// | ||
// http://www.apache.org/licenses/LICENSE-2.0 | ||
// | ||
// Unless required by applicable law or agreed to in writing, | ||
// software distributed under the License is distributed on an | ||
// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY | ||
// KIND, either express or implied. See the License for the | ||
// specific language governing permissions and limitations | ||
// under the License. | ||
|
||
use std::ptr; | ||
|
||
// Swapping the high 8 bits and the low 8 bits of a 16-bit value | ||
fn swap_endian(value: u16) -> u16 { | ||
(value << 8) | (value >> 8) | ||
} | ||
|
||
pub fn to_utf8(utf16: &[u16], is_little_endian: bool) -> Result<Vec<u8>, String> { | ||
// Pre-allocating capacity to avoid dynamic resizing | ||
// Longest case: 1 u16 to 3 u8 | ||
let mut utf8_bytes: Vec<u8> = Vec::with_capacity(utf16.len() * 3); | ||
// For unsafe write to Vec | ||
let ptr = utf8_bytes.as_mut_ptr(); | ||
let mut offset = 0; | ||
let mut iter = utf16.iter(); | ||
while let Some(&wc) = iter.next() { | ||
// Using big endian in this conversion | ||
let wc = if is_little_endian { | ||
swap_endian(wc) | ||
} else { | ||
wc | ||
}; | ||
match wc { | ||
code_point if code_point < 0x80 => { | ||
// 1-byte UTF-8 | ||
// [0000|0000|0ccc|cccc] => [0ccc|cccc] | ||
unsafe { | ||
ptr.add(offset).write(code_point as u8); | ||
} | ||
offset += 1; | ||
} | ||
code_point if code_point < 0x800 => { | ||
// 2-byte UTF-8 | ||
// [0000|0bbb|bbcc|cccc] => [110|bbbbb], [10|cccccc] | ||
let bytes = [ | ||
(code_point >> 6 & 0b1_1111) as u8 | 0b1100_0000, | ||
(code_point & 0b11_1111) as u8 | 0b1000_0000, | ||
]; | ||
unsafe { | ||
ptr::copy_nonoverlapping(bytes.as_ptr(), ptr.add(offset), 2); | ||
} | ||
offset += 2; | ||
} | ||
wc1 if (0xd800..=0xdbff).contains(&wc1) => { | ||
// Surrogate pair (4-byte UTF-8) | ||
// Need extra u16, 2 u16 -> 4 u8 | ||
if let Some(&wc2) = iter.next() { | ||
let wc2 = if is_little_endian { | ||
swap_endian(wc2) | ||
} else { | ||
wc2 | ||
}; | ||
if !(0xdc00..=0xdfff).contains(&wc2) { | ||
return Err("Invalid UTF-16 string: wrong surrogate pair".to_string()); | ||
} | ||
// utf16 to unicode | ||
let code_point = | ||
((((wc1 as u32) - 0xd800) << 10) | ((wc2 as u32) - 0xdc00)) + 0x10000; | ||
// 11110??? 10?????? 10?????? 10?????? | ||
// Need 21 bit suffix of code_point | ||
let bytes = [ | ||
(code_point >> 18 & 0b111) as u8 | 0b1111_0000, | ||
(code_point >> 12 & 0b11_1111) as u8 | 0b1000_0000, | ||
(code_point >> 6 & 0b11_1111) as u8 | 0b1000_0000, | ||
(code_point & 0b11_1111) as u8 | 0b1000_0000, | ||
]; | ||
unsafe { | ||
ptr::copy_nonoverlapping(bytes.as_ptr(), ptr.add(offset), 4); | ||
} | ||
offset += 4; | ||
} else { | ||
return Err("Invalid UTF-16 string: missing surrogate pair".to_string()); | ||
} | ||
} | ||
_ => { | ||
// 3-byte UTF-8, 1 u16 -> 3 u8 | ||
// [aaaa|bbbb|bbcc|cccc] => [1110|aaaa], [10|bbbbbb], [10|cccccc] | ||
// Need 16 bit suffix of wc, as same as wc itself | ||
let bytes = [ | ||
(wc >> 12 | 0b1110_0000) as u8, | ||
(wc >> 6 & 0b11_1111) as u8 | 0b1000_0000, | ||
(wc & 0b11_1111) as u8 | 0b1000_0000, | ||
]; | ||
unsafe { | ||
ptr::copy_nonoverlapping(bytes.as_ptr(), ptr.add(offset), 3); | ||
} | ||
offset += 3; | ||
} | ||
} | ||
} | ||
unsafe { | ||
// As ptr.write don't change the length | ||
utf8_bytes.set_len(offset); | ||
} | ||
Ok(utf8_bytes) | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,113 @@ | ||
// Licensed to the Apache Software Foundation (ASF) under one | ||
// or more contributor license agreements. See the NOTICE file | ||
// distributed with this work for additional information | ||
// regarding copyright ownership. The ASF licenses this file | ||
// to you under the Apache License, Version 2.0 (the | ||
// "License"); you may not use this file except in compliance | ||
// with the License. You may obtain a copy of the License at | ||
// | ||
// http://www.apache.org/licenses/LICENSE-2.0 | ||
// | ||
// Unless required by applicable law or agreed to in writing, | ||
// software distributed under the License is distributed on an | ||
// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY | ||
// KIND, either express or implied. See the License for the | ||
// specific language governing permissions and limitations | ||
// under the License. | ||
|
||
use fury::to_utf8; | ||
|
||
#[test] | ||
fn test_to_utf8() { | ||
let s = "Hé€lo, 世界!😀"; | ||
let is_little_endian = false; | ||
let utf16_bytes = s.encode_utf16().collect::<Vec<u16>>(); | ||
println!("==========init utf16:"); | ||
let utf16_strings: Vec<String> = utf16_bytes | ||
.iter() | ||
.map(|&byte| format!("0x{:04x}", byte)) | ||
.collect(); | ||
println!("{}", utf16_strings.join(",")); | ||
let utf8_bytes = to_utf8(&utf16_bytes, is_little_endian).unwrap(); | ||
println!("==========utf8:"); | ||
let utf8_strings: Vec<String> = utf8_bytes | ||
.iter() | ||
.map(|&byte| format!("0x{:02x}", byte)) | ||
.collect(); | ||
println!("{}", utf8_strings.join(",")); | ||
// final UTF-8 string | ||
let final_string = String::from_utf8(utf8_bytes.clone()).unwrap(); | ||
println!("final string: {}", final_string); | ||
assert_eq!(s, final_string); | ||
} | ||
|
||
// For test | ||
fn swap_endian(value: u16) -> u16 { | ||
((value & 0xff) << 8) | ((value & 0xff00) >> 8) | ||
} | ||
|
||
#[test] | ||
fn test_to_utf8_3byte() { | ||
let s = "é₫l₪₮"; | ||
let utf16_bytes = s.encode_utf16().collect::<Vec<u16>>(); | ||
let utf8_bytes = to_utf8(&utf16_bytes, false).unwrap(); | ||
assert_eq!(String::from_utf8(utf8_bytes.clone()).unwrap(), s); | ||
let utf16_bytes_le = s | ||
.encode_utf16() | ||
.collect::<Vec<u16>>() | ||
.iter() | ||
.map(|&byte| swap_endian(byte)) | ||
.collect::<Vec<u16>>(); | ||
let utf8_bytes_le = to_utf8(&utf16_bytes_le, true).unwrap(); | ||
assert_eq!(String::from_utf8(utf8_bytes_le.clone()).unwrap(), s); | ||
} | ||
|
||
#[test] | ||
fn test_to_utf8_endian() { | ||
let utf16 = &[0x6100, 0x6200]; // 'ab' in UTF-16 little endian | ||
let expected = b"ab"; | ||
let result = to_utf8(utf16, true).unwrap(); | ||
assert_eq!(result, expected, "Little endian test failed"); | ||
let utf16 = &[0x0061, 0x0062]; // 'ab' in UTF-16 big endian | ||
let expected = b"ab"; | ||
let result = to_utf8(utf16, false).unwrap(); | ||
assert_eq!(result, expected, "Big endian test failed"); | ||
} | ||
|
||
#[test] | ||
fn test_to_utf8_surrogate_pair() { | ||
let s = "𝄞💡😀🎻"; | ||
let utf16_bytes = s.encode_utf16().collect::<Vec<u16>>(); | ||
let result_be = to_utf8(&utf16_bytes, false); | ||
assert!(result_be.is_ok()); | ||
assert_eq!(String::from_utf8(result_be.unwrap().clone()).unwrap(), s); | ||
// test little endian | ||
let utf16_bytes_le = s | ||
.encode_utf16() | ||
.collect::<Vec<u16>>() | ||
.iter() | ||
.map(|&byte| swap_endian(byte)) | ||
.collect::<Vec<u16>>(); | ||
let result_le = to_utf8(&utf16_bytes_le, true); | ||
assert!(result_le.is_ok()); | ||
assert_eq!(String::from_utf8(result_le.unwrap().clone()).unwrap(), s); | ||
} | ||
|
||
#[test] | ||
fn test_to_utf8_missing_surrogate_pair() { | ||
let utf16 = &[0x00D8]; // Missing second surrogate | ||
let result = to_utf8(utf16, true); | ||
assert!(result.is_err()); | ||
assert_eq!( | ||
result.unwrap_err(), | ||
"Invalid UTF-16 string: missing surrogate pair" | ||
); | ||
|
||
let utf16 = &[0x00D8, 0x00DA]; // Wrong second surrogate | ||
let result = to_utf8(utf16, true); | ||
assert!(result.is_err()); | ||
assert_eq!( | ||
result.unwrap_err(), | ||
"Invalid UTF-16 string: wrong surrogate pair" | ||
); | ||
} |