├── .github └── workflows │ └── build.yml ├── .gitignore ├── Cargo.toml ├── LICENSE-APACHE ├── LICENSE-MIT ├── README.md └── src └── lib.rs /.github/workflows/build.yml: -------------------------------------------------------------------------------- 1 | name: Build and Test 2 | 3 | on: 4 | pull_request: 5 | push: 6 | branches: 7 | - main 8 | 9 | env: 10 | RUSTFLAGS: -Dwarnings 11 | 12 | jobs: 13 | test: 14 | runs-on: ubuntu-latest 15 | strategy: 16 | matrix: 17 | rust: [stable, 1.46] 18 | steps: 19 | - uses: actions/checkout@v2 20 | - uses: actions-rs/toolchain@v1 21 | with: 22 | toolchain: ${{ matrix.rust }} 23 | profile: minimal 24 | override: true 25 | components: rustfmt 26 | - name: tests 27 | run: cargo test 28 | - name: fmt 29 | run: cargo fmt -- --check 30 | if: matrix.rust == 'stable' -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | /target 2 | Cargo.lock 3 | -------------------------------------------------------------------------------- /Cargo.toml: -------------------------------------------------------------------------------- 1 | [package] 2 | name = "const-utf16" 3 | version = "0.2.1" 4 | authors = ["Ryan Levick "] 5 | edition = "2018" 6 | license = "Apache-2.0/MIT" 7 | repository = "https://github.com/rylev/const-utf16" 8 | documentation = "https://docs.rs/const-utf16" 9 | description = "Utf8 to utf16 conversion functions for use in const contexts" 10 | keywords = ["const", "utf16", "utf8"] 11 | readme = "README.md" 12 | 13 | [dependencies] 14 | -------------------------------------------------------------------------------- /LICENSE-APACHE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. -------------------------------------------------------------------------------- /LICENSE-MIT: -------------------------------------------------------------------------------- 1 | Permission is hereby granted, free of charge, to any 2 | person obtaining a copy of this software and associated 3 | documentation files (the "Software"), to deal in the 4 | Software without restriction, including without 5 | limitation the rights to use, copy, modify, merge, 6 | publish, distribute, sublicense, and/or sell copies of 7 | the Software, and to permit persons to whom the Software 8 | is furnished to do so, subject to the following 9 | conditions: 10 | 11 | The above copyright notice and this permission notice 12 | shall be included in all copies or substantial portions 13 | of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF 16 | ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED 17 | TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A 18 | PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT 19 | SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY 20 | CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION 21 | OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR 22 | IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 23 | DEALINGS IN THE SOFTWARE. -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | [![crates.io](https://img.shields.io/crates/v/const-utf16.svg)](https://crates.io/crates/const-utf16) 2 | [![docs.rs](https://docs.rs/const-utf16/badge.svg)](https://docs.rs/const-utf16/) 3 | [![Build and Test](https://github.com/rylev/const-utf16/workflows/Build%20and%20Test/badge.svg)](https://github.com/rylev/const-utf16/actions) 4 | 5 | # const-utf16 6 | 7 | utf8 to utf16 conversion functions useable in const contexts. 8 | 9 | ## Use 10 | 11 | ```rust 12 | const HELLO_WORLD_UTF16: &[u16] = const_utf16::encode!("Hello, world!"); 13 | ``` 14 | 15 | # Minimum Supported Rust Version (MSRV) 16 | 17 | This crate requires Rust 1.46.0 or newer due to the use of some const expression features. 18 | 19 | ## Attribution 20 | 21 | This code is largely inspired by the [Rust core utf16 conversion code](https://github.com/rust-lang/rust/blob/399b6452b5d9982438be208668bc758479f13725/library/core/src/char/methods.rs#L1627-L1652). 22 | -------------------------------------------------------------------------------- /src/lib.rs: -------------------------------------------------------------------------------- 1 | //! Const evaluated utf8 to utf16 conversion functions. 2 | //! 3 | //! # Use 4 | //! 5 | //! ``` 6 | //! # #[macro_use] 7 | //! # extern crate const_utf16; 8 | //! # fn main() {} 9 | //! const HELLO_WORLD_UTF16: &[u16] = const_utf16::encode!("Hello, world!"); 10 | //! ``` 11 | #![no_std] 12 | #![deny(missing_docs)] 13 | 14 | /// Encode a &str as a utf16 buffer. 15 | #[macro_export] 16 | macro_rules! encode { 17 | ($s:expr) => {{ 18 | $crate::encode!($s, non_null_terminated) 19 | }}; 20 | ($s:expr, $null_terminated:ident) => {{ 21 | const __STRING: &'static str = $s; 22 | const __EXTRA_BYTE: usize = $crate::encode!(@@ $null_terminated); 23 | const __STRING_LEN: usize = __STRING.len() + __EXTRA_BYTE; 24 | const __BUFFER_AND_LEN: (&[u16; __STRING_LEN], usize) = { 25 | let mut result = [0; __STRING_LEN]; 26 | let mut utf16_offset = 0; 27 | 28 | let mut iterator = $crate::CodePointIterator::new(__STRING.as_bytes()); 29 | while let Some((next, mut code)) = iterator.next() { 30 | iterator = next; 31 | if code == 0 && __EXTRA_BYTE == 1 { 32 | #[allow(unconditional_panic)] 33 | let _ = 34 | ["Found a null byte in string which should have no null bytes"][usize::MAX]; 35 | } 36 | if (code & 0xFFFF) == code { 37 | result[utf16_offset] = code as u16; 38 | utf16_offset += 1; 39 | } else { 40 | // Supplementary planes break into surrogates. 41 | code -= 0x1_0000; 42 | result[utf16_offset] = 0xD800 | ((code >> 10) as u16); 43 | result[utf16_offset + 1] = 0xDC00 | ((code as u16) & 0x3FF); 44 | utf16_offset += 2; 45 | } 46 | } 47 | (&{ result }, utf16_offset + __EXTRA_BYTE) 48 | }; 49 | const __OUT: &[u16; __BUFFER_AND_LEN.1] = unsafe { 50 | ::core::mem::transmute::< 51 | &'static &[u16; __STRING_LEN], 52 | &'static &[u16; __BUFFER_AND_LEN.1], 53 | >(&__BUFFER_AND_LEN.0) 54 | }; 55 | __OUT 56 | }}; 57 | (@@ null_terminated) => { 58 | 1 59 | }; 60 | (@@ non_null_terminated) => { 61 | 0 62 | }; 63 | } 64 | 65 | /// Encode a &str as a utf16 buffer with a terminating null byte 66 | /// 67 | /// # Panics 68 | /// 69 | /// This function panics if called with a string that contains any null bytes. 70 | #[macro_export] 71 | macro_rules! encode_null_terminated { 72 | ($s:expr) => {{ 73 | $crate::encode!($s, null_terminated) 74 | }}; 75 | } 76 | 77 | #[doc(hidden)] 78 | pub struct CodePointIterator<'a> { 79 | buffer: &'a [u8], 80 | offset: usize, 81 | } 82 | 83 | impl<'a> CodePointIterator<'a> { 84 | #[doc(hidden)] 85 | pub const fn new(buffer: &'a [u8]) -> Self { 86 | Self::new_with_offset(buffer, 0) 87 | } 88 | 89 | #[doc(hidden)] 90 | pub const fn new_with_offset(buffer: &'a [u8], offset: usize) -> Self { 91 | Self { buffer, offset } 92 | } 93 | 94 | #[doc(hidden)] 95 | pub const fn next(self) -> Option<(Self, u32)> { 96 | if let Some((codepont, num_utf8_bytes)) = next_code_point(self.buffer, self.offset) { 97 | Some(( 98 | Self::new_with_offset(self.buffer, self.offset + num_utf8_bytes), 99 | codepont, 100 | )) 101 | } else { 102 | None 103 | } 104 | } 105 | } 106 | 107 | /// Largely adapted from [Rust core](https://github.com/rust-lang/rust/blob/7e2032390cf34f3ffa726b7bd890141e2684ba63/library/core/src/str/validations.rs#L40-L68). 108 | const fn next_code_point(bytes: &[u8], start: usize) -> Option<(u32, usize)> { 109 | if bytes.len() == start { 110 | return None; 111 | } 112 | let mut num_bytes = 1; 113 | let x = bytes[start + 0]; 114 | if x < 128 { 115 | return Some((x as u32, num_bytes)); 116 | } 117 | // Multibyte case follows 118 | // Decode from a byte combination out of: [[[x y] z] w] 119 | // NOTE: Performance is sensitive to the exact formulation here 120 | let init = utf8_first_byte(x, 2); 121 | let y = unwrap_or_0(bytes, start + 1); 122 | if y != 0 { 123 | num_bytes += 1; 124 | } 125 | let mut ch = utf8_acc_cont_byte(init, y); 126 | if x >= 0xE0 { 127 | // [[x y z] w] case 128 | // 5th bit in 0xE0 .. 0xEF is always clear, so `init` is still valid 129 | let z = unwrap_or_0(bytes, start + 2); 130 | if z != 0 { 131 | num_bytes += 1; 132 | } 133 | let y_z = utf8_acc_cont_byte((y & CONT_MASK) as u32, z); 134 | ch = init << 12 | y_z; 135 | if x >= 0xF0 { 136 | // [x y z w] case 137 | // use only the lower 3 bits of `init` 138 | let w = unwrap_or_0(bytes, start + 3); 139 | if w != 0 { 140 | num_bytes += 1; 141 | } 142 | ch = (init & 7) << 18 | utf8_acc_cont_byte(y_z, w); 143 | } 144 | } 145 | 146 | Some((ch, num_bytes)) 147 | } 148 | 149 | /// Returns the initial codepoint accumulator for the first byte. 150 | /// The first byte is special, only want bottom 5 bits for width 2, 4 bits 151 | /// for width 3, and 3 bits for width 4. 152 | const fn utf8_first_byte(byte: u8, width: u32) -> u32 { 153 | (byte & (0x7F >> width)) as u32 154 | } 155 | 156 | const fn unwrap_or_0(slice: &[u8], index: usize) -> u8 { 157 | if slice.len() > index { 158 | slice[index] 159 | } else { 160 | 0 161 | } 162 | } 163 | 164 | const fn utf8_acc_cont_byte(ch: u32, byte: u8) -> u32 { 165 | (ch << 6) | (byte & CONT_MASK) as u32 166 | } 167 | 168 | /// Mask of the value bits of a continuation byte. 169 | const CONT_MASK: u8 = 0b0011_1111; 170 | 171 | #[cfg(test)] 172 | mod tests { 173 | use super::*; 174 | use core::iter::once; 175 | 176 | #[test] 177 | fn encode_utf16_works() { 178 | const TEXT: &str = "Hello \0ä日本 語"; 179 | let expected = TEXT.encode_utf16(); 180 | const RESULT: &[u16] = encode!(TEXT); 181 | 182 | assert!(RESULT.iter().cloned().eq(expected)); 183 | } 184 | 185 | #[test] 186 | fn encode_utf16_with_null_byte_works() { 187 | const TEXT: &str = "Hello ä日本 語"; 188 | let expected = TEXT.encode_utf16().chain(once(0)); 189 | const RESULT: &[u16] = encode_null_terminated!(TEXT); 190 | 191 | assert!(RESULT.iter().cloned().eq(expected)); 192 | } 193 | } 194 | --------------------------------------------------------------------------------