futf-0.1.5/.cargo_vcs_info.json0000644000000001360000000000100120030ustar { "git": { "sha1": "594e25bef5a87d9d70c93bf27e40538de13e3b10" }, "path_in_vcs": "" }futf-0.1.5/.gitignore000064400000000000000000000000220072674642500126050ustar 00000000000000target Cargo.lock futf-0.1.5/.travis.yml000064400000000000000000000003330072674642500127330ustar 00000000000000language: rust rust: - nightly - beta - stable script: - cargo build - "if [ $TRAVIS_RUST_VERSION = nightly ]; then cargo test; fi" - cargo doc notifications: webhooks: http://build.servo.org:54856/travis futf-0.1.5/Cargo.toml0000644000000014130000000000100100000ustar # THIS FILE IS AUTOMATICALLY GENERATED BY CARGO # # When uploading crates to the registry Cargo will automatically # "normalize" Cargo.toml files for maximal compatibility # with all versions of Cargo and also rewrite `path` dependencies # to registry (e.g., crates.io) dependencies. # # If you are reading this file be aware that the original Cargo.toml # will likely look very different (and much more reasonable). # See Cargo.toml.orig for the original contents. [package] name = "futf" version = "0.1.5" authors = ["Keegan McAllister "] description = "Handling fragments of UTF-8" license = "MIT / Apache-2.0" repository = "https://github.com/servo/futf" [dependencies.mac] version = "0.1.0" [dependencies.new_debug_unreachable] version = "1.0.2" futf-0.1.5/Cargo.toml.orig000064400000000000000000000004310072674642500135100ustar 00000000000000[package] name = "futf" version = "0.1.5" authors = ["Keegan McAllister "] license = "MIT / Apache-2.0" repository = "https://github.com/servo/futf" description = "Handling fragments of UTF-8" [dependencies] mac = "0.1.0" new_debug_unreachable = "1.0.2" futf-0.1.5/LICENSE-APACHE000064400000000000000000000251370072674642500125570ustar 00000000000000 Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 1. Definitions. "License" shall mean the terms and conditions for use, reproduction, and distribution as defined by Sections 1 through 9 of this document. "Licensor" shall mean the copyright owner or entity authorized by the copyright owner that is granting the License. "Legal Entity" shall mean the union of the acting entity and all other entities that control, are controlled by, or are under common control with that entity. For the purposes of this definition, "control" means (i) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares, or (iii) beneficial ownership of such entity. "You" (or "Your") shall mean an individual or Legal Entity exercising permissions granted by this License. "Source" form shall mean the preferred form for making modifications, including but not limited to software source code, documentation source, and configuration files. "Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types. "Work" shall mean the work of authorship, whether in Source or Object form, made available under the License, as indicated by a copyright notice that is included in or attached to the work (an example is provided in the Appendix below). "Derivative Works" shall mean any work, whether in Source or Object form, that is based on (or derived from) the Work and for which the editorial revisions, annotations, elaborations, or other modifications represent, as a whole, an original work of authorship. For the purposes of this License, Derivative Works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work and Derivative Works thereof. "Contribution" shall mean any work of authorship, including the original version of the Work and any modifications or additions to that Work or Derivative Works thereof, that is intentionally submitted to Licensor for inclusion in the Work by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, "submitted" means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Work, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution." "Contributor" shall mean Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Work. 2. Grant of Copyright License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute the Work and such Derivative Works in Source or Object form. 3. Grant of Patent License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Work, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Work to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Work or a Contribution incorporated within the Work constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for that Work shall terminate as of the date such litigation is filed. 4. Redistribution. You may reproduce and distribute copies of the Work or Derivative Works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions: (a) You must give any other recipients of the Work or Derivative Works a copy of this License; and (b) You must cause any modified files to carry prominent notices stating that You changed the files; and (c) You must retain, in the Source form of any Derivative Works that You distribute, all copyright, patent, trademark, and attribution notices from the Source form of the Work, excluding those notices that do not pertain to any part of the Derivative Works; and (d) If the Work includes a "NOTICE" text file as part of its distribution, then any Derivative Works that You distribute must include a readable copy of the attribution notices contained within such NOTICE file, excluding those notices that do not pertain to any part of the Derivative Works, in at least one of the following places: within a NOTICE text file distributed as part of the Derivative Works; within the Source form or documentation, if provided along with the Derivative Works; or, within a display generated by the Derivative Works, if and wherever such third-party notices normally appear. The contents of the NOTICE file are for informational purposes only and do not modify the License. You may add Your own attribution notices within Derivative Works that You distribute, alongside or as an addendum to the NOTICE text from the Work, provided that such additional attribution notices cannot be construed as modifying the License. You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such Derivative Works as a whole, provided Your use, reproduction, and distribution of the Work otherwise complies with the conditions stated in this License. 5. Submission of Contributions. Unless You explicitly state otherwise, any Contribution intentionally submitted for inclusion in the Work by You to the Licensor shall be under the terms and conditions of this License, without any additional terms or conditions. Notwithstanding the above, nothing herein shall supersede or modify the terms of any separate license agreement you may have executed with Licensor regarding such Contributions. 6. Trademarks. This License does not grant permission to use the trade names, trademarks, service marks, or product names of the Licensor, except as required for reasonable and customary use in describing the origin of the Work and reproducing the content of the NOTICE file. 7. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Work (and each Contributor provides its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Work and assume any risks associated with Your exercise of permissions under this License. 8. Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Work (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages. 9. Accepting Warranty or Additional Liability. While redistributing the Work or Derivative Works thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability. END OF TERMS AND CONDITIONS APPENDIX: How to apply the Apache License to your work. To apply the Apache License to your work, attach the following boilerplate notice, with the fields enclosed by brackets "[]" replaced with your own identifying information. (Don't include the brackets!) The text should be enclosed in the appropriate comment syntax for the file format. We also recommend that a file or class name and description of purpose be included on the same "printed page" as the copyright notice for easier identification within third-party archives. Copyright [yyyy] [name of copyright owner] Licensed 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. futf-0.1.5/LICENSE-MIT000064400000000000000000000020450072674642500122600ustar 00000000000000Copyright (c) 2015 Keegan McAllister Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. futf-0.1.5/README.md000064400000000000000000000014670072674642500121120ustar 00000000000000# futf [![Build Status](https://travis-ci.org/servo/futf.svg?branch=master)](https://travis-ci.org/kmcallister/futf) futf is a library for *flexible* UTF-8, or UTF-8 *fragments*. I don't know. Check out the [API documentation](http://doc.servo.org/futf/index.html). Anyway, it takes an index into a byte buffer and tells you things about the UTF-8 codepoint containing that byte. It can deal with incomplete codepoint prefixes / suffixes at the ends of a buffer, which is useful for incremental I/O. It can also handle UTF-16 surrogate code units encoded in the manner of [CESU-8][] or [WTF-8][]. This is a low-level helper for [tendril][] that might be useful more generally. [CESU-8]: http://www.unicode.org/reports/tr26/ [WTF-8]: http://simonsapin.github.io/wtf-8/ [tendril]: https://github.com/kmcallister/tendril futf-0.1.5/src/lib.rs000064400000000000000000000207520072674642500125340ustar 00000000000000// Licensed under the Apache License, Version 2.0 or the MIT license // , at your // option. This file may not be copied, modified, or distributed // except according to those terms. #![cfg_attr(test, feature(test))] #[macro_use] extern crate debug_unreachable; #[macro_use] extern crate mac; #[cfg(test)] extern crate test as std_test; use std::{slice, char}; /// Meaning of a complete or partial UTF-8 codepoint. /// /// Not all checking is performed eagerly. That is, a codepoint `Prefix` or /// `Suffix` may in reality have no valid completion. #[derive(Copy, Clone, PartialEq, Eq, PartialOrd, Ord, Debug, Hash)] pub enum Meaning { /// We found a whole codepoint. Whole(char), /// We found something that isn't a valid Unicode codepoint, but /// it *would* correspond to a UTF-16 leading surrogate code unit, /// i.e. a value in the range `U+D800` - `U+DBFF`. /// /// The argument is the code unit's 10-bit index within that range. /// /// These are found in UTF-8 variants such as CESU-8 and WTF-8. LeadSurrogate(u16), /// We found something that isn't a valid Unicode codepoint, but /// it *would* correspond to a UTF-16 trailing surrogate code unit, /// i.e. a value in the range `U+DC00` - `U+DFFF`. /// /// The argument is the code unit's 10-bit index within that range. /// /// These are found in UTF-8 variants such as CESU-8 and WTF-8. TrailSurrogate(u16), /// We found only a prefix of a codepoint before the buffer ended. /// /// Includes the number of additional bytes needed. Prefix(usize), /// We found only a suffix of a codepoint before running off the /// start of the buffer. /// /// Up to 3 more bytes may be needed. Suffix, } /// Represents a complete or partial UTF-8 codepoint. #[derive(Copy, Clone, PartialEq, Eq, PartialOrd, Ord, Debug, Hash)] pub struct Codepoint<'a> { /// The bytes that make up the partial or full codepoint. /// /// For a `Suffix` this depends on `idx`. We don't scan forward /// for additional continuation bytes after the reverse scan /// failed to locate a multibyte sequence start. pub bytes: &'a [u8], /// Start of the codepoint in the buffer, expressed as an offset /// back from `idx`. pub rewind: usize, /// Meaning of the partial or full codepoint. pub meaning: Meaning, } #[derive(Debug, PartialEq, Eq)] enum Byte { Ascii, Start(usize), Cont, } impl Byte { #[inline(always)] fn classify(x: u8) -> Option { match x & 0xC0 { 0xC0 => match x { x if x & 0b11111_000 == 0b11110_000 => Some(Byte::Start(4)), x if x & 0b1111_0000 == 0b1110_0000 => Some(Byte::Start(3)), x if x & 0b111_00000 == 0b110_00000 => Some(Byte::Start(2)), _ => None, }, 0x80 => Some(Byte::Cont), _ => Some(Byte::Ascii), } } } #[inline(always)] fn all_cont(buf: &[u8]) -> bool { buf.iter().all(|&b| matches!(Byte::classify(b), Some(Byte::Cont))) } // NOTE: Assumes the buffer is a syntactically valid multi-byte UTF-8 sequence: // a starting byte followed by the correct number of continuation bytes. #[inline(always)] unsafe fn decode(buf: &[u8]) -> Option { debug_assert!(buf.len() >= 2); debug_assert!(buf.len() <= 4); let n; match buf.len() { 2 => { n = ((*buf.get_unchecked(0) & 0b11111) as u32) << 6 | ((*buf.get_unchecked(1) & 0x3F) as u32); if n < 0x80 { return None } // Overlong } 3 => { n = ((*buf.get_unchecked(0) & 0b1111) as u32) << 12 | ((*buf.get_unchecked(1) & 0x3F) as u32) << 6 | ((*buf.get_unchecked(2) & 0x3F) as u32); match n { 0x0000 ... 0x07FF => return None, // Overlong 0xD800 ... 0xDBFF => return Some(Meaning::LeadSurrogate(n as u16 - 0xD800)), 0xDC00 ... 0xDFFF => return Some(Meaning::TrailSurrogate(n as u16 - 0xDC00)), _ => {} } } 4 => { n = ((*buf.get_unchecked(0) & 0b111) as u32) << 18 | ((*buf.get_unchecked(1) & 0x3F) as u32) << 12 | ((*buf.get_unchecked(2) & 0x3F) as u32) << 6 | ((*buf.get_unchecked(3) & 0x3F) as u32); if n < 0x1_0000 { return None } // Overlong } _ => debug_unreachable!(), } char::from_u32(n).map(Meaning::Whole) } #[inline(always)] unsafe fn unsafe_slice<'a>(buf: &'a [u8], start: usize, new_len: usize) -> &'a [u8] { debug_assert!(start <= buf.len()); debug_assert!(new_len <= (buf.len() - start)); slice::from_raw_parts(buf.as_ptr().offset(start as isize), new_len) } macro_rules! otry { ($x:expr) => { unwrap_or_return!($x, None) } } /// Describes the UTF-8 codepoint containing the byte at index `idx` within /// `buf`. /// /// Returns `None` if `idx` is out of range, or if `buf` contains invalid UTF-8 /// in the vicinity of `idx`. #[inline] pub fn classify<'a>(buf: &'a [u8], idx: usize) -> Option> { if idx >= buf.len() { return None; } unsafe { let x = *buf.get_unchecked(idx); match otry!(Byte::classify(x)) { Byte::Ascii => Some(Codepoint { bytes: unsafe_slice(buf, idx, 1), rewind: 0, meaning: Meaning::Whole(x as char), }), Byte::Start(n) => { let avail = buf.len() - idx; if avail >= n { let bytes = unsafe_slice(buf, idx, n); if !all_cont(unsafe_slice(bytes, 1, n-1)) { return None; } let meaning = otry!(decode(bytes)); Some(Codepoint { bytes: bytes, rewind: 0, meaning: meaning, }) } else { Some(Codepoint { bytes: unsafe_slice(buf, idx, avail), rewind: 0, meaning: Meaning::Prefix(n - avail), }) } }, Byte::Cont => { let mut start = idx; let mut checked = 0; loop { if start == 0 { // Whoops, fell off the beginning. return Some(Codepoint { bytes: unsafe_slice(buf, 0, idx + 1), rewind: idx, meaning: Meaning::Suffix, }); } start -= 1; checked += 1; match otry!(Byte::classify(*buf.get_unchecked(start))) { Byte::Cont => (), Byte::Start(n) => { let avail = buf.len() - start; if avail >= n { let bytes = unsafe_slice(buf, start, n); if checked < n { if !all_cont(unsafe_slice(bytes, checked, n-checked)) { return None; } } let meaning = otry!(decode(bytes)); return Some(Codepoint { bytes: bytes, rewind: idx - start, meaning: meaning, }); } else { return Some(Codepoint { bytes: unsafe_slice(buf, start, avail), rewind: idx - start, meaning: Meaning::Prefix(n - avail), }); } } _ => return None, } if idx - start >= 3 { // We looked at 3 bytes before a continuation byte // and didn't find a start byte. return None; } } } } } } #[cfg(test)] mod test; futf-0.1.5/src/test.rs000064400000000000000000000253410072674642500127440ustar 00000000000000// Licensed under the Apache License, Version 2.0 or the MIT license // , at your // option. This file may not be copied, modified, or distributed // except according to those terms. use super::{Meaning, Byte, classify, decode, all_cont}; use std::borrow::ToOwned; use std::io::Write; use std_test::Bencher; #[test] fn classify_all_bytes() { for n in 0x00..0x80 { assert_eq!(Byte::classify(n), Some(Byte::Ascii)); } for n in 0x80..0xC0 { assert_eq!(Byte::classify(n), Some(Byte::Cont)); } for n in 0xC0..0xE0 { assert_eq!(Byte::classify(n), Some(Byte::Start(2))); } for n in 0xE0..0xF0 { assert_eq!(Byte::classify(n), Some(Byte::Start(3))); } for n in 0xF0..0xF8 { assert_eq!(Byte::classify(n), Some(Byte::Start(4))); } for n in 0xF8..0xFF { assert_eq!(Byte::classify(n), None); } assert_eq!(Byte::classify(0xFF), None); } #[test] fn test_all_cont() { assert!(all_cont(b"")); assert!(all_cont(b"\x80")); assert!(all_cont(b"\xBF")); assert!(all_cont(b"\x80\xBF\x80\xBF")); assert!(!all_cont(b"z")); assert!(!all_cont(b"\xC0\xBF")); assert!(!all_cont(b"\xFF")); assert!(!all_cont(b"\x80\xBFz\x80\xBF")); assert!(!all_cont(b"\x80\xBF\xC0\x80\xBF")); assert!(!all_cont(b"\x80\xBF\xFF\x80\xBF")); assert!(!all_cont(b"\x80\xBF\x80\xBFz")); assert!(!all_cont(b"\x80\xBF\x80\xBF\xC0")); assert!(!all_cont(b"z\x80\xBF\x80\xBF")); assert!(!all_cont(b"\xC0\x80\xBF\x80\xBF")); } #[test] fn test_decode() { unsafe { assert_eq!(Some(Meaning::Whole('ő')), decode(b"\xC5\x91")); assert_eq!(Some(Meaning::Whole('\u{a66e}')), decode(b"\xEA\x99\xAE")); assert_eq!(Some(Meaning::Whole('\u{1f4a9}')), decode(b"\xF0\x9F\x92\xA9")); assert_eq!(Some(Meaning::Whole('\u{10ffff}')), decode(b"\xF4\x8F\xBF\xBF")); assert_eq!(Some(Meaning::LeadSurrogate(0x0000)), decode(b"\xED\xA0\x80")); assert_eq!(Some(Meaning::LeadSurrogate(0x0001)), decode(b"\xED\xA0\x81")); assert_eq!(Some(Meaning::LeadSurrogate(0x03FE)), decode(b"\xED\xAF\xBE")); assert_eq!(Some(Meaning::LeadSurrogate(0x03FF)), decode(b"\xED\xAF\xBF")); assert_eq!(Some(Meaning::TrailSurrogate(0x0000)), decode(b"\xED\xB0\x80")); assert_eq!(Some(Meaning::TrailSurrogate(0x0001)), decode(b"\xED\xB0\x81")); assert_eq!(Some(Meaning::TrailSurrogate(0x03FE)), decode(b"\xED\xBF\xBE")); assert_eq!(Some(Meaning::TrailSurrogate(0x03FF)), decode(b"\xED\xBF\xBF")); // The last 4-byte UTF-8 sequence. This would be U+1FFFFF, which is out of // range. assert_eq!(None, decode(b"\xF7\xBF\xBF\xBF")); // First otherwise-valid sequence (would be U+110000) that is out of range assert_eq!(None, decode(b"\xF4\x90\x80\x80")); // Overlong sequences assert_eq!(None, decode(b"\xC0\x80")); assert_eq!(None, decode(b"\xC1\xBF")); assert_eq!(None, decode(b"\xE0\x80\x80")); assert_eq!(None, decode(b"\xE0\x9F\xBF")); assert_eq!(None, decode(b"\xF0\x80\x80\x80")); assert_eq!(None, decode(b"\xF0\x8F\xBF\xBF")); // For not-overlong sequence for each sequence length assert_eq!(Some(Meaning::Whole('\u{80}')), decode(b"\xC2\x80")); assert_eq!(Some(Meaning::Whole('\u{800}')), decode(b"\xE0\xA0\x80")); assert_eq!(Some(Meaning::Whole('\u{10000}')), decode(b"\xF0\x90\x80\x80")); } } static JUNK: &'static [u8] = b"\ \xf8\x0d\x07\x25\xa6\x7b\x95\xeb\x47\x01\x7f\xee\ \x3b\x00\x60\x57\x1d\x9e\x5d\x0a\x0b\x0a\x7c\x75\ \x13\xa1\x82\x46\x27\x34\xe9\x52\x61\x0d\xec\x10\ \x54\x49\x6e\x54\xdf\x7b\xe1\x31\x8c\x06\x21\x83\ \x0f\xb5\x1f\x4c\x6a\x71\x52\x42\x74\xe7\x7b\x50\ \x59\x1f\x6a\xd4\xff\x06\x92\x33\xc4\x34\x97\xff\ \xcc\xb5\xc4\x00\x7b\xc3\x4a\x7f\x7e\x63\x96\x58\ \x51\x63\x21\x54\x53\x2f\x03\x8a\x7d\x41\x79\x98\ \x5b\xcb\xb8\x94\x6b\x73\xf3\x0c\x5a\xd7\xc4\x12\ \x7a\x2b\x9a\x2e\x67\x62\x2a\x00\x45\x2c\xfe\x7d\ \x8d\xd6\x51\x4e\x59\x36\x72\x1b\xae\xaa\x06\xe8\ \x71\x1b\x85\xd3\x35\xb5\xbe\x9e\x16\x96\x72\xd8\ \x1a\x48\xba\x4d\x55\x4f\x1b\xa2\x77\xfa\x8f\x71\ \x58\x7d\x03\x93\xa2\x3a\x76\x51\xda\x48\xe2\x3f\ \xeb\x8d\xda\x89\xae\xf7\xbd\x3d\xb6\x37\x97\xca\ \x99\xcc\x4a\x8d\x62\x89\x97\xe3\xc0\xd1\x8d\xc1\ \x26\x11\xbb\x8d\x53\x61\x4f\x76\x03\x00\x30\xd3\ \x5f\x86\x19\x52\x9c\x3e\x99\x8c\xb7\x21\x48\x1c\ \x85\xae\xad\xd5\x74\x00\x6c\x3e\xd0\x17\xff\x76\ \x5c\x32\xc3\xfb\x24\x99\xd4\x4c\xa4\x1f\x66\x46\ \xe7\x2d\x44\x56\x7d\x14\xd9\x76\x91\x37\x2f\xb7\ \xcc\x1b\xd3\xc2"; #[test] fn classify_whole() { assert_eq!(JUNK.len(), 256); for &c in &['\0', '\x01', 'o', 'z', 'ő', '\u{2764}', '\u{a66e}', '\u{1f4a9}', '\u{1f685}'] { for idx in 0 .. JUNK.len() - 3 { let mut buf = JUNK.to_owned(); let ch = format!("{}", c).into_bytes(); (&mut buf[idx..]).write_all(&ch).unwrap(); for j in 0 .. ch.len() { let class = classify(&buf, idx+j).unwrap(); assert_eq!(class.bytes, &*ch); assert_eq!(class.rewind, j); assert_eq!(class.meaning, Meaning::Whole(c)); } } } } #[test] fn classify_surrogates() { for &(s, b) in &[ (Meaning::LeadSurrogate(0x0000), b"\xED\xA0\x80"), (Meaning::LeadSurrogate(0x0001), b"\xED\xA0\x81"), (Meaning::LeadSurrogate(0x03FE), b"\xED\xAF\xBE"), (Meaning::LeadSurrogate(0x03FF), b"\xED\xAF\xBF"), (Meaning::TrailSurrogate(0x0000), b"\xED\xB0\x80"), (Meaning::TrailSurrogate(0x0001), b"\xED\xB0\x81"), (Meaning::TrailSurrogate(0x03FE), b"\xED\xBF\xBE"), (Meaning::TrailSurrogate(0x03FF), b"\xED\xBF\xBF"), ] { for idx in 0 .. JUNK.len() - 2 { let mut buf = JUNK.to_owned(); (&mut buf[idx..]).write_all(b).unwrap(); let class = classify(&buf, idx).unwrap(); assert_eq!(class.bytes, b); assert_eq!(class.rewind, 0); assert_eq!(class.meaning, s); } } } #[test] fn classify_prefix_suffix() { for &c in &['ő', '\u{a66e}', '\u{1f4a9}'] { let ch = format!("{}", c).into_bytes(); for pfx in 1 .. ch.len() - 1 { let mut buf = JUNK.to_owned(); let buflen = buf.len(); (&mut buf[buflen - pfx .. buflen]).write_all(&ch[..pfx]).unwrap(); for j in 0 .. pfx { let idx = buflen - 1 - j; let class = classify(&buf, idx).unwrap(); assert_eq!(class.bytes, &ch[..pfx]); assert_eq!(class.rewind, pfx - 1 - j); assert_eq!(class.meaning, Meaning::Prefix(ch.len() - pfx)); } } for sfx in 1 .. ch.len() - 1 { let ch_bytes = &ch[ch.len() - sfx ..]; let mut buf = JUNK.to_owned(); (&mut *buf).write_all(ch_bytes).unwrap(); for j in 0 .. sfx { let class = classify(&buf, j).unwrap(); assert!(ch_bytes.starts_with(class.bytes)); assert_eq!(class.rewind, j); assert_eq!(class.meaning, Meaning::Suffix); } } } } #[test] fn out_of_bounds() { assert!(classify(b"", 0).is_none()); assert!(classify(b"", 7).is_none()); assert!(classify(b"aaaaaaa", 7).is_none()); } #[test] fn malformed() { assert_eq!(None, classify(b"\xFF", 0)); assert_eq!(None, classify(b"\xC5\xC5", 0)); assert_eq!(None, classify(b"x\x91", 1)); assert_eq!(None, classify(b"\x91\x91\x91\x91", 3)); assert_eq!(None, classify(b"\x91\x91\x91\x91\x91", 4)); assert_eq!(None, classify(b"\xEA\x91\xFF", 1)); assert_eq!(None, classify(b"\xF0\x90\x90\xF0", 0)); assert_eq!(None, classify(b"\xF0\x90\x90\xF0", 1)); assert_eq!(None, classify(b"\xF0\x90\x90\xF0", 2)); for i in 0..4 { // out of range: U+110000 assert_eq!(None, classify(b"\xF4\x90\x80\x80", i)); // out of range: U+1FFFFF assert_eq!(None, classify(b"\xF7\xBF\xBF\xBF", i)); // Overlong sequences assert_eq!(None, classify(b"\xC0\x80", i)); assert_eq!(None, classify(b"\xC1\xBF", i)); assert_eq!(None, classify(b"\xE0\x80\x80", i)); assert_eq!(None, classify(b"\xE0\x9F\xBF", i)); assert_eq!(None, classify(b"\xF0\x80\x80\x80", i)); assert_eq!(None, classify(b"\xF0\x8F\xBF\xBF", i)); } } static TEXT: &'static str = " All human beings are born free and equal in dignity and rights. They are endowed with reason and conscience and should act towards one another in a spirit of brotherhood. Minden emberi lény szabadon születik és egyenlő méltósága és joga van. Az emberek, ésszel és lelkiismerettel bírván, egymással szemben testvéri szellemben kell hogy viseltessenek. เราทุกคนเกิดมาอย่างอิสระ เราทุกคนมีความคิดและความเข้าใจเป็นของเราเอง เราทุกคนควรได้รับการปฏิบัติในทางเดียวกัน. 모든 인간은 태어날 때부터 자유로우며 그 존엄과 권리에 있어 동등하다. 인간은 천부적으로 이성과 양심을 부여받았으며 서로 형제애의 정신으로 행동하여야 한다. ro remna cu se jinzi co zifre je simdu'i be le ry. nilselsi'a .e lei ry. selcru .i ry. se menli gi'e se sezmarde .i .ei jeseki'ubo ry. simyzu'e ta'i le tunba ᏂᎦᏓ ᎠᏂᏴᏫ ᏂᎨᎫᏓᎸᎾ ᎠᎴ ᎤᏂᏠᏱ ᎤᎾᏕᎿ ᏚᏳᎧᏛ ᎨᏒᎢ. ᎨᏥᏁᎳ ᎤᎾᏓᏅᏖᏗ ᎠᎴ ᎤᏃᏟᏍᏗ ᎠᎴ ᏌᏊ ᎨᏒ ᏧᏂᎸᏫᏍᏓᏁᏗ ᎠᎾᏟᏅᏢ ᎠᏓᏅᏙ ᎬᏗ."; // random static IXES: &'static [usize] = &[778, 156, 87, 604, 1216, 365, 884, 311, 469, 515, 709, 162, 871, 206, 634, 442]; static BOUNDARY: &'static [bool] = &[false, true, true, false, false, true, true, true, true, false, false, true, true, true, false, false]; #[bench] fn std_utf8_check(b: &mut Bencher) { b.iter(|| { assert!(IXES.iter().zip(BOUNDARY.iter()).all(|(&ix, &expect)| { expect == TEXT.is_char_boundary(ix) })); }); } // We don't expect to be as fast as is_char_boundary, because we provide more // information. But we shouldn't be tremendously slower, either. A factor of // 5-10 is expected on this text. #[bench] fn futf_check(b: &mut Bencher) { b.iter(|| { assert!(IXES.iter().zip(BOUNDARY.iter()).all(|(&ix, &expect)| { expect == (::classify(TEXT.as_bytes(), ix).unwrap().rewind == 0) })); }); }