ucd-util-0.1.5/Cargo.toml.orig010064400017500000144000000007221351506402100143450ustar0000000000000000[package] name = "ucd-util" version = "0.1.5" #:version authors = ["Andrew Gallant "] description = """ A small utility library for working with the Unicode character database. """ documentation = "https://docs.rs/ucd-util" homepage = "https://github.com/BurntSushi/ucd-generate" repository = "https://github.com/BurntSushi/ucd-generate" readme = "README.md" keywords = ["unicode", "database", "character", "property"] license = "MIT/Apache-2.0" ucd-util-0.1.5/Cargo.toml0000644000000017170000000000000106300ustar00# 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 believe there's an error in this file please file an # issue against the rust-lang/cargo repository. If you're # editing this file be aware that the upstream Cargo.toml # will likely look very different (and much more reasonable) [package] name = "ucd-util" version = "0.1.5" authors = ["Andrew Gallant "] description = "A small utility library for working with the Unicode character database.\n" homepage = "https://github.com/BurntSushi/ucd-generate" documentation = "https://docs.rs/ucd-util" readme = "README.md" keywords = ["unicode", "database", "character", "property"] license = "MIT/Apache-2.0" repository = "https://github.com/BurntSushi/ucd-generate" ucd-util-0.1.5/Cargo.toml.orig0000644000000017200000000000000115610ustar00# 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 believe there's an error in this file please file an # issue against the rust-lang/cargo repository. If you're # editing this file be aware that the upstream Cargo.toml # will likely look very different (and much more reasonable) [package] name = "ucd-util" version = "0.1.5" authors = ["Andrew Gallant "] description = "A small utility library for working with the Unicode character database.\n" homepage = "https://github.com/BurntSushi/ucd-generate" documentation = "https://docs.rs/ucd-util" readme = "README.md" keywords = ["unicode", "database", "character", "property"] license = "MIT/Apache-2.0" repository = "https://github.com/BurntSushi/ucd-generate" ucd-util-0.1.5/LICENSE-APACHE010064400017500000144000000251371324750327500134240ustar0000000000000000 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. ucd-util-0.1.5/LICENSE-MIT010064400017500000144000000020711324737324600131270ustar0000000000000000The MIT License (MIT) Copyright (c) 2015 Andrew Gallant 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. ucd-util-0.1.5/LICENSE-UNICODE010064400017500000144000000054361337357032100135650ustar0000000000000000UNICODE, INC. LICENSE AGREEMENT - DATA FILES AND SOFTWARE Unicode Data Files include all data files under the directories http://www.unicode.org/Public/, http://www.unicode.org/reports/, http://www.unicode.org/cldr/data/, http://source.icu-project.org/repos/icu/, and http://www.unicode.org/utility/trac/browser/. Unicode Data Files do not include PDF online code charts under the directory http://www.unicode.org/Public/. Software includes any source code published in the Unicode Standard or under the directories http://www.unicode.org/Public/, http://www.unicode.org/reports/, http://www.unicode.org/cldr/data/, http://source.icu-project.org/repos/icu/, and http://www.unicode.org/utility/trac/browser/. NOTICE TO USER: Carefully read the following legal agreement. BY DOWNLOADING, INSTALLING, COPYING OR OTHERWISE USING UNICODE INC.'S DATA FILES ("DATA FILES"), AND/OR SOFTWARE ("SOFTWARE"), YOU UNEQUIVOCALLY ACCEPT, AND AGREE TO BE BOUND BY, ALL OF THE TERMS AND CONDITIONS OF THIS AGREEMENT. IF YOU DO NOT AGREE, DO NOT DOWNLOAD, INSTALL, COPY, DISTRIBUTE OR USE THE DATA FILES OR SOFTWARE. COPYRIGHT AND PERMISSION NOTICE Copyright © 1991-2018 Unicode, Inc. All rights reserved. Distributed under the Terms of Use in http://www.unicode.org/copyright.html. Permission is hereby granted, free of charge, to any person obtaining a copy of the Unicode data files and any associated documentation (the "Data Files") or Unicode software and any associated documentation (the "Software") to deal in the Data Files or Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, and/or sell copies of the Data Files or Software, and to permit persons to whom the Data Files or Software are furnished to do so, provided that either (a) this copyright and permission notice appear with all copies of the Data Files or Software, or (b) this copyright and permission notice appear in associated Documentation. THE DATA FILES AND SOFTWARE ARE 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 OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THE DATA FILES OR SOFTWARE. Except as contained in this notice, the name of a copyright holder shall not be used in advertising or otherwise to promote the sale, use or other dealings in these Data Files or Software without prior written authorization of the copyright holder.ucd-util-0.1.5/README.md010064400017500000144000000016731337357032100127520ustar0000000000000000ucd-util ======== A library for small auxiliary Unicode functions. This includes things like symbol or character name canonicalization, ideograph name generation and helper functions for searching property name and value tables. [![Linux build status](https://api.travis-ci.org/BurntSushi/ucd-generate.png)](https://travis-ci.org/BurntSushi/ucd-generate) [![](http://meritbadge.herokuapp.com/ucd-generate)](https://crates.io/crates/ucd-util) ### Documentation https://docs.rs/ucd-util ### License This project is licensed under either of * Apache License, Version 2.0, ([LICENSE-APACHE](LICENSE-APACHE) or http://www.apache.org/licenses/LICENSE-2.0) * MIT license ([LICENSE-MIT](LICENSE-MIT) or http://opensource.org/licenses/MIT) at your option. The data in [`src/unicode_tables/`](src/unicode_tables) is licensed inder the Unicode License Agreement ([LICENSE-UNICODE](LICENSE-UNICODE) or http://www.unicode.org/copyright.html#License). ucd-util-0.1.5/src/hangul.rs010064400017500000144000000056451322427753300141150ustar0000000000000000use unicode_tables::jamo_short_name::JAMO_SHORT_NAME; // This implementation should correspond to the algorithms described in // Unicode 3.12. /// A set of ranges that corresponds to the set of all Hangul syllable /// codepoints. /// /// These ranges are defined in Unicode 4.8 Table 4-13. pub const RANGE_HANGUL_SYLLABLE: &'static [(u32, u32)] = &[ (0xAC00, 0xD7A3), ]; const S_BASE: u32 = 0xAC00; const L_BASE: u32 = 0x1100; const V_BASE: u32 = 0x1161; const T_BASE: u32 = 0x11A7; const T_COUNT: u32 = 28; const N_COUNT: u32 = 588; /// Return the character name of the given precomposed Hangul codepoint. /// /// If the given codepoint does not correspond to a precomposed Hangul /// codepoint in the inclusive range `AC00..D7A3`, then this returns `None`. /// /// This implements the algorithms described in Unicode 3.12 and Unicode 4.8. pub fn hangul_name(cp: u32) -> Option { let mut name = "HANGUL SYLLABLE ".to_string(); let (lpart, vpart, tpart) = match hangul_full_canonical_decomposition(cp) { None => return None, Some(triple) => triple, }; name.push_str(jamo_short_name(lpart)); name.push_str(jamo_short_name(vpart)); name.push_str(tpart.map_or("", jamo_short_name)); Some(name) } /// Return the full canonical decomposition of the given precomposed Hangul /// codepoint. /// /// If the decomposition does not have any trailing consonant, then the third /// part of the tuple returned is `None`. /// /// If the given codepoint does not correspond to a precomposed Hangul /// codepoint in the inclusive range `AC00..D7A3`, then this returns `None`. /// /// This implements the algorithms described in Unicode 3.12 and Unicode 4.8. pub fn hangul_full_canonical_decomposition( cp: u32, ) -> Option<(u32, u32, Option)> { if !(0xAC00 <= cp && cp <= 0xD7A3) { return None; } let s_index = cp - S_BASE; let l_index = s_index / N_COUNT; let v_index = (s_index % N_COUNT) / T_COUNT; let t_index = s_index % T_COUNT; let l_part = L_BASE + l_index; let v_part = V_BASE + v_index; let t_part = if t_index == 0 { None } else { Some(T_BASE + t_index) }; Some((l_part, v_part, t_part)) } fn jamo_short_name(cp: u32) -> &'static str { let i = JAMO_SHORT_NAME.binary_search_by_key(&cp, |p| p.0).unwrap(); JAMO_SHORT_NAME[i].1 } #[cfg(test)] mod tests { use super::{hangul_name, hangul_full_canonical_decomposition}; #[test] fn canon_decomp() { assert_eq!( hangul_full_canonical_decomposition(0xD4DB), Some((0x1111, 0x1171, Some(0x11B6)))); } #[test] fn name() { assert_eq!(hangul_name(0xD4DB).unwrap(), "HANGUL SYLLABLE PWILH"); } #[test] fn all() { for cp in 0xAC00..(0xD7A3 + 1) { hangul_name(cp).unwrap(); } } #[test] fn invalid() { assert!(hangul_name(0).is_none()); } } ucd-util-0.1.5/src/ideograph.rs010064400017500000144000000043311311711720600145570ustar0000000000000000/// A set of ranges that corresponds to the set of all ideograph codepoints. /// /// These ranges are defined in Unicode 4.8 Table 4-13. pub const RANGE_IDEOGRAPH: &'static [(u32, u32)] = &[ (0x3400, 0x4DB5), (0x4E00, 0x9FD5), (0x4E00, 0x9FD5), (0x20000, 0x2A6D6), (0x2A700, 0x2B734), (0x2B740, 0x2B81D), (0x2B820, 0x2CEA1), (0x17000, 0x187EC), (0xF900, 0xFA6D), (0xFA70, 0xFAD9), (0x2F800, 0x2FA1D), ]; /// Return the character name of the given ideograph codepoint. /// /// This operation is only defined on ideographic codepoints. This includes /// precisely the following inclusive ranges: /// /// * `3400..4DB5` /// * `4E00..9FD5` /// * `20000..2A6D6` /// * `2A700..2B734` /// * `2B740..2B81D` /// * `2B820..2CEA1` /// * `17000..187EC` /// * `F900..FA6D` /// * `FA70..FAD9` /// * `2F800..2FA1D` /// /// If the given codepoint is not in any of the above ranges, then `None` is /// returned. /// /// This implements the algorithm described in Unicode 4.8. pub fn ideograph_name(cp: u32) -> Option { // This match should be in sync with the `RANGE_IDEOGRAPH` constant. match cp { 0x3400...0x4DB5 | 0x4E00...0x9FD5 | 0x20000...0x2A6D6 | 0x2A700...0x2B734 | 0x2B740...0x2B81D | 0x2B820...0x2CEA1 => { Some(format!("CJK UNIFIED IDEOGRAPH-{:04X}", cp)) } 0x17000...0x187EC => { Some(format!("TANGUT IDEOGRAPH-{:04X}", cp)) } 0xF900...0xFA6D | 0xFA70...0xFAD9 | 0x2F800...0x2FA1D => { Some(format!("CJK COMPATIBILITY IDEOGRAPH-{:04X}", cp)) } _ => None, } } #[cfg(test)] mod tests { use super::ideograph_name; #[test] fn name() { assert_eq!( ideograph_name(0x4E00).unwrap(), "CJK UNIFIED IDEOGRAPH-4E00"); assert_eq!( ideograph_name(0x9FD5).unwrap(), "CJK UNIFIED IDEOGRAPH-9FD5"); assert_eq!( ideograph_name(0x17000).unwrap(), "TANGUT IDEOGRAPH-17000"); assert_eq!( ideograph_name(0xF900).unwrap(), "CJK COMPATIBILITY IDEOGRAPH-F900"); } #[test] fn invalid() { assert!(ideograph_name(0).is_none()); } } ucd-util-0.1.5/src/lib.rs010064400017500000144000000020221351474153200133640ustar0000000000000000/*! The `ucd-util` crate contains a smattering of utility functions that implement various algorithms specified by Unicode. There is no specific goal for exhaustiveness. Instead, implementations should be added on an as-needed basis. A *current* design constraint of this crate is that it should not bring in any large Unicode tables. For example, to use the various property name and value canonicalization functions, you'll need to supply your own table, which can be generated using `ucd-generate`. */ #![deny(missing_docs)] #![allow(unknown_lints)] #![allow(ellipsis_inclusive_range_patterns)] mod hangul; mod ideograph; mod name; mod property; mod unicode_tables; pub use hangul::{ RANGE_HANGUL_SYLLABLE, hangul_name, hangul_full_canonical_decomposition, }; pub use ideograph::{RANGE_IDEOGRAPH, ideograph_name}; pub use name::{character_name_normalize, symbolic_name_normalize}; pub use property::{ PropertyTable, PropertyValueTable, PropertyValues, canonical_property_name, property_values, canonical_property_value, }; ucd-util-0.1.5/src/name.rs010064400017500000144000000170731351506373200135520ustar0000000000000000/// Normalize the given character name in place according to UAX44-LM2. /// /// See: http://unicode.org/reports/tr44/#UAX44-LM2 pub fn character_name_normalize(string: &mut String) { let bytes = unsafe { // SAFETY: `character_name_normalize_bytes` guarantees that // `bytes[..len]` is valid UTF-8. string.as_mut_vec() }; let len = character_name_normalize_bytes(bytes).len(); bytes.truncate(len); } /// Normalize the given character name in place according to UAX44-LM2. /// /// The slice returned is guaranteed to be valid UTF-8 for all possible values /// of `slice`. /// /// See: http://unicode.org/reports/tr44/#UAX44-LM2 fn character_name_normalize_bytes(slice: &mut [u8]) -> &mut [u8] { // According to Unicode 4.8, character names consist only of Latin // capital letters A to Z, ASCII digits, ASCII space or ASCII hypen. // Therefore, we can do very simplistic case folding and operate on the // raw bytes, since everything is ASCII. Note that we don't actually know // whether `slice` is all ASCII or not, so we drop all non-ASCII bytes. let mut next_write = 0; let mut prev_letter = false; // let mut prev_space = true; for i in 0..slice.len() { // SAFETY ARGUMENT: To guarantee that the resulting slice is valid // UTF-8, we ensure that the slice contains only ASCII bytes. In // particular, we drop every non-ASCII byte from the normalized string. let b = slice[i]; if b == b' ' { // Drop spaces. } else if b == b'_' { // Drop the underscore. } else if b == b'-' { let medial = prev_letter && slice.get(i+1).map_or(false, |b| b.is_ascii_alphabetic()); let mut keep_hyphen = !medial; // We want to keep the hypen only if it isn't medial. However, // there is one exception. We need to keep the hypen in the // character (U+1180) named `HANGUL JUNGSEONG O-E`. So we check for // that here. let next_e = slice .get(i+1) .map_or(false, |&b| b == b'E' || b == b'e'); // More characters after the final E are fine, as long as they are // underscores and spaces. let rest_empty = i+2 >= slice.len() || slice[i+2..].iter().all(|&b| b == b' ' || b == b'_'); if !keep_hyphen && next_e && rest_empty { keep_hyphen = slice[..next_write] == b"hanguljungseongo"[..]; } if keep_hyphen { slice[next_write] = b; next_write += 1; } } else if b'A' <= b && b <= b'Z' { slice[next_write] = b + (b'a' - b'A'); next_write += 1; } else if b <= 0x7F { slice[next_write] = b; next_write += 1; } // prev_space = false; prev_letter = b.is_ascii_alphabetic(); } &mut slice[..next_write] } /// Normalize the given symbolic name in place according to UAX44-LM3. /// /// A "symbolic name" typically corresponds to property names and property /// value aliases. Note, though, that it should not be applied to property /// string values. /// /// See: http://unicode.org/reports/tr44/#UAX44-LM2 pub fn symbolic_name_normalize(string: &mut String) { let bytes = unsafe { // SAFETY: `symbolic_name_normalize_bytes` guarantees that // `bytes[..len]` is valid UTF-8. string.as_mut_vec() }; let len = symbolic_name_normalize_bytes(bytes).len(); bytes.truncate(len); } /// Normalize the given symbolic name in place according to UAX44-LM3. /// /// A "symbolic name" typically corresponds to property names and property /// value aliases. Note, though, that it should not be applied to property /// string values. /// /// The slice returned is guaranteed to be valid UTF-8 for all possible values /// of `slice`. /// /// See: http://unicode.org/reports/tr44/#UAX44-LM3 fn symbolic_name_normalize_bytes(slice: &mut [u8]) -> &mut [u8] { // I couldn't find a place in the standard that specified that property // names/aliases had a particular structure (unlike character names), but // we assume that it's ASCII only and drop anything that isn't ASCII. let mut start = 0; let mut starts_with_is = false; if slice.len() >= 2 { // Ignore any "is" prefix. starts_with_is = slice[0..2] == b"is"[..] || slice[0..2] == b"IS"[..] || slice[0..2] == b"iS"[..] || slice[0..2] == b"Is"[..]; if starts_with_is { start = 2; } } let mut next_write = 0; for i in start..slice.len() { // SAFETY ARGUMENT: To guarantee that the resulting slice is valid // UTF-8, we ensure that the slice contains only ASCII bytes. In // particular, we drop every non-ASCII byte from the normalized string. let b = slice[i]; if b == b' ' || b == b'_' || b == b'-' { continue; } else if b'A' <= b && b <= b'Z' { slice[next_write] = b + (b'a' - b'A'); next_write += 1; } else if b <= 0x7F { slice[next_write] = b; next_write += 1; } } // Special case: ISO_Comment has a 'isc' abbreviation. Since we generally // ignore 'is' prefixes, the 'isc' abbreviation gets caught in the cross // fire and ends up creating an alias for 'c' to 'ISO_Comment', but it // is actually an alias for the 'Other' general category. if starts_with_is && next_write == 1 && slice[0] == b'c' { slice[0] = b'i'; slice[1] = b's'; slice[2] = b'c'; next_write = 3; } &mut slice[..next_write] } #[cfg(test)] mod tests { use super::{ character_name_normalize, character_name_normalize_bytes, symbolic_name_normalize, symbolic_name_normalize_bytes, }; fn char_norm(s: &str) -> String { let mut s = s.to_string(); character_name_normalize(&mut s); s } fn sym_norm(s: &str) -> String { let mut s = s.to_string(); symbolic_name_normalize(&mut s); s } #[test] fn char_normalize() { assert_eq!(char_norm("HANGUL JUNGSEONG O-E"), "hanguljungseongo-e"); assert_eq!(char_norm("HANGUL JUNGSEONG O-E _"), "hanguljungseongo-e"); assert_eq!(char_norm("zero-width space"), "zerowidthspace"); assert_eq!(char_norm("zerowidthspace"), "zerowidthspace"); assert_eq!(char_norm("ZERO WIDTH SPACE"), "zerowidthspace"); assert_eq!(char_norm("TIBETAN MARK TSA -PHRU"), "tibetanmarktsa-phru"); assert_eq!(char_norm("tibetan_letter_-a"), "tibetanletter-a"); } #[test] fn sym_normalize() { assert_eq!(sym_norm("Line_Break"), "linebreak"); assert_eq!(sym_norm("Line-break"), "linebreak"); assert_eq!(sym_norm("linebreak"), "linebreak"); assert_eq!(sym_norm("BA"), "ba"); assert_eq!(sym_norm("ba"), "ba"); assert_eq!(sym_norm("Greek"), "greek"); assert_eq!(sym_norm("isGreek"), "greek"); assert_eq!(sym_norm("IS_Greek"), "greek"); assert_eq!(sym_norm("isc"), "isc"); assert_eq!(sym_norm("is c"), "isc"); assert_eq!(sym_norm("is_c"), "isc"); } #[test] fn valid_utf8_character() { let mut x = b"abc\xFFxyz".to_vec(); let y = character_name_normalize_bytes(&mut x); assert_eq!(y, b"abcxyz"); } #[test] fn valid_utf8_symbolic() { let mut x = b"abc\xFFxyz".to_vec(); let y = symbolic_name_normalize_bytes(&mut x); assert_eq!(y, b"abcxyz"); } } ucd-util-0.1.5/src/property.rs010066400017500000144000000111171324737477700145310ustar0000000000000000/// The type of a property name table. /// /// A property name table is a sequence of sorted tuples, where the first /// value in each tuple is a normalized property name and the second value of /// each tuple is the corresponding canonical property name. pub type PropertyTable = &'static [(&'static str, &'static str)]; /// Find the canonical property name for the given normalized property name. /// /// If no such property exists, then `None` is returned. /// /// The normalized property name must have been normalized according to /// UAX44 LM3, which can be done using `symbolic_name_normalize`. pub fn canonical_property_name( property_table: PropertyTable, normalized_property_name: &str, ) -> Option<&'static str> { property_table .binary_search_by_key(&normalized_property_name, |&(n, _)| n) .ok() .map(|i| property_table[i].1) } /// Type of a property value table. /// /// A property value table maps property names to a mapping of property values, /// where the mapping of property values is represented by a sequence of /// tuples. The first element of each tuple is a normalized property value /// while the second element of each tuple is the corresponding canonical /// property value. /// /// Note that a property value table only includes values for properties that /// are catalogs, enumerations or binary properties. Properties that have /// string values (such as case or decomposition mappings), numeric values /// or are miscellaneous are not represented in this table. pub type PropertyValueTable = &'static [(&'static str, PropertyValues)]; /// A mapping of property values for a specific property. /// /// The first element of each tuple is a normalized property value while the /// second element of each tuple is the corresponding canonical property /// value. pub type PropertyValues = &'static [(&'static str, &'static str)]; /// Find the set of possible property values for a given property. /// /// The set returned is a mapping expressed as a sorted list of tuples. /// The first element of each tuple is a normalized property value while the /// second element of each tuple is the corresponding canonical property /// value. /// /// If no such property exists, then `None` is returned. /// /// The given property name must be in its canonical form, which can be /// found using `canonical_property_name`. pub fn property_values( property_value_table: PropertyValueTable, canonical_property_name: &str, ) -> Option { property_value_table .binary_search_by_key(&canonical_property_name, |&(n, _)| n) .ok() .map(|i| property_value_table[i].1) } /// Find the canonical property value for the given normalized property /// value. /// /// The given property values should correspond to the values for the property /// under question, which can be found using `property_values`. /// /// If no such property value exists, then `None` is returned. /// /// The normalized property value must have been normalized according to /// UAX44 LM3, which can be done using `symbolic_name_normalize`. pub fn canonical_property_value( property_values: PropertyValues, normalized_property_value: &str, ) -> Option<&'static str> { // This is cute. The types line up, so why not? canonical_property_name(property_values, normalized_property_value) } #[cfg(test)] mod tests { use unicode_tables::property_names::PROPERTY_NAMES; use unicode_tables::property_values::PROPERTY_VALUES; use super::{ canonical_property_name, property_values, canonical_property_value, }; #[test] fn canonical_property_name_1() { assert_eq!( canonical_property_name(PROPERTY_NAMES, "gc"), Some("General_Category")); assert_eq!( canonical_property_name(PROPERTY_NAMES, "generalcategory"), Some("General_Category")); assert_eq!( canonical_property_name(PROPERTY_NAMES, "g c"), None); } #[test] fn property_values_1() { assert_eq!( property_values(PROPERTY_VALUES, "White_Space"), Some(&[ ("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ][..])); } #[test] fn canonical_property_value_1() { let values = property_values(PROPERTY_VALUES, "White_Space").unwrap(); assert_eq!(canonical_property_value(values, "false"), Some("No")); assert_eq!(canonical_property_value(values, "t"), Some("Yes")); assert_eq!(canonical_property_value(values, "F"), None); } } ucd-util-0.1.5/src/unicode_tables/jamo_short_name.rs010064400017500000144000000022301351474453500207520ustar0000000000000000// DO NOT EDIT THIS FILE. IT WAS AUTOMATICALLY GENERATED BY: // // ucd-generate jamo-short-name /home/andrew/tmp/ucd/12.1.0/ // // ucd-generate is available on crates.io. pub const JAMO_SHORT_NAME: &'static [(u32, &'static str)] = &[ (4352, "G"), (4353, "GG"), (4354, "N"), (4355, "D"), (4356, "DD"), (4357, "R"), (4358, "M"), (4359, "B"), (4360, "BB"), (4361, "S"), (4362, "SS"), (4363, ""), (4364, "J"), (4365, "JJ"), (4366, "C"), (4367, "K"), (4368, "T"), (4369, "P"), (4370, "H"), (4449, "A"), (4450, "AE"), (4451, "YA"), (4452, "YAE"), (4453, "EO"), (4454, "E"), (4455, "YEO"), (4456, "YE"), (4457, "O"), (4458, "WA"), (4459, "WAE"), (4460, "OE"), (4461, "YO"), (4462, "U"), (4463, "WEO"), (4464, "WE"), (4465, "WI"), (4466, "YU"), (4467, "EU"), (4468, "YI"), (4469, "I"), (4520, "G"), (4521, "GG"), (4522, "GS"), (4523, "N"), (4524, "NJ"), (4525, "NH"), (4526, "D"), (4527, "L"), (4528, "LG"), (4529, "LM"), (4530, "LB"), (4531, "LS"), (4532, "LT"), (4533, "LP"), (4534, "LH"), (4535, "M"), (4536, "B"), (4537, "BS"), (4538, "S"), (4539, "SS"), (4540, "NG"), (4541, "J"), (4542, "C"), (4543, "K"), (4544, "T"), (4545, "P"), (4546, "H"), ]; ucd-util-0.1.5/src/unicode_tables/mod.rs010066400017500000144000000001441322427740100163570ustar0000000000000000pub mod jamo_short_name; #[cfg(test)] pub mod property_names; #[cfg(test)] pub mod property_values; ucd-util-0.1.5/src/unicode_tables/property_names.rs010064400017500000144000000217451351474453500206700ustar0000000000000000// DO NOT EDIT THIS FILE. IT WAS AUTOMATICALLY GENERATED BY: // // ucd-generate property-names /home/andrew/tmp/ucd/12.1.0/ // // ucd-generate is available on crates.io. pub const PROPERTY_NAMES: &'static [(&'static str, &'static str)] = &[ ("age", "Age"), ("ahex", "ASCII_Hex_Digit"), ("alpha", "Alphabetic"), ("alphabetic", "Alphabetic"), ("asciihexdigit", "ASCII_Hex_Digit"), ("bc", "Bidi_Class"), ("bidic", "Bidi_Control"), ("bidiclass", "Bidi_Class"), ("bidicontrol", "Bidi_Control"), ("bidim", "Bidi_Mirrored"), ("bidimirrored", "Bidi_Mirrored"), ("bidimirroringglyph", "Bidi_Mirroring_Glyph"), ("bidipairedbracket", "Bidi_Paired_Bracket"), ("bidipairedbrackettype", "Bidi_Paired_Bracket_Type"), ("blk", "Block"), ("block", "Block"), ("bmg", "Bidi_Mirroring_Glyph"), ("bpb", "Bidi_Paired_Bracket"), ("bpt", "Bidi_Paired_Bracket_Type"), ("canonicalcombiningclass", "Canonical_Combining_Class"), ("cased", "Cased"), ("casefolding", "Case_Folding"), ("caseignorable", "Case_Ignorable"), ("ccc", "Canonical_Combining_Class"), ("ce", "Composition_Exclusion"), ("cf", "Case_Folding"), ("changeswhencasefolded", "Changes_When_Casefolded"), ("changeswhencasemapped", "Changes_When_Casemapped"), ("changeswhenlowercased", "Changes_When_Lowercased"), ("changeswhennfkccasefolded", "Changes_When_NFKC_Casefolded"), ("changeswhentitlecased", "Changes_When_Titlecased"), ("changeswhenuppercased", "Changes_When_Uppercased"), ("ci", "Case_Ignorable"), ("cjkaccountingnumeric", "kAccountingNumeric"), ("cjkcompatibilityvariant", "kCompatibilityVariant"), ("cjkiicore", "kIICore"), ("cjkirggsource", "kIRG_GSource"), ("cjkirghsource", "kIRG_HSource"), ("cjkirgjsource", "kIRG_JSource"), ("cjkirgkpsource", "kIRG_KPSource"), ("cjkirgksource", "kIRG_KSource"), ("cjkirgmsource", "kIRG_MSource"), ("cjkirgtsource", "kIRG_TSource"), ("cjkirgusource", "kIRG_USource"), ("cjkirgvsource", "kIRG_VSource"), ("cjkothernumeric", "kOtherNumeric"), ("cjkprimarynumeric", "kPrimaryNumeric"), ("cjkrsunicode", "kRSUnicode"), ("compex", "Full_Composition_Exclusion"), ("compositionexclusion", "Composition_Exclusion"), ("cwcf", "Changes_When_Casefolded"), ("cwcm", "Changes_When_Casemapped"), ("cwkcf", "Changes_When_NFKC_Casefolded"), ("cwl", "Changes_When_Lowercased"), ("cwt", "Changes_When_Titlecased"), ("cwu", "Changes_When_Uppercased"), ("dash", "Dash"), ("decompositionmapping", "Decomposition_Mapping"), ("decompositiontype", "Decomposition_Type"), ("defaultignorablecodepoint", "Default_Ignorable_Code_Point"), ("dep", "Deprecated"), ("deprecated", "Deprecated"), ("di", "Default_Ignorable_Code_Point"), ("dia", "Diacritic"), ("diacritic", "Diacritic"), ("dm", "Decomposition_Mapping"), ("dt", "Decomposition_Type"), ("ea", "East_Asian_Width"), ("eastasianwidth", "East_Asian_Width"), ("emoji", "Emoji"), ("emojicomponent", "Emoji_Component"), ("emojimodifier", "Emoji_Modifier"), ("emojimodifierbase", "Emoji_Modifier_Base"), ("emojipresentation", "Emoji_Presentation"), ("equideo", "Equivalent_Unified_Ideograph"), ("equivalentunifiedideograph", "Equivalent_Unified_Ideograph"), ("expandsonnfc", "Expands_On_NFC"), ("expandsonnfd", "Expands_On_NFD"), ("expandsonnfkc", "Expands_On_NFKC"), ("expandsonnfkd", "Expands_On_NFKD"), ("ext", "Extender"), ("extendedpictographic", "Extended_Pictographic"), ("extender", "Extender"), ("fcnfkc", "FC_NFKC_Closure"), ("fcnfkcclosure", "FC_NFKC_Closure"), ("fullcompositionexclusion", "Full_Composition_Exclusion"), ("gc", "General_Category"), ("gcb", "Grapheme_Cluster_Break"), ("generalcategory", "General_Category"), ("graphemebase", "Grapheme_Base"), ("graphemeclusterbreak", "Grapheme_Cluster_Break"), ("graphemeextend", "Grapheme_Extend"), ("graphemelink", "Grapheme_Link"), ("grbase", "Grapheme_Base"), ("grext", "Grapheme_Extend"), ("grlink", "Grapheme_Link"), ("hangulsyllabletype", "Hangul_Syllable_Type"), ("hex", "Hex_Digit"), ("hexdigit", "Hex_Digit"), ("hst", "Hangul_Syllable_Type"), ("hyphen", "Hyphen"), ("idc", "ID_Continue"), ("idcontinue", "ID_Continue"), ("ideo", "Ideographic"), ("ideographic", "Ideographic"), ("ids", "ID_Start"), ("idsb", "IDS_Binary_Operator"), ("idsbinaryoperator", "IDS_Binary_Operator"), ("idst", "IDS_Trinary_Operator"), ("idstart", "ID_Start"), ("idstrinaryoperator", "IDS_Trinary_Operator"), ("indicpositionalcategory", "Indic_Positional_Category"), ("indicsyllabiccategory", "Indic_Syllabic_Category"), ("inpc", "Indic_Positional_Category"), ("insc", "Indic_Syllabic_Category"), ("isc", "ISO_Comment"), ("jamoshortname", "Jamo_Short_Name"), ("jg", "Joining_Group"), ("joinc", "Join_Control"), ("joincontrol", "Join_Control"), ("joininggroup", "Joining_Group"), ("joiningtype", "Joining_Type"), ("jsn", "Jamo_Short_Name"), ("jt", "Joining_Type"), ("kaccountingnumeric", "kAccountingNumeric"), ("kcompatibilityvariant", "kCompatibilityVariant"), ("kiicore", "kIICore"), ("kirggsource", "kIRG_GSource"), ("kirghsource", "kIRG_HSource"), ("kirgjsource", "kIRG_JSource"), ("kirgkpsource", "kIRG_KPSource"), ("kirgksource", "kIRG_KSource"), ("kirgmsource", "kIRG_MSource"), ("kirgtsource", "kIRG_TSource"), ("kirgusource", "kIRG_USource"), ("kirgvsource", "kIRG_VSource"), ("kothernumeric", "kOtherNumeric"), ("kprimarynumeric", "kPrimaryNumeric"), ("krsunicode", "kRSUnicode"), ("lb", "Line_Break"), ("lc", "Lowercase_Mapping"), ("linebreak", "Line_Break"), ("loe", "Logical_Order_Exception"), ("logicalorderexception", "Logical_Order_Exception"), ("lower", "Lowercase"), ("lowercase", "Lowercase"), ("lowercasemapping", "Lowercase_Mapping"), ("math", "Math"), ("na", "Name"), ("na1", "Unicode_1_Name"), ("name", "Name"), ("namealias", "Name_Alias"), ("nchar", "Noncharacter_Code_Point"), ("nfcqc", "NFC_Quick_Check"), ("nfcquickcheck", "NFC_Quick_Check"), ("nfdqc", "NFD_Quick_Check"), ("nfdquickcheck", "NFD_Quick_Check"), ("nfkccasefold", "NFKC_Casefold"), ("nfkccf", "NFKC_Casefold"), ("nfkcqc", "NFKC_Quick_Check"), ("nfkcquickcheck", "NFKC_Quick_Check"), ("nfkdqc", "NFKD_Quick_Check"), ("nfkdquickcheck", "NFKD_Quick_Check"), ("noncharactercodepoint", "Noncharacter_Code_Point"), ("nt", "Numeric_Type"), ("numerictype", "Numeric_Type"), ("numericvalue", "Numeric_Value"), ("nv", "Numeric_Value"), ("oalpha", "Other_Alphabetic"), ("ocomment", "ISO_Comment"), ("odi", "Other_Default_Ignorable_Code_Point"), ("ogrext", "Other_Grapheme_Extend"), ("oidc", "Other_ID_Continue"), ("oids", "Other_ID_Start"), ("olower", "Other_Lowercase"), ("omath", "Other_Math"), ("otheralphabetic", "Other_Alphabetic"), ("otherdefaultignorablecodepoint", "Other_Default_Ignorable_Code_Point"), ("othergraphemeextend", "Other_Grapheme_Extend"), ("otheridcontinue", "Other_ID_Continue"), ("otheridstart", "Other_ID_Start"), ("otherlowercase", "Other_Lowercase"), ("othermath", "Other_Math"), ("otheruppercase", "Other_Uppercase"), ("oupper", "Other_Uppercase"), ("patsyn", "Pattern_Syntax"), ("patternsyntax", "Pattern_Syntax"), ("patternwhitespace", "Pattern_White_Space"), ("patws", "Pattern_White_Space"), ("pcm", "Prepended_Concatenation_Mark"), ("prependedconcatenationmark", "Prepended_Concatenation_Mark"), ("qmark", "Quotation_Mark"), ("quotationmark", "Quotation_Mark"), ("radical", "Radical"), ("regionalindicator", "Regional_Indicator"), ("ri", "Regional_Indicator"), ("sb", "Sentence_Break"), ("sc", "Script"), ("scf", "Simple_Case_Folding"), ("script", "Script"), ("scriptextensions", "Script_Extensions"), ("scx", "Script_Extensions"), ("sd", "Soft_Dotted"), ("sentencebreak", "Sentence_Break"), ("sentenceterminal", "Sentence_Terminal"), ("sfc", "Simple_Case_Folding"), ("simplecasefolding", "Simple_Case_Folding"), ("simplelowercasemapping", "Simple_Lowercase_Mapping"), ("simpletitlecasemapping", "Simple_Titlecase_Mapping"), ("simpleuppercasemapping", "Simple_Uppercase_Mapping"), ("slc", "Simple_Lowercase_Mapping"), ("softdotted", "Soft_Dotted"), ("space", "White_Space"), ("stc", "Simple_Titlecase_Mapping"), ("sterm", "Sentence_Terminal"), ("suc", "Simple_Uppercase_Mapping"), ("tc", "Titlecase_Mapping"), ("term", "Terminal_Punctuation"), ("terminalpunctuation", "Terminal_Punctuation"), ("titlecasemapping", "Titlecase_Mapping"), ("uc", "Uppercase_Mapping"), ("uideo", "Unified_Ideograph"), ("unicode1name", "Unicode_1_Name"), ("unicoderadicalstroke", "kRSUnicode"), ("unifiedideograph", "Unified_Ideograph"), ("upper", "Uppercase"), ("uppercase", "Uppercase"), ("uppercasemapping", "Uppercase_Mapping"), ("urs", "kRSUnicode"), ("variationselector", "Variation_Selector"), ("verticalorientation", "Vertical_Orientation"), ("vo", "Vertical_Orientation"), ("vs", "Variation_Selector"), ("wb", "Word_Break"), ("whitespace", "White_Space"), ("wordbreak", "Word_Break"), ("wspace", "White_Space"), ("xidc", "XID_Continue"), ("xidcontinue", "XID_Continue"), ("xids", "XID_Start"), ("xidstart", "XID_Start"), ("xonfc", "Expands_On_NFC"), ("xonfd", "Expands_On_NFD"), ("xonfkc", "Expands_On_NFKC"), ("xonfkd", "Expands_On_NFKD"), ]; ucd-util-0.1.5/src/unicode_tables/property_values.rs010064400017500000144000001761431351474453500210670ustar0000000000000000// DO NOT EDIT THIS FILE. IT WAS AUTOMATICALLY GENERATED BY: // // ucd-generate property-values /home/andrew/tmp/ucd/12.1.0/ // // ucd-generate is available on crates.io. pub const PROPERTY_VALUES: &'static [(&'static str, &'static [(&'static str, &'static str)])] = &[ ("ASCII_Hex_Digit", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Age", &[("1.1", "V1_1"), ("10.0", "V10_0"), ("11.0", "V11_0"), ("12.0", "V12_0"), ("12.1", "V12_1"), ("2.0", "V2_0"), ("2.1", "V2_1"), ("3.0", "V3_0"), ("3.1", "V3_1"), ("3.2", "V3_2"), ("4.0", "V4_0"), ("4.1", "V4_1"), ("5.0", "V5_0"), ("5.1", "V5_1"), ("5.2", "V5_2"), ("6.0", "V6_0"), ("6.1", "V6_1"), ("6.2", "V6_2"), ("6.3", "V6_3"), ("7.0", "V7_0"), ("8.0", "V8_0"), ("9.0", "V9_0"), ("na", "Unassigned"), ("unassigned", "Unassigned"), ("v100", "V10_0"), ("v11", "V1_1"), ("v110", "V11_0"), ("v120", "V12_0"), ("v121", "V12_1"), ("v20", "V2_0"), ("v21", "V2_1"), ("v30", "V3_0"), ("v31", "V3_1"), ("v32", "V3_2"), ("v40", "V4_0"), ("v41", "V4_1"), ("v50", "V5_0"), ("v51", "V5_1"), ("v52", "V5_2"), ("v60", "V6_0"), ("v61", "V6_1"), ("v62", "V6_2"), ("v63", "V6_3"), ("v70", "V7_0"), ("v80", "V8_0"), ("v90", "V9_0"), ]), ("Alphabetic", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Bidi_Class", &[("al", "Arabic_Letter"), ("an", "Arabic_Number"), ("arabicletter", "Arabic_Letter"), ("arabicnumber", "Arabic_Number"), ("b", "Paragraph_Separator"), ("bn", "Boundary_Neutral"), ("boundaryneutral", "Boundary_Neutral"), ("commonseparator", "Common_Separator"), ("cs", "Common_Separator"), ("en", "European_Number"), ("es", "European_Separator"), ("et", "European_Terminator"), ("europeannumber", "European_Number"), ("europeanseparator", "European_Separator"), ("europeanterminator", "European_Terminator"), ("firststrongisolate", "First_Strong_Isolate"), ("fsi", "First_Strong_Isolate"), ("l", "Left_To_Right"), ("lefttoright", "Left_To_Right"), ("lefttorightembedding", "Left_To_Right_Embedding"), ("lefttorightisolate", "Left_To_Right_Isolate"), ("lefttorightoverride", "Left_To_Right_Override"), ("lre", "Left_To_Right_Embedding"), ("lri", "Left_To_Right_Isolate"), ("lro", "Left_To_Right_Override"), ("nonspacingmark", "Nonspacing_Mark"), ("nsm", "Nonspacing_Mark"), ("on", "Other_Neutral"), ("otherneutral", "Other_Neutral"), ("paragraphseparator", "Paragraph_Separator"), ("pdf", "Pop_Directional_Format"), ("pdi", "Pop_Directional_Isolate"), ("popdirectionalformat", "Pop_Directional_Format"), ("popdirectionalisolate", "Pop_Directional_Isolate"), ("r", "Right_To_Left"), ("righttoleft", "Right_To_Left"), ("righttoleftembedding", "Right_To_Left_Embedding"), ("righttoleftisolate", "Right_To_Left_Isolate"), ("righttoleftoverride", "Right_To_Left_Override"), ("rle", "Right_To_Left_Embedding"), ("rli", "Right_To_Left_Isolate"), ("rlo", "Right_To_Left_Override"), ("s", "Segment_Separator"), ("segmentseparator", "Segment_Separator"), ("whitespace", "White_Space"), ("ws", "White_Space"), ]), ("Bidi_Control", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Bidi_Mirrored", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Bidi_Paired_Bracket_Type", &[("c", "Close"), ("close", "Close"), ("n", "None"), ("none", "None"), ("o", "Open"), ("open", "Open"), ]), ("Block", &[("adlam", "Adlam"), ("aegeannumbers", "Aegean_Numbers"), ("ahom", "Ahom"), ("alchemical", "Alchemical_Symbols"), ("alchemicalsymbols", "Alchemical_Symbols"), ("alphabeticpf", "Alphabetic_Presentation_Forms"), ("alphabeticpresentationforms", "Alphabetic_Presentation_Forms"), ("anatolianhieroglyphs", "Anatolian_Hieroglyphs"), ("ancientgreekmusic", "Ancient_Greek_Musical_Notation"), ("ancientgreekmusicalnotation", "Ancient_Greek_Musical_Notation"), ("ancientgreeknumbers", "Ancient_Greek_Numbers"), ("ancientsymbols", "Ancient_Symbols"), ("arabic", "Arabic"), ("arabicexta", "Arabic_Extended_A"), ("arabicextendeda", "Arabic_Extended_A"), ("arabicmath", "Arabic_Mathematical_Alphabetic_Symbols"), ("arabicmathematicalalphabeticsymbols", "Arabic_Mathematical_Alphabetic_Symbols"), ("arabicpfa", "Arabic_Presentation_Forms_A"), ("arabicpfb", "Arabic_Presentation_Forms_B"), ("arabicpresentationformsa", "Arabic_Presentation_Forms_A"), ("arabicpresentationformsb", "Arabic_Presentation_Forms_B"), ("arabicsup", "Arabic_Supplement"), ("arabicsupplement", "Arabic_Supplement"), ("armenian", "Armenian"), ("arrows", "Arrows"), ("ascii", "Basic_Latin"), ("avestan", "Avestan"), ("balinese", "Balinese"), ("bamum", "Bamum"), ("bamumsup", "Bamum_Supplement"), ("bamumsupplement", "Bamum_Supplement"), ("basiclatin", "Basic_Latin"), ("bassavah", "Bassa_Vah"), ("batak", "Batak"), ("bengali", "Bengali"), ("bhaiksuki", "Bhaiksuki"), ("blockelements", "Block_Elements"), ("bopomofo", "Bopomofo"), ("bopomofoext", "Bopomofo_Extended"), ("bopomofoextended", "Bopomofo_Extended"), ("boxdrawing", "Box_Drawing"), ("brahmi", "Brahmi"), ("braille", "Braille_Patterns"), ("braillepatterns", "Braille_Patterns"), ("buginese", "Buginese"), ("buhid", "Buhid"), ("byzantinemusic", "Byzantine_Musical_Symbols"), ("byzantinemusicalsymbols", "Byzantine_Musical_Symbols"), ("canadiansyllabics", "Unified_Canadian_Aboriginal_Syllabics"), ("carian", "Carian"), ("caucasianalbanian", "Caucasian_Albanian"), ("chakma", "Chakma"), ("cham", "Cham"), ("cherokee", "Cherokee"), ("cherokeesup", "Cherokee_Supplement"), ("cherokeesupplement", "Cherokee_Supplement"), ("chesssymbols", "Chess_Symbols"), ("cjk", "CJK_Unified_Ideographs"), ("cjkcompat", "CJK_Compatibility"), ("cjkcompatforms", "CJK_Compatibility_Forms"), ("cjkcompatibility", "CJK_Compatibility"), ("cjkcompatibilityforms", "CJK_Compatibility_Forms"), ("cjkcompatibilityideographs", "CJK_Compatibility_Ideographs"), ("cjkcompatibilityideographssupplement", "CJK_Compatibility_Ideographs_Supplement"), ("cjkcompatideographs", "CJK_Compatibility_Ideographs"), ("cjkcompatideographssup", "CJK_Compatibility_Ideographs_Supplement"), ("cjkexta", "CJK_Unified_Ideographs_Extension_A"), ("cjkextb", "CJK_Unified_Ideographs_Extension_B"), ("cjkextc", "CJK_Unified_Ideographs_Extension_C"), ("cjkextd", "CJK_Unified_Ideographs_Extension_D"), ("cjkexte", "CJK_Unified_Ideographs_Extension_E"), ("cjkextf", "CJK_Unified_Ideographs_Extension_F"), ("cjkradicalssup", "CJK_Radicals_Supplement"), ("cjkradicalssupplement", "CJK_Radicals_Supplement"), ("cjkstrokes", "CJK_Strokes"), ("cjksymbols", "CJK_Symbols_And_Punctuation"), ("cjksymbolsandpunctuation", "CJK_Symbols_And_Punctuation"), ("cjkunifiedideographs", "CJK_Unified_Ideographs"), ("cjkunifiedideographsextensiona", "CJK_Unified_Ideographs_Extension_A"), ("cjkunifiedideographsextensionb", "CJK_Unified_Ideographs_Extension_B"), ("cjkunifiedideographsextensionc", "CJK_Unified_Ideographs_Extension_C"), ("cjkunifiedideographsextensiond", "CJK_Unified_Ideographs_Extension_D"), ("cjkunifiedideographsextensione", "CJK_Unified_Ideographs_Extension_E"), ("cjkunifiedideographsextensionf", "CJK_Unified_Ideographs_Extension_F"), ("combiningdiacriticalmarks", "Combining_Diacritical_Marks"), ("combiningdiacriticalmarksextended", "Combining_Diacritical_Marks_Extended"), ("combiningdiacriticalmarksforsymbols", "Combining_Diacritical_Marks_For_Symbols"), ("combiningdiacriticalmarkssupplement", "Combining_Diacritical_Marks_Supplement"), ("combininghalfmarks", "Combining_Half_Marks"), ("combiningmarksforsymbols", "Combining_Diacritical_Marks_For_Symbols"), ("commonindicnumberforms", "Common_Indic_Number_Forms"), ("compatjamo", "Hangul_Compatibility_Jamo"), ("controlpictures", "Control_Pictures"), ("coptic", "Coptic"), ("copticepactnumbers", "Coptic_Epact_Numbers"), ("countingrod", "Counting_Rod_Numerals"), ("countingrodnumerals", "Counting_Rod_Numerals"), ("cuneiform", "Cuneiform"), ("cuneiformnumbers", "Cuneiform_Numbers_And_Punctuation"), ("cuneiformnumbersandpunctuation", "Cuneiform_Numbers_And_Punctuation"), ("currencysymbols", "Currency_Symbols"), ("cypriotsyllabary", "Cypriot_Syllabary"), ("cyrillic", "Cyrillic"), ("cyrillicexta", "Cyrillic_Extended_A"), ("cyrillicextb", "Cyrillic_Extended_B"), ("cyrillicextc", "Cyrillic_Extended_C"), ("cyrillicextendeda", "Cyrillic_Extended_A"), ("cyrillicextendedb", "Cyrillic_Extended_B"), ("cyrillicextendedc", "Cyrillic_Extended_C"), ("cyrillicsup", "Cyrillic_Supplement"), ("cyrillicsupplement", "Cyrillic_Supplement"), ("cyrillicsupplementary", "Cyrillic_Supplement"), ("deseret", "Deseret"), ("devanagari", "Devanagari"), ("devanagariext", "Devanagari_Extended"), ("devanagariextended", "Devanagari_Extended"), ("diacriticals", "Combining_Diacritical_Marks"), ("diacriticalsext", "Combining_Diacritical_Marks_Extended"), ("diacriticalsforsymbols", "Combining_Diacritical_Marks_For_Symbols"), ("diacriticalssup", "Combining_Diacritical_Marks_Supplement"), ("dingbats", "Dingbats"), ("dogra", "Dogra"), ("domino", "Domino_Tiles"), ("dominotiles", "Domino_Tiles"), ("duployan", "Duployan"), ("earlydynasticcuneiform", "Early_Dynastic_Cuneiform"), ("egyptianhieroglyphformatcontrols", "Egyptian_Hieroglyph_Format_Controls"), ("egyptianhieroglyphs", "Egyptian_Hieroglyphs"), ("elbasan", "Elbasan"), ("elymaic", "Elymaic"), ("emoticons", "Emoticons"), ("enclosedalphanum", "Enclosed_Alphanumerics"), ("enclosedalphanumerics", "Enclosed_Alphanumerics"), ("enclosedalphanumericsupplement", "Enclosed_Alphanumeric_Supplement"), ("enclosedalphanumsup", "Enclosed_Alphanumeric_Supplement"), ("enclosedcjk", "Enclosed_CJK_Letters_And_Months"), ("enclosedcjklettersandmonths", "Enclosed_CJK_Letters_And_Months"), ("enclosedideographicsup", "Enclosed_Ideographic_Supplement"), ("enclosedideographicsupplement", "Enclosed_Ideographic_Supplement"), ("ethiopic", "Ethiopic"), ("ethiopicext", "Ethiopic_Extended"), ("ethiopicexta", "Ethiopic_Extended_A"), ("ethiopicextended", "Ethiopic_Extended"), ("ethiopicextendeda", "Ethiopic_Extended_A"), ("ethiopicsup", "Ethiopic_Supplement"), ("ethiopicsupplement", "Ethiopic_Supplement"), ("generalpunctuation", "General_Punctuation"), ("geometricshapes", "Geometric_Shapes"), ("geometricshapesext", "Geometric_Shapes_Extended"), ("geometricshapesextended", "Geometric_Shapes_Extended"), ("georgian", "Georgian"), ("georgianext", "Georgian_Extended"), ("georgianextended", "Georgian_Extended"), ("georgiansup", "Georgian_Supplement"), ("georgiansupplement", "Georgian_Supplement"), ("glagolitic", "Glagolitic"), ("glagoliticsup", "Glagolitic_Supplement"), ("glagoliticsupplement", "Glagolitic_Supplement"), ("gothic", "Gothic"), ("grantha", "Grantha"), ("greek", "Greek_And_Coptic"), ("greekandcoptic", "Greek_And_Coptic"), ("greekext", "Greek_Extended"), ("greekextended", "Greek_Extended"), ("gujarati", "Gujarati"), ("gunjalagondi", "Gunjala_Gondi"), ("gurmukhi", "Gurmukhi"), ("halfandfullforms", "Halfwidth_And_Fullwidth_Forms"), ("halfmarks", "Combining_Half_Marks"), ("halfwidthandfullwidthforms", "Halfwidth_And_Fullwidth_Forms"), ("hangul", "Hangul_Syllables"), ("hangulcompatibilityjamo", "Hangul_Compatibility_Jamo"), ("hanguljamo", "Hangul_Jamo"), ("hanguljamoextendeda", "Hangul_Jamo_Extended_A"), ("hanguljamoextendedb", "Hangul_Jamo_Extended_B"), ("hangulsyllables", "Hangul_Syllables"), ("hanifirohingya", "Hanifi_Rohingya"), ("hanunoo", "Hanunoo"), ("hatran", "Hatran"), ("hebrew", "Hebrew"), ("highprivateusesurrogates", "High_Private_Use_Surrogates"), ("highpusurrogates", "High_Private_Use_Surrogates"), ("highsurrogates", "High_Surrogates"), ("hiragana", "Hiragana"), ("idc", "Ideographic_Description_Characters"), ("ideographicdescriptioncharacters", "Ideographic_Description_Characters"), ("ideographicsymbols", "Ideographic_Symbols_And_Punctuation"), ("ideographicsymbolsandpunctuation", "Ideographic_Symbols_And_Punctuation"), ("imperialaramaic", "Imperial_Aramaic"), ("indicnumberforms", "Common_Indic_Number_Forms"), ("indicsiyaqnumbers", "Indic_Siyaq_Numbers"), ("inscriptionalpahlavi", "Inscriptional_Pahlavi"), ("inscriptionalparthian", "Inscriptional_Parthian"), ("ipaext", "IPA_Extensions"), ("ipaextensions", "IPA_Extensions"), ("jamo", "Hangul_Jamo"), ("jamoexta", "Hangul_Jamo_Extended_A"), ("jamoextb", "Hangul_Jamo_Extended_B"), ("javanese", "Javanese"), ("kaithi", "Kaithi"), ("kanaexta", "Kana_Extended_A"), ("kanaextendeda", "Kana_Extended_A"), ("kanasup", "Kana_Supplement"), ("kanasupplement", "Kana_Supplement"), ("kanbun", "Kanbun"), ("kangxi", "Kangxi_Radicals"), ("kangxiradicals", "Kangxi_Radicals"), ("kannada", "Kannada"), ("katakana", "Katakana"), ("katakanaext", "Katakana_Phonetic_Extensions"), ("katakanaphoneticextensions", "Katakana_Phonetic_Extensions"), ("kayahli", "Kayah_Li"), ("kharoshthi", "Kharoshthi"), ("khmer", "Khmer"), ("khmersymbols", "Khmer_Symbols"), ("khojki", "Khojki"), ("khudawadi", "Khudawadi"), ("lao", "Lao"), ("latin1", "Latin_1_Supplement"), ("latin1sup", "Latin_1_Supplement"), ("latin1supplement", "Latin_1_Supplement"), ("latinexta", "Latin_Extended_A"), ("latinextadditional", "Latin_Extended_Additional"), ("latinextb", "Latin_Extended_B"), ("latinextc", "Latin_Extended_C"), ("latinextd", "Latin_Extended_D"), ("latinexte", "Latin_Extended_E"), ("latinextendeda", "Latin_Extended_A"), ("latinextendedadditional", "Latin_Extended_Additional"), ("latinextendedb", "Latin_Extended_B"), ("latinextendedc", "Latin_Extended_C"), ("latinextendedd", "Latin_Extended_D"), ("latinextendede", "Latin_Extended_E"), ("lepcha", "Lepcha"), ("letterlikesymbols", "Letterlike_Symbols"), ("limbu", "Limbu"), ("lineara", "Linear_A"), ("linearbideograms", "Linear_B_Ideograms"), ("linearbsyllabary", "Linear_B_Syllabary"), ("lisu", "Lisu"), ("lowsurrogates", "Low_Surrogates"), ("lycian", "Lycian"), ("lydian", "Lydian"), ("mahajani", "Mahajani"), ("mahjong", "Mahjong_Tiles"), ("mahjongtiles", "Mahjong_Tiles"), ("makasar", "Makasar"), ("malayalam", "Malayalam"), ("mandaic", "Mandaic"), ("manichaean", "Manichaean"), ("marchen", "Marchen"), ("masaramgondi", "Masaram_Gondi"), ("mathalphanum", "Mathematical_Alphanumeric_Symbols"), ("mathematicalalphanumericsymbols", "Mathematical_Alphanumeric_Symbols"), ("mathematicaloperators", "Mathematical_Operators"), ("mathoperators", "Mathematical_Operators"), ("mayannumerals", "Mayan_Numerals"), ("medefaidrin", "Medefaidrin"), ("meeteimayek", "Meetei_Mayek"), ("meeteimayekext", "Meetei_Mayek_Extensions"), ("meeteimayekextensions", "Meetei_Mayek_Extensions"), ("mendekikakui", "Mende_Kikakui"), ("meroiticcursive", "Meroitic_Cursive"), ("meroitichieroglyphs", "Meroitic_Hieroglyphs"), ("miao", "Miao"), ("miscarrows", "Miscellaneous_Symbols_And_Arrows"), ("miscellaneousmathematicalsymbolsa", "Miscellaneous_Mathematical_Symbols_A"), ("miscellaneousmathematicalsymbolsb", "Miscellaneous_Mathematical_Symbols_B"), ("miscellaneoussymbols", "Miscellaneous_Symbols"), ("miscellaneoussymbolsandarrows", "Miscellaneous_Symbols_And_Arrows"), ("miscellaneoussymbolsandpictographs", "Miscellaneous_Symbols_And_Pictographs"), ("miscellaneoustechnical", "Miscellaneous_Technical"), ("miscmathsymbolsa", "Miscellaneous_Mathematical_Symbols_A"), ("miscmathsymbolsb", "Miscellaneous_Mathematical_Symbols_B"), ("miscpictographs", "Miscellaneous_Symbols_And_Pictographs"), ("miscsymbols", "Miscellaneous_Symbols"), ("misctechnical", "Miscellaneous_Technical"), ("modi", "Modi"), ("modifierletters", "Spacing_Modifier_Letters"), ("modifiertoneletters", "Modifier_Tone_Letters"), ("mongolian", "Mongolian"), ("mongoliansup", "Mongolian_Supplement"), ("mongoliansupplement", "Mongolian_Supplement"), ("mro", "Mro"), ("multani", "Multani"), ("music", "Musical_Symbols"), ("musicalsymbols", "Musical_Symbols"), ("myanmar", "Myanmar"), ("myanmarexta", "Myanmar_Extended_A"), ("myanmarextb", "Myanmar_Extended_B"), ("myanmarextendeda", "Myanmar_Extended_A"), ("myanmarextendedb", "Myanmar_Extended_B"), ("nabataean", "Nabataean"), ("nandinagari", "Nandinagari"), ("nb", "No_Block"), ("newa", "Newa"), ("newtailue", "New_Tai_Lue"), ("nko", "NKo"), ("noblock", "No_Block"), ("numberforms", "Number_Forms"), ("nushu", "Nushu"), ("nyiakengpuachuehmong", "Nyiakeng_Puachue_Hmong"), ("ocr", "Optical_Character_Recognition"), ("ogham", "Ogham"), ("olchiki", "Ol_Chiki"), ("oldhungarian", "Old_Hungarian"), ("olditalic", "Old_Italic"), ("oldnortharabian", "Old_North_Arabian"), ("oldpermic", "Old_Permic"), ("oldpersian", "Old_Persian"), ("oldsogdian", "Old_Sogdian"), ("oldsoutharabian", "Old_South_Arabian"), ("oldturkic", "Old_Turkic"), ("opticalcharacterrecognition", "Optical_Character_Recognition"), ("oriya", "Oriya"), ("ornamentaldingbats", "Ornamental_Dingbats"), ("osage", "Osage"), ("osmanya", "Osmanya"), ("ottomansiyaqnumbers", "Ottoman_Siyaq_Numbers"), ("pahawhhmong", "Pahawh_Hmong"), ("palmyrene", "Palmyrene"), ("paucinhau", "Pau_Cin_Hau"), ("phagspa", "Phags_Pa"), ("phaistos", "Phaistos_Disc"), ("phaistosdisc", "Phaistos_Disc"), ("phoenician", "Phoenician"), ("phoneticext", "Phonetic_Extensions"), ("phoneticextensions", "Phonetic_Extensions"), ("phoneticextensionssupplement", "Phonetic_Extensions_Supplement"), ("phoneticextsup", "Phonetic_Extensions_Supplement"), ("playingcards", "Playing_Cards"), ("privateuse", "Private_Use_Area"), ("privateusearea", "Private_Use_Area"), ("psalterpahlavi", "Psalter_Pahlavi"), ("pua", "Private_Use_Area"), ("punctuation", "General_Punctuation"), ("rejang", "Rejang"), ("rumi", "Rumi_Numeral_Symbols"), ("ruminumeralsymbols", "Rumi_Numeral_Symbols"), ("runic", "Runic"), ("samaritan", "Samaritan"), ("saurashtra", "Saurashtra"), ("sharada", "Sharada"), ("shavian", "Shavian"), ("shorthandformatcontrols", "Shorthand_Format_Controls"), ("siddham", "Siddham"), ("sinhala", "Sinhala"), ("sinhalaarchaicnumbers", "Sinhala_Archaic_Numbers"), ("smallforms", "Small_Form_Variants"), ("smallformvariants", "Small_Form_Variants"), ("smallkanaext", "Small_Kana_Extension"), ("smallkanaextension", "Small_Kana_Extension"), ("sogdian", "Sogdian"), ("sorasompeng", "Sora_Sompeng"), ("soyombo", "Soyombo"), ("spacingmodifierletters", "Spacing_Modifier_Letters"), ("specials", "Specials"), ("sundanese", "Sundanese"), ("sundanesesup", "Sundanese_Supplement"), ("sundanesesupplement", "Sundanese_Supplement"), ("suparrowsa", "Supplemental_Arrows_A"), ("suparrowsb", "Supplemental_Arrows_B"), ("suparrowsc", "Supplemental_Arrows_C"), ("superandsub", "Superscripts_And_Subscripts"), ("superscriptsandsubscripts", "Superscripts_And_Subscripts"), ("supmathoperators", "Supplemental_Mathematical_Operators"), ("supplementalarrowsa", "Supplemental_Arrows_A"), ("supplementalarrowsb", "Supplemental_Arrows_B"), ("supplementalarrowsc", "Supplemental_Arrows_C"), ("supplementalmathematicaloperators", "Supplemental_Mathematical_Operators"), ("supplementalpunctuation", "Supplemental_Punctuation"), ("supplementalsymbolsandpictographs", "Supplemental_Symbols_And_Pictographs"), ("supplementaryprivateuseareaa", "Supplementary_Private_Use_Area_A"), ("supplementaryprivateuseareab", "Supplementary_Private_Use_Area_B"), ("suppuaa", "Supplementary_Private_Use_Area_A"), ("suppuab", "Supplementary_Private_Use_Area_B"), ("suppunctuation", "Supplemental_Punctuation"), ("supsymbolsandpictographs", "Supplemental_Symbols_And_Pictographs"), ("suttonsignwriting", "Sutton_SignWriting"), ("sylotinagri", "Syloti_Nagri"), ("symbolsandpictographsexta", "Symbols_And_Pictographs_Extended_A"), ("symbolsandpictographsextendeda", "Symbols_And_Pictographs_Extended_A"), ("syriac", "Syriac"), ("syriacsup", "Syriac_Supplement"), ("syriacsupplement", "Syriac_Supplement"), ("tagalog", "Tagalog"), ("tagbanwa", "Tagbanwa"), ("tags", "Tags"), ("taile", "Tai_Le"), ("taitham", "Tai_Tham"), ("taiviet", "Tai_Viet"), ("taixuanjing", "Tai_Xuan_Jing_Symbols"), ("taixuanjingsymbols", "Tai_Xuan_Jing_Symbols"), ("takri", "Takri"), ("tamil", "Tamil"), ("tamilsup", "Tamil_Supplement"), ("tamilsupplement", "Tamil_Supplement"), ("tangut", "Tangut"), ("tangutcomponents", "Tangut_Components"), ("telugu", "Telugu"), ("thaana", "Thaana"), ("thai", "Thai"), ("tibetan", "Tibetan"), ("tifinagh", "Tifinagh"), ("tirhuta", "Tirhuta"), ("transportandmap", "Transport_And_Map_Symbols"), ("transportandmapsymbols", "Transport_And_Map_Symbols"), ("ucas", "Unified_Canadian_Aboriginal_Syllabics"), ("ucasext", "Unified_Canadian_Aboriginal_Syllabics_Extended"), ("ugaritic", "Ugaritic"), ("unifiedcanadianaboriginalsyllabics", "Unified_Canadian_Aboriginal_Syllabics"), ("unifiedcanadianaboriginalsyllabicsextended", "Unified_Canadian_Aboriginal_Syllabics_Extended"), ("vai", "Vai"), ("variationselectors", "Variation_Selectors"), ("variationselectorssupplement", "Variation_Selectors_Supplement"), ("vedicext", "Vedic_Extensions"), ("vedicextensions", "Vedic_Extensions"), ("verticalforms", "Vertical_Forms"), ("vs", "Variation_Selectors"), ("vssup", "Variation_Selectors_Supplement"), ("wancho", "Wancho"), ("warangciti", "Warang_Citi"), ("yijing", "Yijing_Hexagram_Symbols"), ("yijinghexagramsymbols", "Yijing_Hexagram_Symbols"), ("yiradicals", "Yi_Radicals"), ("yisyllables", "Yi_Syllables"), ("zanabazarsquare", "Zanabazar_Square"), ]), ("Canonical_Combining_Class", &[("", "Iota_Subscript"), ("0", "Not_Reordered"), ("1", "Overlay"), ("10", "CCC10"), ("103", "CCC103"), ("107", "CCC107"), ("11", "CCC11"), ("118", "CCC118"), ("12", "CCC12"), ("122", "CCC122"), ("129", "CCC129"), ("13", "CCC13"), ("130", "CCC130"), ("132", "CCC132"), ("133", "CCC133"), ("14", "CCC14"), ("15", "CCC15"), ("16", "CCC16"), ("17", "CCC17"), ("18", "CCC18"), ("19", "CCC19"), ("20", "CCC20"), ("200", "Attached_Below_Left"), ("202", "Attached_Below"), ("21", "CCC21"), ("214", "Attached_Above"), ("216", "Attached_Above_Right"), ("218", "Below_Left"), ("22", "CCC22"), ("220", "Below"), ("222", "Below_Right"), ("224", "Left"), ("226", "Right"), ("228", "Above_Left"), ("23", "CCC23"), ("230", "Above"), ("232", "Above_Right"), ("233", "Double_Below"), ("234", "Double_Above"), ("24", "CCC24"), ("240", "Iota_Subscript"), ("25", "CCC25"), ("26", "CCC26"), ("27", "CCC27"), ("28", "CCC28"), ("29", "CCC29"), ("30", "CCC30"), ("31", "CCC31"), ("32", "CCC32"), ("33", "CCC33"), ("34", "CCC34"), ("35", "CCC35"), ("36", "CCC36"), ("7", "Nukta"), ("8", "Kana_Voicing"), ("84", "CCC84"), ("9", "Virama"), ("91", "CCC91"), ("a", "Above"), ("above", "Above"), ("aboveleft", "Above_Left"), ("aboveright", "Above_Right"), ("al", "Above_Left"), ("ar", "Above_Right"), ("ata", "Attached_Above"), ("atar", "Attached_Above_Right"), ("atb", "Attached_Below"), ("atbl", "Attached_Below_Left"), ("attachedabove", "Attached_Above"), ("attachedaboveright", "Attached_Above_Right"), ("attachedbelow", "Attached_Below"), ("attachedbelowleft", "Attached_Below_Left"), ("b", "Below"), ("below", "Below"), ("belowleft", "Below_Left"), ("belowright", "Below_Right"), ("bl", "Below_Left"), ("br", "Below_Right"), ("ccc10", "CCC10"), ("ccc103", "CCC103"), ("ccc107", "CCC107"), ("ccc11", "CCC11"), ("ccc118", "CCC118"), ("ccc12", "CCC12"), ("ccc122", "CCC122"), ("ccc129", "CCC129"), ("ccc13", "CCC13"), ("ccc130", "CCC130"), ("ccc132", "CCC132"), ("ccc133", "CCC133"), ("ccc14", "CCC14"), ("ccc15", "CCC15"), ("ccc16", "CCC16"), ("ccc17", "CCC17"), ("ccc18", "CCC18"), ("ccc19", "CCC19"), ("ccc20", "CCC20"), ("ccc21", "CCC21"), ("ccc22", "CCC22"), ("ccc23", "CCC23"), ("ccc24", "CCC24"), ("ccc25", "CCC25"), ("ccc26", "CCC26"), ("ccc27", "CCC27"), ("ccc28", "CCC28"), ("ccc29", "CCC29"), ("ccc30", "CCC30"), ("ccc31", "CCC31"), ("ccc32", "CCC32"), ("ccc33", "CCC33"), ("ccc34", "CCC34"), ("ccc35", "CCC35"), ("ccc36", "CCC36"), ("ccc84", "CCC84"), ("ccc91", "CCC91"), ("da", "Double_Above"), ("db", "Double_Below"), ("doubleabove", "Double_Above"), ("doublebelow", "Double_Below"), ("iotasubscript", "Iota_Subscript"), ("kanavoicing", "Kana_Voicing"), ("kv", "Kana_Voicing"), ("l", "Left"), ("left", "Left"), ("nk", "Nukta"), ("notreordered", "Not_Reordered"), ("nr", "Not_Reordered"), ("nukta", "Nukta"), ("ov", "Overlay"), ("overlay", "Overlay"), ("r", "Right"), ("right", "Right"), ("virama", "Virama"), ("vr", "Virama"), ]), ("Case_Ignorable", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Cased", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Changes_When_Casefolded", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Changes_When_Casemapped", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Changes_When_Lowercased", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Changes_When_NFKC_Casefolded", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Changes_When_Titlecased", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Changes_When_Uppercased", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Composition_Exclusion", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Dash", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Decomposition_Type", &[("can", "Canonical"), ("canonical", "Canonical"), ("circle", "Circle"), ("com", "Compat"), ("compat", "Compat"), ("enc", "Circle"), ("fin", "Final"), ("final", "Final"), ("font", "Font"), ("fra", "Fraction"), ("fraction", "Fraction"), ("init", "Initial"), ("initial", "Initial"), ("med", "Medial"), ("medial", "Medial"), ("nar", "Narrow"), ("narrow", "Narrow"), ("nb", "Nobreak"), ("nobreak", "Nobreak"), ("none", "None"), ("o", "Isolated"), ("olated", "Isolated"), ("small", "Small"), ("sml", "Small"), ("sqr", "Square"), ("square", "Square"), ("sub", "Sub"), ("sup", "Super"), ("super", "Super"), ("vert", "Vertical"), ("vertical", "Vertical"), ("wide", "Wide"), ]), ("Default_Ignorable_Code_Point", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Deprecated", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Diacritic", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("East_Asian_Width", &[("a", "Ambiguous"), ("ambiguous", "Ambiguous"), ("f", "Fullwidth"), ("fullwidth", "Fullwidth"), ("h", "Halfwidth"), ("halfwidth", "Halfwidth"), ("n", "Neutral"), ("na", "Narrow"), ("narrow", "Narrow"), ("neutral", "Neutral"), ("w", "Wide"), ("wide", "Wide"), ]), ("Expands_On_NFC", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Expands_On_NFD", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Expands_On_NFKC", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Expands_On_NFKD", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Extender", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Full_Composition_Exclusion", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("General_Category", &[("c", "Other"), ("casedletter", "Cased_Letter"), ("cc", "Control"), ("cf", "Format"), ("closepunctuation", "Close_Punctuation"), ("cn", "Unassigned"), ("cntrl", "Control"), ("co", "Private_Use"), ("combiningmark", "Mark"), ("connectorpunctuation", "Connector_Punctuation"), ("control", "Control"), ("cs", "Surrogate"), ("currencysymbol", "Currency_Symbol"), ("dashpunctuation", "Dash_Punctuation"), ("decimalnumber", "Decimal_Number"), ("digit", "Decimal_Number"), ("enclosingmark", "Enclosing_Mark"), ("finalpunctuation", "Final_Punctuation"), ("format", "Format"), ("initialpunctuation", "Initial_Punctuation"), ("l", "Letter"), ("lc", "Cased_Letter"), ("letter", "Letter"), ("letternumber", "Letter_Number"), ("lineseparator", "Line_Separator"), ("ll", "Lowercase_Letter"), ("lm", "Modifier_Letter"), ("lo", "Other_Letter"), ("lowercaseletter", "Lowercase_Letter"), ("lt", "Titlecase_Letter"), ("lu", "Uppercase_Letter"), ("m", "Mark"), ("mark", "Mark"), ("mathsymbol", "Math_Symbol"), ("mc", "Spacing_Mark"), ("me", "Enclosing_Mark"), ("mn", "Nonspacing_Mark"), ("modifierletter", "Modifier_Letter"), ("modifiersymbol", "Modifier_Symbol"), ("n", "Number"), ("nd", "Decimal_Number"), ("nl", "Letter_Number"), ("no", "Other_Number"), ("nonspacingmark", "Nonspacing_Mark"), ("number", "Number"), ("openpunctuation", "Open_Punctuation"), ("other", "Other"), ("otherletter", "Other_Letter"), ("othernumber", "Other_Number"), ("otherpunctuation", "Other_Punctuation"), ("othersymbol", "Other_Symbol"), ("p", "Punctuation"), ("paragraphseparator", "Paragraph_Separator"), ("pc", "Connector_Punctuation"), ("pd", "Dash_Punctuation"), ("pe", "Close_Punctuation"), ("pf", "Final_Punctuation"), ("pi", "Initial_Punctuation"), ("po", "Other_Punctuation"), ("privateuse", "Private_Use"), ("ps", "Open_Punctuation"), ("punct", "Punctuation"), ("punctuation", "Punctuation"), ("s", "Symbol"), ("sc", "Currency_Symbol"), ("separator", "Separator"), ("sk", "Modifier_Symbol"), ("sm", "Math_Symbol"), ("so", "Other_Symbol"), ("spaceseparator", "Space_Separator"), ("spacingmark", "Spacing_Mark"), ("surrogate", "Surrogate"), ("symbol", "Symbol"), ("titlecaseletter", "Titlecase_Letter"), ("unassigned", "Unassigned"), ("uppercaseletter", "Uppercase_Letter"), ("z", "Separator"), ("zl", "Line_Separator"), ("zp", "Paragraph_Separator"), ("zs", "Space_Separator"), ]), ("Grapheme_Base", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Grapheme_Cluster_Break", &[("cn", "Control"), ("control", "Control"), ("cr", "CR"), ("eb", "E_Base"), ("ebase", "E_Base"), ("ebasegaz", "E_Base_GAZ"), ("ebg", "E_Base_GAZ"), ("em", "E_Modifier"), ("emodifier", "E_Modifier"), ("ex", "Extend"), ("extend", "Extend"), ("gaz", "Glue_After_Zwj"), ("glueafterzwj", "Glue_After_Zwj"), ("l", "L"), ("lf", "LF"), ("lv", "LV"), ("lvt", "LVT"), ("other", "Other"), ("pp", "Prepend"), ("prepend", "Prepend"), ("regionalindicator", "Regional_Indicator"), ("ri", "Regional_Indicator"), ("sm", "SpacingMark"), ("spacingmark", "SpacingMark"), ("t", "T"), ("v", "V"), ("xx", "Other"), ("zwj", "ZWJ"), ]), ("Grapheme_Extend", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Grapheme_Link", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Hangul_Syllable_Type", &[("l", "Leading_Jamo"), ("leadingjamo", "Leading_Jamo"), ("lv", "LV_Syllable"), ("lvsyllable", "LV_Syllable"), ("lvt", "LVT_Syllable"), ("lvtsyllable", "LVT_Syllable"), ("na", "Not_Applicable"), ("notapplicable", "Not_Applicable"), ("t", "Trailing_Jamo"), ("trailingjamo", "Trailing_Jamo"), ("v", "Vowel_Jamo"), ("voweljamo", "Vowel_Jamo"), ]), ("Hex_Digit", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Hyphen", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("IDS_Binary_Operator", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("IDS_Trinary_Operator", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("ID_Continue", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("ID_Start", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Ideographic", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Indic_Positional_Category", &[("bottom", "Bottom"), ("bottomandleft", "Bottom_And_Left"), ("bottomandright", "Bottom_And_Right"), ("left", "Left"), ("leftandright", "Left_And_Right"), ("na", "NA"), ("overstruck", "Overstruck"), ("right", "Right"), ("top", "Top"), ("topandbottom", "Top_And_Bottom"), ("topandbottomandright", "Top_And_Bottom_And_Right"), ("topandleft", "Top_And_Left"), ("topandleftandright", "Top_And_Left_And_Right"), ("topandright", "Top_And_Right"), ("visualorderleft", "Visual_Order_Left"), ]), ("Indic_Syllabic_Category", &[("avagraha", "Avagraha"), ("bindu", "Bindu"), ("brahmijoiningnumber", "Brahmi_Joining_Number"), ("cantillationmark", "Cantillation_Mark"), ("consonant", "Consonant"), ("consonantdead", "Consonant_Dead"), ("consonantfinal", "Consonant_Final"), ("consonantheadletter", "Consonant_Head_Letter"), ("consonantinitialpostfixed", "Consonant_Initial_Postfixed"), ("consonantkiller", "Consonant_Killer"), ("consonantmedial", "Consonant_Medial"), ("consonantplaceholder", "Consonant_Placeholder"), ("consonantprecedingrepha", "Consonant_Preceding_Repha"), ("consonantprefixed", "Consonant_Prefixed"), ("consonantsubjoined", "Consonant_Subjoined"), ("consonantsucceedingrepha", "Consonant_Succeeding_Repha"), ("consonantwithstacker", "Consonant_With_Stacker"), ("geminationmark", "Gemination_Mark"), ("invisiblestacker", "Invisible_Stacker"), ("joiner", "Joiner"), ("modifyingletter", "Modifying_Letter"), ("nonjoiner", "Non_Joiner"), ("nukta", "Nukta"), ("number", "Number"), ("numberjoiner", "Number_Joiner"), ("other", "Other"), ("purekiller", "Pure_Killer"), ("registershifter", "Register_Shifter"), ("syllablemodifier", "Syllable_Modifier"), ("toneletter", "Tone_Letter"), ("tonemark", "Tone_Mark"), ("virama", "Virama"), ("visarga", "Visarga"), ("vowel", "Vowel"), ("voweldependent", "Vowel_Dependent"), ("vowelindependent", "Vowel_Independent"), ]), ("Jamo_Short_Name", &[("a", "A"), ("ae", "AE"), ("b", "B"), ("bb", "BB"), ("bs", "BS"), ("c", "C"), ("d", "D"), ("dd", "DD"), ("e", "E"), ("eo", "EO"), ("eu", "EU"), ("g", "G"), ("gg", "GG"), ("gs", "GS"), ("h", "H"), ("i", "I"), ("j", "J"), ("jj", "JJ"), ("k", "K"), ("l", "L"), ("lb", "LB"), ("lg", "LG"), ("lh", "LH"), ("lm", "LM"), ("lp", "LP"), ("ls", "LS"), ("lt", "LT"), ("m", "M"), ("n", "N"), ("ng", "NG"), ("nh", "NH"), ("nj", "NJ"), ("o", "O"), ("oe", "OE"), ("p", "P"), ("r", "R"), ("s", "S"), ("ss", "SS"), ("t", "T"), ("u", "U"), ("wa", "WA"), ("wae", "WAE"), ("we", "WE"), ("weo", "WEO"), ("wi", "WI"), ("ya", "YA"), ("yae", "YAE"), ("ye", "YE"), ("yeo", "YEO"), ("yi", "YI"), ("yo", "YO"), ("yu", "YU"), ]), ("Join_Control", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Joining_Group", &[("africanfeh", "African_Feh"), ("africannoon", "African_Noon"), ("africanqaf", "African_Qaf"), ("ain", "Ain"), ("alaph", "Alaph"), ("alef", "Alef"), ("beh", "Beh"), ("beth", "Beth"), ("burushaskiyehbarree", "Burushaski_Yeh_Barree"), ("dal", "Dal"), ("dalathrish", "Dalath_Rish"), ("e", "E"), ("farsiyeh", "Farsi_Yeh"), ("fe", "Fe"), ("feh", "Feh"), ("finalsemkath", "Final_Semkath"), ("gaf", "Gaf"), ("gamal", "Gamal"), ("hah", "Hah"), ("hamzaonhehgoal", "Hamza_On_Heh_Goal"), ("hanifirohingyakinnaya", "Hanifi_Rohingya_Kinna_Ya"), ("hanifirohingyapa", "Hanifi_Rohingya_Pa"), ("he", "He"), ("heh", "Heh"), ("hehgoal", "Heh_Goal"), ("heth", "Heth"), ("kaf", "Kaf"), ("kaph", "Kaph"), ("khaph", "Khaph"), ("knottedheh", "Knotted_Heh"), ("lam", "Lam"), ("lamadh", "Lamadh"), ("malayalambha", "Malayalam_Bha"), ("malayalamja", "Malayalam_Ja"), ("malayalamlla", "Malayalam_Lla"), ("malayalamllla", "Malayalam_Llla"), ("malayalamnga", "Malayalam_Nga"), ("malayalamnna", "Malayalam_Nna"), ("malayalamnnna", "Malayalam_Nnna"), ("malayalamnya", "Malayalam_Nya"), ("malayalamra", "Malayalam_Ra"), ("malayalamssa", "Malayalam_Ssa"), ("malayalamtta", "Malayalam_Tta"), ("manichaeanaleph", "Manichaean_Aleph"), ("manichaeanayin", "Manichaean_Ayin"), ("manichaeanbeth", "Manichaean_Beth"), ("manichaeandaleth", "Manichaean_Daleth"), ("manichaeandhamedh", "Manichaean_Dhamedh"), ("manichaeanfive", "Manichaean_Five"), ("manichaeangimel", "Manichaean_Gimel"), ("manichaeanheth", "Manichaean_Heth"), ("manichaeanhundred", "Manichaean_Hundred"), ("manichaeankaph", "Manichaean_Kaph"), ("manichaeanlamedh", "Manichaean_Lamedh"), ("manichaeanmem", "Manichaean_Mem"), ("manichaeannun", "Manichaean_Nun"), ("manichaeanone", "Manichaean_One"), ("manichaeanpe", "Manichaean_Pe"), ("manichaeanqoph", "Manichaean_Qoph"), ("manichaeanresh", "Manichaean_Resh"), ("manichaeansadhe", "Manichaean_Sadhe"), ("manichaeansamekh", "Manichaean_Samekh"), ("manichaeantaw", "Manichaean_Taw"), ("manichaeanten", "Manichaean_Ten"), ("manichaeanteth", "Manichaean_Teth"), ("manichaeanthamedh", "Manichaean_Thamedh"), ("manichaeantwenty", "Manichaean_Twenty"), ("manichaeanwaw", "Manichaean_Waw"), ("manichaeanyodh", "Manichaean_Yodh"), ("manichaeanzayin", "Manichaean_Zayin"), ("meem", "Meem"), ("mim", "Mim"), ("nojoininggroup", "No_Joining_Group"), ("noon", "Noon"), ("nun", "Nun"), ("nya", "Nya"), ("pe", "Pe"), ("qaf", "Qaf"), ("qaph", "Qaph"), ("reh", "Reh"), ("reversedpe", "Reversed_Pe"), ("rohingyayeh", "Rohingya_Yeh"), ("sad", "Sad"), ("sadhe", "Sadhe"), ("seen", "Seen"), ("semkath", "Semkath"), ("shin", "Shin"), ("straightwaw", "Straight_Waw"), ("swashkaf", "Swash_Kaf"), ("syriacwaw", "Syriac_Waw"), ("tah", "Tah"), ("taw", "Taw"), ("tehmarbuta", "Teh_Marbuta"), ("tehmarbutagoal", "Hamza_On_Heh_Goal"), ("teth", "Teth"), ("waw", "Waw"), ("yeh", "Yeh"), ("yehbarree", "Yeh_Barree"), ("yehwithtail", "Yeh_With_Tail"), ("yudh", "Yudh"), ("yudhhe", "Yudh_He"), ("zain", "Zain"), ("zhain", "Zhain"), ]), ("Joining_Type", &[("c", "Join_Causing"), ("d", "Dual_Joining"), ("dualjoining", "Dual_Joining"), ("joincausing", "Join_Causing"), ("l", "Left_Joining"), ("leftjoining", "Left_Joining"), ("nonjoining", "Non_Joining"), ("r", "Right_Joining"), ("rightjoining", "Right_Joining"), ("t", "Transparent"), ("transparent", "Transparent"), ("u", "Non_Joining"), ]), ("Line_Break", &[("", "Infix_Numeric"), ("ai", "Ambiguous"), ("al", "Alphabetic"), ("alphabetic", "Alphabetic"), ("ambiguous", "Ambiguous"), ("b2", "Break_Both"), ("ba", "Break_After"), ("bb", "Break_Before"), ("bk", "Mandatory_Break"), ("breakafter", "Break_After"), ("breakbefore", "Break_Before"), ("breakboth", "Break_Both"), ("breaksymbols", "Break_Symbols"), ("carriagereturn", "Carriage_Return"), ("cb", "Contingent_Break"), ("cj", "Conditional_Japanese_Starter"), ("cl", "Close_Punctuation"), ("closeparenthesis", "Close_Parenthesis"), ("closepunctuation", "Close_Punctuation"), ("cm", "Combining_Mark"), ("combiningmark", "Combining_Mark"), ("complexcontext", "Complex_Context"), ("conditionaljapanesestarter", "Conditional_Japanese_Starter"), ("contingentbreak", "Contingent_Break"), ("cp", "Close_Parenthesis"), ("cr", "Carriage_Return"), ("eb", "E_Base"), ("ebase", "E_Base"), ("em", "E_Modifier"), ("emodifier", "E_Modifier"), ("ex", "Exclamation"), ("exclamation", "Exclamation"), ("gl", "Glue"), ("glue", "Glue"), ("h2", "H2"), ("h3", "H3"), ("hebrewletter", "Hebrew_Letter"), ("hl", "Hebrew_Letter"), ("hy", "Hyphen"), ("hyphen", "Hyphen"), ("id", "Ideographic"), ("ideographic", "Ideographic"), ("in", "Inseparable"), ("infixnumeric", "Infix_Numeric"), ("inseparable", "Inseparable"), ("inseperable", "Inseparable"), ("jl", "JL"), ("jt", "JT"), ("jv", "JV"), ("lf", "Line_Feed"), ("linefeed", "Line_Feed"), ("mandatorybreak", "Mandatory_Break"), ("nextline", "Next_Line"), ("nl", "Next_Line"), ("nonstarter", "Nonstarter"), ("ns", "Nonstarter"), ("nu", "Numeric"), ("numeric", "Numeric"), ("op", "Open_Punctuation"), ("openpunctuation", "Open_Punctuation"), ("po", "Postfix_Numeric"), ("postfixnumeric", "Postfix_Numeric"), ("pr", "Prefix_Numeric"), ("prefixnumeric", "Prefix_Numeric"), ("qu", "Quotation"), ("quotation", "Quotation"), ("regionalindicator", "Regional_Indicator"), ("ri", "Regional_Indicator"), ("sa", "Complex_Context"), ("sg", "Surrogate"), ("sp", "Space"), ("space", "Space"), ("surrogate", "Surrogate"), ("sy", "Break_Symbols"), ("unknown", "Unknown"), ("wj", "Word_Joiner"), ("wordjoiner", "Word_Joiner"), ("xx", "Unknown"), ("zw", "ZWSpace"), ("zwj", "ZWJ"), ("zwspace", "ZWSpace"), ]), ("Logical_Order_Exception", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Lowercase", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Math", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("NFC_Quick_Check", &[("m", "Maybe"), ("maybe", "Maybe"), ("n", "No"), ("no", "No"), ("y", "Yes"), ("yes", "Yes"), ]), ("NFD_Quick_Check", &[("n", "No"), ("no", "No"), ("y", "Yes"), ("yes", "Yes"), ]), ("NFKC_Quick_Check", &[("m", "Maybe"), ("maybe", "Maybe"), ("n", "No"), ("no", "No"), ("y", "Yes"), ("yes", "Yes"), ]), ("NFKD_Quick_Check", &[("n", "No"), ("no", "No"), ("y", "Yes"), ("yes", "Yes"), ]), ("Noncharacter_Code_Point", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Numeric_Type", &[("de", "Decimal"), ("decimal", "Decimal"), ("di", "Digit"), ("digit", "Digit"), ("none", "None"), ("nu", "Numeric"), ("numeric", "Numeric"), ]), ("Other_Alphabetic", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Other_Default_Ignorable_Code_Point", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Other_Grapheme_Extend", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Other_ID_Continue", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Other_ID_Start", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Other_Lowercase", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Other_Math", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Other_Uppercase", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Pattern_Syntax", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Pattern_White_Space", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Prepended_Concatenation_Mark", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Quotation_Mark", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Radical", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Regional_Indicator", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Script", &[("adlam", "Adlam"), ("adlm", "Adlam"), ("aghb", "Caucasian_Albanian"), ("ahom", "Ahom"), ("anatolianhieroglyphs", "Anatolian_Hieroglyphs"), ("arab", "Arabic"), ("arabic", "Arabic"), ("armenian", "Armenian"), ("armi", "Imperial_Aramaic"), ("armn", "Armenian"), ("avestan", "Avestan"), ("avst", "Avestan"), ("bali", "Balinese"), ("balinese", "Balinese"), ("bamu", "Bamum"), ("bamum", "Bamum"), ("bass", "Bassa_Vah"), ("bassavah", "Bassa_Vah"), ("batak", "Batak"), ("batk", "Batak"), ("beng", "Bengali"), ("bengali", "Bengali"), ("bhaiksuki", "Bhaiksuki"), ("bhks", "Bhaiksuki"), ("bopo", "Bopomofo"), ("bopomofo", "Bopomofo"), ("brah", "Brahmi"), ("brahmi", "Brahmi"), ("brai", "Braille"), ("braille", "Braille"), ("bugi", "Buginese"), ("buginese", "Buginese"), ("buhd", "Buhid"), ("buhid", "Buhid"), ("cakm", "Chakma"), ("canadianaboriginal", "Canadian_Aboriginal"), ("cans", "Canadian_Aboriginal"), ("cari", "Carian"), ("carian", "Carian"), ("caucasianalbanian", "Caucasian_Albanian"), ("chakma", "Chakma"), ("cham", "Cham"), ("cher", "Cherokee"), ("cherokee", "Cherokee"), ("common", "Common"), ("copt", "Coptic"), ("coptic", "Coptic"), ("cprt", "Cypriot"), ("cuneiform", "Cuneiform"), ("cypriot", "Cypriot"), ("cyrillic", "Cyrillic"), ("cyrl", "Cyrillic"), ("deseret", "Deseret"), ("deva", "Devanagari"), ("devanagari", "Devanagari"), ("dogr", "Dogra"), ("dogra", "Dogra"), ("dsrt", "Deseret"), ("dupl", "Duployan"), ("duployan", "Duployan"), ("egyp", "Egyptian_Hieroglyphs"), ("egyptianhieroglyphs", "Egyptian_Hieroglyphs"), ("elba", "Elbasan"), ("elbasan", "Elbasan"), ("elym", "Elymaic"), ("elymaic", "Elymaic"), ("ethi", "Ethiopic"), ("ethiopic", "Ethiopic"), ("geor", "Georgian"), ("georgian", "Georgian"), ("glag", "Glagolitic"), ("glagolitic", "Glagolitic"), ("gong", "Gunjala_Gondi"), ("gonm", "Masaram_Gondi"), ("goth", "Gothic"), ("gothic", "Gothic"), ("gran", "Grantha"), ("grantha", "Grantha"), ("greek", "Greek"), ("grek", "Greek"), ("gujarati", "Gujarati"), ("gujr", "Gujarati"), ("gunjalagondi", "Gunjala_Gondi"), ("gurmukhi", "Gurmukhi"), ("guru", "Gurmukhi"), ("han", "Han"), ("hang", "Hangul"), ("hangul", "Hangul"), ("hani", "Han"), ("hanifirohingya", "Hanifi_Rohingya"), ("hano", "Hanunoo"), ("hanunoo", "Hanunoo"), ("hatr", "Hatran"), ("hatran", "Hatran"), ("hebr", "Hebrew"), ("hebrew", "Hebrew"), ("hira", "Hiragana"), ("hiragana", "Hiragana"), ("hluw", "Anatolian_Hieroglyphs"), ("hmng", "Pahawh_Hmong"), ("hmnp", "Nyiakeng_Puachue_Hmong"), ("hrkt", "Katakana_Or_Hiragana"), ("hung", "Old_Hungarian"), ("imperialaramaic", "Imperial_Aramaic"), ("inherited", "Inherited"), ("inscriptionalpahlavi", "Inscriptional_Pahlavi"), ("inscriptionalparthian", "Inscriptional_Parthian"), ("ital", "Old_Italic"), ("java", "Javanese"), ("javanese", "Javanese"), ("kaithi", "Kaithi"), ("kali", "Kayah_Li"), ("kana", "Katakana"), ("kannada", "Kannada"), ("katakana", "Katakana"), ("katakanaorhiragana", "Katakana_Or_Hiragana"), ("kayahli", "Kayah_Li"), ("khar", "Kharoshthi"), ("kharoshthi", "Kharoshthi"), ("khmer", "Khmer"), ("khmr", "Khmer"), ("khoj", "Khojki"), ("khojki", "Khojki"), ("khudawadi", "Khudawadi"), ("knda", "Kannada"), ("kthi", "Kaithi"), ("lana", "Tai_Tham"), ("lao", "Lao"), ("laoo", "Lao"), ("latin", "Latin"), ("latn", "Latin"), ("lepc", "Lepcha"), ("lepcha", "Lepcha"), ("limb", "Limbu"), ("limbu", "Limbu"), ("lina", "Linear_A"), ("linb", "Linear_B"), ("lineara", "Linear_A"), ("linearb", "Linear_B"), ("lisu", "Lisu"), ("lyci", "Lycian"), ("lycian", "Lycian"), ("lydi", "Lydian"), ("lydian", "Lydian"), ("mahajani", "Mahajani"), ("mahj", "Mahajani"), ("maka", "Makasar"), ("makasar", "Makasar"), ("malayalam", "Malayalam"), ("mand", "Mandaic"), ("mandaic", "Mandaic"), ("mani", "Manichaean"), ("manichaean", "Manichaean"), ("marc", "Marchen"), ("marchen", "Marchen"), ("masaramgondi", "Masaram_Gondi"), ("medefaidrin", "Medefaidrin"), ("medf", "Medefaidrin"), ("meeteimayek", "Meetei_Mayek"), ("mend", "Mende_Kikakui"), ("mendekikakui", "Mende_Kikakui"), ("merc", "Meroitic_Cursive"), ("mero", "Meroitic_Hieroglyphs"), ("meroiticcursive", "Meroitic_Cursive"), ("meroitichieroglyphs", "Meroitic_Hieroglyphs"), ("miao", "Miao"), ("mlym", "Malayalam"), ("modi", "Modi"), ("mong", "Mongolian"), ("mongolian", "Mongolian"), ("mro", "Mro"), ("mroo", "Mro"), ("mtei", "Meetei_Mayek"), ("mult", "Multani"), ("multani", "Multani"), ("myanmar", "Myanmar"), ("mymr", "Myanmar"), ("nabataean", "Nabataean"), ("nand", "Nandinagari"), ("nandinagari", "Nandinagari"), ("narb", "Old_North_Arabian"), ("nbat", "Nabataean"), ("newa", "Newa"), ("newtailue", "New_Tai_Lue"), ("nko", "Nko"), ("nkoo", "Nko"), ("nshu", "Nushu"), ("nushu", "Nushu"), ("nyiakengpuachuehmong", "Nyiakeng_Puachue_Hmong"), ("ogam", "Ogham"), ("ogham", "Ogham"), ("olchiki", "Ol_Chiki"), ("olck", "Ol_Chiki"), ("oldhungarian", "Old_Hungarian"), ("olditalic", "Old_Italic"), ("oldnortharabian", "Old_North_Arabian"), ("oldpermic", "Old_Permic"), ("oldpersian", "Old_Persian"), ("oldsogdian", "Old_Sogdian"), ("oldsoutharabian", "Old_South_Arabian"), ("oldturkic", "Old_Turkic"), ("oriya", "Oriya"), ("orkh", "Old_Turkic"), ("orya", "Oriya"), ("osage", "Osage"), ("osge", "Osage"), ("osma", "Osmanya"), ("osmanya", "Osmanya"), ("pahawhhmong", "Pahawh_Hmong"), ("palm", "Palmyrene"), ("palmyrene", "Palmyrene"), ("pauc", "Pau_Cin_Hau"), ("paucinhau", "Pau_Cin_Hau"), ("perm", "Old_Permic"), ("phag", "Phags_Pa"), ("phagspa", "Phags_Pa"), ("phli", "Inscriptional_Pahlavi"), ("phlp", "Psalter_Pahlavi"), ("phnx", "Phoenician"), ("phoenician", "Phoenician"), ("plrd", "Miao"), ("prti", "Inscriptional_Parthian"), ("psalterpahlavi", "Psalter_Pahlavi"), ("qaac", "Coptic"), ("qaai", "Inherited"), ("rejang", "Rejang"), ("rjng", "Rejang"), ("rohg", "Hanifi_Rohingya"), ("runic", "Runic"), ("runr", "Runic"), ("samaritan", "Samaritan"), ("samr", "Samaritan"), ("sarb", "Old_South_Arabian"), ("saur", "Saurashtra"), ("saurashtra", "Saurashtra"), ("sgnw", "SignWriting"), ("sharada", "Sharada"), ("shavian", "Shavian"), ("shaw", "Shavian"), ("shrd", "Sharada"), ("sidd", "Siddham"), ("siddham", "Siddham"), ("signwriting", "SignWriting"), ("sind", "Khudawadi"), ("sinh", "Sinhala"), ("sinhala", "Sinhala"), ("sogd", "Sogdian"), ("sogdian", "Sogdian"), ("sogo", "Old_Sogdian"), ("sora", "Sora_Sompeng"), ("sorasompeng", "Sora_Sompeng"), ("soyo", "Soyombo"), ("soyombo", "Soyombo"), ("sund", "Sundanese"), ("sundanese", "Sundanese"), ("sylo", "Syloti_Nagri"), ("sylotinagri", "Syloti_Nagri"), ("syrc", "Syriac"), ("syriac", "Syriac"), ("tagalog", "Tagalog"), ("tagb", "Tagbanwa"), ("tagbanwa", "Tagbanwa"), ("taile", "Tai_Le"), ("taitham", "Tai_Tham"), ("taiviet", "Tai_Viet"), ("takr", "Takri"), ("takri", "Takri"), ("tale", "Tai_Le"), ("talu", "New_Tai_Lue"), ("tamil", "Tamil"), ("taml", "Tamil"), ("tang", "Tangut"), ("tangut", "Tangut"), ("tavt", "Tai_Viet"), ("telu", "Telugu"), ("telugu", "Telugu"), ("tfng", "Tifinagh"), ("tglg", "Tagalog"), ("thaa", "Thaana"), ("thaana", "Thaana"), ("thai", "Thai"), ("tibetan", "Tibetan"), ("tibt", "Tibetan"), ("tifinagh", "Tifinagh"), ("tirh", "Tirhuta"), ("tirhuta", "Tirhuta"), ("ugar", "Ugaritic"), ("ugaritic", "Ugaritic"), ("unknown", "Unknown"), ("vai", "Vai"), ("vaii", "Vai"), ("wancho", "Wancho"), ("wara", "Warang_Citi"), ("warangciti", "Warang_Citi"), ("wcho", "Wancho"), ("xpeo", "Old_Persian"), ("xsux", "Cuneiform"), ("yi", "Yi"), ("yiii", "Yi"), ("zanabazarsquare", "Zanabazar_Square"), ("zanb", "Zanabazar_Square"), ("zinh", "Inherited"), ("zyyy", "Common"), ("zzzz", "Unknown"), ]), ("Script_Extensions", &[("adlam", "Adlam"), ("adlm", "Adlam"), ("aghb", "Caucasian_Albanian"), ("ahom", "Ahom"), ("anatolianhieroglyphs", "Anatolian_Hieroglyphs"), ("arab", "Arabic"), ("arabic", "Arabic"), ("armenian", "Armenian"), ("armi", "Imperial_Aramaic"), ("armn", "Armenian"), ("avestan", "Avestan"), ("avst", "Avestan"), ("bali", "Balinese"), ("balinese", "Balinese"), ("bamu", "Bamum"), ("bamum", "Bamum"), ("bass", "Bassa_Vah"), ("bassavah", "Bassa_Vah"), ("batak", "Batak"), ("batk", "Batak"), ("beng", "Bengali"), ("bengali", "Bengali"), ("bhaiksuki", "Bhaiksuki"), ("bhks", "Bhaiksuki"), ("bopo", "Bopomofo"), ("bopomofo", "Bopomofo"), ("brah", "Brahmi"), ("brahmi", "Brahmi"), ("brai", "Braille"), ("braille", "Braille"), ("bugi", "Buginese"), ("buginese", "Buginese"), ("buhd", "Buhid"), ("buhid", "Buhid"), ("cakm", "Chakma"), ("canadianaboriginal", "Canadian_Aboriginal"), ("cans", "Canadian_Aboriginal"), ("cari", "Carian"), ("carian", "Carian"), ("caucasianalbanian", "Caucasian_Albanian"), ("chakma", "Chakma"), ("cham", "Cham"), ("cher", "Cherokee"), ("cherokee", "Cherokee"), ("common", "Common"), ("copt", "Coptic"), ("coptic", "Coptic"), ("cprt", "Cypriot"), ("cuneiform", "Cuneiform"), ("cypriot", "Cypriot"), ("cyrillic", "Cyrillic"), ("cyrl", "Cyrillic"), ("deseret", "Deseret"), ("deva", "Devanagari"), ("devanagari", "Devanagari"), ("dogr", "Dogra"), ("dogra", "Dogra"), ("dsrt", "Deseret"), ("dupl", "Duployan"), ("duployan", "Duployan"), ("egyp", "Egyptian_Hieroglyphs"), ("egyptianhieroglyphs", "Egyptian_Hieroglyphs"), ("elba", "Elbasan"), ("elbasan", "Elbasan"), ("elym", "Elymaic"), ("elymaic", "Elymaic"), ("ethi", "Ethiopic"), ("ethiopic", "Ethiopic"), ("geor", "Georgian"), ("georgian", "Georgian"), ("glag", "Glagolitic"), ("glagolitic", "Glagolitic"), ("gong", "Gunjala_Gondi"), ("gonm", "Masaram_Gondi"), ("goth", "Gothic"), ("gothic", "Gothic"), ("gran", "Grantha"), ("grantha", "Grantha"), ("greek", "Greek"), ("grek", "Greek"), ("gujarati", "Gujarati"), ("gujr", "Gujarati"), ("gunjalagondi", "Gunjala_Gondi"), ("gurmukhi", "Gurmukhi"), ("guru", "Gurmukhi"), ("han", "Han"), ("hang", "Hangul"), ("hangul", "Hangul"), ("hani", "Han"), ("hanifirohingya", "Hanifi_Rohingya"), ("hano", "Hanunoo"), ("hanunoo", "Hanunoo"), ("hatr", "Hatran"), ("hatran", "Hatran"), ("hebr", "Hebrew"), ("hebrew", "Hebrew"), ("hira", "Hiragana"), ("hiragana", "Hiragana"), ("hluw", "Anatolian_Hieroglyphs"), ("hmng", "Pahawh_Hmong"), ("hmnp", "Nyiakeng_Puachue_Hmong"), ("hrkt", "Katakana_Or_Hiragana"), ("hung", "Old_Hungarian"), ("imperialaramaic", "Imperial_Aramaic"), ("inherited", "Inherited"), ("inscriptionalpahlavi", "Inscriptional_Pahlavi"), ("inscriptionalparthian", "Inscriptional_Parthian"), ("ital", "Old_Italic"), ("java", "Javanese"), ("javanese", "Javanese"), ("kaithi", "Kaithi"), ("kali", "Kayah_Li"), ("kana", "Katakana"), ("kannada", "Kannada"), ("katakana", "Katakana"), ("katakanaorhiragana", "Katakana_Or_Hiragana"), ("kayahli", "Kayah_Li"), ("khar", "Kharoshthi"), ("kharoshthi", "Kharoshthi"), ("khmer", "Khmer"), ("khmr", "Khmer"), ("khoj", "Khojki"), ("khojki", "Khojki"), ("khudawadi", "Khudawadi"), ("knda", "Kannada"), ("kthi", "Kaithi"), ("lana", "Tai_Tham"), ("lao", "Lao"), ("laoo", "Lao"), ("latin", "Latin"), ("latn", "Latin"), ("lepc", "Lepcha"), ("lepcha", "Lepcha"), ("limb", "Limbu"), ("limbu", "Limbu"), ("lina", "Linear_A"), ("linb", "Linear_B"), ("lineara", "Linear_A"), ("linearb", "Linear_B"), ("lisu", "Lisu"), ("lyci", "Lycian"), ("lycian", "Lycian"), ("lydi", "Lydian"), ("lydian", "Lydian"), ("mahajani", "Mahajani"), ("mahj", "Mahajani"), ("maka", "Makasar"), ("makasar", "Makasar"), ("malayalam", "Malayalam"), ("mand", "Mandaic"), ("mandaic", "Mandaic"), ("mani", "Manichaean"), ("manichaean", "Manichaean"), ("marc", "Marchen"), ("marchen", "Marchen"), ("masaramgondi", "Masaram_Gondi"), ("medefaidrin", "Medefaidrin"), ("medf", "Medefaidrin"), ("meeteimayek", "Meetei_Mayek"), ("mend", "Mende_Kikakui"), ("mendekikakui", "Mende_Kikakui"), ("merc", "Meroitic_Cursive"), ("mero", "Meroitic_Hieroglyphs"), ("meroiticcursive", "Meroitic_Cursive"), ("meroitichieroglyphs", "Meroitic_Hieroglyphs"), ("miao", "Miao"), ("mlym", "Malayalam"), ("modi", "Modi"), ("mong", "Mongolian"), ("mongolian", "Mongolian"), ("mro", "Mro"), ("mroo", "Mro"), ("mtei", "Meetei_Mayek"), ("mult", "Multani"), ("multani", "Multani"), ("myanmar", "Myanmar"), ("mymr", "Myanmar"), ("nabataean", "Nabataean"), ("nand", "Nandinagari"), ("nandinagari", "Nandinagari"), ("narb", "Old_North_Arabian"), ("nbat", "Nabataean"), ("newa", "Newa"), ("newtailue", "New_Tai_Lue"), ("nko", "Nko"), ("nkoo", "Nko"), ("nshu", "Nushu"), ("nushu", "Nushu"), ("nyiakengpuachuehmong", "Nyiakeng_Puachue_Hmong"), ("ogam", "Ogham"), ("ogham", "Ogham"), ("olchiki", "Ol_Chiki"), ("olck", "Ol_Chiki"), ("oldhungarian", "Old_Hungarian"), ("olditalic", "Old_Italic"), ("oldnortharabian", "Old_North_Arabian"), ("oldpermic", "Old_Permic"), ("oldpersian", "Old_Persian"), ("oldsogdian", "Old_Sogdian"), ("oldsoutharabian", "Old_South_Arabian"), ("oldturkic", "Old_Turkic"), ("oriya", "Oriya"), ("orkh", "Old_Turkic"), ("orya", "Oriya"), ("osage", "Osage"), ("osge", "Osage"), ("osma", "Osmanya"), ("osmanya", "Osmanya"), ("pahawhhmong", "Pahawh_Hmong"), ("palm", "Palmyrene"), ("palmyrene", "Palmyrene"), ("pauc", "Pau_Cin_Hau"), ("paucinhau", "Pau_Cin_Hau"), ("perm", "Old_Permic"), ("phag", "Phags_Pa"), ("phagspa", "Phags_Pa"), ("phli", "Inscriptional_Pahlavi"), ("phlp", "Psalter_Pahlavi"), ("phnx", "Phoenician"), ("phoenician", "Phoenician"), ("plrd", "Miao"), ("prti", "Inscriptional_Parthian"), ("psalterpahlavi", "Psalter_Pahlavi"), ("qaac", "Coptic"), ("qaai", "Inherited"), ("rejang", "Rejang"), ("rjng", "Rejang"), ("rohg", "Hanifi_Rohingya"), ("runic", "Runic"), ("runr", "Runic"), ("samaritan", "Samaritan"), ("samr", "Samaritan"), ("sarb", "Old_South_Arabian"), ("saur", "Saurashtra"), ("saurashtra", "Saurashtra"), ("sgnw", "SignWriting"), ("sharada", "Sharada"), ("shavian", "Shavian"), ("shaw", "Shavian"), ("shrd", "Sharada"), ("sidd", "Siddham"), ("siddham", "Siddham"), ("signwriting", "SignWriting"), ("sind", "Khudawadi"), ("sinh", "Sinhala"), ("sinhala", "Sinhala"), ("sogd", "Sogdian"), ("sogdian", "Sogdian"), ("sogo", "Old_Sogdian"), ("sora", "Sora_Sompeng"), ("sorasompeng", "Sora_Sompeng"), ("soyo", "Soyombo"), ("soyombo", "Soyombo"), ("sund", "Sundanese"), ("sundanese", "Sundanese"), ("sylo", "Syloti_Nagri"), ("sylotinagri", "Syloti_Nagri"), ("syrc", "Syriac"), ("syriac", "Syriac"), ("tagalog", "Tagalog"), ("tagb", "Tagbanwa"), ("tagbanwa", "Tagbanwa"), ("taile", "Tai_Le"), ("taitham", "Tai_Tham"), ("taiviet", "Tai_Viet"), ("takr", "Takri"), ("takri", "Takri"), ("tale", "Tai_Le"), ("talu", "New_Tai_Lue"), ("tamil", "Tamil"), ("taml", "Tamil"), ("tang", "Tangut"), ("tangut", "Tangut"), ("tavt", "Tai_Viet"), ("telu", "Telugu"), ("telugu", "Telugu"), ("tfng", "Tifinagh"), ("tglg", "Tagalog"), ("thaa", "Thaana"), ("thaana", "Thaana"), ("thai", "Thai"), ("tibetan", "Tibetan"), ("tibt", "Tibetan"), ("tifinagh", "Tifinagh"), ("tirh", "Tirhuta"), ("tirhuta", "Tirhuta"), ("ugar", "Ugaritic"), ("ugaritic", "Ugaritic"), ("unknown", "Unknown"), ("vai", "Vai"), ("vaii", "Vai"), ("wancho", "Wancho"), ("wara", "Warang_Citi"), ("warangciti", "Warang_Citi"), ("wcho", "Wancho"), ("xpeo", "Old_Persian"), ("xsux", "Cuneiform"), ("yi", "Yi"), ("yiii", "Yi"), ("zanabazarsquare", "Zanabazar_Square"), ("zanb", "Zanabazar_Square"), ("zinh", "Inherited"), ("zyyy", "Common"), ("zzzz", "Unknown"), ]), ("Sentence_Break", &[("at", "ATerm"), ("aterm", "ATerm"), ("cl", "Close"), ("close", "Close"), ("cr", "CR"), ("ex", "Extend"), ("extend", "Extend"), ("fo", "Format"), ("format", "Format"), ("le", "OLetter"), ("lf", "LF"), ("lo", "Lower"), ("lower", "Lower"), ("nu", "Numeric"), ("numeric", "Numeric"), ("oletter", "OLetter"), ("other", "Other"), ("sc", "SContinue"), ("scontinue", "SContinue"), ("se", "Sep"), ("sep", "Sep"), ("sp", "Sp"), ("st", "STerm"), ("sterm", "STerm"), ("up", "Upper"), ("upper", "Upper"), ("xx", "Other"), ]), ("Sentence_Terminal", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Soft_Dotted", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Terminal_Punctuation", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Unified_Ideograph", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Uppercase", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Variation_Selector", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Vertical_Orientation", &[("r", "Rotated"), ("rotated", "Rotated"), ("tr", "Transformed_Rotated"), ("transformedrotated", "Transformed_Rotated"), ("transformedupright", "Transformed_Upright"), ("tu", "Transformed_Upright"), ("u", "Upright"), ("upright", "Upright"), ]), ("White_Space", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("Word_Break", &[("aletter", "ALetter"), ("cr", "CR"), ("doublequote", "Double_Quote"), ("dq", "Double_Quote"), ("eb", "E_Base"), ("ebase", "E_Base"), ("ebasegaz", "E_Base_GAZ"), ("ebg", "E_Base_GAZ"), ("em", "E_Modifier"), ("emodifier", "E_Modifier"), ("ex", "ExtendNumLet"), ("extend", "Extend"), ("extendnumlet", "ExtendNumLet"), ("fo", "Format"), ("format", "Format"), ("gaz", "Glue_After_Zwj"), ("glueafterzwj", "Glue_After_Zwj"), ("hebrewletter", "Hebrew_Letter"), ("hl", "Hebrew_Letter"), ("ka", "Katakana"), ("katakana", "Katakana"), ("le", "ALetter"), ("lf", "LF"), ("mb", "MidNumLet"), ("midletter", "MidLetter"), ("midnum", "MidNum"), ("midnumlet", "MidNumLet"), ("ml", "MidLetter"), ("mn", "MidNum"), ("newline", "Newline"), ("nl", "Newline"), ("nu", "Numeric"), ("numeric", "Numeric"), ("other", "Other"), ("regionalindicator", "Regional_Indicator"), ("ri", "Regional_Indicator"), ("singlequote", "Single_Quote"), ("sq", "Single_Quote"), ("wsegspace", "WSegSpace"), ("xx", "Other"), ("zwj", "ZWJ"), ]), ("XID_Continue", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ("XID_Start", &[("f", "No"), ("false", "No"), ("n", "No"), ("no", "No"), ("t", "Yes"), ("true", "Yes"), ("y", "Yes"), ("yes", "Yes"), ]), ]; ucd-util-0.1.5/.cargo_vcs_info.json0000644000000001120000000000000126160ustar00{ "git": { "sha1": "faf428c6997b232d957f4048a88c0ed154bde881" } }