Update to unicode 16 (#41)

switch to u32 for LEXICON_OFFSETS, as unicode 16 makes these bigger than can fit in a u16
progval · Sep 12, 2024 · 6b24cdb · 6b24cdb
1 parent 1204fe0
commit 6b24cdb
Show file tree

Hide file tree

Showing 6 changed files with 5,208 additions and 18 deletions.
diff --git a/README.md b/README.md
@@ -3,7 +3,7 @@
 [![Build Status](https://travis-ci.org/ProgVal/unicode_names2.png)](https://travis-ci.org/ProgVal/unicode_names2)
 
 Time and memory efficiently mapping characters to and from their
-Unicode 15.1 names, at runtime and compile-time.
+Unicode 16.0 names, at runtime and compile-time.
 
 ```rust
 fn main() {

diff --git a/build.rs b/build.rs
@@ -3,13 +3,13 @@ use unicode_names2_generator as generator;
 
 /// [UnicodeData.txt] contains Unicode Character Data
 ///
-/// [UnicodeData.txt]:https://www.unicode.org/Public/15.1.0/ucd/UnicodeData.txt
+/// [UnicodeData.txt]: https://www.unicode.org/Public/16.0.0/ucd/UnicodeData.txt
 const UNICODE_DATA: &str = include_str!("data/UnicodeData.txt");
 /// Unicode aliases
 ///
 /// [NamesList.txt] contents contains a map of unicode aliases to their corresponding values.
 ///
-/// [NamesList.txt]: https://www.unicode.org/Public/15.1.0/ucd/NameAliases.txt
+/// [NamesList.txt]: https://www.unicode.org/Public/16.0.0/ucd/NameAliases.txt
 const NAME_ALIASES: &str = include_str!("data/NameAliases.txt");
 
 fn main() {

diff --git a/data/NameAliases.txt b/data/NameAliases.txt
@@ -1,7 +1,8 @@
-# NameAliases-15.1.0.txt
-# Date: 2023-01-05
-# © 2023 Unicode®, Inc.
-# For terms of use, see https://www.unicode.org/terms_of_use.html
+# NameAliases-16.0.0.txt
+# Date: 2024-04-24
+# © 2024 Unicode®, Inc.
+# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
+# For terms of use and license, see https://www.unicode.org/terms_of_use.html
 #
 # Unicode Character Database
 # For documentation, see https://www.unicode.org/reports/tr44/
@@ -320,12 +321,16 @@ FEFF;BOM;abbreviation
 FEFF;ZWNBSP;abbreviation
 122D4;CUNEIFORM SIGN NU11 TENU;correction
 122D5;CUNEIFORM SIGN NU11 OVER NU11 BUR OVER BUR;correction
+12327;CUNEIFORM SIGN KALAM;correction
+1680B;BAMUM LETTER PHASE-A MAEMGBIEE;correction
 16E56;MEDEFAIDRIN CAPITAL LETTER H;correction
 16E57;MEDEFAIDRIN CAPITAL LETTER NG;correction
 16E76;MEDEFAIDRIN SMALL LETTER H;correction
 16E77;MEDEFAIDRIN SMALL LETTER NG;correction
 1B001;HENTAIGANA LETTER E-1;correction
 1D0C5;BYZANTINE MUSICAL SYMBOL FTHORA SKLIRON CHROMA VASIS;correction
+1E899;MENDE KIKAKUI SYLLABLE M172 MBO;correction
+1E89A;MENDE KIKAKUI SYLLABLE M174 MBOO;correction
 E0100;VS17;abbreviation
 E0101;VS18;abbreviation
 E0102;VS19;abbreviation