Support Unicode 16.0.0 (#9)

Author: yhirose

README.md

@@ -3,7 +3,7 @@ cpp-unicodelib
 
 [![](https://github.com/yhirose/cpp-unicodelib/workflows/CMake/badge.svg)](https://github.com/yhirose/cpp-unicodelib/actions)
 
-A C++17 single-file header-only Unicode library. (Unicode 15.1)
+A C++17 single-file header-only Unicode library. (Unicode 16.0.0)
 
 API
 ---

UCD/Blocks.txt

@@ -1,7 +1,8 @@
-# Blocks-15.1.0.txt
-# Date: 2023-07-28, 15:47:20 GMT
-# © 2023 Unicode®, Inc.
-# For terms of use, see https://www.unicode.org/terms_of_use.html
+# Blocks-16.0.0.txt
+# Date: 2024-02-02
+# © 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/
@@ -217,6 +218,7 @@ FFF0..FFFF; Specials
 10500..1052F; Elbasan
 10530..1056F; Caucasian Albanian
 10570..105BF; Vithkuqi
+105C0..105FF; Todhri
 10600..1077F; Linear A
 10780..107BF; Latin Extended-F
 10800..1083F; Cypriot Syllabary
@@ -239,6 +241,7 @@ FFF0..FFFF; Specials
 10C00..10C4F; Old Turkic
 10C80..10CFF; Old Hungarian
 10D00..10D3F; Hanifi Rohingya
+10D40..10D8F; Garay
 10E60..10E7F; Rumi Numeral Symbols
 10E80..10EBF; Yezidi
 10EC0..10EFF; Arabic Extended-C
@@ -258,12 +261,14 @@ FFF0..FFFF; Specials
 11280..112AF; Multani
 112B0..112FF; Khudawadi
 11300..1137F; Grantha
+11380..113FF; Tulu-Tigalari
 11400..1147F; Newa
 11480..114DF; Tirhuta
 11580..115FF; Siddham
 11600..1165F; Modi
 11660..1167F; Mongolian Supplement
 11680..116CF; Takri
+116D0..116FF; Myanmar Extended-C
 11700..1174F; Ahom
 11800..1184F; Dogra
 118A0..118FF; Warang Citi
@@ -274,6 +279,7 @@ FFF0..FFFF; Specials
 11AB0..11ABF; Unified Canadian Aboriginal Syllabics Extended-A
 11AC0..11AFF; Pau Cin Hau
 11B00..11B5F; Devanagari Extended-A
+11BC0..11BFF; Sunuwar
 11C00..11C6F; Bhaiksuki
 11C70..11CBF; Marchen
 11D00..11D5F; Masaram Gondi
@@ -288,12 +294,15 @@ FFF0..FFFF; Specials
 12F90..12FFF; Cypro-Minoan
 13000..1342F; Egyptian Hieroglyphs
 13430..1345F; Egyptian Hieroglyph Format Controls
+13460..143FF; Egyptian Hieroglyphs Extended-A
 14400..1467F; Anatolian Hieroglyphs
+16100..1613F; Gurung Khema
 16800..16A3F; Bamum Supplement
 16A40..16A6F; Mro
 16A70..16ACF; Tangsa
 16AD0..16AFF; Bassa Vah
 16B00..16B8F; Pahawh Hmong
+16D40..16D7F; Kirat Rai
 16E40..16E9F; Medefaidrin
 16F00..16F9F; Miao
 16FE0..16FFF; Ideographic Symbols and Punctuation
@@ -308,6 +317,7 @@ FFF0..FFFF; Specials
 1B170..1B2FF; Nushu
 1BC00..1BC9F; Duployan
 1BCA0..1BCAF; Shorthand Format Controls
+1CC00..1CEBF; Symbols for Legacy Computing Supplement
 1CF00..1CFCF; Znamenny Musical Notation
 1D000..1D0FF; Byzantine Musical Symbols
 1D100..1D1FF; Musical Symbols
@@ -325,6 +335,7 @@ FFF0..FFFF; Specials
 1E290..1E2BF; Toto
 1E2C0..1E2FF; Wancho
 1E4D0..1E4FF; Nag Mundari
+1E5D0..1E5FF; Ol Onal
 1E7E0..1E7FF; Ethiopic Extended-B
 1E800..1E8DF; Mende Kikakui
 1E900..1E95F; Adlam

UCD/CaseFolding.txt

@@ -1,8 +1,8 @@
-# CaseFolding-15.1.0.txt
-# Date: 2023-05-12, 21:53:10 GMT
-# © 2023 Unicode®, Inc.
+# CaseFolding-16.0.0.txt
+# Date: 2024-04-30, 21:48:11 GMT
+# © 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, see https://www.unicode.org/terms_of_use.html
+# 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/
@@ -603,6 +603,7 @@
 1C86; C; 044A; # CYRILLIC SMALL LETTER TALL HARD SIGN
 1C87; C; 0463; # CYRILLIC SMALL LETTER TALL YAT
 1C88; C; A64B; # CYRILLIC SMALL LETTER UNBLENDED UK
+1C89; C; 1C8A; # CYRILLIC CAPITAL LETTER TJE
 1C90; C; 10D0; # GEORGIAN MTAVRULI CAPITAL LETTER AN
 1C91; C; 10D1; # GEORGIAN MTAVRULI CAPITAL LETTER BAN
 1C92; C; 10D2; # GEORGIAN MTAVRULI CAPITAL LETTER GAN
@@ -1240,9 +1241,13 @@ A7C5; C; 0282; # LATIN CAPITAL LETTER S WITH HOOK
 A7C6; C; 1D8E; # LATIN CAPITAL LETTER Z WITH PALATAL HOOK
 A7C7; C; A7C8; # LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY
 A7C9; C; A7CA; # LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY
+A7CB; C; 0264; # LATIN CAPITAL LETTER RAMS HORN
+A7CC; C; A7CD; # LATIN CAPITAL LETTER S WITH DIAGONAL STROKE
 A7D0; C; A7D1; # LATIN CAPITAL LETTER CLOSED INSULAR G
 A7D6; C; A7D7; # LATIN CAPITAL LETTER MIDDLE SCOTS S
 A7D8; C; A7D9; # LATIN CAPITAL LETTER SIGMOID S
+A7DA; C; A7DB; # LATIN CAPITAL LETTER LAMBDA
+A7DC; C; 019B; # LATIN CAPITAL LETTER LAMBDA WITH STROKE
 A7F5; C; A7F6; # LATIN CAPITAL LETTER REVERSED HALF H
 AB70; C; 13A0; # CHEROKEE SMALL LETTER A
 AB71; C; 13A1; # CHEROKEE SMALL LETTER E
@@ -1525,6 +1530,28 @@ FF3A; C; FF5A; # FULLWIDTH LATIN CAPITAL LETTER Z
 10CB0; C; 10CF0; # OLD HUNGARIAN CAPITAL LETTER EZS
 10CB1; C; 10CF1; # OLD HUNGARIAN CAPITAL LETTER ENT-SHAPED SIGN
 10CB2; C; 10CF2; # OLD HUNGARIAN CAPITAL LETTER US
+10D50; C; 10D70; # GARAY CAPITAL LETTER A
+10D51; C; 10D71; # GARAY CAPITAL LETTER CA
+10D52; C; 10D72; # GARAY CAPITAL LETTER MA
+10D53; C; 10D73; # GARAY CAPITAL LETTER KA
+10D54; C; 10D74; # GARAY CAPITAL LETTER BA
+10D55; C; 10D75; # GARAY CAPITAL LETTER JA
+10D56; C; 10D76; # GARAY CAPITAL LETTER SA
+10D57; C; 10D77; # GARAY CAPITAL LETTER WA
+10D58; C; 10D78; # GARAY CAPITAL LETTER LA
+10D59; C; 10D79; # GARAY CAPITAL LETTER GA
+10D5A; C; 10D7A; # GARAY CAPITAL LETTER DA
+10D5B; C; 10D7B; # GARAY CAPITAL LETTER XA
+10D5C; C; 10D7C; # GARAY CAPITAL LETTER YA
+10D5D; C; 10D7D; # GARAY CAPITAL LETTER TA
+10D5E; C; 10D7E; # GARAY CAPITAL LETTER RA
+10D5F; C; 10D7F; # GARAY CAPITAL LETTER NYA
+10D60; C; 10D80; # GARAY CAPITAL LETTER FA
+10D61; C; 10D81; # GARAY CAPITAL LETTER NA
+10D62; C; 10D82; # GARAY CAPITAL LETTER PA
+10D63; C; 10D83; # GARAY CAPITAL LETTER HA
+10D64; C; 10D84; # GARAY CAPITAL LETTER OLD KA
+10D65; C; 10D85; # GARAY CAPITAL LETTER OLD NA
 118A0; C; 118C0; # WARANG CITI CAPITAL LETTER NGAA
 118A1; C; 118C1; # WARANG CITI CAPITAL LETTER A
 118A2; C; 118C2; # WARANG CITI CAPITAL LETTER WI

UCD/CompositionExclusions.txt

@@ -1,7 +1,8 @@
-# CompositionExclusions-15.1.0.txt
-# Date: 2023-01-05
-# © 2023 Unicode®, Inc.
-# For terms of use, see https://www.unicode.org/terms_of_use.html
+# CompositionExclusions-16.0.0.txt
+# Date: 2024-02-02
+# © 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/