Update to Unicode 16.0

fastly · Sep 17, 2024 · 5705d43 · 5705d43
1 parent 521789f
commit 5705d43
Show file tree

Hide file tree

Showing 39 changed files with 5,686 additions and 116 deletions.
diff --git a/share/ucd/CaseFolding.txt b/share/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

diff --git a/share/ucd/Makefile b/share/ucd/Makefile
@@ -1,4 +1,4 @@
-UCD_URL ?= https://www.unicode.org/Public/15.1.0/ucd/
+UCD_URL ?= https://www.unicode.org/Public/16.0.0/ucd/
 
 WGET ?= wget
 

diff --git a/share/ucd/Scripts.txt b/share/ucd/Scripts.txt
diff --git a/share/ucd/UnicodeData.txt b/share/ucd/UnicodeData.txt
diff --git a/src/libre/class.h b/src/libre/class.h
@@ -57,6 +57,7 @@ extern const struct class utf8_Egyptian_Hieroglyphs;
 extern const struct class utf8_Elbasan;
 extern const struct class utf8_Elymaic;
 extern const struct class utf8_Ethiopic;
+extern const struct class utf8_Garay;
 extern const struct class utf8_Georgian;
 extern const struct class utf8_Glagolitic;
 extern const struct class utf8_Gothic;
@@ -65,6 +66,7 @@ extern const struct class utf8_Greek;
 extern const struct class utf8_Gujarati;
 extern const struct class utf8_Gunjala_Gondi;
 extern const struct class utf8_Gurmukhi;
+extern const struct class utf8_Gurung_Khema;
 extern const struct class utf8_Han;
 extern const struct class utf8_Hangul;
 extern const struct class utf8_Hanifi_Rohingya;
@@ -80,12 +82,14 @@ extern const struct class utf8_Javanese;
 extern const struct class utf8_Kaithi;
 extern const struct class utf8_Kannada;
 extern const struct class utf8_Katakana;
+extern const struct class utf8_Kawi;
 extern const struct class utf8_Kayah_Li;
 extern const struct class utf8_Kharoshthi;
 extern const struct class utf8_Khitan_Small_Script;
 extern const struct class utf8_Khmer;
 extern const struct class utf8_Khojki;
 extern const struct class utf8_Khudawadi;
+extern const struct class utf8_Kirat_Rai;
 extern const struct class utf8_Lao;
 extern const struct class utf8_Latin;
 extern const struct class utf8_Lepcha;
@@ -114,9 +118,10 @@ extern const struct class utf8_Mro;
 extern const struct class utf8_Multani;
 extern const struct class utf8_Myanmar;
 extern const struct class utf8_Nabataean;
+extern const struct class utf8_Nag_Mundari;
 extern const struct class utf8_Nandinagari;
-extern const struct class utf8_New_Tai_Lue;
 extern const struct class utf8_Newa;
+extern const struct class utf8_New_Tai_Lue;
 extern const struct class utf8_Nko;
 extern const struct class utf8_Nushu;
 extern const struct class utf8_Nyiakeng_Puachue_Hmong;
@@ -131,6 +136,7 @@ extern const struct class utf8_Old_Sogdian;
 extern const struct class utf8_Old_South_Arabian;
 extern const struct class utf8_Old_Turkic;
 extern const struct class utf8_Old_Uyghur;
+extern const struct class utf8_Ol_Onal;
 extern const struct class utf8_Oriya;
 extern const struct class utf8_Osage;
 extern const struct class utf8_Osmanya;
@@ -153,6 +159,7 @@ extern const struct class utf8_Sogdian;
 extern const struct class utf8_Sora_Sompeng;
 extern const struct class utf8_Soyombo;
 extern const struct class utf8_Sundanese;
+extern const struct class utf8_Sunuwar;
 extern const struct class utf8_Syloti_Nagri;
 extern const struct class utf8_Syriac;
 extern const struct class utf8_Tagalog;
@@ -170,7 +177,9 @@ extern const struct class utf8_Thai;
 extern const struct class utf8_Tibetan;
 extern const struct class utf8_Tifinagh;
 extern const struct class utf8_Tirhuta;
+extern const struct class utf8_Todhri;
 extern const struct class utf8_Toto;
+extern const struct class utf8_Tulu_Tigalari;
 extern const struct class utf8_Ugaritic;
 extern const struct class utf8_Vai;
 extern const struct class utf8_Vithkuqi;

diff --git a/src/libre/class/utf8_Arabic.c b/src/libre/class/utf8_Arabic.c
diff --git a/src/libre/class/utf8_Balinese.c b/src/libre/class/utf8_Balinese.c
diff --git a/src/libre/class/utf8_Common.c b/src/libre/class/utf8_Common.c
diff --git a/src/libre/class/utf8_Cyrillic.c b/src/libre/class/utf8_Cyrillic.c
diff --git a/src/libre/class/utf8_Egyptian_Hieroglyphs.c b/src/libre/class/utf8_Egyptian_Hieroglyphs.c
diff --git a/src/libre/class/utf8_Garay.c b/src/libre/class/utf8_Garay.c
diff --git a/src/libre/class/utf8_Gurung_Khema.c b/src/libre/class/utf8_Gurung_Khema.c
diff --git a/src/libre/class/utf8_Kawi.c b/src/libre/class/utf8_Kawi.c
diff --git a/src/libre/class/utf8_Khitan_Small_Script.c b/src/libre/class/utf8_Khitan_Small_Script.c
diff --git a/src/libre/class/utf8_Kirat_Rai.c b/src/libre/class/utf8_Kirat_Rai.c