From cab2fa7f3329bb79f2ca1e0fee352d8d843cb169 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 24 Oct 2023 09:06:57 +0200 Subject: [PATCH] Garay (#552) --- unicodetools/data/ucd/dev/Blocks.txt | 1 + unicodetools/data/ucd/dev/CaseFolding.txt | 24 ++++- unicodetools/data/ucd/dev/DerivedAge.txt | 7 +- .../data/ucd/dev/DerivedCoreProperties.txt | 98 +++++++++++++++---- .../ucd/dev/DerivedNormalizationProps.txt | 53 +++++++++- unicodetools/data/ucd/dev/EastAsianWidth.txt | 12 ++- unicodetools/data/ucd/dev/LineBreak.txt | 12 ++- .../data/ucd/dev/NormalizationTest.txt | 12 ++- unicodetools/data/ucd/dev/PropList.txt | 17 +++- .../data/ucd/dev/PropertyValueAliases.txt | 4 +- .../data/ucd/dev/ScriptExtensions.txt | 26 ++--- unicodetools/data/ucd/dev/Scripts.txt | 17 +++- unicodetools/data/ucd/dev/UnicodeData.txt | 69 +++++++++++++ .../data/ucd/dev/VerticalOrientation.txt | 12 ++- .../dev/auxiliary/GraphemeBreakProperty.txt | 5 +- .../dev/auxiliary/SentenceBreakProperty.txt | 20 ++-- .../ucd/dev/auxiliary/WordBreakProperty.txt | 16 ++- .../ucd/dev/extracted/DerivedBidiClass.txt | 23 +++-- .../dev/extracted/DerivedCombiningClass.txt | 18 +++- .../dev/extracted/DerivedEastAsianWidth.txt | 14 ++- .../dev/extracted/DerivedGeneralCategory.txt | 35 ++++--- .../ucd/dev/extracted/DerivedJoiningType.txt | 5 +- .../ucd/dev/extracted/DerivedLineBreak.txt | 24 +++-- .../data/ucd/dev/extracted/DerivedName.txt | 73 +++++++++++++- .../ucd/dev/extracted/DerivedNumericType.txt | 5 +- .../dev/extracted/DerivedNumericValues.txt | 32 +++--- .../org/unicode/props/UcdPropertyValues.java | 2 + .../org/unicode/text/UCD/ShortBlockNames.txt | 1 + 28 files changed, 528 insertions(+), 109 deletions(-) diff --git a/unicodetools/data/ucd/dev/Blocks.txt b/unicodetools/data/ucd/dev/Blocks.txt index a8539ea1b..f213cc086 100644 --- a/unicodetools/data/ucd/dev/Blocks.txt +++ b/unicodetools/data/ucd/dev/Blocks.txt @@ -240,6 +240,7 @@ 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 diff --git a/unicodetools/data/ucd/dev/CaseFolding.txt b/unicodetools/data/ucd/dev/CaseFolding.txt index ba43df3ec..91afcbbf8 100644 --- a/unicodetools/data/ucd/dev/CaseFolding.txt +++ b/unicodetools/data/ucd/dev/CaseFolding.txt @@ -1,5 +1,5 @@ # CaseFolding-16.0.0.txt -# Date: 2023-10-03, 19:01:21 GMT +# Date: 2023-10-16, 14:29:43 GMT # © 2023 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 @@ -1526,6 +1526,28 @@ 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/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index 8870764d0..57dd38b3b 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-16.0.0.txt -# Date: 2023-10-23, 11:33:37 GMT +# Date: 2023-10-23, 18:44:20 GMT # © 2023 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 @@ -2014,6 +2014,9 @@ FDFE..FDFF ; 14.0 # [2] ARABIC LIGATURE SUBHAANAHU WA TAAALAA..ARABIC LIGAT 0CDC ; 16.0 # KANNADA ARCHAIC SHRII 1C89..1C8A ; 16.0 # [2] CYRILLIC CAPITAL LETTER TJE..CYRILLIC SMALL LETTER TJE 105C0..105F3 ; 16.0 # [52] TODHRI LETTER A..TODHRI LETTER OO +10D40..10D65 ; 16.0 # [38] GARAY DIGIT ZERO..GARAY CAPITAL LETTER OLD NA +10D69..10D85 ; 16.0 # [29] GARAY VOWEL SIGN E..GARAY SMALL LETTER OLD NA +10D8E..10D8F ; 16.0 # [2] GARAY PLUS SIGN..GARAY MINUS SIGN 10EC2..10EC4 ; 16.0 # [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EFC ; 16.0 # ARABIC COMBINING ALEF OVERLAY 116D0..116E3 ; 16.0 # [20] MYANMAR PAO DIGIT ZERO..MYANMAR EASTERN PWO KAREN DIGIT NINE @@ -2022,6 +2025,6 @@ FDFE..FDFF ; 14.0 # [2] ARABIC LIGATURE SUBHAANAHU WA TAAALAA..ARABIC LIGAT 1CEB0..1CEB3 ; 16.0 # [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET 1F8B2 ; 16.0 # RIGHTWARDS ARROW WITH LOWER HOOK -# Total code points: 130 +# Total code points: 199 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 344998b7f..42df9cdb7 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-16.0.0.txt -# Date: 2023-10-23, 11:33:57 GMT +# Date: 2023-10-23, 18:44:51 GMT # © 2023 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 @@ -177,6 +177,7 @@ FF5C ; Math # Sm FULLWIDTH VERTICAL LINE FF5E ; Math # Sm FULLWIDTH TILDE FFE2 ; Math # Sm FULLWIDTH NOT SIGN FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS ARROW +10D8E..10D8F ; Math # Sm [2] GARAY PLUS SIGN..GARAY MINUS SIGN 1D400..1D454 ; Math # L& [85] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL ITALIC SMALL G 1D456..1D49C ; Math # L& [71] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL SCRIPT CAPITAL A 1D49E..1D49F ; Math # L& [2] MATHEMATICAL SCRIPT CAPITAL C..MATHEMATICAL SCRIPT CAPITAL D @@ -253,7 +254,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 1EEAB..1EEBB ; Math # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1EEF0..1EEF1 ; Math # Sm [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL -# Total code points: 2310 +# Total code points: 2312 # ================================================ @@ -1040,6 +1041,13 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 10CC0..10CF2 ; Alphabetic # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 10D00..10D23 ; Alphabetic # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA 10D24..10D27 ; Alphabetic # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10D4A..10D4D ; Alphabetic # Lo [4] GARAY VOWEL SIGN A..GARAY VOWEL SIGN EE +10D4E ; Alphabetic # Lm GARAY VOWEL LENGTH MARK +10D4F ; Alphabetic # Lo GARAY SUKUN +10D50..10D65 ; Alphabetic # L& [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA +10D69 ; Alphabetic # Mn GARAY VOWEL SIGN E +10D6F ; Alphabetic # Lm GARAY REDUPLICATION MARK +10D70..10D85 ; Alphabetic # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA 10E80..10EA9 ; Alphabetic # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EAB..10EAC ; Alphabetic # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EB0..10EB1 ; Alphabetic # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE @@ -1407,7 +1415,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 30000..3134A ; Alphabetic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Alphabetic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 138481 +# Total code points: 138533 # ================================================ @@ -2066,6 +2074,7 @@ FF41..FF5A ; Lowercase # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 10787..107B0 ; Lowercase # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK 107B2..107BA ; Lowercase # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10CC0..10CF2 ; Lowercase # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US +10D70..10D85 ; Lowercase # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA 118C0..118DF ; Lowercase # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E60..16E7F ; Lowercase # L& [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y 1D41A..1D433 ; Lowercase # L& [26] MATHEMATICAL BOLD SMALL A..MATHEMATICAL BOLD SMALL Z @@ -2102,7 +2111,7 @@ FF41..FF5A ; Lowercase # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 1E030..1E06D ; Lowercase # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E922..1E943 ; Lowercase # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2545 +# Total code points: 2567 # ================================================ @@ -2724,6 +2733,7 @@ FF21..FF3A ; Uppercase # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH 1058C..10592 ; Uppercase # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE 10594..10595 ; Uppercase # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE 10C80..10CB2 ; Uppercase # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US +10D50..10D65 ; Uppercase # L& [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA 118A0..118BF ; Uppercase # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 16E40..16E5F ; Uppercase # L& [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y 1D400..1D419 ; Uppercase # L& [26] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL BOLD CAPITAL Z @@ -2762,7 +2772,7 @@ FF21..FF3A ; Uppercase # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH 1F150..1F169 ; Uppercase # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Uppercase # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 1952 +# Total code points: 1974 # ================================================ @@ -2904,6 +2914,8 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 107B2..107BA ; Cased # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10C80..10CB2 ; Cased # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 10CC0..10CF2 ; Cased # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US +10D50..10D65 ; Cased # L& [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA +10D70..10D85 ; Cased # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA 118A0..118DF ; Cased # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E40..16E7F ; Cased # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 1D400..1D454 ; Cased # L& [85] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL ITALIC SMALL G @@ -2945,7 +2957,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1F150..1F169 ; Cased # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Cased # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 4528 +# Total code points: 4572 # ================================================ @@ -3303,6 +3315,9 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 10A3F ; Case_Ignorable # Mn KHAROSHTHI VIRAMA 10AE5..10AE6 ; Case_Ignorable # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW 10D24..10D27 ; Case_Ignorable # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10D4E ; Case_Ignorable # Lm GARAY VOWEL LENGTH MARK +10D69..10D6D ; Case_Ignorable # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK +10D6F ; Case_Ignorable # Lm GARAY REDUPLICATION MARK 10EAB..10EAC ; Case_Ignorable # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EFC..10EFF ; Case_Ignorable # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Case_Ignorable # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW @@ -3447,7 +3462,7 @@ E0001 ; Case_Ignorable # Cf LANGUAGE TAG E0020..E007F ; Case_Ignorable # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2709 +# Total code points: 2716 # ================================================ @@ -4063,11 +4078,12 @@ FF21..FF3A ; Changes_When_Lowercased # L& [26] FULLWIDTH LATIN CAPITAL LETTE 1058C..10592 ; Changes_When_Lowercased # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE 10594..10595 ; Changes_When_Lowercased # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE 10C80..10CB2 ; Changes_When_Lowercased # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US +10D50..10D65 ; Changes_When_Lowercased # L& [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA 118A0..118BF ; Changes_When_Lowercased # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 16E40..16E5F ; Changes_When_Lowercased # L& [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y 1E900..1E921 ; Changes_When_Lowercased # L& [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA -# Total code points: 1434 +# Total code points: 1456 # ================================================ @@ -4701,11 +4717,12 @@ FF41..FF5A ; Changes_When_Uppercased # L& [26] FULLWIDTH LATIN SMALL LETTER 105B3..105B9 ; Changes_When_Uppercased # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE 105BB..105BC ; Changes_When_Uppercased # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10CC0..10CF2 ; Changes_When_Uppercased # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US +10D70..10D85 ; Changes_When_Uppercased # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA 118C0..118DF ; Changes_When_Uppercased # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E60..16E7F ; Changes_When_Uppercased # L& [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y 1E922..1E943 ; Changes_When_Uppercased # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 1526 +# Total code points: 1548 # ================================================ @@ -5338,11 +5355,12 @@ FF41..FF5A ; Changes_When_Titlecased # L& [26] FULLWIDTH LATIN SMALL LETTER 105B3..105B9 ; Changes_When_Titlecased # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE 105BB..105BC ; Changes_When_Titlecased # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10CC0..10CF2 ; Changes_When_Titlecased # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US +10D70..10D85 ; Changes_When_Titlecased # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA 118C0..118DF ; Changes_When_Titlecased # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E60..16E7F ; Changes_When_Titlecased # L& [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y 1E922..1E943 ; Changes_When_Titlecased # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 1453 +# Total code points: 1475 # ================================================ @@ -5970,11 +5988,12 @@ FF21..FF3A ; Changes_When_Casefolded # L& [26] FULLWIDTH LATIN CAPITAL LETTE 1058C..10592 ; Changes_When_Casefolded # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE 10594..10595 ; Changes_When_Casefolded # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE 10C80..10CB2 ; Changes_When_Casefolded # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US +10D50..10D65 ; Changes_When_Casefolded # L& [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA 118A0..118BF ; Changes_When_Casefolded # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 16E40..16E5F ; Changes_When_Casefolded # L& [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y 1E900..1E921 ; Changes_When_Casefolded # L& [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA -# Total code points: 1507 +# Total code points: 1529 # ================================================ @@ -6111,11 +6130,13 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 105BB..105BC ; Changes_When_Casemapped # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10C80..10CB2 ; Changes_When_Casemapped # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 10CC0..10CF2 ; Changes_When_Casemapped # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US +10D50..10D65 ; Changes_When_Casemapped # L& [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA +10D70..10D85 ; Changes_When_Casemapped # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA 118A0..118DF ; Changes_When_Casemapped # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E40..16E7F ; Changes_When_Casemapped # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 1E900..1E943 ; Changes_When_Casemapped # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2929 +# Total code points: 2973 # ================================================ @@ -6650,6 +6671,12 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10C80..10CB2 ; ID_Start # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 10CC0..10CF2 ; ID_Start # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 10D00..10D23 ; ID_Start # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA +10D4A..10D4D ; ID_Start # Lo [4] GARAY VOWEL SIGN A..GARAY VOWEL SIGN EE +10D4E ; ID_Start # Lm GARAY VOWEL LENGTH MARK +10D4F ; ID_Start # Lo GARAY SUKUN +10D50..10D65 ; ID_Start # L& [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA +10D6F ; ID_Start # Lm GARAY REDUPLICATION MARK +10D70..10D85 ; ID_Start # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA 10E80..10EA9 ; ID_Start # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EB0..10EB1 ; ID_Start # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; ID_Start # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW @@ -6872,7 +6899,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; ID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; ID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 137059 +# Total code points: 137110 # ================================================ @@ -7793,6 +7820,14 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 10D00..10D23 ; ID_Continue # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA 10D24..10D27 ; ID_Continue # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D30..10D39 ; ID_Continue # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE +10D40..10D49 ; ID_Continue # Nd [10] GARAY DIGIT ZERO..GARAY DIGIT NINE +10D4A..10D4D ; ID_Continue # Lo [4] GARAY VOWEL SIGN A..GARAY VOWEL SIGN EE +10D4E ; ID_Continue # Lm GARAY VOWEL LENGTH MARK +10D4F ; ID_Continue # Lo GARAY SUKUN +10D50..10D65 ; ID_Continue # L& [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA +10D69..10D6D ; ID_Continue # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK +10D6F ; ID_Continue # Lm GARAY REDUPLICATION MARK +10D70..10D85 ; ID_Continue # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA 10E80..10EA9 ; ID_Continue # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EAB..10EAC ; ID_Continue # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EB0..10EB1 ; ID_Continue # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE @@ -8236,7 +8271,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 140232 +# Total code points: 140298 # ================================================ @@ -8772,6 +8807,12 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 10C80..10CB2 ; XID_Start # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 10CC0..10CF2 ; XID_Start # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 10D00..10D23 ; XID_Start # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA +10D4A..10D4D ; XID_Start # Lo [4] GARAY VOWEL SIGN A..GARAY VOWEL SIGN EE +10D4E ; XID_Start # Lm GARAY VOWEL LENGTH MARK +10D4F ; XID_Start # Lo GARAY SUKUN +10D50..10D65 ; XID_Start # L& [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA +10D6F ; XID_Start # Lm GARAY REDUPLICATION MARK +10D70..10D85 ; XID_Start # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA 10E80..10EA9 ; XID_Start # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EB0..10EB1 ; XID_Start # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; XID_Start # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW @@ -8994,7 +9035,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 30000..3134A ; XID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; XID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 137036 +# Total code points: 137087 # ================================================ @@ -9916,6 +9957,14 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 10D00..10D23 ; XID_Continue # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA 10D24..10D27 ; XID_Continue # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D30..10D39 ; XID_Continue # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE +10D40..10D49 ; XID_Continue # Nd [10] GARAY DIGIT ZERO..GARAY DIGIT NINE +10D4A..10D4D ; XID_Continue # Lo [4] GARAY VOWEL SIGN A..GARAY VOWEL SIGN EE +10D4E ; XID_Continue # Lm GARAY VOWEL LENGTH MARK +10D4F ; XID_Continue # Lo GARAY SUKUN +10D50..10D65 ; XID_Continue # L& [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA +10D69..10D6D ; XID_Continue # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK +10D6F ; XID_Continue # Lm GARAY REDUPLICATION MARK +10D70..10D85 ; XID_Continue # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA 10E80..10EA9 ; XID_Continue # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EAB..10EAC ; XID_Continue # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EB0..10EB1 ; XID_Continue # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE @@ -10359,7 +10408,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 140213 +# Total code points: 140279 # ================================================ @@ -10662,6 +10711,7 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 10A3F ; Grapheme_Extend # Mn KHAROSHTHI VIRAMA 10AE5..10AE6 ; Grapheme_Extend # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW 10D24..10D27 ; Grapheme_Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10D69..10D6D ; Grapheme_Extend # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; Grapheme_Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EFC..10EFF ; Grapheme_Extend # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Grapheme_Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW @@ -10796,7 +10846,7 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. E0020..E007F ; Grapheme_Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2127 +# Total code points: 2132 # ================================================ @@ -12090,6 +12140,15 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 10CFA..10CFF ; Grapheme_Base # No [6] OLD HUNGARIAN NUMBER ONE..OLD HUNGARIAN NUMBER ONE THOUSAND 10D00..10D23 ; Grapheme_Base # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA 10D30..10D39 ; Grapheme_Base # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE +10D40..10D49 ; Grapheme_Base # Nd [10] GARAY DIGIT ZERO..GARAY DIGIT NINE +10D4A..10D4D ; Grapheme_Base # Lo [4] GARAY VOWEL SIGN A..GARAY VOWEL SIGN EE +10D4E ; Grapheme_Base # Lm GARAY VOWEL LENGTH MARK +10D4F ; Grapheme_Base # Lo GARAY SUKUN +10D50..10D65 ; Grapheme_Base # L& [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA +10D6E ; Grapheme_Base # Pd GARAY HYPHEN +10D6F ; Grapheme_Base # Lm GARAY REDUPLICATION MARK +10D70..10D85 ; Grapheme_Base # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA +10D8E..10D8F ; Grapheme_Base # Sm [2] GARAY PLUS SIGN..GARAY MINUS SIGN 10E60..10E7E ; Grapheme_Base # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS 10E80..10EA9 ; Grapheme_Base # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EAD ; Grapheme_Base # Pd YEZIDI HYPHENATION MARK @@ -12556,7 +12615,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 30000..3134A ; Grapheme_Base # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Grapheme_Base # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 147741 +# Total code points: 147805 # ================================================ @@ -12805,6 +12864,7 @@ FE20..FE2F ; InCB; Extend # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING 10A3F ; InCB; Extend # Mn KHAROSHTHI VIRAMA 10AE5..10AE6 ; InCB; Extend # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW 10D24..10D27 ; InCB; Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10D69..10D6D ; InCB; Extend # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; InCB; Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EFD..10EFF ; InCB; Extend # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; InCB; Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW @@ -12860,6 +12920,6 @@ FE20..FE2F ; InCB; Extend # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING 1E8D0..1E8D6 ; InCB; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; InCB; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA -# Total code points: 885 +# Total code points: 890 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt b/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt index 102600acc..d549b4f51 100644 --- a/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt +++ b/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt @@ -1,5 +1,5 @@ # DerivedNormalizationProps-16.0.0.txt -# Date: 2023-10-16, 14:22:26 GMT +# Date: 2023-10-23, 18:44:57 GMT # © 2023 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 @@ -7018,6 +7018,28 @@ FFF0..FFF8 ; NFKC_CF; # Cn [9] ...... -# Total code points: 10492 +# Total code points: 10514 # ================================================ @@ -13090,6 +13112,28 @@ FFF0..FFF8 ; NFKC_SCF; # Cn [9] ...... -# Total code points: 10454 +# Total code points: 10476 # ================================================ @@ -15993,6 +16037,7 @@ FFF0..FFF8 ; Changes_When_NFKC_Casefolded # Cn [9] ...... -# Total code points: 10492 +# Total code points: 10514 # EOF diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index cc28c2251..1d710c3d3 100644 --- a/unicodetools/data/ucd/dev/EastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/EastAsianWidth.txt @@ -1,5 +1,5 @@ # EastAsianWidth-16.0.0.txt -# Date: 2023-10-23, 11:34:03 GMT +# Date: 2023-10-23, 18:45:00 GMT # © 2023 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 @@ -1943,6 +1943,16 @@ FFFD ; A # So REPLACEMENT CHARACTER 10D00..10D23 ; N # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA 10D24..10D27 ; N # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D30..10D39 ; N # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE +10D40..10D49 ; N # Nd [10] GARAY DIGIT ZERO..GARAY DIGIT NINE +10D4A..10D4D ; N # Lo [4] GARAY VOWEL SIGN A..GARAY VOWEL SIGN EE +10D4E ; N # Lm GARAY VOWEL LENGTH MARK +10D4F ; N # Lo GARAY SUKUN +10D50..10D65 ; N # Lu [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA +10D69..10D6D ; N # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK +10D6E ; N # Pd GARAY HYPHEN +10D6F ; N # Lm GARAY REDUPLICATION MARK +10D70..10D85 ; N # Ll [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA +10D8E..10D8F ; N # Sm [2] GARAY PLUS SIGN..GARAY MINUS SIGN 10E60..10E7E ; N # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS 10E80..10EA9 ; N # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EAB..10EAC ; N # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 5c64ab8b1..f826adf12 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,5 @@ # LineBreak-16.0.0.txt -# Date: 2023-10-23, 11:34:04 GMT +# Date: 2023-10-23, 18:45:02 GMT # © 2023 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 @@ -2796,6 +2796,16 @@ FFFD ; AI # So REPLACEMENT CHARACTER 10D00..10D23 ; AL # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA 10D24..10D27 ; CM # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D30..10D39 ; NU # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE +10D40..10D49 ; NU # Nd [10] GARAY DIGIT ZERO..GARAY DIGIT NINE +10D4A..10D4D ; AL # Lo [4] GARAY VOWEL SIGN A..GARAY VOWEL SIGN EE +10D4E ; AL # Lm GARAY VOWEL LENGTH MARK +10D4F ; AL # Lo GARAY SUKUN +10D50..10D65 ; AL # Lu [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA +10D69..10D6D ; CM # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK +10D6E ; BA # Pd GARAY HYPHEN +10D6F ; AL # Lm GARAY REDUPLICATION MARK +10D70..10D85 ; AL # Ll [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA +10D8E..10D8F ; AL # Sm [2] GARAY PLUS SIGN..GARAY MINUS SIGN 10E60..10E7E ; AL # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS 10E80..10EA9 ; AL # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EAB..10EAC ; CM # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK diff --git a/unicodetools/data/ucd/dev/NormalizationTest.txt b/unicodetools/data/ucd/dev/NormalizationTest.txt index 5a4e3fc79..ccd79ae54 100644 --- a/unicodetools/data/ucd/dev/NormalizationTest.txt +++ b/unicodetools/data/ucd/dev/NormalizationTest.txt @@ -1,5 +1,5 @@ # NormalizationTest-16.0.0.txt -# Date: 2023-10-09, 15:12:35 GMT +# Date: 2023-10-23, 12:24:21 GMT # © 2023 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 @@ -18558,6 +18558,16 @@ FFEE;FFEE;FFEE;25CB;25CB; # (￮; ￮; ￮; ○; ○; ) HALFWIDTH WHITE CIRCLE 0061 10D26 0315 0300 05AE 0062;0061 05AE 10D26 0300 0315 0062;0061 05AE 10D26 0300 0315 0062;0061 05AE 10D26 0300 0315 0062;0061 05AE 10D26 0300 0315 0062; # (a◌𐴦◌̕◌̀◌֮b; a◌֮◌𐴦◌̀◌̕b; a◌֮◌𐴦◌̀◌̕b; a◌֮◌𐴦◌̀◌̕b; a◌֮◌𐴦◌̀◌̕b; ) LATIN SMALL LETTER A, HANIFI ROHINGYA SIGN TANA, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B 0061 0315 0300 05AE 10D27 0062;00E0 05AE 10D27 0315 0062;0061 05AE 0300 10D27 0315 0062;00E0 05AE 10D27 0315 0062;0061 05AE 0300 10D27 0315 0062; # (a◌̕◌̀◌֮◌𐴧b; à◌֮◌𐴧◌̕b; a◌֮◌̀◌𐴧◌̕b; à◌֮◌𐴧◌̕b; a◌֮◌̀◌𐴧◌̕b; ) LATIN SMALL LETTER A, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, HANIFI ROHINGYA SIGN TASSI, LATIN SMALL LETTER B 0061 10D27 0315 0300 05AE 0062;0061 05AE 10D27 0300 0315 0062;0061 05AE 10D27 0300 0315 0062;0061 05AE 10D27 0300 0315 0062;0061 05AE 10D27 0300 0315 0062; # (a◌𐴧◌̕◌̀◌֮b; a◌֮◌𐴧◌̀◌̕b; a◌֮◌𐴧◌̀◌̕b; a◌֮◌𐴧◌̀◌̕b; a◌֮◌𐴧◌̀◌̕b; ) LATIN SMALL LETTER A, HANIFI ROHINGYA SIGN TASSI, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B +0061 0315 0300 05AE 10D69 0062;00E0 05AE 10D69 0315 0062;0061 05AE 0300 10D69 0315 0062;00E0 05AE 10D69 0315 0062;0061 05AE 0300 10D69 0315 0062; # (a◌̕◌̀◌֮◌𐵩b; à◌֮◌𐵩◌̕b; a◌֮◌̀◌𐵩◌̕b; à◌֮◌𐵩◌̕b; a◌֮◌̀◌𐵩◌̕b; ) LATIN SMALL LETTER A, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, GARAY VOWEL SIGN E, LATIN SMALL LETTER B +0061 10D69 0315 0300 05AE 0062;0061 05AE 10D69 0300 0315 0062;0061 05AE 10D69 0300 0315 0062;0061 05AE 10D69 0300 0315 0062;0061 05AE 10D69 0300 0315 0062; # (a◌𐵩◌̕◌̀◌֮b; a◌֮◌𐵩◌̀◌̕b; a◌֮◌𐵩◌̀◌̕b; a◌֮◌𐵩◌̀◌̕b; a◌֮◌𐵩◌̀◌̕b; ) LATIN SMALL LETTER A, GARAY VOWEL SIGN E, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B +0061 0315 0300 05AE 10D6A 0062;00E0 05AE 10D6A 0315 0062;0061 05AE 0300 10D6A 0315 0062;00E0 05AE 10D6A 0315 0062;0061 05AE 0300 10D6A 0315 0062; # (a◌̕◌̀◌֮◌𐵪b; à◌֮◌𐵪◌̕b; a◌֮◌̀◌𐵪◌̕b; à◌֮◌𐵪◌̕b; a◌֮◌̀◌𐵪◌̕b; ) LATIN SMALL LETTER A, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, GARAY CONSONANT GEMINATION MARK, LATIN SMALL LETTER B +0061 10D6A 0315 0300 05AE 0062;0061 05AE 10D6A 0300 0315 0062;0061 05AE 10D6A 0300 0315 0062;0061 05AE 10D6A 0300 0315 0062;0061 05AE 10D6A 0300 0315 0062; # (a◌𐵪◌̕◌̀◌֮b; a◌֮◌𐵪◌̀◌̕b; a◌֮◌𐵪◌̀◌̕b; a◌֮◌𐵪◌̀◌̕b; a◌֮◌𐵪◌̀◌̕b; ) LATIN SMALL LETTER A, GARAY CONSONANT GEMINATION MARK, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B +0061 0315 0300 05AE 10D6B 0062;00E0 05AE 10D6B 0315 0062;0061 05AE 0300 10D6B 0315 0062;00E0 05AE 10D6B 0315 0062;0061 05AE 0300 10D6B 0315 0062; # (a◌̕◌̀◌֮◌𐵫b; à◌֮◌𐵫◌̕b; a◌֮◌̀◌𐵫◌̕b; à◌֮◌𐵫◌̕b; a◌֮◌̀◌𐵫◌̕b; ) LATIN SMALL LETTER A, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, GARAY COMBINING DOT ABOVE, LATIN SMALL LETTER B +0061 10D6B 0315 0300 05AE 0062;0061 05AE 10D6B 0300 0315 0062;0061 05AE 10D6B 0300 0315 0062;0061 05AE 10D6B 0300 0315 0062;0061 05AE 10D6B 0300 0315 0062; # (a◌𐵫◌̕◌̀◌֮b; a◌֮◌𐵫◌̀◌̕b; a◌֮◌𐵫◌̀◌̕b; a◌֮◌𐵫◌̀◌̕b; a◌֮◌𐵫◌̀◌̕b; ) LATIN SMALL LETTER A, GARAY COMBINING DOT ABOVE, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B +0061 0315 0300 05AE 10D6C 0062;00E0 05AE 10D6C 0315 0062;0061 05AE 0300 10D6C 0315 0062;00E0 05AE 10D6C 0315 0062;0061 05AE 0300 10D6C 0315 0062; # (a◌̕◌̀◌֮◌𐵬b; à◌֮◌𐵬◌̕b; a◌֮◌̀◌𐵬◌̕b; à◌֮◌𐵬◌̕b; a◌֮◌̀◌𐵬◌̕b; ) LATIN SMALL LETTER A, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, GARAY COMBINING DOUBLE DOT ABOVE, LATIN SMALL LETTER B +0061 10D6C 0315 0300 05AE 0062;0061 05AE 10D6C 0300 0315 0062;0061 05AE 10D6C 0300 0315 0062;0061 05AE 10D6C 0300 0315 0062;0061 05AE 10D6C 0300 0315 0062; # (a◌𐵬◌̕◌̀◌֮b; a◌֮◌𐵬◌̀◌̕b; a◌֮◌𐵬◌̀◌̕b; a◌֮◌𐵬◌̀◌̕b; a◌֮◌𐵬◌̀◌̕b; ) LATIN SMALL LETTER A, GARAY COMBINING DOUBLE DOT ABOVE, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B +0061 0315 0300 05AE 10D6D 0062;00E0 05AE 10D6D 0315 0062;0061 05AE 0300 10D6D 0315 0062;00E0 05AE 10D6D 0315 0062;0061 05AE 0300 10D6D 0315 0062; # (a◌̕◌̀◌֮◌𐵭b; à◌֮◌𐵭◌̕b; a◌֮◌̀◌𐵭◌̕b; à◌֮◌𐵭◌̕b; a◌֮◌̀◌𐵭◌̕b; ) LATIN SMALL LETTER A, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, GARAY CONSONANT NASALIZATION MARK, LATIN SMALL LETTER B +0061 10D6D 0315 0300 05AE 0062;0061 05AE 10D6D 0300 0315 0062;0061 05AE 10D6D 0300 0315 0062;0061 05AE 10D6D 0300 0315 0062;0061 05AE 10D6D 0300 0315 0062; # (a◌𐵭◌̕◌̀◌֮b; a◌֮◌𐵭◌̀◌̕b; a◌֮◌𐵭◌̀◌̕b; a◌֮◌𐵭◌̀◌̕b; a◌֮◌𐵭◌̀◌̕b; ) LATIN SMALL LETTER A, GARAY CONSONANT NASALIZATION MARK, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B 0061 0315 0300 05AE 10EAB 0062;00E0 05AE 10EAB 0315 0062;0061 05AE 0300 10EAB 0315 0062;00E0 05AE 10EAB 0315 0062;0061 05AE 0300 10EAB 0315 0062; # (a◌̕◌̀◌֮◌𐺫b; à◌֮◌𐺫◌̕b; a◌֮◌̀◌𐺫◌̕b; à◌֮◌𐺫◌̕b; a◌֮◌̀◌𐺫◌̕b; ) LATIN SMALL LETTER A, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, YEZIDI COMBINING HAMZA MARK, LATIN SMALL LETTER B 0061 10EAB 0315 0300 05AE 0062;0061 05AE 10EAB 0300 0315 0062;0061 05AE 10EAB 0300 0315 0062;0061 05AE 10EAB 0300 0315 0062;0061 05AE 10EAB 0300 0315 0062; # (a◌𐺫◌̕◌̀◌֮b; a◌֮◌𐺫◌̀◌̕b; a◌֮◌𐺫◌̀◌̕b; a◌֮◌𐺫◌̀◌̕b; a◌֮◌𐺫◌̀◌̕b; ) LATIN SMALL LETTER A, YEZIDI COMBINING HAMZA MARK, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B 0061 0315 0300 05AE 10EAC 0062;00E0 05AE 10EAC 0315 0062;0061 05AE 0300 10EAC 0315 0062;00E0 05AE 10EAC 0315 0062;0061 05AE 0300 10EAC 0315 0062; # (a◌̕◌̀◌֮◌𐺬b; à◌֮◌𐺬◌̕b; a◌֮◌̀◌𐺬◌̕b; à◌֮◌𐺬◌̕b; a◌֮◌̀◌𐺬◌̕b; ) LATIN SMALL LETTER A, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, YEZIDI COMBINING MADDA MARK, LATIN SMALL LETTER B diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt index 8c1f3934d..2fa585a17 100644 --- a/unicodetools/data/ucd/dev/PropList.txt +++ b/unicodetools/data/ucd/dev/PropList.txt @@ -1,5 +1,5 @@ # PropList-16.0.0.txt -# Date: 2023-10-13, 11:33:44 GMT +# Date: 2023-10-23, 12:20:11 GMT # © 2023 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 @@ -62,9 +62,10 @@ FE31..FE32 ; Dash # Pd [2] PRESENTATION FORM FOR VERTICAL EM DASH..PRESENTA FE58 ; Dash # Pd SMALL EM DASH FE63 ; Dash # Pd SMALL HYPHEN-MINUS FF0D ; Dash # Pd FULLWIDTH HYPHEN-MINUS +10D6E ; Dash # Pd GARAY HYPHEN 10EAD ; Dash # Pd YEZIDI HYPHENATION MARK -# Total code points: 30 +# Total code points: 31 # ================================================ @@ -690,6 +691,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 10A05..10A06 ; Other_Alphabetic # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O 10A0C..10A0F ; Other_Alphabetic # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA 10D24..10D27 ; Other_Alphabetic # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10D69 ; Other_Alphabetic # Mn GARAY VOWEL SIGN E 10EAB..10EAC ; Other_Alphabetic # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EFC ; Other_Alphabetic # Mn ARABIC COMBINING ALEF OVERLAY 11000 ; Other_Alphabetic # Mc BRAHMI SIGN CANDRABINDU @@ -836,7 +838,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 1F150..1F169 ; Other_Alphabetic # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Other_Alphabetic # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 1427 +# Total code points: 1428 # ================================================ @@ -1044,6 +1046,8 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON 10AE5..10AE6 ; Diacritic # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW 10D22..10D23 ; Diacritic # Lo [2] HANIFI ROHINGYA MARK SAKIN..HANIFI ROHINGYA MARK NA KHONNA 10D24..10D27 ; Diacritic # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10D4E ; Diacritic # Lm GARAY VOWEL LENGTH MARK +10D69..10D6D ; Diacritic # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EFD..10EFF ; Diacritic # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Diacritic # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; Diacritic # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW @@ -1105,7 +1109,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON 1E944..1E946 ; Diacritic # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK 1E948..1E94A ; Diacritic # Mn [3] ADLAM CONSONANT MODIFIER..ADLAM NUKTA -# Total code points: 1144 +# Total code points: 1150 # ================================================ @@ -1134,6 +1138,9 @@ AADD ; Extender # Lm TAI VIET SYMBOL SAM AAF3..AAF4 ; Extender # Lm [2] MEETEI MAYEK SYLLABLE REPETITION MARK..MEETEI MAYEK WORD REPETITION MARK FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK 10781..10782 ; Extender # Lm [2] MODIFIER LETTER SUPERSCRIPT TRIANGULAR COLON..MODIFIER LETTER SUPERSCRIPT HALF TRIANGULAR COLON +10D4E ; Extender # Lm GARAY VOWEL LENGTH MARK +10D6A ; Extender # Mn GARAY CONSONANT GEMINATION MARK +10D6F ; Extender # Lm GARAY REDUPLICATION MARK 1135D ; Extender # Lo GRANTHA SIGN PLUTA 115C6..115C8 ; Extender # Po [3] SIDDHAM REPETITION MARK-1..SIDDHAM REPETITION MARK-3 11A98 ; Extender # Mn SOYOMBO GEMINATION MARK @@ -1143,7 +1150,7 @@ FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND 1E13C..1E13D ; Extender # Lm [2] NYIAKENG PUACHUE HMONG SIGN XW XW..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E944..1E946 ; Extender # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK -# Total code points: 50 +# Total code points: 53 # ================================================ diff --git a/unicodetools/data/ucd/dev/PropertyValueAliases.txt b/unicodetools/data/ucd/dev/PropertyValueAliases.txt index 9878b8548..82f13eefd 100644 --- a/unicodetools/data/ucd/dev/PropertyValueAliases.txt +++ b/unicodetools/data/ucd/dev/PropertyValueAliases.txt @@ -1,5 +1,5 @@ # PropertyValueAliases-16.0.0.txt -# Date: 2023-10-23, 11:34:11 GMT +# Date: 2023-10-23, 18:45:09 GMT # © 2023 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 @@ -258,6 +258,7 @@ blk; Ethiopic_Ext ; Ethiopic_Extended blk; Ethiopic_Ext_A ; Ethiopic_Extended_A blk; Ethiopic_Ext_B ; Ethiopic_Extended_B blk; Ethiopic_Sup ; Ethiopic_Supplement +blk; Garay ; Garay blk; Geometric_Shapes ; Geometric_Shapes blk; Geometric_Shapes_Ext ; Geometric_Shapes_Extended blk; Georgian ; Georgian @@ -1331,6 +1332,7 @@ sc ; Egyp ; Egyptian_Hieroglyphs sc ; Elba ; Elbasan sc ; Elym ; Elymaic sc ; Ethi ; Ethiopic +sc ; Gara ; Garay sc ; Geor ; Georgian sc ; Glag ; Glagolitic sc ; Gong ; Gunjala_Gondi diff --git a/unicodetools/data/ucd/dev/ScriptExtensions.txt b/unicodetools/data/ucd/dev/ScriptExtensions.txt index 23141fb82..99ae29159 100644 --- a/unicodetools/data/ucd/dev/ScriptExtensions.txt +++ b/unicodetools/data/ucd/dev/ScriptExtensions.txt @@ -1,5 +1,5 @@ -# ScriptExtensions-15.1.0.txt -# Date: 2023-02-01, 23:02:24 GMT +# ScriptExtensions-16.0.0.txt +# Date: 2023-10-09, 14:49:47 GMT # © 2023 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 @@ -497,15 +497,6 @@ FE45..FE46 ; Bopo Hang Hani Hira Kana # Po [2] SESAME DOT..WHITE SESAME DOT # ================================================ -# Script_Extensions=Arab Nkoo Rohg Syrc Thaa Yezi - -060C ; Arab Nkoo Rohg Syrc Thaa Yezi # Po ARABIC COMMA -061B ; Arab Nkoo Rohg Syrc Thaa Yezi # Po ARABIC SEMICOLON - -# Total code points: 2 - -# ================================================ - # Script_Extensions=Bopo Hang Hani Hira Kana Yiii 3001..3002 ; Bopo Hang Hani Hira Kana Yiii # Po [2] IDEOGRAPHIC COMMA..IDEOGRAPHIC FULL STOP @@ -545,9 +536,18 @@ FF64..FF65 ; Bopo Hang Hani Hira Kana Yiii # Po [2] HALFWIDTH IDEOGRAPHIC C # ================================================ -# Script_Extensions=Adlm Arab Nkoo Rohg Syrc Thaa Yezi +# Script_Extensions=Arab Gara Nkoo Rohg Syrc Thaa Yezi + +060C ; Arab Gara Nkoo Rohg Syrc Thaa Yezi # Po ARABIC COMMA +061B ; Arab Gara Nkoo Rohg Syrc Thaa Yezi # Po ARABIC SEMICOLON + +# Total code points: 2 + +# ================================================ + +# Script_Extensions=Adlm Arab Gara Nkoo Rohg Syrc Thaa Yezi -061F ; Adlm Arab Nkoo Rohg Syrc Thaa Yezi # Po ARABIC QUESTION MARK +061F ; Adlm Arab Gara Nkoo Rohg Syrc Thaa Yezi # Po ARABIC QUESTION MARK # Total code points: 1 diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index fe079ceba..9c32a15b9 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,5 +1,5 @@ # Scripts-16.0.0.txt -# Date: 2023-10-23, 11:34:29 GMT +# Date: 2023-10-23, 18:45:30 GMT # © 2023 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 @@ -3035,6 +3035,21 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI # ================================================ +10D40..10D49 ; Garay # Nd [10] GARAY DIGIT ZERO..GARAY DIGIT NINE +10D4A..10D4D ; Garay # Lo [4] GARAY VOWEL SIGN A..GARAY VOWEL SIGN EE +10D4E ; Garay # Lm GARAY VOWEL LENGTH MARK +10D4F ; Garay # Lo GARAY SUKUN +10D50..10D65 ; Garay # L& [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA +10D69..10D6D ; Garay # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK +10D6E ; Garay # Pd GARAY HYPHEN +10D6F ; Garay # Lm GARAY REDUPLICATION MARK +10D70..10D85 ; Garay # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA +10D8E..10D8F ; Garay # Sm [2] GARAY PLUS SIGN..GARAY MINUS SIGN + +# Total code points: 69 + +# ================================================ + 11BC0..11BE0 ; Sunuwar # Lo [33] SUNUWAR LETTER DEVI..SUNUWAR LETTER KLOKO 11BE1 ; Sunuwar # Po SUNUWAR SIGN PVO 11BF0..11BF9 ; Sunuwar # Nd [10] SUNUWAR DIGIT ZERO..SUNUWAR DIGIT NINE diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index f04fa52fd..c2c986b26 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -19379,6 +19379,75 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 10D37;HANIFI ROHINGYA DIGIT SEVEN;Nd;0;AN;;7;7;7;N;;;;; 10D38;HANIFI ROHINGYA DIGIT EIGHT;Nd;0;AN;;8;8;8;N;;;;; 10D39;HANIFI ROHINGYA DIGIT NINE;Nd;0;AN;;9;9;9;N;;;;; +10D40;GARAY DIGIT ZERO;Nd;0;AN;;0;0;0;N;;;;; +10D41;GARAY DIGIT ONE;Nd;0;AN;;1;1;1;N;;;;; +10D42;GARAY DIGIT TWO;Nd;0;AN;;2;2;2;N;;;;; +10D43;GARAY DIGIT THREE;Nd;0;AN;;3;3;3;N;;;;; +10D44;GARAY DIGIT FOUR;Nd;0;AN;;4;4;4;N;;;;; +10D45;GARAY DIGIT FIVE;Nd;0;AN;;5;5;5;N;;;;; +10D46;GARAY DIGIT SIX;Nd;0;AN;;6;6;6;N;;;;; +10D47;GARAY DIGIT SEVEN;Nd;0;AN;;7;7;7;N;;;;; +10D48;GARAY DIGIT EIGHT;Nd;0;AN;;8;8;8;N;;;;; +10D49;GARAY DIGIT NINE;Nd;0;AN;;9;9;9;N;;;;; +10D4A;GARAY VOWEL SIGN A;Lo;0;R;;;;;N;;;;; +10D4B;GARAY VOWEL SIGN I;Lo;0;R;;;;;N;;;;; +10D4C;GARAY VOWEL SIGN O;Lo;0;R;;;;;N;;;;; +10D4D;GARAY VOWEL SIGN EE;Lo;0;R;;;;;N;;;;; +10D4E;GARAY VOWEL LENGTH MARK;Lm;0;R;;;;;N;;;;; +10D4F;GARAY SUKUN;Lo;0;R;;;;;N;;;;; +10D50;GARAY CAPITAL LETTER A;Lu;0;R;;;;;N;;;;10D70; +10D51;GARAY CAPITAL LETTER CA;Lu;0;R;;;;;N;;;;10D71; +10D52;GARAY CAPITAL LETTER MA;Lu;0;R;;;;;N;;;;10D72; +10D53;GARAY CAPITAL LETTER KA;Lu;0;R;;;;;N;;;;10D73; +10D54;GARAY CAPITAL LETTER BA;Lu;0;R;;;;;N;;;;10D74; +10D55;GARAY CAPITAL LETTER JA;Lu;0;R;;;;;N;;;;10D75; +10D56;GARAY CAPITAL LETTER SA;Lu;0;R;;;;;N;;;;10D76; +10D57;GARAY CAPITAL LETTER WA;Lu;0;R;;;;;N;;;;10D77; +10D58;GARAY CAPITAL LETTER LA;Lu;0;R;;;;;N;;;;10D78; +10D59;GARAY CAPITAL LETTER GA;Lu;0;R;;;;;N;;;;10D79; +10D5A;GARAY CAPITAL LETTER DA;Lu;0;R;;;;;N;;;;10D7A; +10D5B;GARAY CAPITAL LETTER XA;Lu;0;R;;;;;N;;;;10D7B; +10D5C;GARAY CAPITAL LETTER YA;Lu;0;R;;;;;N;;;;10D7C; +10D5D;GARAY CAPITAL LETTER TA;Lu;0;R;;;;;N;;;;10D7D; +10D5E;GARAY CAPITAL LETTER RA;Lu;0;R;;;;;N;;;;10D7E; +10D5F;GARAY CAPITAL LETTER NYA;Lu;0;R;;;;;N;;;;10D7F; +10D60;GARAY CAPITAL LETTER FA;Lu;0;R;;;;;N;;;;10D80; +10D61;GARAY CAPITAL LETTER NA;Lu;0;R;;;;;N;;;;10D81; +10D62;GARAY CAPITAL LETTER PA;Lu;0;R;;;;;N;;;;10D82; +10D63;GARAY CAPITAL LETTER HA;Lu;0;R;;;;;N;;;;10D83; +10D64;GARAY CAPITAL LETTER OLD KA;Lu;0;R;;;;;N;;;;10D84; +10D65;GARAY CAPITAL LETTER OLD NA;Lu;0;R;;;;;N;;;;10D85; +10D69;GARAY VOWEL SIGN E;Mn;230;NSM;;;;;N;;;;; +10D6A;GARAY CONSONANT GEMINATION MARK;Mn;230;NSM;;;;;N;;;;; +10D6B;GARAY COMBINING DOT ABOVE;Mn;230;NSM;;;;;N;;;;; +10D6C;GARAY COMBINING DOUBLE DOT ABOVE;Mn;230;NSM;;;;;N;;;;; +10D6D;GARAY CONSONANT NASALIZATION MARK;Mn;230;NSM;;;;;N;;;;; +10D6E;GARAY HYPHEN;Pd;0;ON;;;;;N;;;;; +10D6F;GARAY REDUPLICATION MARK;Lm;0;R;;;;;N;;;;; +10D70;GARAY SMALL LETTER A;Ll;0;R;;;;;N;;;10D50;;10D50 +10D71;GARAY SMALL LETTER CA;Ll;0;R;;;;;N;;;10D51;;10D51 +10D72;GARAY SMALL LETTER MA;Ll;0;R;;;;;N;;;10D52;;10D52 +10D73;GARAY SMALL LETTER KA;Ll;0;R;;;;;N;;;10D53;;10D53 +10D74;GARAY SMALL LETTER BA;Ll;0;R;;;;;N;;;10D54;;10D54 +10D75;GARAY SMALL LETTER JA;Ll;0;R;;;;;N;;;10D55;;10D55 +10D76;GARAY SMALL LETTER SA;Ll;0;R;;;;;N;;;10D56;;10D56 +10D77;GARAY SMALL LETTER WA;Ll;0;R;;;;;N;;;10D57;;10D57 +10D78;GARAY SMALL LETTER LA;Ll;0;R;;;;;N;;;10D58;;10D58 +10D79;GARAY SMALL LETTER GA;Ll;0;R;;;;;N;;;10D59;;10D59 +10D7A;GARAY SMALL LETTER DA;Ll;0;R;;;;;N;;;10D5A;;10D5A +10D7B;GARAY SMALL LETTER XA;Ll;0;R;;;;;N;;;10D5B;;10D5B +10D7C;GARAY SMALL LETTER YA;Ll;0;R;;;;;N;;;10D5C;;10D5C +10D7D;GARAY SMALL LETTER TA;Ll;0;R;;;;;N;;;10D5D;;10D5D +10D7E;GARAY SMALL LETTER RA;Ll;0;R;;;;;N;;;10D5E;;10D5E +10D7F;GARAY SMALL LETTER NYA;Ll;0;R;;;;;N;;;10D5F;;10D5F +10D80;GARAY SMALL LETTER FA;Ll;0;R;;;;;N;;;10D60;;10D60 +10D81;GARAY SMALL LETTER NA;Ll;0;R;;;;;N;;;10D61;;10D61 +10D82;GARAY SMALL LETTER PA;Ll;0;R;;;;;N;;;10D62;;10D62 +10D83;GARAY SMALL LETTER HA;Ll;0;R;;;;;N;;;10D63;;10D63 +10D84;GARAY SMALL LETTER OLD KA;Ll;0;R;;;;;N;;;10D64;;10D64 +10D85;GARAY SMALL LETTER OLD NA;Ll;0;R;;;;;N;;;10D65;;10D65 +10D8E;GARAY PLUS SIGN;Sm;0;R;;;;;N;;;;; +10D8F;GARAY MINUS SIGN;Sm;0;R;;;;;N;;;;; 10E60;RUMI DIGIT ONE;No;0;AN;;;1;1;N;;;;; 10E61;RUMI DIGIT TWO;No;0;AN;;;2;2;N;;;;; 10E62;RUMI DIGIT THREE;No;0;AN;;;3;3;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index ac24b7df6..5b43d648e 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ # VerticalOrientation-16.0.0.txt -# Date: 2023-10-23, 11:34:31 GMT +# Date: 2023-10-23, 18:45:34 GMT # © 2023 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 @@ -1767,6 +1767,16 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 10D00..10D23 ; R # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA 10D24..10D27 ; R # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D30..10D39 ; R # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE +10D40..10D49 ; R # Nd [10] GARAY DIGIT ZERO..GARAY DIGIT NINE +10D4A..10D4D ; R # Lo [4] GARAY VOWEL SIGN A..GARAY VOWEL SIGN EE +10D4E ; R # Lm GARAY VOWEL LENGTH MARK +10D4F ; R # Lo GARAY SUKUN +10D50..10D65 ; R # Lu [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA +10D69..10D6D ; R # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK +10D6E ; R # Pd GARAY HYPHEN +10D6F ; R # Lm GARAY REDUPLICATION MARK +10D70..10D85 ; R # Ll [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA +10D8E..10D8F ; R # Sm [2] GARAY PLUS SIGN..GARAY MINUS SIGN 10E60..10E7E ; R # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS 10E80..10EA9 ; R # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EAB..10EAC ; R # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK diff --git a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt index 797d5c000..91bb0bd24 100644 --- a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt @@ -1,5 +1,5 @@ # GraphemeBreakProperty-16.0.0.txt -# Date: 2023-10-13, 11:29:23 GMT +# Date: 2023-10-23, 18:45:01 GMT # © 2023 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 @@ -324,6 +324,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 10A3F ; Extend # Mn KHAROSHTHI VIRAMA 10AE5..10AE6 ; Extend # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW 10D24..10D27 ; Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10D69..10D6D ; Extend # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EFC..10EFF ; Extend # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW @@ -459,7 +460,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2132 +# Total code points: 2137 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 54c8be3db..592650679 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ # SentenceBreakProperty-16.0.0.txt -# Date: 2023-10-17, 12:29:35 GMT +# Date: 2023-10-23, 18:45:31 GMT # © 2023 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 @@ -371,6 +371,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 10A3F ; Extend # Mn KHAROSHTHI VIRAMA 10AE5..10AE6 ; Extend # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW 10D24..10D27 ; Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10D69..10D6D ; Extend # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EFC..10EFF ; Extend # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW @@ -567,7 +568,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2552 +# Total code points: 2557 # ================================================ @@ -1262,6 +1263,7 @@ FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 10787..107B0 ; Lower # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK 107B2..107BA ; Lower # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10CC0..10CF2 ; Lower # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US +10D70..10D85 ; Lower # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA 118C0..118DF ; Lower # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E60..16E7F ; Lower # L& [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y 1D41A..1D433 ; Lower # L& [26] MATHEMATICAL BOLD SMALL A..MATHEMATICAL BOLD SMALL Z @@ -1298,7 +1300,7 @@ FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1E030..1E06D ; Lower # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E922..1E943 ; Lower # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2498 +# Total code points: 2520 # ================================================ @@ -1918,6 +1920,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 1058C..10592 ; Upper # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE 10594..10595 ; Upper # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE 10C80..10CB2 ; Upper # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US +10D50..10D65 ; Upper # L& [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA 118A0..118BF ; Upper # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 16E40..16E5F ; Upper # L& [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y 1D400..1D419 ; Upper # L& [26] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL BOLD CAPITAL Z @@ -1956,7 +1959,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 1F150..1F169 ; Upper # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Upper # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 1937 +# Total code points: 1959 # ================================================ @@ -2356,6 +2359,10 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10B80..10B91 ; OLetter # Lo [18] PSALTER PAHLAVI LETTER ALEPH..PSALTER PAHLAVI LETTER TAW 10C00..10C48 ; OLetter # Lo [73] OLD TURKIC LETTER ORKHON A..OLD TURKIC LETTER ORKHON BASH 10D00..10D23 ; OLetter # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA +10D4A..10D4D ; OLetter # Lo [4] GARAY VOWEL SIGN A..GARAY VOWEL SIGN EE +10D4E ; OLetter # Lm GARAY VOWEL LENGTH MARK +10D4F ; OLetter # Lo GARAY SUKUN +10D6F ; OLetter # Lm GARAY REDUPLICATION MARK 10E80..10EA9 ; OLetter # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EB0..10EB1 ; OLetter # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; OLetter # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW @@ -2541,7 +2548,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; OLetter # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; OLetter # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 132748 +# Total code points: 132755 # ================================================ @@ -2589,6 +2596,7 @@ ABF0..ABF9 ; Numeric # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT N FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 104A0..104A9 ; Numeric # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE 10D30..10D39 ; Numeric # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE +10D40..10D49 ; Numeric # Nd [10] GARAY DIGIT ZERO..GARAY DIGIT NINE 11066..1106F ; Numeric # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE 110BD ; Numeric # Cf KAITHI NUMBER SIGN 110CD ; Numeric # Cf KAITHI NUMBER SIGN ABOVE @@ -2619,7 +2627,7 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Numeric # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 724 +# Total code points: 734 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index f7b1418ea..fea8a243b 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-16.0.0.txt -# Date: 2023-10-17, 12:29:39 GMT +# Date: 2023-10-23, 18:45:34 GMT # © 2023 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 @@ -407,6 +407,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 10A3F ; Extend # Mn KHAROSHTHI VIRAMA 10AE5..10AE6 ; Extend # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW 10D24..10D27 ; Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10D69..10D6D ; Extend # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EFC..10EFF ; Extend # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW @@ -604,7 +605,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2556 +# Total code points: 2561 # ================================================ @@ -1114,6 +1115,12 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10C80..10CB2 ; ALetter # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 10CC0..10CF2 ; ALetter # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 10D00..10D23 ; ALetter # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA +10D4A..10D4D ; ALetter # Lo [4] GARAY VOWEL SIGN A..GARAY VOWEL SIGN EE +10D4E ; ALetter # Lm GARAY VOWEL LENGTH MARK +10D4F ; ALetter # Lo GARAY SUKUN +10D50..10D65 ; ALetter # L& [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA +10D6F ; ALetter # Lm GARAY REDUPLICATION MARK +10D70..10D85 ; ALetter # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA 10E80..10EA9 ; ALetter # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EB0..10EB1 ; ALetter # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; ALetter # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW @@ -1316,7 +1323,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1F150..1F169 ; ALetter # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; ALetter # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 29582 +# Total code points: 29633 # ================================================ @@ -1409,6 +1416,7 @@ ABF0..ABF9 ; Numeric # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT N FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 104A0..104A9 ; Numeric # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE 10D30..10D39 ; Numeric # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE +10D40..10D49 ; Numeric # Nd [10] GARAY DIGIT ZERO..GARAY DIGIT NINE 11066..1106F ; Numeric # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE 110BD ; Numeric # Cf KAITHI NUMBER SIGN 110CD ; Numeric # Cf KAITHI NUMBER SIGN ABOVE @@ -1439,7 +1447,7 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Numeric # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 723 +# Total code points: 733 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index aa56aeb63..c84daee40 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-16.0.0.txt -# Date: 2023-10-23, 11:33:55 GMT +# Date: 2023-10-23, 18:44:48 GMT # © 2023 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 @@ -84,6 +84,7 @@ # 10D00..10D3F Hanifi_Rohingya # @missing: 10D00..10D3F; Arabic_Letter +# 10D40..10D8F Garay # 10E60..10E7F Rumi_Numeral_Symbols # 10E80..10EBF Yezidi # @missing: 10D40..10EBF; Right_To_Left @@ -1275,6 +1276,13 @@ FB46..FB4F ; R # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE AL 10C80..10CB2 ; R # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 10CC0..10CF2 ; R # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 10CFA..10CFF ; R # No [6] OLD HUNGARIAN NUMBER ONE..OLD HUNGARIAN NUMBER ONE THOUSAND +10D4A..10D4D ; R # Lo [4] GARAY VOWEL SIGN A..GARAY VOWEL SIGN EE +10D4E ; R # Lm GARAY VOWEL LENGTH MARK +10D4F ; R # Lo GARAY SUKUN +10D50..10D65 ; R # L& [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA +10D6F ; R # Lm GARAY REDUPLICATION MARK +10D70..10D85 ; R # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA +10D8E..10D8F ; R # Sm [2] GARAY PLUS SIGN..GARAY MINUS SIGN 10E80..10EA9 ; R # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EAD ; R # Pd YEZIDI HYPHENATION MARK 10EB0..10EB1 ; R # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE @@ -1293,8 +1301,8 @@ FB46..FB4F ; R # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE AL 1E950..1E959 ; R # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1E95E..1E95F ; R # Po [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK -# The above property value applies to 2156 code points not listed here. -# Total code points: 3647 +# The above property value applies to 2087 code points not listed here. +# Total code points: 3631 # ================================================ @@ -1383,9 +1391,10 @@ FFE5..FFE6 ; ET # Sc [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN 0890..0891 ; AN # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE 08E2 ; AN # Cf ARABIC DISPUTED END OF AYAH 10D30..10D39 ; AN # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE +10D40..10D49 ; AN # Nd [10] GARAY DIGIT ZERO..GARAY DIGIT NINE 10E60..10E7E ; AN # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS -# Total code points: 63 +# Total code points: 73 # ================================================ @@ -1899,6 +1908,7 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE 101A0 ; ON # So GREEK SYMBOL TAU RHO 1091F ; ON # Po PHOENICIAN WORD SEPARATOR 10B39..10B3F ; ON # Po [7] AVESTAN ABBREVIATION MARK..LARGE ONE RING OVER TWO RINGS PUNCTUATION +10D6E ; ON # Pd GARAY HYPHEN 11052..11065 ; ON # No [20] BRAHMI NUMBER ONE..BRAHMI NUMBER ONE THOUSAND 11660..1166C ; ON # Po [13] MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT 11FD5..11FDC ; ON # So [8] TAMIL SIGN NEL..TAMIL SIGN MUKKURUNI @@ -1954,7 +1964,7 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE 1FB00..1FB92 ; ON # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; ON # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON -# Total code points: 6039 +# Total code points: 6040 # ================================================ @@ -2229,6 +2239,7 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 10A3F ; NSM # Mn KHAROSHTHI VIRAMA 10AE5..10AE6 ; NSM # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW 10D24..10D27 ; NSM # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10D69..10D6D ; NSM # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; NSM # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EFC..10EFF ; NSM # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; NSM # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW @@ -2354,7 +2365,7 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 1E944..1E94A ; NSM # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1995 +# Total code points: 2000 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index 46b3a8bdc..6073d7d68 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-16.0.0.txt -# Date: 2023-10-23, 11:33:57 GMT +# Date: 2023-10-23, 18:44:51 GMT # © 2023 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 @@ -1460,6 +1460,15 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 10CFA..10CFF ; 0 # No [6] OLD HUNGARIAN NUMBER ONE..OLD HUNGARIAN NUMBER ONE THOUSAND 10D00..10D23 ; 0 # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA 10D30..10D39 ; 0 # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE +10D40..10D49 ; 0 # Nd [10] GARAY DIGIT ZERO..GARAY DIGIT NINE +10D4A..10D4D ; 0 # Lo [4] GARAY VOWEL SIGN A..GARAY VOWEL SIGN EE +10D4E ; 0 # Lm GARAY VOWEL LENGTH MARK +10D4F ; 0 # Lo GARAY SUKUN +10D50..10D65 ; 0 # L& [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA +10D6E ; 0 # Pd GARAY HYPHEN +10D6F ; 0 # Lm GARAY REDUPLICATION MARK +10D70..10D85 ; 0 # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA +10D8E..10D8F ; 0 # Sm [2] GARAY PLUS SIGN..GARAY MINUS SIGN 10E60..10E7E ; 0 # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS 10E80..10EA9 ; 0 # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EAD ; 0 # Pd YEZIDI HYPHENATION MARK @@ -2013,8 +2022,8 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] .. 100000..10FFFD; 0 # Co [65534] .. -# The above property value applies to 826636 code points not listed here. -# Total code points: 1113189 +# The above property value applies to 826567 code points not listed here. +# Total code points: 1113184 # ================================================ @@ -2724,6 +2733,7 @@ FE2E..FE2F ; 230 # Mn [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBINING CYR 10A38 ; 230 # Mn KHAROSHTHI SIGN BAR ABOVE 10AE5 ; 230 # Mn MANICHAEAN ABBREVIATION MARK ABOVE 10D24..10D27 ; 230 # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10D69..10D6D ; 230 # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; 230 # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10F48..10F4A ; 230 # Mn [3] SOGDIAN COMBINING DOT ABOVE..SOGDIAN COMBINING CURVE ABOVE 10F4C ; 230 # Mn SOGDIAN COMBINING HOOK ABOVE @@ -2749,7 +2759,7 @@ FE2E..FE2F ; 230 # Mn [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBINING CYR 1E4EF ; 230 # Mn NAG MUNDARI SIGN SUTUH 1E944..1E949 ; 230 # Mn [6] ADLAM ALIF LENGTHENER..ADLAM GEMINATE CONSONANT MODIFIER -# Total code points: 511 +# Total code points: 516 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index 6c35d451f..a452d3406 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-16.0.0.txt -# Date: 2023-10-23, 11:33:59 GMT +# Date: 2023-10-23, 18:44:54 GMT # © 2023 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 @@ -1468,6 +1468,16 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 10D00..10D23 ; N # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA 10D24..10D27 ; N # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D30..10D39 ; N # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE +10D40..10D49 ; N # Nd [10] GARAY DIGIT ZERO..GARAY DIGIT NINE +10D4A..10D4D ; N # Lo [4] GARAY VOWEL SIGN A..GARAY VOWEL SIGN EE +10D4E ; N # Lm GARAY VOWEL LENGTH MARK +10D4F ; N # Lo GARAY SUKUN +10D50..10D65 ; N # L& [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA +10D69..10D6D ; N # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK +10D6E ; N # Pd GARAY HYPHEN +10D6F ; N # Lm GARAY REDUPLICATION MARK +10D70..10D85 ; N # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA +10D8E..10D8F ; N # Sm [2] GARAY PLUS SIGN..GARAY MINUS SIGN 10E60..10E7E ; N # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS 10E80..10EA9 ; N # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EAB..10EAC ; N # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK @@ -2050,7 +2060,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 766154 code points not listed here. +# The above property value applies to 766085 code points not listed here. # Total code points: 792618 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index 1fd4fcd76..5291e0f0c 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-16.0.0.txt -# Date: 2023-10-23, 11:33:59 GMT +# Date: 2023-10-23, 18:44:54 GMT # © 2023 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 @@ -432,7 +432,10 @@ FFFE..FFFF ; Cn # [2] .. 10CB3..10CBF ; Cn # [13] .. 10CF3..10CF9 ; Cn # [7] .. 10D28..10D2F ; Cn # [8] .. -10D3A..10E5F ; Cn # [294] .. +10D3A..10D3F ; Cn # [6] .. +10D66..10D68 ; Cn # [3] .. +10D86..10D8D ; Cn # [8] .. +10D90..10E5F ; Cn # [208] .. 10E7F ; Cn # 10EAA ; Cn # 10EAE..10EAF ; Cn # [2] .. @@ -729,7 +732,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 824588 +# Total code points: 824519 # ================================================ @@ -1348,6 +1351,7 @@ FF21..FF3A ; Lu # [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAP 1058C..10592 ; Lu # [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE 10594..10595 ; Lu # [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE 10C80..10CB2 ; Lu # [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US +10D50..10D65 ; Lu # [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA 118A0..118BF ; Lu # [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 16E40..16E5F ; Lu # [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y 1D400..1D419 ; Lu # [26] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL BOLD CAPITAL Z @@ -1383,7 +1387,7 @@ FF21..FF3A ; Lu # [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAP 1D7CA ; Lu # MATHEMATICAL BOLD CAPITAL DIGAMMA 1E900..1E921 ; Lu # [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA -# Total code points: 1832 +# Total code points: 1854 # ================================================ @@ -2014,6 +2018,7 @@ FF41..FF5A ; Ll # [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL 105B3..105B9 ; Ll # [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE 105BB..105BC ; Ll # [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10CC0..10CF2 ; Ll # [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US +10D70..10D85 ; Ll # [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA 118C0..118DF ; Ll # [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E60..16E7F ; Ll # [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y 1D41A..1D433 ; Ll # [26] MATHEMATICAL BOLD SMALL A..MATHEMATICAL BOLD SMALL Z @@ -2049,7 +2054,7 @@ FF41..FF5A ; Ll # [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL 1DF25..1DF2A ; Ll # [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK 1E922..1E943 ; Ll # [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2234 +# Total code points: 2256 # ================================================ @@ -2132,6 +2137,8 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 10780..10785 ; Lm # [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; Lm # [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK 107B2..107BA ; Lm # [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +10D4E ; Lm # GARAY VOWEL LENGTH MARK +10D6F ; Lm # GARAY REDUPLICATION MARK 16B40..16B43 ; Lm # [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM 16F93..16F9F ; Lm # [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 16FE0..16FE1 ; Lm # [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK @@ -2144,7 +2151,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 1E4EB ; Lm # NAG MUNDARI SIGN OJOD 1E94B ; Lm # ADLAM NASALIZATION MARK -# Total code points: 397 +# Total code points: 399 # ================================================ @@ -2491,6 +2498,8 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 10B80..10B91 ; Lo # [18] PSALTER PAHLAVI LETTER ALEPH..PSALTER PAHLAVI LETTER TAW 10C00..10C48 ; Lo # [73] OLD TURKIC LETTER ORKHON A..OLD TURKIC LETTER ORKHON BASH 10D00..10D23 ; Lo # [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA +10D4A..10D4D ; Lo # [4] GARAY VOWEL SIGN A..GARAY VOWEL SIGN EE +10D4F ; Lo # GARAY SUKUN 10E80..10EA9 ; Lo # [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EB0..10EB1 ; Lo # [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; Lo # [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW @@ -2665,7 +2674,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 30000..3134A ; Lo # [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Lo # [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 132324 +# Total code points: 132329 # ================================================ @@ -2893,6 +2902,7 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 10A3F ; Mn # KHAROSHTHI VIRAMA 10AE5..10AE6 ; Mn # [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW 10D24..10D27 ; Mn # [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10D69..10D6D ; Mn # [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; Mn # [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EFC..10EFF ; Mn # [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Mn # [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW @@ -3018,7 +3028,7 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 1E944..1E94A ; Mn # [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; Mn # [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1987 +# Total code points: 1992 # ================================================ @@ -3264,6 +3274,7 @@ ABF0..ABF9 ; Nd # [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE FF10..FF19 ; Nd # [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 104A0..104A9 ; Nd # [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE 10D30..10D39 ; Nd # [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE +10D40..10D49 ; Nd # [10] GARAY DIGIT ZERO..GARAY DIGIT NINE 11066..1106F ; Nd # [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE 110F0..110F9 ; Nd # [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE 11136..1113F ; Nd # [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE @@ -3292,7 +3303,7 @@ FF10..FF19 ; Nd # [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E950..1E959 ; Nd # [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Nd # [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 710 +# Total code points: 720 # ================================================ @@ -3499,9 +3510,10 @@ FE31..FE32 ; Pd # [2] PRESENTATION FORM FOR VERTICAL EM DASH..PRESENTATION FE58 ; Pd # SMALL EM DASH FE63 ; Pd # SMALL HYPHEN-MINUS FF0D ; Pd # FULLWIDTH HYPHEN-MINUS +10D6E ; Pd # GARAY HYPHEN 10EAD ; Pd # YEZIDI HYPHENATION MARK -# Total code points: 26 +# Total code points: 27 # ================================================ @@ -3937,6 +3949,7 @@ FF5C ; Sm # FULLWIDTH VERTICAL LINE FF5E ; Sm # FULLWIDTH TILDE FFE2 ; Sm # FULLWIDTH NOT SIGN FFE9..FFEC ; Sm # [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS ARROW +10D8E..10D8F ; Sm # [2] GARAY PLUS SIGN..GARAY MINUS SIGN 1D6C1 ; Sm # MATHEMATICAL BOLD NABLA 1D6DB ; Sm # MATHEMATICAL BOLD PARTIAL DIFFERENTIAL 1D6FB ; Sm # MATHEMATICAL ITALIC NABLA @@ -3949,7 +3962,7 @@ FFE9..FFEC ; Sm # [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS ARROW 1D7C3 ; Sm # MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL 1EEF0..1EEF1 ; Sm # [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL -# Total code points: 948 +# Total code points: 950 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt index ea82c725e..f18399146 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt @@ -1,5 +1,5 @@ # DerivedJoiningType-16.0.0.txt -# Date: 2023-10-13, 11:29:21 GMT +# Date: 2023-10-23, 18:44:56 GMT # © 2023 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 @@ -439,6 +439,7 @@ FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATI 10A3F ; T # Mn KHAROSHTHI VIRAMA 10AE5..10AE6 ; T # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW 10D24..10D27 ; T # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10D69..10D6D ; T # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; T # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EFC..10EFF ; T # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; T # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW @@ -570,6 +571,6 @@ E0001 ; T # Cf LANGUAGE TAG E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2152 +# Total code points: 2157 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 84d7fa20b..10c5055c3 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-16.0.0.txt -# Date: 2023-10-23, 11:34:00 GMT +# Date: 2023-10-23, 18:44:56 GMT # © 2023 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 @@ -68,8 +68,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 762596 code points not listed here. -# Total code points: 900064 +# The above property value applies to 762527 code points not listed here. +# Total code points: 899995 # ================================================ @@ -521,6 +521,7 @@ A9F0..A9F9 ; NU # Nd [10] MYANMAR TAI LAING DIGIT ZERO..MYANMAR TAI LAING DI ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 104A0..104A9 ; NU # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE 10D30..10D39 ; NU # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE +10D40..10D49 ; NU # Nd [10] GARAY DIGIT ZERO..GARAY DIGIT NINE 110BD ; NU # Cf KAITHI NUMBER SIGN 110CD ; NU # Cf KAITHI NUMBER SIGN ABOVE 110F0..110F9 ; NU # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE @@ -548,7 +549,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 1E950..1E959 ; NU # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; NU # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 654 +# Total code points: 664 # ================================================ @@ -1299,6 +1300,13 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 10CC0..10CF2 ; AL # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 10CFA..10CFF ; AL # No [6] OLD HUNGARIAN NUMBER ONE..OLD HUNGARIAN NUMBER ONE THOUSAND 10D00..10D23 ; AL # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA +10D4A..10D4D ; AL # Lo [4] GARAY VOWEL SIGN A..GARAY VOWEL SIGN EE +10D4E ; AL # Lm GARAY VOWEL LENGTH MARK +10D4F ; AL # Lo GARAY SUKUN +10D50..10D65 ; AL # L& [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA +10D6F ; AL # Lm GARAY REDUPLICATION MARK +10D70..10D85 ; AL # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA +10D8E..10D8F ; AL # Sm [2] GARAY PLUS SIGN..GARAY MINUS SIGN 10E60..10E7E ; AL # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS 10E80..10EA9 ; AL # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EB0..10EB1 ; AL # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE @@ -1588,7 +1596,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1FB00..1FB92 ; AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; AL # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON -# Total code points: 21827 +# Total code points: 21880 # ================================================ @@ -2153,6 +2161,7 @@ FFF9..FFFB ; CM # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTAT 10A3F ; CM # Mn KHAROSHTHI VIRAMA 10AE5..10AE6 ; CM # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW 10D24..10D27 ; CM # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10D69..10D6D ; CM # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; CM # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EFC..10EFF ; CM # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; CM # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW @@ -2344,7 +2353,7 @@ E0001 ; CM # Cf LANGUAGE TAG E0020..E007F ; CM # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; CM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2431 +# Total code points: 2436 # ================================================ @@ -2458,6 +2467,7 @@ ABEB ; BA # Po MEETEI MAYEK CHEIKHEI 10A50..10A57 ; BA # Po [8] KHAROSHTHI PUNCTUATION DOT..KHAROSHTHI PUNCTUATION DOUBLE DANDA 10AF0..10AF5 ; BA # Po [6] MANICHAEAN PUNCTUATION STAR..MANICHAEAN PUNCTUATION TWO DOTS 10B39..10B3F ; BA # Po [7] AVESTAN ABBREVIATION MARK..LARGE ONE RING OVER TWO RINGS PUNCTUATION +10D6E ; BA # Pd GARAY HYPHEN 10EAD ; BA # Pd YEZIDI HYPHENATION MARK 11047..11048 ; BA # Po [2] BRAHMI DANDA..BRAHMI DOUBLE DANDA 110BE..110C1 ; BA # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA @@ -2494,7 +2504,7 @@ ABEB ; BA # Po MEETEI MAYEK CHEIKHEI 1BC9F ; BA # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1DA87..1DA8A ; BA # Po [4] SIGNWRITING COMMA..SIGNWRITING COLON -# Total code points: 266 +# Total code points: 267 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 23b333a94..80307982a 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-16.0.0.txt -# Date: 2023-10-23, 11:34:01 GMT +# Date: 2023-10-23, 18:44:57 GMT # © 2023 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 @@ -30044,6 +30044,75 @@ FFFD ; REPLACEMENT CHARACTER 10D37 ; HANIFI ROHINGYA DIGIT SEVEN 10D38 ; HANIFI ROHINGYA DIGIT EIGHT 10D39 ; HANIFI ROHINGYA DIGIT NINE +10D40 ; GARAY DIGIT ZERO +10D41 ; GARAY DIGIT ONE +10D42 ; GARAY DIGIT TWO +10D43 ; GARAY DIGIT THREE +10D44 ; GARAY DIGIT FOUR +10D45 ; GARAY DIGIT FIVE +10D46 ; GARAY DIGIT SIX +10D47 ; GARAY DIGIT SEVEN +10D48 ; GARAY DIGIT EIGHT +10D49 ; GARAY DIGIT NINE +10D4A ; GARAY VOWEL SIGN A +10D4B ; GARAY VOWEL SIGN I +10D4C ; GARAY VOWEL SIGN O +10D4D ; GARAY VOWEL SIGN EE +10D4E ; GARAY VOWEL LENGTH MARK +10D4F ; GARAY SUKUN +10D50 ; GARAY CAPITAL LETTER A +10D51 ; GARAY CAPITAL LETTER CA +10D52 ; GARAY CAPITAL LETTER MA +10D53 ; GARAY CAPITAL LETTER KA +10D54 ; GARAY CAPITAL LETTER BA +10D55 ; GARAY CAPITAL LETTER JA +10D56 ; GARAY CAPITAL LETTER SA +10D57 ; GARAY CAPITAL LETTER WA +10D58 ; GARAY CAPITAL LETTER LA +10D59 ; GARAY CAPITAL LETTER GA +10D5A ; GARAY CAPITAL LETTER DA +10D5B ; GARAY CAPITAL LETTER XA +10D5C ; GARAY CAPITAL LETTER YA +10D5D ; GARAY CAPITAL LETTER TA +10D5E ; GARAY CAPITAL LETTER RA +10D5F ; GARAY CAPITAL LETTER NYA +10D60 ; GARAY CAPITAL LETTER FA +10D61 ; GARAY CAPITAL LETTER NA +10D62 ; GARAY CAPITAL LETTER PA +10D63 ; GARAY CAPITAL LETTER HA +10D64 ; GARAY CAPITAL LETTER OLD KA +10D65 ; GARAY CAPITAL LETTER OLD NA +10D69 ; GARAY VOWEL SIGN E +10D6A ; GARAY CONSONANT GEMINATION MARK +10D6B ; GARAY COMBINING DOT ABOVE +10D6C ; GARAY COMBINING DOUBLE DOT ABOVE +10D6D ; GARAY CONSONANT NASALIZATION MARK +10D6E ; GARAY HYPHEN +10D6F ; GARAY REDUPLICATION MARK +10D70 ; GARAY SMALL LETTER A +10D71 ; GARAY SMALL LETTER CA +10D72 ; GARAY SMALL LETTER MA +10D73 ; GARAY SMALL LETTER KA +10D74 ; GARAY SMALL LETTER BA +10D75 ; GARAY SMALL LETTER JA +10D76 ; GARAY SMALL LETTER SA +10D77 ; GARAY SMALL LETTER WA +10D78 ; GARAY SMALL LETTER LA +10D79 ; GARAY SMALL LETTER GA +10D7A ; GARAY SMALL LETTER DA +10D7B ; GARAY SMALL LETTER XA +10D7C ; GARAY SMALL LETTER YA +10D7D ; GARAY SMALL LETTER TA +10D7E ; GARAY SMALL LETTER RA +10D7F ; GARAY SMALL LETTER NYA +10D80 ; GARAY SMALL LETTER FA +10D81 ; GARAY SMALL LETTER NA +10D82 ; GARAY SMALL LETTER PA +10D83 ; GARAY SMALL LETTER HA +10D84 ; GARAY SMALL LETTER OLD KA +10D85 ; GARAY SMALL LETTER OLD NA +10D8E ; GARAY PLUS SIGN +10D8F ; GARAY MINUS SIGN 10E60 ; RUMI DIGIT ONE 10E61 ; RUMI DIGIT TWO 10E62 ; RUMI DIGIT THREE @@ -44306,6 +44375,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 149943 +# Total code points: 150012 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedNumericType.txt b/unicodetools/data/ucd/dev/extracted/DerivedNumericType.txt index edc53da78..438477313 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedNumericType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedNumericType.txt @@ -1,5 +1,5 @@ # DerivedNumericType-16.0.0.txt -# Date: 2023-10-17, 12:29:07 GMT +# Date: 2023-10-23, 18:44:59 GMT # © 2023 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 @@ -260,6 +260,7 @@ ABF0..ABF9 ; Decimal # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT N FF10..FF19 ; Decimal # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 104A0..104A9 ; Decimal # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE 10D30..10D39 ; Decimal # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE +10D40..10D49 ; Decimal # Nd [10] GARAY DIGIT ZERO..GARAY DIGIT NINE 11066..1106F ; Decimal # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE 110F0..110F9 ; Decimal # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE 11136..1113F ; Decimal # Nd [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE @@ -288,6 +289,6 @@ FF10..FF19 ; Decimal # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E950..1E959 ; Decimal # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Decimal # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 710 +# Total code points: 720 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedNumericValues.txt b/unicodetools/data/ucd/dev/extracted/DerivedNumericValues.txt index 88c117d56..c4bbab74b 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedNumericValues.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedNumericValues.txt @@ -1,5 +1,5 @@ # DerivedNumericValues-16.0.0.txt -# Date: 2023-10-17, 12:29:07 GMT +# Date: 2023-10-23, 18:45:00 GMT # © 2023 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 @@ -91,6 +91,7 @@ FF10 ; 0.0 ; ; 0 # Nd FULLWIDTH DIGIT ZERO 1018A ; 0.0 ; ; 0 # No GREEK ZERO SIGN 104A0 ; 0.0 ; ; 0 # Nd OSMANYA DIGIT ZERO 10D30 ; 0.0 ; ; 0 # Nd HANIFI ROHINGYA DIGIT ZERO +10D40 ; 0.0 ; ; 0 # Nd GARAY DIGIT ZERO 11066 ; 0.0 ; ; 0 # Nd BRAHMI DIGIT ZERO 110F0 ; 0.0 ; ; 0 # Nd SORA SOMPENG DIGIT ZERO 11136 ; 0.0 ; ; 0 # Nd CHAKMA DIGIT ZERO @@ -129,7 +130,7 @@ FF10 ; 0.0 ; ; 0 # Nd FULLWIDTH DIGIT ZERO 1F10B..1F10C ; 0.0 ; ; 0 # No [2] DINGBAT CIRCLED SANS-SERIF DIGIT ZERO..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO 1FBF0 ; 0.0 ; ; 0 # Nd SEGMENTED DIGIT ZERO -# Total code points: 91 +# Total code points: 92 # ================================================ @@ -499,6 +500,7 @@ FF11 ; 1.0 ; ; 1 # Nd FULLWIDTH DIGIT ONE 10BA9 ; 1.0 ; ; 1 # No PSALTER PAHLAVI NUMBER ONE 10CFA ; 1.0 ; ; 1 # No OLD HUNGARIAN NUMBER ONE 10D31 ; 1.0 ; ; 1 # Nd HANIFI ROHINGYA DIGIT ONE +10D41 ; 1.0 ; ; 1 # Nd GARAY DIGIT ONE 10E60 ; 1.0 ; ; 1 # No RUMI DIGIT ONE 10F1D ; 1.0 ; ; 1 # No OLD SOGDIAN NUMBER ONE 10F51 ; 1.0 ; ; 1 # No SOGDIAN NUMBER ONE @@ -559,7 +561,7 @@ FF11 ; 1.0 ; ; 1 # Nd FULLWIDTH DIGIT ONE 1FBF1 ; 1.0 ; ; 1 # Nd SEGMENTED DIGIT ONE 2092A ; 1.0 ; ; 1 # Lo CJK UNIFIED IDEOGRAPH-2092A -# Total code points: 147 +# Total code points: 148 # ================================================ @@ -653,6 +655,7 @@ FF12 ; 2.0 ; ; 2 # Nd FULLWIDTH DIGIT TWO 10B79 ; 2.0 ; ; 2 # No INSCRIPTIONAL PAHLAVI NUMBER TWO 10BAA ; 2.0 ; ; 2 # No PSALTER PAHLAVI NUMBER TWO 10D32 ; 2.0 ; ; 2 # Nd HANIFI ROHINGYA DIGIT TWO +10D42 ; 2.0 ; ; 2 # Nd GARAY DIGIT TWO 10E61 ; 2.0 ; ; 2 # No RUMI DIGIT TWO 10F1E ; 2.0 ; ; 2 # No OLD SOGDIAN NUMBER TWO 10FC6 ; 2.0 ; ; 2 # No CHORASMIAN NUMBER TWO @@ -716,7 +719,7 @@ FF12 ; 2.0 ; ; 2 # Nd FULLWIDTH DIGIT TWO 1FBF2 ; 2.0 ; ; 2 # Nd SEGMENTED DIGIT TWO 22390 ; 2.0 ; ; 2 # Lo CJK UNIFIED IDEOGRAPH-22390 -# Total code points: 149 +# Total code points: 150 # ================================================ @@ -801,6 +804,7 @@ FF13 ; 3.0 ; ; 3 # Nd FULLWIDTH DIGIT THREE 10B7A ; 3.0 ; ; 3 # No INSCRIPTIONAL PAHLAVI NUMBER THREE 10BAB ; 3.0 ; ; 3 # No PSALTER PAHLAVI NUMBER THREE 10D33 ; 3.0 ; ; 3 # Nd HANIFI ROHINGYA DIGIT THREE +10D43 ; 3.0 ; ; 3 # Nd GARAY DIGIT THREE 10E62 ; 3.0 ; ; 3 # No RUMI DIGIT THREE 10F1F ; 3.0 ; ; 3 # No OLD SOGDIAN NUMBER THREE 10FC7 ; 3.0 ; ; 3 # No CHORASMIAN NUMBER THREE @@ -867,7 +871,7 @@ FF13 ; 3.0 ; ; 3 # Nd FULLWIDTH DIGIT THREE 22998 ; 3.0 ; ; 3 # Lo CJK UNIFIED IDEOGRAPH-22998 23B1B ; 3.0 ; ; 3 # Lo CJK UNIFIED IDEOGRAPH-23B1B -# Total code points: 147 +# Total code points: 148 # ================================================ @@ -946,6 +950,7 @@ FF14 ; 4.0 ; ; 4 # Nd FULLWIDTH DIGIT FOUR 10B7B ; 4.0 ; ; 4 # No INSCRIPTIONAL PAHLAVI NUMBER FOUR 10BAC ; 4.0 ; ; 4 # No PSALTER PAHLAVI NUMBER FOUR 10D34 ; 4.0 ; ; 4 # Nd HANIFI ROHINGYA DIGIT FOUR +10D44 ; 4.0 ; ; 4 # Nd GARAY DIGIT FOUR 10E63 ; 4.0 ; ; 4 # No RUMI DIGIT FOUR 10F20 ; 4.0 ; ; 4 # No OLD SOGDIAN NUMBER FOUR 10FC8 ; 4.0 ; ; 4 # No CHORASMIAN NUMBER FOUR @@ -1011,7 +1016,7 @@ FF14 ; 4.0 ; ; 4 # Nd FULLWIDTH DIGIT FOUR 200E2 ; 4.0 ; ; 4 # Lo CJK UNIFIED IDEOGRAPH-200E2 2626D ; 4.0 ; ; 4 # Lo CJK UNIFIED IDEOGRAPH-2626D -# Total code points: 138 +# Total code points: 139 # ================================================ @@ -1095,6 +1100,7 @@ FF15 ; 5.0 ; ; 5 # Nd FULLWIDTH DIGIT FIVE 10AEC ; 5.0 ; ; 5 # No MANICHAEAN NUMBER FIVE 10CFB ; 5.0 ; ; 5 # No OLD HUNGARIAN NUMBER FIVE 10D35 ; 5.0 ; ; 5 # Nd HANIFI ROHINGYA DIGIT FIVE +10D45 ; 5.0 ; ; 5 # Nd GARAY DIGIT FIVE 10E64 ; 5.0 ; ; 5 # No RUMI DIGIT FIVE 10F21 ; 5.0 ; ; 5 # No OLD SOGDIAN NUMBER FIVE 11056 ; 5.0 ; ; 5 # No BRAHMI NUMBER FIVE @@ -1157,7 +1163,7 @@ FF15 ; 5.0 ; ; 5 # Nd FULLWIDTH DIGIT FIVE 1FBF5 ; 5.0 ; ; 5 # Nd SEGMENTED DIGIT FIVE 20121 ; 5.0 ; ; 5 # Lo CJK UNIFIED IDEOGRAPH-20121 -# Total code points: 136 +# Total code points: 137 # ================================================ @@ -1232,6 +1238,7 @@ FF16 ; 6.0 ; ; 6 # Nd FULLWIDTH DIGIT SIX 104A6 ; 6.0 ; ; 6 # Nd OSMANYA DIGIT SIX 109C5 ; 6.0 ; ; 6 # No MEROITIC CURSIVE NUMBER SIX 10D36 ; 6.0 ; ; 6 # Nd HANIFI ROHINGYA DIGIT SIX +10D46 ; 6.0 ; ; 6 # Nd GARAY DIGIT SIX 10E65 ; 6.0 ; ; 6 # No RUMI DIGIT SIX 11057 ; 6.0 ; ; 6 # No BRAHMI NUMBER SIX 1106C ; 6.0 ; ; 6 # Nd BRAHMI DIGIT SIX @@ -1288,7 +1295,7 @@ FF16 ; 6.0 ; ; 6 # Nd FULLWIDTH DIGIT SIX 1FBF6 ; 6.0 ; ; 6 # Nd SEGMENTED DIGIT SIX 20AEA ; 6.0 ; ; 6 # Lo CJK UNIFIED IDEOGRAPH-20AEA -# Total code points: 120 +# Total code points: 121 # ================================================ @@ -1362,6 +1369,7 @@ FF17 ; 7.0 ; ; 7 # Nd FULLWIDTH DIGIT SEVEN 104A7 ; 7.0 ; ; 7 # Nd OSMANYA DIGIT SEVEN 109C6 ; 7.0 ; ; 7 # No MEROITIC CURSIVE NUMBER SEVEN 10D37 ; 7.0 ; ; 7 # Nd HANIFI ROHINGYA DIGIT SEVEN +10D47 ; 7.0 ; ; 7 # Nd GARAY DIGIT SEVEN 10E66 ; 7.0 ; ; 7 # No RUMI DIGIT SEVEN 11058 ; 7.0 ; ; 7 # No BRAHMI NUMBER SEVEN 1106D ; 7.0 ; ; 7 # Nd BRAHMI DIGIT SEVEN @@ -1417,7 +1425,7 @@ FF17 ; 7.0 ; ; 7 # Nd FULLWIDTH DIGIT SEVEN 1FBF7 ; 7.0 ; ; 7 # Nd SEGMENTED DIGIT SEVEN 20001 ; 7.0 ; ; 7 # Lo CJK UNIFIED IDEOGRAPH-20001 -# Total code points: 120 +# Total code points: 121 # ================================================ @@ -1488,6 +1496,7 @@ FF18 ; 8.0 ; ; 8 # Nd FULLWIDTH DIGIT EIGHT 104A8 ; 8.0 ; ; 8 # Nd OSMANYA DIGIT EIGHT 109C7 ; 8.0 ; ; 8 # No MEROITIC CURSIVE NUMBER EIGHT 10D38 ; 8.0 ; ; 8 # Nd HANIFI ROHINGYA DIGIT EIGHT +10D48 ; 8.0 ; ; 8 # Nd GARAY DIGIT EIGHT 10E67 ; 8.0 ; ; 8 # No RUMI DIGIT EIGHT 11059 ; 8.0 ; ; 8 # No BRAHMI NUMBER EIGHT 1106E ; 8.0 ; ; 8 # Nd BRAHMI DIGIT EIGHT @@ -1542,7 +1551,7 @@ FF18 ; 8.0 ; ; 8 # Nd FULLWIDTH DIGIT EIGHT 1F109 ; 8.0 ; ; 8 # No DIGIT EIGHT COMMA 1FBF8 ; 8.0 ; ; 8 # Nd SEGMENTED DIGIT EIGHT -# Total code points: 115 +# Total code points: 116 # ================================================ @@ -1616,6 +1625,7 @@ FF19 ; 9.0 ; ; 9 # Nd FULLWIDTH DIGIT NINE 104A9 ; 9.0 ; ; 9 # Nd OSMANYA DIGIT NINE 109C8 ; 9.0 ; ; 9 # No MEROITIC CURSIVE NUMBER NINE 10D39 ; 9.0 ; ; 9 # Nd HANIFI ROHINGYA DIGIT NINE +10D49 ; 9.0 ; ; 9 # Nd GARAY DIGIT NINE 10E68 ; 9.0 ; ; 9 # No RUMI DIGIT NINE 1105A ; 9.0 ; ; 9 # No BRAHMI NUMBER NINE 1106F ; 9.0 ; ; 9 # Nd BRAHMI DIGIT NINE @@ -1671,7 +1681,7 @@ FF19 ; 9.0 ; ; 9 # Nd FULLWIDTH DIGIT NINE 1FBF9 ; 9.0 ; ; 9 # Nd SEGMENTED DIGIT NINE 2F890 ; 9.0 ; ; 9 # Lo CJK COMPATIBILITY IDEOGRAPH-2F890 -# Total code points: 121 +# Total code points: 122 # ================================================ diff --git a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java index dcf634227..7bfd6bb67 100644 --- a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java +++ b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java @@ -283,6 +283,7 @@ public enum Block_Values implements Named { Ethiopic_Extended_A("Ethiopic_Ext_A"), Ethiopic_Extended_B("Ethiopic_Ext_B"), Ethiopic_Supplement("Ethiopic_Sup"), + Garay("Garay"), Geometric_Shapes("Geometric_Shapes"), Geometric_Shapes_Extended("Geometric_Shapes_Ext"), Georgian("Georgian"), @@ -1740,6 +1741,7 @@ public enum Script_Values implements Named { Elbasan("Elba"), Elymaic("Elym"), Ethiopic("Ethi"), + Garay("Gara"), Georgian("Geor"), Glagolitic("Glag"), Gunjala_Gondi("Gong"), diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt index fbe76d410..d41ec1c0d 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt @@ -106,6 +106,7 @@ Ethiopic_Ext_A ; Ethiopic_Extended_A Ethiopic_Ext_B ; Ethiopic_Extended_B Ethiopic_Sup ; Ethiopic_Supplement Punctuation ; General_Punctuation +Garay ; Garay Geometric_Shapes ; Geometric_Shapes Geometric_Shapes_Ext ; Geometric_Shapes_Extended Georgian ; Georgian