diff --git a/unicodetools/data/ucd/dev/Blocks.txt b/unicodetools/data/ucd/dev/Blocks.txt index f22f50480b..6dcbf10c7f 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 @@ -311,6 +312,7 @@ FFF0..FFFF; Specials 1B170..1B2FF; Nushu 1BC00..1BC9F; Duployan 1BCA0..1BCAF; Shorthand Format Controls +1CC00..1CEBF; Symbols for Legacy Computing Supplement 1CF00..1CFCF; Znamenny Musical Notation 1D000..1D0FF; Byzantine Musical Symbols 1D100..1D1FF; Musical Symbols diff --git a/unicodetools/data/ucd/dev/CaseFolding.txt b/unicodetools/data/ucd/dev/CaseFolding.txt index ba43df3ece..50c19fe788 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: 2023-10-24, 18:13:17 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 @@ -1241,6 +1241,8 @@ A7C5; C; 0282; # LATIN CAPITAL LETTER S WITH HOOK A7C6; C; 1D8E; # LATIN CAPITAL LETTER Z WITH PALATAL HOOK A7C7; C; A7C8; # LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9; C; A7CA; # LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7CB; C; 0264; # LATIN CAPITAL LETTER RAMS HORN +A7CC; C; A7CD; # LATIN CAPITAL LETTER S WITH DIAGONAL STROKE A7D0; C; A7D1; # LATIN CAPITAL LETTER CLOSED INSULAR G A7D6; C; A7D7; # LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8; C; A7D9; # LATIN CAPITAL LETTER SIGMOID S @@ -1526,6 +1528,28 @@ 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 7b88d70432..58fde1821f 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, 13:16:27 GMT +# Date: 2023-10-24, 18:13:19 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 @@ -2013,15 +2013,19 @@ FDFE..FDFF ; 14.0 # [2] ARABIC LIGATURE SUBHAANAHU WA TAAALAA..ARABIC LIGAT 0C5C ; 16.0 # TELUGU ARCHAIC SHRII 0CDC ; 16.0 # KANNADA ARCHAIC SHRII 1C89..1C8A ; 16.0 # [2] CYRILLIC CAPITAL LETTER TJE..CYRILLIC SMALL LETTER TJE +A7CB..A7CD ; 16.0 # [3] LATIN CAPITAL LETTER RAMS HORN..LATIN SMALL LETTER S WITH DIAGONAL STROKE 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 11BC0..11BE1 ; 16.0 # [34] SUNUWAR LETTER DEVI..SUNUWAR SIGN PVO 11BF0..11BF9 ; 16.0 # [10] SUNUWAR DIGIT ZERO..SUNUWAR DIGIT NINE -1E5D0..1E5FA ; 16.0 # [43] OL ONAL LETTER O..OL ONAL DIGIT NINE -1E5FF ; 16.0 # OL ONAL ABBREVIATION SIGN +1CEB0..1CEB3 ; 16.0 # [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET +1F8B2 ; 16.0 # RIGHTWARDS ARROW WITH LOWER HOOK -# Total code points: 169 +# Total code points: 202 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 35f05ddec9..ed911b6ad1 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, 13:16:58 GMT +# Date: 2023-10-24, 18:13:41 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 # ================================================ @@ -831,7 +832,7 @@ A771..A787 ; Alphabetic # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER A788 ; Alphabetic # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; Alphabetic # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; Alphabetic # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CA ; Alphabetic # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CD ; Alphabetic # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE A7D0..A7D1 ; Alphabetic # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; Alphabetic # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7D9 ; Alphabetic # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S @@ -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 @@ -1353,8 +1361,6 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 1E2C0..1E2EB ; Alphabetic # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E4D0..1E4EA ; Alphabetic # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL 1E4EB ; Alphabetic # Lm NAG MUNDARI SIGN OJOD -1E5D0..1E5ED ; Alphabetic # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG -1E5F0 ; Alphabetic # Lo OL ONAL SIGN HODDOND 1E7E0..1E7E6 ; Alphabetic # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; Alphabetic # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; Alphabetic # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -1409,7 +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: 138512 +# Total code points: 138536 # ================================================ @@ -2040,6 +2046,7 @@ A7C1 ; Lowercase # L& LATIN SMALL LETTER OLD POLISH O A7C3 ; Lowercase # L& LATIN SMALL LETTER ANGLICANA W A7C8 ; Lowercase # L& LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7CA ; Lowercase # L& LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7CD ; Lowercase # L& LATIN SMALL LETTER S WITH DIAGONAL STROKE A7D1 ; Lowercase # L& LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; Lowercase # L& LATIN SMALL LETTER DOUBLE THORN A7D5 ; Lowercase # L& LATIN SMALL LETTER DOUBLE WYNN @@ -2068,6 +2075,7 @@ 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 @@ -2104,7 +2112,7 @@ 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: 2568 # ================================================ @@ -2714,6 +2722,7 @@ A7C0 ; Uppercase # L& LATIN CAPITAL LETTER OLD POLISH O A7C2 ; Uppercase # L& LATIN CAPITAL LETTER ANGLICANA W A7C4..A7C7 ; Uppercase # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Uppercase # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7CB..A7CC ; Uppercase # L& [2] LATIN CAPITAL LETTER RAMS HORN..LATIN CAPITAL LETTER S WITH DIAGONAL STROKE A7D0 ; Uppercase # L& LATIN CAPITAL LETTER CLOSED INSULAR G A7D6 ; Uppercase # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Uppercase # L& LATIN CAPITAL LETTER SIGMOID S @@ -2726,6 +2735,7 @@ 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 @@ -2764,7 +2774,7 @@ 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: 1976 # ================================================ @@ -2872,7 +2882,7 @@ A722..A76F ; Cased # L& [78] LATIN CAPITAL LETTER EGYPTOLOGICAL ALEF..LATIN A770 ; Cased # Lm MODIFIER LETTER US A771..A787 ; Cased # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T A78B..A78E ; Cased # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT -A790..A7CA ; Cased # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CD ; Cased # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE A7D0..A7D1 ; Cased # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; Cased # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7D9 ; Cased # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S @@ -2906,6 +2916,8 @@ 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 @@ -2947,7 +2959,7 @@ 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: 4575 # ================================================ @@ -3305,6 +3317,9 @@ 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 @@ -3441,7 +3456,6 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 1E2EC..1E2EF ; Case_Ignorable # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E4EB ; Case_Ignorable # Lm NAG MUNDARI SIGN OJOD 1E4EC..1E4EF ; Case_Ignorable # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH -1E5EE..1E5EF ; Case_Ignorable # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E8D0..1E8D6 ; Case_Ignorable # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Case_Ignorable # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA 1E94B ; Case_Ignorable # Lm ADLAM NASALIZATION MARK @@ -3450,7 +3464,7 @@ 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: 2711 +# Total code points: 2716 # ================================================ @@ -4054,6 +4068,7 @@ A7C0 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER OLD POLI A7C2 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER ANGLICANA W A7C4..A7C7 ; Changes_When_Lowercased # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7CB..A7CC ; Changes_When_Lowercased # L& [2] LATIN CAPITAL LETTER RAMS HORN..LATIN CAPITAL LETTER S WITH DIAGONAL STROKE A7D0 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER CLOSED INSULAR G A7D6 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER SIGMOID S @@ -4066,11 +4081,12 @@ 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: 1458 # ================================================ @@ -4227,8 +4243,7 @@ FF21..FF3A ; Changes_When_Lowercased # L& [26] FULLWIDTH LATIN CAPITAL LETTE 0259 ; Changes_When_Uppercased # L& LATIN SMALL LETTER SCHWA 025B..025C ; Changes_When_Uppercased # L& [2] LATIN SMALL LETTER OPEN E..LATIN SMALL LETTER REVERSED OPEN E 0260..0261 ; Changes_When_Uppercased # L& [2] LATIN SMALL LETTER G WITH HOOK..LATIN SMALL LETTER SCRIPT G -0263 ; Changes_When_Uppercased # L& LATIN SMALL LETTER GAMMA -0265..0266 ; Changes_When_Uppercased # L& [2] LATIN SMALL LETTER TURNED H..LATIN SMALL LETTER H WITH HOOK +0263..0266 ; Changes_When_Uppercased # L& [4] LATIN SMALL LETTER GAMMA..LATIN SMALL LETTER H WITH HOOK 0268..026C ; Changes_When_Uppercased # L& [5] LATIN SMALL LETTER I WITH STROKE..LATIN SMALL LETTER L WITH BELT 026F ; Changes_When_Uppercased # L& LATIN SMALL LETTER TURNED M 0271..0272 ; Changes_When_Uppercased # L& [2] LATIN SMALL LETTER M WITH HOOK..LATIN SMALL LETTER N WITH LEFT HOOK @@ -4688,6 +4703,7 @@ A7C1 ; Changes_When_Uppercased # L& LATIN SMALL LETTER OLD POLISH A7C3 ; Changes_When_Uppercased # L& LATIN SMALL LETTER ANGLICANA W A7C8 ; Changes_When_Uppercased # L& LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7CA ; Changes_When_Uppercased # L& LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7CD ; Changes_When_Uppercased # L& LATIN SMALL LETTER S WITH DIAGONAL STROKE A7D1 ; Changes_When_Uppercased # L& LATIN SMALL LETTER CLOSED INSULAR G A7D7 ; Changes_When_Uppercased # L& LATIN SMALL LETTER MIDDLE SCOTS S A7D9 ; Changes_When_Uppercased # L& LATIN SMALL LETTER SIGMOID S @@ -4704,11 +4720,12 @@ 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: 1550 # ================================================ @@ -4866,8 +4883,7 @@ FF41..FF5A ; Changes_When_Uppercased # L& [26] FULLWIDTH LATIN SMALL LETTER 0259 ; Changes_When_Titlecased # L& LATIN SMALL LETTER SCHWA 025B..025C ; Changes_When_Titlecased # L& [2] LATIN SMALL LETTER OPEN E..LATIN SMALL LETTER REVERSED OPEN E 0260..0261 ; Changes_When_Titlecased # L& [2] LATIN SMALL LETTER G WITH HOOK..LATIN SMALL LETTER SCRIPT G -0263 ; Changes_When_Titlecased # L& LATIN SMALL LETTER GAMMA -0265..0266 ; Changes_When_Titlecased # L& [2] LATIN SMALL LETTER TURNED H..LATIN SMALL LETTER H WITH HOOK +0263..0266 ; Changes_When_Titlecased # L& [4] LATIN SMALL LETTER GAMMA..LATIN SMALL LETTER H WITH HOOK 0268..026C ; Changes_When_Titlecased # L& [5] LATIN SMALL LETTER I WITH STROKE..LATIN SMALL LETTER L WITH BELT 026F ; Changes_When_Titlecased # L& LATIN SMALL LETTER TURNED M 0271..0272 ; Changes_When_Titlecased # L& [2] LATIN SMALL LETTER M WITH HOOK..LATIN SMALL LETTER N WITH LEFT HOOK @@ -5325,6 +5341,7 @@ A7C1 ; Changes_When_Titlecased # L& LATIN SMALL LETTER OLD POLISH A7C3 ; Changes_When_Titlecased # L& LATIN SMALL LETTER ANGLICANA W A7C8 ; Changes_When_Titlecased # L& LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7CA ; Changes_When_Titlecased # L& LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7CD ; Changes_When_Titlecased # L& LATIN SMALL LETTER S WITH DIAGONAL STROKE A7D1 ; Changes_When_Titlecased # L& LATIN SMALL LETTER CLOSED INSULAR G A7D7 ; Changes_When_Titlecased # L& LATIN SMALL LETTER MIDDLE SCOTS S A7D9 ; Changes_When_Titlecased # L& LATIN SMALL LETTER SIGMOID S @@ -5341,11 +5358,12 @@ 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: 1477 # ================================================ @@ -5958,6 +5976,7 @@ A7C0 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER OLD POLI A7C2 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER ANGLICANA W A7C4..A7C7 ; Changes_When_Casefolded # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7CB..A7CC ; Changes_When_Casefolded # L& [2] LATIN CAPITAL LETTER RAMS HORN..LATIN CAPITAL LETTER S WITH DIAGONAL STROKE A7D0 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER CLOSED INSULAR G A7D6 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER SIGMOID S @@ -5973,11 +5992,12 @@ 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: 1531 # ================================================ @@ -6005,8 +6025,7 @@ FF21..FF3A ; Changes_When_Casefolded # L& [26] FULLWIDTH LATIN CAPITAL LETTE 0259 ; Changes_When_Casemapped # L& LATIN SMALL LETTER SCHWA 025B..025C ; Changes_When_Casemapped # L& [2] LATIN SMALL LETTER OPEN E..LATIN SMALL LETTER REVERSED OPEN E 0260..0261 ; Changes_When_Casemapped # L& [2] LATIN SMALL LETTER G WITH HOOK..LATIN SMALL LETTER SCRIPT G -0263 ; Changes_When_Casemapped # L& LATIN SMALL LETTER GAMMA -0265..0266 ; Changes_When_Casemapped # L& [2] LATIN SMALL LETTER TURNED H..LATIN SMALL LETTER H WITH HOOK +0263..0266 ; Changes_When_Casemapped # L& [4] LATIN SMALL LETTER GAMMA..LATIN SMALL LETTER H WITH HOOK 0268..026C ; Changes_When_Casemapped # L& [5] LATIN SMALL LETTER I WITH STROKE..LATIN SMALL LETTER L WITH BELT 026F ; Changes_When_Casemapped # L& LATIN SMALL LETTER TURNED M 0271..0272 ; Changes_When_Casemapped # L& [2] LATIN SMALL LETTER M WITH HOOK..LATIN SMALL LETTER N WITH LEFT HOOK @@ -6091,7 +6110,7 @@ A779..A787 ; Changes_When_Casemapped # L& [15] LATIN CAPITAL LETTER INSULAR A78B..A78D ; Changes_When_Casemapped # L& [3] LATIN CAPITAL LETTER SALTILLO..LATIN CAPITAL LETTER TURNED H A790..A794 ; Changes_When_Casemapped # L& [5] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER C WITH PALATAL HOOK A796..A7AE ; Changes_When_Casemapped # L& [25] LATIN CAPITAL LETTER B WITH FLOURISH..LATIN CAPITAL LETTER SMALL CAPITAL I -A7B0..A7CA ; Changes_When_Casemapped # L& [27] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7B0..A7CD ; Changes_When_Casemapped # L& [30] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER S WITH DIAGONAL STROKE A7D0..A7D1 ; Changes_When_Casemapped # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G A7D6..A7D9 ; Changes_When_Casemapped # L& [4] LATIN CAPITAL LETTER MIDDLE SCOTS S..LATIN SMALL LETTER SIGMOID S A7F5..A7F6 ; Changes_When_Casemapped # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H @@ -6114,11 +6133,13 @@ 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: 2977 # ================================================ @@ -6494,7 +6515,7 @@ A771..A787 ; ID_Start # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER I A788 ; ID_Start # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; ID_Start # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ID_Start # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CA ; ID_Start # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CD ; ID_Start # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE A7D0..A7D1 ; ID_Start # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; ID_Start # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7D9 ; ID_Start # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S @@ -6653,6 +6674,12 @@ 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 @@ -6825,8 +6852,6 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1E2C0..1E2EB ; ID_Start # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E4D0..1E4EA ; ID_Start # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL 1E4EB ; ID_Start # Lm NAG MUNDARI SIGN OJOD -1E5D0..1E5ED ; ID_Start # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG -1E5F0 ; ID_Start # Lo OL ONAL SIGN HODDOND 1E7E0..1E7E6 ; ID_Start # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; ID_Start # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; ID_Start # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -6877,7 +6902,7 @@ 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: 137090 +# Total code points: 137113 # ================================================ @@ -7561,7 +7586,7 @@ A771..A787 ; ID_Continue # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTE A788 ; ID_Continue # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; ID_Continue # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ID_Continue # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CA ; ID_Continue # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CD ; ID_Continue # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE A7D0..A7D1 ; ID_Continue # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; ID_Continue # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7D9 ; ID_Continue # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S @@ -7798,6 +7823,14 @@ 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 @@ -8186,10 +8219,6 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 1E4EB ; ID_Continue # Lm NAG MUNDARI SIGN OJOD 1E4EC..1E4EF ; ID_Continue # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH 1E4F0..1E4F9 ; ID_Continue # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE -1E5D0..1E5ED ; ID_Continue # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG -1E5EE..1E5EF ; ID_Continue # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR -1E5F0 ; ID_Continue # Lo OL ONAL SIGN HODDOND -1E5F1..1E5FA ; ID_Continue # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE 1E7E0..1E7E6 ; ID_Continue # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; ID_Continue # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; ID_Continue # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -8245,7 +8274,7 @@ 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: 140275 +# Total code points: 140301 # ================================================ @@ -8617,7 +8646,7 @@ A771..A787 ; XID_Start # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER A788 ; XID_Start # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; XID_Start # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; XID_Start # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CA ; XID_Start # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CD ; XID_Start # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE A7D0..A7D1 ; XID_Start # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; XID_Start # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7D9 ; XID_Start # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S @@ -8781,6 +8810,12 @@ 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 @@ -8953,8 +8988,6 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1E2C0..1E2EB ; XID_Start # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E4D0..1E4EA ; XID_Start # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL 1E4EB ; XID_Start # Lm NAG MUNDARI SIGN OJOD -1E5D0..1E5ED ; XID_Start # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG -1E5F0 ; XID_Start # Lo OL ONAL SIGN HODDOND 1E7E0..1E7E6 ; XID_Start # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; XID_Start # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; XID_Start # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -9005,7 +9038,7 @@ 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: 137067 +# Total code points: 137090 # ================================================ @@ -9684,7 +9717,7 @@ A771..A787 ; XID_Continue # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETT A788 ; XID_Continue # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; XID_Continue # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; XID_Continue # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CA ; XID_Continue # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CD ; XID_Continue # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE A7D0..A7D1 ; XID_Continue # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; XID_Continue # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7D9 ; XID_Continue # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S @@ -9927,6 +9960,14 @@ 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 @@ -10315,10 +10356,6 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 1E4EB ; XID_Continue # Lm NAG MUNDARI SIGN OJOD 1E4EC..1E4EF ; XID_Continue # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH 1E4F0..1E4F9 ; XID_Continue # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE -1E5D0..1E5ED ; XID_Continue # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG -1E5EE..1E5EF ; XID_Continue # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR -1E5F0 ; XID_Continue # Lo OL ONAL SIGN HODDOND -1E5F1..1E5FA ; XID_Continue # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE 1E7E0..1E7E6 ; XID_Continue # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; XID_Continue # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; XID_Continue # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -10374,7 +10411,7 @@ 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: 140256 +# Total code points: 140282 # ================================================ @@ -10677,6 +10714,7 @@ 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 @@ -10806,13 +10844,12 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 1E2AE ; Grapheme_Extend # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; Grapheme_Extend # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E4EC..1E4EF ; Grapheme_Extend # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH -1E5EE..1E5EF ; Grapheme_Extend # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E8D0..1E8D6 ; Grapheme_Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Grapheme_Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA 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: 2129 +# Total code points: 2132 # ================================================ @@ -11767,7 +11804,7 @@ A788 ; Grapheme_Base # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; Grapheme_Base # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; Grapheme_Base # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; Grapheme_Base # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CA ; Grapheme_Base # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CD ; Grapheme_Base # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE A7D0..A7D1 ; Grapheme_Base # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; Grapheme_Base # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7D9 ; Grapheme_Base # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S @@ -12106,6 +12143,15 @@ 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 @@ -12389,6 +12435,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1BC90..1BC99 ; Grapheme_Base # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW 1BC9C ; Grapheme_Base # So DUPLOYAN SIGN O WITH CROSS 1BC9F ; Grapheme_Base # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP +1CEB0..1CEB3 ; Grapheme_Base # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET 1CF50..1CFC3 ; Grapheme_Base # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK 1D000..1D0F5 ; Grapheme_Base # So [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126 ; Grapheme_Base # So [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 @@ -12469,10 +12516,6 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1E4D0..1E4EA ; Grapheme_Base # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL 1E4EB ; Grapheme_Base # Lm NAG MUNDARI SIGN OJOD 1E4F0..1E4F9 ; Grapheme_Base # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE -1E5D0..1E5ED ; Grapheme_Base # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG -1E5F0 ; Grapheme_Base # Lo OL ONAL SIGN HODDOND -1E5F1..1E5FA ; Grapheme_Base # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE -1E5FF ; Grapheme_Base # Po OL ONAL ABBREVIATION SIGN 1E7E0..1E7E6 ; Grapheme_Base # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; Grapheme_Base # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; Grapheme_Base # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -12552,7 +12595,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1F850..1F859 ; Grapheme_Base # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; Grapheme_Base # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; Grapheme_Base # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F8B0..1F8B1 ; Grapheme_Base # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST +1F8B0..1F8B2 ; Grapheme_Base # So [3] ARROW POINTING UPWARDS THEN NORTH WEST..RIGHTWARDS ARROW WITH LOWER HOOK 1F900..1FA53 ; Grapheme_Base # So [340] CIRCLED CROSS FORMEE WITH FOUR DOTS..BLACK CHESS KNIGHT-BISHOP 1FA60..1FA6D ; Grapheme_Base # So [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER 1FA70..1FA7C ; Grapheme_Base # So [13] BALLET SHOES..CRUTCH @@ -12575,7 +12618,7 @@ 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: 147778 +# Total code points: 147808 # ================================================ @@ -12824,6 +12867,7 @@ 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 @@ -12876,10 +12920,9 @@ FE20..FE2F ; InCB; Extend # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING 1E2AE ; InCB; Extend # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; InCB; Extend # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E4EC..1E4EF ; InCB; Extend # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH -1E5EE..1E5EF ; InCB; Extend # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 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: 887 +# Total code points: 890 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt b/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt index 102600acc7..4a18ccf918 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: 2023-10-24, 18:13:45 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 @@ -5370,6 +5370,8 @@ A7C5 ; NFKC_CF; 0282 # L& LATIN CAPITAL LETTER S WITH H A7C6 ; NFKC_CF; 1D8E # L& LATIN CAPITAL LETTER Z WITH PALATAL HOOK A7C7 ; NFKC_CF; A7C8 # L& LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; NFKC_CF; A7CA # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7CB ; NFKC_CF; 0264 # L& LATIN CAPITAL LETTER RAMS HORN +A7CC ; NFKC_CF; A7CD # L& LATIN CAPITAL LETTER S WITH DIAGONAL STROKE A7D0 ; NFKC_CF; A7D1 # L& LATIN CAPITAL LETTER CLOSED INSULAR G A7D6 ; NFKC_CF; A7D7 # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; NFKC_CF; A7D9 # L& LATIN CAPITAL LETTER SIGMOID S @@ -7018,6 +7020,28 @@ FFF0..FFF8 ; NFKC_CF; # Cn [9] ...... -# Total code points: 10492 +# Total code points: 10516 # ================================================ @@ -11442,6 +11466,8 @@ A7C5 ; NFKC_SCF; 0282 # L& LATIN CAPITAL LETTER S WITH A7C6 ; NFKC_SCF; 1D8E # L& LATIN CAPITAL LETTER Z WITH PALATAL HOOK A7C7 ; NFKC_SCF; A7C8 # L& LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; NFKC_SCF; A7CA # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7CB ; NFKC_SCF; 0264 # L& LATIN CAPITAL LETTER RAMS HORN +A7CC ; NFKC_SCF; A7CD # L& LATIN CAPITAL LETTER S WITH DIAGONAL STROKE A7D0 ; NFKC_SCF; A7D1 # L& LATIN CAPITAL LETTER CLOSED INSULAR G A7D6 ; NFKC_SCF; A7D7 # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; NFKC_SCF; A7D9 # L& LATIN CAPITAL LETTER SIGMOID S @@ -13090,6 +13116,28 @@ FFF0..FFF8 ; NFKC_SCF; # Cn [9] ...... -# Total code points: 10454 +# Total code points: 10478 # ================================================ @@ -15851,6 +15899,7 @@ A7C0 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER OLD A7C2 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER ANGLICANA W A7C4..A7C7 ; Changes_When_NFKC_Casefolded # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7CB..A7CC ; Changes_When_NFKC_Casefolded # L& [2] LATIN CAPITAL LETTER RAMS HORN..LATIN CAPITAL LETTER S WITH DIAGONAL STROKE A7D0 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER CLOSED INSULAR G A7D6 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER SIGMOID S @@ -15993,6 +16042,7 @@ FFF0..FFF8 ; Changes_When_NFKC_Casefolded # Cn [9] ...... -# Total code points: 10492 +# Total code points: 10516 # EOF diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index cedef03516..9156e2d4ff 100644 --- a/unicodetools/data/ucd/dev/EastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/EastAsianWidth.txt @@ -1,5 +1,9 @@ # EastAsianWidth-16.0.0.txt +<<<<<<< HEAD # Date: 2023-10-23, 13:17:06 GMT +======= +# Date: 2023-10-24, 18:13:48 GMT +>>>>>>> la-vache/main # © 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 @@ -1543,7 +1547,7 @@ A788 ; N # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; N # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; N # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; N # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CA ; N # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CD ; N # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE A7D0..A7D1 ; N # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; N # Ll LATIN SMALL LETTER DOUBLE THORN A7D5..A7D9 ; N # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S @@ -1943,6 +1947,16 @@ 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 @@ -2333,6 +2347,7 @@ FFFD ; A # So REPLACEMENT CHARACTER 1BC9D..1BC9E ; N # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK 1BC9F ; N # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3 ; N # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CEB0..1CEB3 ; N # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET 1CF00..1CF2D ; N # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT 1CF30..1CF46 ; N # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1CF50..1CFC3 ; N # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK @@ -2585,7 +2600,7 @@ FFFD ; A # So REPLACEMENT CHARACTER 1F850..1F859 ; N # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; N # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; N # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F8B0..1F8B1 ; N # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST +1F8B0..1F8B2 ; N # So [3] ARROW POINTING UPWARDS THEN NORTH WEST..RIGHTWARDS ARROW WITH LOWER HOOK 1F900..1F90B ; N # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT 1F90C..1F93A ; W # So [47] PINCHED FINGERS..FENCER 1F93B ; N # So MODERN PENTATHLON diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 32f11b842a..937622bf7e 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,9 @@ # LineBreak-16.0.0.txt +<<<<<<< HEAD # Date: 2023-10-23, 13:17:08 GMT +======= +# Date: 2023-10-24, 18:13:49 GMT +>>>>>>> la-vache/main # © 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 @@ -1578,7 +1582,7 @@ A788 ; AL # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; AL # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; AL # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; AL # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CA ; AL # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CD ; AL # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE A7D0..A7D1 ; AL # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; AL # Ll LATIN SMALL LETTER DOUBLE THORN A7D5..A7D9 ; AL # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S @@ -2796,6 +2800,16 @@ 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 @@ -3238,6 +3252,7 @@ FFFD ; AI # So REPLACEMENT CHARACTER 1BC9D..1BC9E ; CM # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK 1BC9F ; BA # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3 ; CM # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CEB0..1CEB3 ; AL # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET 1CF00..1CF2D ; CM # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT 1CF30..1CF46 ; CM # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1CF50..1CFC3 ; AL # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK @@ -3542,7 +3557,8 @@ FFFD ; AI # So REPLACEMENT CHARACTER 1F890..1F8AD ; AL # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS 1F8AE..1F8AF ; ID # Cn [2] .. 1F8B0..1F8B1 ; ID # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST -1F8B2..1F8FF ; ID # Cn [78] .. +1F8B2 ; AL # So RIGHTWARDS ARROW WITH LOWER HOOK +1F8B3..1F8FF ; ID # Cn [77] .. 1F900..1F90B ; AL # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT 1F90C ; EB # So PINCHED FINGERS 1F90D..1F90E ; ID # So [2] WHITE HEART..BROWN HEART diff --git a/unicodetools/data/ucd/dev/NormalizationTest.txt b/unicodetools/data/ucd/dev/NormalizationTest.txt index f02a9a6faa..d4adad8769 100644 --- a/unicodetools/data/ucd/dev/NormalizationTest.txt +++ b/unicodetools/data/ucd/dev/NormalizationTest.txt @@ -1,5 +1,9 @@ # NormalizationTest-16.0.0.txt +<<<<<<< HEAD # Date: 2023-10-23, 13:17:12 GMT +======= +# Date: 2023-10-23, 12:24:21 GMT +>>>>>>> la-vache/main # © 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 +18562,16 @@ 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 94d9018702..f8433ea3fb 100644 --- a/unicodetools/data/ucd/dev/PropList.txt +++ b/unicodetools/data/ucd/dev/PropList.txt @@ -1,5 +1,9 @@ # PropList-16.0.0.txt +<<<<<<< HEAD # Date: 2023-10-23, 13:17:12 GMT +======= +# Date: 2023-10-23, 12:20:11 GMT +>>>>>>> la-vache/main # © 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 +66,10 @@ 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 +695,7 @@ 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 +842,7 @@ 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 +1050,8 @@ 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 @@ -1106,7 +1114,11 @@ 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 +<<<<<<< HEAD # Total code points: 1146 +======= +# Total code points: 1150 +>>>>>>> la-vache/main # ================================================ @@ -1135,6 +1147,9 @@ 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 @@ -1145,7 +1160,11 @@ FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND 1E5EF ; Extender # Mn OL ONAL SIGN IKIR 1E944..1E946 ; Extender # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK +<<<<<<< HEAD # Total code points: 51 +======= +# Total code points: 53 +>>>>>>> la-vache/main # ================================================ diff --git a/unicodetools/data/ucd/dev/PropertyValueAliases.txt b/unicodetools/data/ucd/dev/PropertyValueAliases.txt index 408d8c1429..505daaf782 100644 --- a/unicodetools/data/ucd/dev/PropertyValueAliases.txt +++ b/unicodetools/data/ucd/dev/PropertyValueAliases.txt @@ -1,5 +1,9 @@ # PropertyValueAliases-16.0.0.txt +<<<<<<< HEAD # Date: 2023-10-23, 13:17:15 GMT +======= +# Date: 2023-10-23, 18:45:09 GMT +>>>>>>> la-vache/main # © 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 +262,7 @@ 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 @@ -442,6 +447,7 @@ blk; Sutton_SignWriting ; Sutton_SignWriting blk; Syloti_Nagri ; Syloti_Nagri blk; Symbols_And_Pictographs_Ext_A ; Symbols_And_Pictographs_Extended_A blk; Symbols_For_Legacy_Computing ; Symbols_For_Legacy_Computing +blk; Symbols_For_Legacy_Computing_Sup ; Symbols_For_Legacy_Computing_Supplement blk; Syriac ; Syriac blk; Syriac_Sup ; Syriac_Supplement blk; Tagalog ; Tagalog @@ -1331,6 +1337,7 @@ 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 4f46be8e7e..2e763fa765 100644 --- a/unicodetools/data/ucd/dev/ScriptExtensions.txt +++ b/unicodetools/data/ucd/dev/ScriptExtensions.txt @@ -1,5 +1,9 @@ # ScriptExtensions-16.0.0.txt +<<<<<<< HEAD # Date: 2023-10-09, 13:22:09 GMT +======= +# Date: 2023-10-09, 14:49:47 GMT +>>>>>>> la-vache/main # © 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 +501,6 @@ 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 +540,18 @@ 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 9b29be83bd..04bde2ae34 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,5 +1,9 @@ # Scripts-16.0.0.txt +<<<<<<< HEAD # Date: 2023-10-23, 13:17:36 GMT +======= +# Date: 2023-10-24, 18:14:16 GMT +>>>>>>> la-vache/main # © 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 @@ -522,6 +526,7 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR 101D0..101FC ; Common # So [45] PHAISTOS DISC SIGN PEDESTRIAN..PHAISTOS DISC SIGN WAVY BAND 102E1..102FB ; Common # No [27] COPTIC EPACT DIGIT ONE..COPTIC EPACT NUMBER NINE HUNDRED 1BCA0..1BCA3 ; Common # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CEB0..1CEB3 ; Common # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET 1CF50..1CFC3 ; Common # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK 1D000..1D0F5 ; Common # So [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126 ; Common # So [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 @@ -614,7 +619,7 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR 1F850..1F859 ; Common # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; Common # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; Common # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F8B0..1F8B1 ; Common # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST +1F8B0..1F8B2 ; Common # So [3] ARROW POINTING UPWARDS THEN NORTH WEST..RIGHTWARDS ARROW WITH LOWER HOOK 1F900..1FA53 ; Common # So [340] CIRCLED CROSS FORMEE WITH FOUR DOTS..BLACK CHESS KNIGHT-BISHOP 1FA60..1FA6D ; Common # So [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER 1FA70..1FA7C ; Common # So [13] BALLET SHOES..CRUTCH @@ -630,7 +635,7 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR E0001 ; Common # Cf LANGUAGE TAG E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG -# Total code points: 8306 +# Total code points: 8311 # ================================================ @@ -673,7 +678,7 @@ A770 ; Latin # Lm MODIFIER LETTER US A771..A787 ; Latin # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T A78B..A78E ; Latin # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; Latin # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CA ; Latin # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CD ; Latin # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE A7D0..A7D1 ; Latin # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; Latin # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7D9 ; Latin # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S @@ -699,7 +704,7 @@ FF41..FF5A ; Latin # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1DF0B..1DF1E ; Latin # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1DF25..1DF2A ; Latin # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK -# Total code points: 1481 +# Total code points: 1484 # ================================================ @@ -3034,6 +3039,7 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI # ================================================ +<<<<<<< HEAD 1E5D0..1E5ED ; Ol_Onal # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG 1E5EE..1E5EF ; Ol_Onal # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E5F0 ; Ol_Onal # Lo OL ONAL SIGN HODDOND @@ -3041,6 +3047,20 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI 1E5FF ; Ol_Onal # Po OL ONAL ABBREVIATION SIGN # Total code points: 44 +======= +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 +>>>>>>> la-vache/main # ================================================ diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 730980ac7b..20da9b7d8f 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -610,7 +610,7 @@ 0261;LATIN SMALL LETTER SCRIPT G;Ll;0;L;;;;;N;;;A7AC;;A7AC 0262;LATIN LETTER SMALL CAPITAL G;Ll;0;L;;;;;N;;;;; 0263;LATIN SMALL LETTER GAMMA;Ll;0;L;;;;;N;;;0194;;0194 -0264;LATIN SMALL LETTER RAMS HORN;Ll;0;L;;;;;N;LATIN SMALL LETTER BABY GAMMA;;;; +0264;LATIN SMALL LETTER RAMS HORN;Ll;0;L;;;;;N;LATIN SMALL LETTER BABY GAMMA;;A7CB;;A7CB 0265;LATIN SMALL LETTER TURNED H;Ll;0;L;;;;;N;;;A78D;;A78D 0266;LATIN SMALL LETTER H WITH HOOK;Ll;0;L;;;;;N;LATIN SMALL LETTER H HOOK;;A7AA;;A7AA 0267;LATIN SMALL LETTER HENG WITH HOOK;Ll;0;L;;;;;N;LATIN SMALL LETTER HENG HOOK;;;; @@ -14265,6 +14265,9 @@ A7C7;LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY;Lu;0;L;;;;;N;;;;A7C8; A7C8;LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY;Ll;0;L;;;;;N;;;A7C7;;A7C7 A7C9;LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY;Lu;0;L;;;;;N;;;;A7CA; A7CA;LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY;Ll;0;L;;;;;N;;;A7C9;;A7C9 +A7CB;LATIN CAPITAL LETTER RAMS HORN;Lu;0;L;;;;;N;;;;0264; +A7CC;LATIN CAPITAL LETTER S WITH DIAGONAL STROKE;Lu;0;L;;;;;N;;;;A7CD; +A7CD;LATIN SMALL LETTER S WITH DIAGONAL STROKE;Ll;0;L;;;;;N;;;A7CC;;A7CC A7D0;LATIN CAPITAL LETTER CLOSED INSULAR G;Lu;0;L;;;;;N;;;;A7D1; A7D1;LATIN SMALL LETTER CLOSED INSULAR G;Ll;0;L;;;;;N;;;A7D0;;A7D0 A7D3;LATIN SMALL LETTER DOUBLE THORN;Ll;0;L;;;;;N;;;;; @@ -19379,6 +19382,75 @@ 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;;;;; @@ -28105,6 +28177,10 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1BCA1;SHORTHAND FORMAT CONTINUING OVERLAP;Cf;0;BN;;;;;N;;;;; 1BCA2;SHORTHAND FORMAT DOWN STEP;Cf;0;BN;;;;;N;;;;; 1BCA3;SHORTHAND FORMAT UP STEP;Cf;0;BN;;;;;N;;;;; +1CEB0;HORIZONTAL ZIGZAG LINE;So;0;ON;;;;;N;;;;; +1CEB1;KEYHOLE;So;0;ON;;;;;N;;;;; +1CEB2;OLD PERSONAL COMPUTER WITH MONITOR IN PORTRAIT ORIENTATION;So;0;ON;;;;;N;;;;; +1CEB3;BLACK RIGHT TRIANGLE CARET;So;0;ON;;;;;N;;;;; 1CF00;ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT;Mn;0;NSM;;;;;N;;;;; 1CF01;ZNAMENNY COMBINING MARK NIZKO S KRYZHEM ON LEFT;Mn;0;NSM;;;;;N;;;;; 1CF02;ZNAMENNY COMBINING MARK TSATA ON LEFT;Mn;0;NSM;;;;;N;;;;; @@ -33526,6 +33602,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1F8AD;WHITE ARROW SHAFT WIDTH TWO THIRDS;So;0;ON;;;;;N;;;;; 1F8B0;ARROW POINTING UPWARDS THEN NORTH WEST;So;0;ON;;;;;N;;;;; 1F8B1;ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST;So;0;ON;;;;;N;;;;; +1F8B2;RIGHTWARDS ARROW WITH LOWER HOOK;So;0;ON;;;;;N;;;;; 1F900;CIRCLED CROSS FORMEE WITH FOUR DOTS;So;0;ON;;;;;N;;;;; 1F901;CIRCLED CROSS FORMEE WITH TWO DOTS;So;0;ON;;;;;N;;;;; 1F902;CIRCLED CROSS FORMEE;So;0;ON;;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index 4ad011c028..87a06000dd 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,9 @@ # VerticalOrientation-16.0.0.txt +<<<<<<< HEAD # Date: 2023-10-23, 13:17:39 GMT +======= +# Date: 2023-10-24, 18:14:20 GMT +>>>>>>> la-vache/main # © 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 @@ -1355,7 +1359,7 @@ A788 ; R # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; R # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; R # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; R # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CA ; R # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CD ; R # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE A7D0..A7D1 ; R # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; R # Ll LATIN SMALL LETTER DOUBLE THORN A7D5..A7D9 ; R # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S @@ -1767,6 +1771,16 @@ 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 @@ -2178,6 +2192,7 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 1BC9D..1BC9E ; R # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK 1BC9F ; R # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3 ; R # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CEB0..1CEB3 ; R # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET 1CF00..1CF2D ; U # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT 1CF2E..1CF2F ; U # Cn [2] .. 1CF30..1CF46 ; U # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG @@ -2404,7 +2419,7 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 1F850..1F859 ; R # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; R # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; R # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F8B0..1F8B1 ; R # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST +1F8B0..1F8B2 ; R # So [3] ARROW POINTING UPWARDS THEN NORTH WEST..RIGHTWARDS ARROW WITH LOWER HOOK 1F900..1F9FF ; U # So [256] CIRCLED CROSS FORMEE WITH FOUR DOTS..NAZAR AMULET 1FA00..1FA53 ; U # So [84] NEUTRAL CHESS KING..BLACK CHESS KNIGHT-BISHOP 1FA54..1FA5F ; U # Cn [12] .. diff --git a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt index 14914021d8..91bb0bd24e 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: 2023-10-23, 13:17:07 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 @@ -453,14 +454,13 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1E2AE ; Extend # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; Extend # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E4EC..1E4EF ; Extend # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH -1E5EE..1E5EF ; Extend # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA 1F3FB..1F3FF ; Extend # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2134 +# Total code points: 2137 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 1aeb9ae030..3ced5cec31 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: 2023-10-23, 13:17:36 GMT +# Date: 2023-10-24, 18:14:17 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 @@ -562,13 +563,12 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1E2AE ; Extend # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; Extend # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E4EC..1E4EF ; Extend # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH -1E5EE..1E5EF ; Extend # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2554 +# Total code points: 2557 # ================================================ @@ -1235,6 +1235,7 @@ A7C1 ; Lower # L& LATIN SMALL LETTER OLD POLISH O A7C3 ; Lower # L& LATIN SMALL LETTER ANGLICANA W A7C8 ; Lower # L& LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7CA ; Lower # L& LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7CD ; Lower # L& LATIN SMALL LETTER S WITH DIAGONAL STROKE A7D1 ; Lower # L& LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; Lower # L& LATIN SMALL LETTER DOUBLE THORN A7D5 ; Lower # L& LATIN SMALL LETTER DOUBLE WYNN @@ -1263,6 +1264,7 @@ 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 @@ -1299,7 +1301,7 @@ 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: 2521 # ================================================ @@ -1907,6 +1909,7 @@ A7C0 ; Upper # L& LATIN CAPITAL LETTER OLD POLISH O A7C2 ; Upper # L& LATIN CAPITAL LETTER ANGLICANA W A7C4..A7C7 ; Upper # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Upper # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7CB..A7CC ; Upper # L& [2] LATIN CAPITAL LETTER RAMS HORN..LATIN CAPITAL LETTER S WITH DIAGONAL STROKE A7D0 ; Upper # L& LATIN CAPITAL LETTER CLOSED INSULAR G A7D6 ; Upper # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Upper # L& LATIN CAPITAL LETTER SIGMOID S @@ -1919,6 +1922,7 @@ 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 @@ -1957,7 +1961,7 @@ 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: 1961 # ================================================ @@ -2357,6 +2361,10 @@ 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 @@ -2493,8 +2501,6 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1E2C0..1E2EB ; OLetter # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E4D0..1E4EA ; OLetter # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL 1E4EB ; OLetter # Lm NAG MUNDARI SIGN OJOD -1E5D0..1E5ED ; OLetter # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG -1E5F0 ; OLetter # Lo OL ONAL SIGN HODDOND 1E7E0..1E7E6 ; OLetter # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; OLetter # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; OLetter # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -2544,7 +2550,7 @@ 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: 132779 +# Total code points: 132755 # ================================================ @@ -2592,6 +2598,7 @@ 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 +2626,6 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E140..1E149 ; Numeric # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E2F0..1E2F9 ; Numeric # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE 1E4F0..1E4F9 ; Numeric # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE -1E5F1..1E5FA ; Numeric # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE 1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Numeric # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index 0c3a3fd594..4f89925fd0 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: 2023-10-23, 13:17:40 GMT +# Date: 2023-10-24, 18:14:20 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 @@ -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 @@ -598,14 +599,13 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1E2AE ; Extend # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; Extend # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E4EC..1E4EF ; Extend # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH -1E5EE..1E5EF ; Extend # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA 1F3FB..1F3FF ; Extend # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2558 +# Total code points: 2561 # ================================================ @@ -984,7 +984,7 @@ A788 ; ALetter # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; ALetter # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; ALetter # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ALetter # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CA ; ALetter # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CD ; ALetter # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE A7D0..A7D1 ; ALetter # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; ALetter # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7D9 ; ALetter # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S @@ -1115,6 +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 @@ -1273,8 +1279,6 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1E2C0..1E2EB ; ALetter # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E4D0..1E4EA ; ALetter # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL 1E4EB ; ALetter # Lm NAG MUNDARI SIGN OJOD -1E5D0..1E5ED ; ALetter # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG -1E5F0 ; ALetter # Lo OL ONAL SIGN HODDOND 1E7E0..1E7E6 ; ALetter # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; ALetter # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; ALetter # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -1319,7 +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: 29613 +# Total code points: 29636 # ================================================ @@ -1412,6 +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 +1444,6 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E140..1E149 ; Numeric # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E2F0..1E2F9 ; Numeric # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE 1E4F0..1E4F9 ; Numeric # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE -1E5F1..1E5FA ; Numeric # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE 1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Numeric # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index cfbe5e9c02..37d75f4fc4 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, 13:16:54 GMT +# Date: 2023-10-24, 18:13:39 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 @@ -660,7 +661,7 @@ A771..A787 ; L # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR A789..A78A ; L # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; L # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; L # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CA ; L # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CD ; L # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE A7D0..A7D1 ; L # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; L # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7D9 ; L # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S @@ -1164,10 +1165,6 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 1E4D0..1E4EA ; L # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL 1E4EB ; L # Lm NAG MUNDARI SIGN OJOD 1E4F0..1E4F9 ; L # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE -1E5D0..1E5ED ; L # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG -1E5F0 ; L # Lo OL ONAL SIGN HODDOND -1E5F1..1E5FA ; L # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE -1E5FF ; L # Po OL ONAL ABBREVIATION SIGN 1E7E0..1E7E6 ; L # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; L # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; L # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -1191,8 +1188,8 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER F0000..FFFFD ; L # Co [65534] .. 100000..10FFFD; L # Co [65534] .. -# The above property value applies to 820298 code points not listed here. -# Total code points: 1096265 +# The above property value applies to 820334 code points not listed here. +# Total code points: 1096262 # ================================================ @@ -1279,6 +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 @@ -1297,8 +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 # ================================================ @@ -1387,9 +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 # ================================================ @@ -1903,11 +1908,13 @@ 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 11FE1..11FF1 ; ON # So [17] TAMIL SIGN PAARAM..TAMIL SIGN VAKAIYARAA 16FE2 ; ON # Po OLD CHINESE HOOK MARK +1CEB0..1CEB3 ; ON # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET 1D1E9..1D1EA ; ON # So [2] MUSICAL SYMBOL SORI..MUSICAL SYMBOL KORON 1D200..1D241 ; ON # So [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54 1D245 ; ON # So GREEK MUSICAL LEIMMA @@ -1944,7 +1951,7 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE 1F850..1F859 ; ON # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; ON # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; ON # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F8B0..1F8B1 ; ON # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST +1F8B0..1F8B2 ; ON # So [3] ARROW POINTING UPWARDS THEN NORTH WEST..RIGHTWARDS ARROW WITH LOWER HOOK 1F900..1FA53 ; ON # So [340] CIRCLED CROSS FORMEE WITH FOUR DOTS..BLACK CHESS KNIGHT-BISHOP 1FA60..1FA6D ; ON # So [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER 1FA70..1FA7C ; ON # So [13] BALLET SHOES..CRUTCH @@ -1957,7 +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: 6034 +# Total code points: 6040 # ================================================ @@ -2232,6 +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 @@ -2353,12 +2361,11 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 1E2AE ; NSM # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; NSM # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E4EC..1E4EF ; NSM # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH -1E5EE..1E5EF ; NSM # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E8D0..1E8D6 ; NSM # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; NSM # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1997 +# Total code points: 2000 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index 4c38edf61f..15b1ed776b 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, 13:16:57 GMT +# Date: 2023-10-24, 18:13:41 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 @@ -1092,7 +1092,7 @@ A788 ; 0 # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; 0 # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; 0 # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; 0 # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CA ; 0 # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CD ; 0 # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE A7D0..A7D1 ; 0 # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; 0 # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7D9 ; 0 # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S @@ -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 @@ -1818,6 +1827,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1BC9D ; 0 # Mn DUPLOYAN THICK LETTER SELECTOR 1BC9F ; 0 # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3 ; 0 # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CEB0..1CEB3 ; 0 # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET 1CF00..1CF2D ; 0 # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT 1CF30..1CF46 ; 0 # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1CF50..1CFC3 ; 0 # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK @@ -1905,10 +1915,6 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1E4D0..1E4EA ; 0 # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL 1E4EB ; 0 # Lm NAG MUNDARI SIGN OJOD 1E4F0..1E4F9 ; 0 # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE -1E5D0..1E5ED ; 0 # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG -1E5F0 ; 0 # Lo OL ONAL SIGN HODDOND -1E5F1..1E5FA ; 0 # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE -1E5FF ; 0 # Po OL ONAL ABBREVIATION SIGN 1E7E0..1E7E6 ; 0 # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; 0 # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; 0 # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -1988,7 +1994,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1F850..1F859 ; 0 # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; 0 # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; 0 # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F8B0..1F8B1 ; 0 # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST +1F8B0..1F8B2 ; 0 # So [3] ARROW POINTING UPWARDS THEN NORTH WEST..RIGHTWARDS ARROW WITH LOWER HOOK 1F900..1FA53 ; 0 # So [340] CIRCLED CROSS FORMEE WITH FOUR DOTS..BLACK CHESS KNIGHT-BISHOP 1FA60..1FA6D ; 0 # So [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER 1FA70..1FA7C ; 0 # So [13] BALLET SHOES..CRUTCH @@ -2016,8 +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 826597 code points not listed here. -# Total code points: 1113187 +# The above property value applies to 826564 code points not listed here. +# Total code points: 1113184 # ================================================ @@ -2576,10 +2582,9 @@ FE27..FE2D ; 220 # Mn [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CON 1D17B..1D182 ; 220 # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE 1D18A..1D18B ; 220 # Mn [2] MUSICAL SYMBOL COMBINING DOUBLE TONGUE..MUSICAL SYMBOL COMBINING TRIPLE TONGUE 1E4EE ; 220 # Mn NAG MUNDARI SIGN IKIR -1E5EF ; 220 # Mn OL ONAL SIGN IKIR 1E8D0..1E8D6 ; 220 # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS -# Total code points: 182 +# Total code points: 181 # ================================================ @@ -2728,6 +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 @@ -2751,10 +2757,9 @@ FE2E..FE2F ; 230 # Mn [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBINING CYR 1E2AE ; 230 # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; 230 # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E4EF ; 230 # Mn NAG MUNDARI SIGN SUTUH -1E5EE ; 230 # Mn OL ONAL SIGN MU 1E944..1E949 ; 230 # Mn [6] ADLAM ALIF LENGTHENER..ADLAM GEMINATE CONSONANT MODIFIER -# Total code points: 512 +# Total code points: 516 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index e8440e57d6..b6936e45a7 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, 13:17:00 GMT +# Date: 2023-10-24, 18:13:43 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 @@ -1180,7 +1180,7 @@ A788 ; N # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; N # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; N # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; N # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CA ; N # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CD ; N # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE A7D0..A7D1 ; N # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; N # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7D9 ; N # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S @@ -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 @@ -1836,6 +1846,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 1BC9D..1BC9E ; N # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK 1BC9F ; N # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3 ; N # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CEB0..1CEB3 ; N # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET 1CF00..1CF2D ; N # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT 1CF30..1CF46 ; N # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1CF50..1CFC3 ; N # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK @@ -1940,11 +1951,6 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 1E4EB ; N # Lm NAG MUNDARI SIGN OJOD 1E4EC..1E4EF ; N # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH 1E4F0..1E4F9 ; N # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE -1E5D0..1E5ED ; N # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG -1E5EE..1E5EF ; N # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR -1E5F0 ; N # Lo OL ONAL SIGN HODDOND -1E5F1..1E5FA ; N # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE -1E5FF ; N # Po OL ONAL ABBREVIATION SIGN 1E7E0..1E7E6 ; N # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; N # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; N # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -2042,7 +2048,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 1F850..1F859 ; N # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; N # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; N # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F8B0..1F8B1 ; N # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST +1F8B0..1F8B2 ; N # So [3] ARROW POINTING UPWARDS THEN NORTH WEST..RIGHTWARDS ARROW WITH LOWER HOOK 1F900..1F90B ; N # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT 1F93B ; N # So MODERN PENTATHLON 1F946 ; N # So RIFLE @@ -2054,7 +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 766115 code points not listed here. +# The above property value applies to 766082 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 9678fe2ea5..40404afd6f 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, 13:17:01 GMT +# Date: 2023-10-24, 18:13:43 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 @@ -295,7 +295,7 @@ A48D..A48F ; Cn # [3] .. A4C7..A4CF ; Cn # [9] .. A62C..A63F ; Cn # [20] .. A6F8..A6FF ; Cn # [8] .. -A7CB..A7CF ; Cn # [5] .. +A7CE..A7CF ; Cn # [2] .. A7D2 ; Cn # A7D4 ; Cn # A7DA..A7F1 ; Cn # [24] .. @@ -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] .. @@ -579,7 +582,8 @@ FFFE..FFFF ; Cn # [2] .. 1BC7D..1BC7F ; Cn # [3] .. 1BC89..1BC8F ; Cn # [7] .. 1BC9A..1BC9B ; Cn # [2] .. -1BCA4..1CEFF ; Cn # [4700] .. +1BCA4..1CEAF ; Cn # [4620] .. +1CEB4..1CEFF ; Cn # [76] .. 1CF2E..1CF2F ; Cn # [2] .. 1CF47..1CF4F ; Cn # [9] .. 1CFC4..1CFFF ; Cn # [60] .. @@ -630,9 +634,7 @@ FFFE..FFFF ; Cn # [2] .. 1E2AF..1E2BF ; Cn # [17] .. 1E2FA..1E2FE ; Cn # [5] .. 1E300..1E4CF ; Cn # [464] .. -1E4FA..1E5CF ; Cn # [214] .. -1E5FB..1E5FE ; Cn # [4] .. -1E600..1E7DF ; Cn # [480] .. +1E4FA..1E7DF ; Cn # [742] .. 1E7E7 ; Cn # 1E7EC ; Cn # 1E7EF ; Cn # @@ -702,7 +704,7 @@ FFFE..FFFF ; Cn # [2] .. 1F85A..1F85F ; Cn # [6] .. 1F888..1F88F ; Cn # [8] .. 1F8AE..1F8AF ; Cn # [2] .. -1F8B2..1F8FF ; Cn # [78] .. +1F8B3..1F8FF ; Cn # [77] .. 1FA54..1FA5F ; Cn # [12] .. 1FA6E..1FA6F ; Cn # [2] .. 1FA7D..1FA7F ; Cn # [3] .. @@ -730,7 +732,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 824549 +# Total code points: 824516 # ================================================ @@ -1337,6 +1339,7 @@ A7C0 ; Lu # LATIN CAPITAL LETTER OLD POLISH O A7C2 ; Lu # LATIN CAPITAL LETTER ANGLICANA W A7C4..A7C7 ; Lu # [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Lu # LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7CB..A7CC ; Lu # [2] LATIN CAPITAL LETTER RAMS HORN..LATIN CAPITAL LETTER S WITH DIAGONAL STROKE A7D0 ; Lu # LATIN CAPITAL LETTER CLOSED INSULAR G A7D6 ; Lu # LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Lu # LATIN CAPITAL LETTER SIGMOID S @@ -1349,6 +1352,7 @@ 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 @@ -1384,7 +1388,7 @@ 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: 1856 # ================================================ @@ -1995,6 +1999,7 @@ A7C1 ; Ll # LATIN SMALL LETTER OLD POLISH O A7C3 ; Ll # LATIN SMALL LETTER ANGLICANA W A7C8 ; Ll # LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7CA ; Ll # LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7CD ; Ll # LATIN SMALL LETTER S WITH DIAGONAL STROKE A7D1 ; Ll # LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; Ll # LATIN SMALL LETTER DOUBLE THORN A7D5 ; Ll # LATIN SMALL LETTER DOUBLE WYNN @@ -2015,6 +2020,7 @@ 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 @@ -2050,7 +2056,7 @@ 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: 2257 # ================================================ @@ -2133,6 +2139,8 @@ 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 @@ -2145,7 +2153,7 @@ 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 # ================================================ @@ -2492,6 +2500,8 @@ 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 @@ -2618,8 +2628,6 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 1E290..1E2AD ; Lo # [30] TOTO LETTER PA..TOTO LETTER A 1E2C0..1E2EB ; Lo # [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E4D0..1E4EA ; Lo # [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL -1E5D0..1E5ED ; Lo # [30] OL ONAL LETTER O..OL ONAL LETTER EG -1E5F0 ; Lo # OL ONAL SIGN HODDOND 1E7E0..1E7E6 ; Lo # [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; Lo # [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; Lo # [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -2668,7 +2676,7 @@ 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: 132355 +# Total code points: 132329 # ================================================ @@ -2896,6 +2904,7 @@ 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 @@ -3017,12 +3026,11 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 1E2AE ; Mn # TOTO SIGN RISING TONE 1E2EC..1E2EF ; Mn # [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E4EC..1E4EF ; Mn # [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH -1E5EE..1E5EF ; Mn # [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E8D0..1E8D6 ; Mn # [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Mn # [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; Mn # [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1989 +# Total code points: 1992 # ================================================ @@ -3268,6 +3276,7 @@ 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 @@ -3293,7 +3302,6 @@ FF10..FF19 ; Nd # [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E140..1E149 ; Nd # [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E2F0..1E2F9 ; Nd # [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE 1E4F0..1E4F9 ; Nd # [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE -1E5F1..1E5FA ; Nd # [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE 1E950..1E959 ; Nd # [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Nd # [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE @@ -3504,9 +3512,10 @@ 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 # ================================================ @@ -3881,10 +3890,9 @@ FF64..FF65 ; Po # [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDL 16FE2 ; Po # OLD CHINESE HOOK MARK 1BC9F ; Po # DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1DA87..1DA8B ; Po # [5] SIGNWRITING COMMA..SIGNWRITING PARENTHESIS -1E5FF ; Po # OL ONAL ABBREVIATION SIGN 1E95E..1E95F ; Po # [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK -# Total code points: 630 +# Total code points: 629 # ================================================ @@ -3943,6 +3951,7 @@ 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 @@ -3955,7 +3964,7 @@ 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 # ================================================ @@ -4156,6 +4165,7 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 16B3C..16B3F ; So # [4] PAHAWH HMONG SIGN XYEEM NTXIV..PAHAWH HMONG SIGN XYEEM FAIB 16B45 ; So # PAHAWH HMONG SIGN CIM TSOV ROG 1BC9C ; So # DUPLOYAN SIGN O WITH CROSS +1CEB0..1CEB3 ; So # [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET 1CF50..1CFC3 ; So # [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK 1D000..1D0F5 ; So # [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126 ; So # [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 @@ -4200,7 +4210,7 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1F850..1F859 ; So # [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; So # [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; So # [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F8B0..1F8B1 ; So # [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST +1F8B0..1F8B2 ; So # [3] ARROW POINTING UPWARDS THEN NORTH WEST..RIGHTWARDS ARROW WITH LOWER HOOK 1F900..1FA53 ; So # [340] CIRCLED CROSS FORMEE WITH FOUR DOTS..BLACK CHESS KNIGHT-BISHOP 1FA60..1FA6D ; So # [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER 1FA70..1FA7C ; So # [13] BALLET SHOES..CRUTCH @@ -4213,7 +4223,7 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1FB00..1FB92 ; So # [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; So # [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON -# Total code points: 6639 +# Total code points: 6644 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt index 675fd06193..f183991460 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: 2023-10-23, 13:17:02 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 @@ -563,7 +564,6 @@ FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATI 1E2AE ; T # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; T # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E4EC..1E4EF ; T # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH -1E5EE..1E5EF ; T # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E8D0..1E8D6 ; T # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; T # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA 1E94B ; T # Lm ADLAM NASALIZATION MARK @@ -571,6 +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: 2154 +# Total code points: 2157 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index e32720de3d..e270d7e04c 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, 13:17:03 GMT +# Date: 2023-10-24, 18:13:45 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 762556 code points not listed here. -# Total code points: 900024 +# The above property value applies to 762524 code points not listed here. +# Total code points: 899992 # ================================================ @@ -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 @@ -545,7 +546,6 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 1E140..1E149 ; NU # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E2F0..1E2F9 ; NU # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE 1E4F0..1E4F9 ; NU # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE -1E5F1..1E5FA ; NU # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE 1E950..1E959 ; NU # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; NU # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE @@ -1136,7 +1136,7 @@ A788 ; AL # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; AL # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; AL # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; AL # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CA ; AL # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CD ; AL # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE A7D0..A7D1 ; AL # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; AL # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7D9 ; AL # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S @@ -1300,6 +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 @@ -1437,6 +1444,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1BC80..1BC88 ; AL # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL 1BC90..1BC99 ; AL # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW 1BC9C ; AL # So DUPLOYAN SIGN O WITH CROSS +1CEB0..1CEB3 ; AL # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET 1CF50..1CFC3 ; AL # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK 1D000..1D0F5 ; AL # So [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126 ; AL # So [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 @@ -1510,9 +1518,6 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1E2C0..1E2EB ; AL # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E4D0..1E4EA ; AL # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL 1E4EB ; AL # Lm NAG MUNDARI SIGN OJOD -1E5D0..1E5ED ; AL # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG -1E5F0 ; AL # Lo OL ONAL SIGN HODDOND -1E5FF ; AL # Po OL ONAL ABBREVIATION SIGN 1E7E0..1E7E6 ; AL # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; AL # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; AL # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -1585,12 +1590,13 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1F850..1F859 ; AL # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; AL # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; AL # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS +1F8B2 ; AL # So RIGHTWARDS ARROW WITH LOWER HOOK 1F900..1F90B ; AL # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT 1FA00..1FA53 ; AL # So [84] NEUTRAL CHESS KING..BLACK CHESS KNIGHT-BISHOP 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: 21854 +# Total code points: 21883 # ================================================ @@ -1833,8 +1839,8 @@ FFE4 ; ID # So FULLWIDTH BROKEN BAR 30000..3134A ; ID # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; ID # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# The above property value applies to 61978 code points not listed here. -# Total code points: 172568 +# The above property value applies to 61977 code points not listed here. +# Total code points: 172567 # ================================================ @@ -2155,6 +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 @@ -2340,14 +2347,13 @@ FFF9..FFFB ; CM # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTAT 1E2AE ; CM # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; CM # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E4EC..1E4EF ; CM # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH -1E5EE..1E5EF ; CM # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E8D0..1E8D6 ; CM # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; CM # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA 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: 2433 +# Total code points: 2436 # ================================================ @@ -2461,6 +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 @@ -2497,7 +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 55d29d0e24..56df153fa1 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, 13:17:03 GMT +# Date: 2023-10-24, 18:13:45 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 @@ -14238,6 +14238,9 @@ A7C7 ; LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C8 ; LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY A7CA ; LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7CB ; LATIN CAPITAL LETTER RAMS HORN +A7CC ; LATIN CAPITAL LETTER S WITH DIAGONAL STROKE +A7CD ; LATIN SMALL LETTER S WITH DIAGONAL STROKE A7D0 ; LATIN CAPITAL LETTER CLOSED INSULAR G A7D1 ; LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; LATIN SMALL LETTER DOUBLE THORN @@ -30044,6 +30047,75 @@ 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 @@ -37904,6 +37976,10 @@ FFFD ; REPLACEMENT CHARACTER 1BCA1 ; SHORTHAND FORMAT CONTINUING OVERLAP 1BCA2 ; SHORTHAND FORMAT DOWN STEP 1BCA3 ; SHORTHAND FORMAT UP STEP +1CEB0 ; HORIZONTAL ZIGZAG LINE +1CEB1 ; KEYHOLE +1CEB2 ; OLD PERSONAL COMPUTER WITH MONITOR IN PORTRAIT ORIENTATION +1CEB3 ; BLACK RIGHT TRIANGLE CARET 1CF00 ; ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT 1CF01 ; ZNAMENNY COMBINING MARK NIZKO S KRYZHEM ON LEFT 1CF02 ; ZNAMENNY COMBINING MARK TSATA ON LEFT @@ -40799,50 +40875,6 @@ FFFD ; REPLACEMENT CHARACTER 1E4F7 ; NAG MUNDARI DIGIT SEVEN 1E4F8 ; NAG MUNDARI DIGIT EIGHT 1E4F9 ; NAG MUNDARI DIGIT NINE -1E5D0 ; OL ONAL LETTER O -1E5D1 ; OL ONAL LETTER OM -1E5D2 ; OL ONAL LETTER ONG -1E5D3 ; OL ONAL LETTER ORR -1E5D4 ; OL ONAL LETTER OO -1E5D5 ; OL ONAL LETTER OY -1E5D6 ; OL ONAL LETTER A -1E5D7 ; OL ONAL LETTER AD -1E5D8 ; OL ONAL LETTER AB -1E5D9 ; OL ONAL LETTER AH -1E5DA ; OL ONAL LETTER AL -1E5DB ; OL ONAL LETTER AW -1E5DC ; OL ONAL LETTER I -1E5DD ; OL ONAL LETTER IT -1E5DE ; OL ONAL LETTER IP -1E5DF ; OL ONAL LETTER ITT -1E5E0 ; OL ONAL LETTER ID -1E5E1 ; OL ONAL LETTER IN -1E5E2 ; OL ONAL LETTER U -1E5E3 ; OL ONAL LETTER UK -1E5E4 ; OL ONAL LETTER UDD -1E5E5 ; OL ONAL LETTER UJ -1E5E6 ; OL ONAL LETTER UNY -1E5E7 ; OL ONAL LETTER UR -1E5E8 ; OL ONAL LETTER E -1E5E9 ; OL ONAL LETTER ES -1E5EA ; OL ONAL LETTER EH -1E5EB ; OL ONAL LETTER EC -1E5EC ; OL ONAL LETTER ENN -1E5ED ; OL ONAL LETTER EG -1E5EE ; OL ONAL SIGN MU -1E5EF ; OL ONAL SIGN IKIR -1E5F0 ; OL ONAL SIGN HODDOND -1E5F1 ; OL ONAL DIGIT ZERO -1E5F2 ; OL ONAL DIGIT ONE -1E5F3 ; OL ONAL DIGIT TWO -1E5F4 ; OL ONAL DIGIT THREE -1E5F5 ; OL ONAL DIGIT FOUR -1E5F6 ; OL ONAL DIGIT FIVE -1E5F7 ; OL ONAL DIGIT SIX -1E5F8 ; OL ONAL DIGIT SEVEN -1E5F9 ; OL ONAL DIGIT EIGHT -1E5FA ; OL ONAL DIGIT NINE -1E5FF ; OL ONAL ABBREVIATION SIGN 1E7E0 ; ETHIOPIC SYLLABLE HHYA 1E7E1 ; ETHIOPIC SYLLABLE HHYU 1E7E2 ; ETHIOPIC SYLLABLE HHYI @@ -43325,6 +43357,7 @@ FFFD ; REPLACEMENT CHARACTER 1F8AD ; WHITE ARROW SHAFT WIDTH TWO THIRDS 1F8B0 ; ARROW POINTING UPWARDS THEN NORTH WEST 1F8B1 ; ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST +1F8B2 ; RIGHTWARDS ARROW WITH LOWER HOOK 1F900 ; CIRCLED CROSS FORMEE WITH FOUR DOTS 1F901 ; CIRCLED CROSS FORMEE WITH TWO DOTS 1F902 ; CIRCLED CROSS FORMEE @@ -44345,6 +44378,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 149982 +# Total code points: 150015 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedNumericType.txt b/unicodetools/data/ucd/dev/extracted/DerivedNumericType.txt index e0ecb4cf68..4384773139 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: 2023-10-23, 13:17:06 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 @@ -285,7 +286,6 @@ FF10..FF19 ; Decimal # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E140..1E149 ; Decimal # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E2F0..1E2F9 ; Decimal # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE 1E4F0..1E4F9 ; Decimal # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE -1E5F1..1E5FA ; Decimal # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE 1E950..1E959 ; Decimal # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Decimal # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE diff --git a/unicodetools/data/ucd/dev/extracted/DerivedNumericValues.txt b/unicodetools/data/ucd/dev/extracted/DerivedNumericValues.txt index af2036b5c7..c4bbab74b2 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: 2023-10-23, 13:17:06 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 @@ -124,7 +125,6 @@ FF10 ; 0.0 ; ; 0 # Nd FULLWIDTH DIGIT ZERO 1E140 ; 0.0 ; ; 0 # Nd NYIAKENG PUACHUE HMONG DIGIT ZERO 1E2F0 ; 0.0 ; ; 0 # Nd WANCHO DIGIT ZERO 1E4F0 ; 0.0 ; ; 0 # Nd NAG MUNDARI DIGIT ZERO -1E5F1 ; 0.0 ; ; 0 # Nd OL ONAL DIGIT ZERO 1E950 ; 0.0 ; ; 0 # Nd ADLAM DIGIT ZERO 1F100..1F101 ; 0.0 ; ; 0 # No [2] DIGIT ZERO FULL STOP..DIGIT ZERO COMMA 1F10B..1F10C ; 0.0 ; ; 0 # No [2] DINGBAT CIRCLED SANS-SERIF DIGIT ZERO..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO @@ -500,6 +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 @@ -550,7 +551,6 @@ FF11 ; 1.0 ; ; 1 # Nd FULLWIDTH DIGIT ONE 1E141 ; 1.0 ; ; 1 # Nd NYIAKENG PUACHUE HMONG DIGIT ONE 1E2F1 ; 1.0 ; ; 1 # Nd WANCHO DIGIT ONE 1E4F1 ; 1.0 ; ; 1 # Nd NAG MUNDARI DIGIT ONE -1E5F2 ; 1.0 ; ; 1 # Nd OL ONAL DIGIT ONE 1E8C7 ; 1.0 ; ; 1 # No MENDE KIKAKUI DIGIT ONE 1E951 ; 1.0 ; ; 1 # Nd ADLAM DIGIT ONE 1EC71 ; 1.0 ; ; 1 # No INDIC SIYAQ NUMBER ONE @@ -655,6 +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 @@ -707,7 +708,6 @@ FF12 ; 2.0 ; ; 2 # Nd FULLWIDTH DIGIT TWO 1E142 ; 2.0 ; ; 2 # Nd NYIAKENG PUACHUE HMONG DIGIT TWO 1E2F2 ; 2.0 ; ; 2 # Nd WANCHO DIGIT TWO 1E4F2 ; 2.0 ; ; 2 # Nd NAG MUNDARI DIGIT TWO -1E5F3 ; 2.0 ; ; 2 # Nd OL ONAL DIGIT TWO 1E8C8 ; 2.0 ; ; 2 # No MENDE KIKAKUI DIGIT TWO 1E952 ; 2.0 ; ; 2 # Nd ADLAM DIGIT TWO 1EC72 ; 2.0 ; ; 2 # No INDIC SIYAQ NUMBER TWO @@ -804,6 +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 @@ -857,7 +858,6 @@ FF13 ; 3.0 ; ; 3 # Nd FULLWIDTH DIGIT THREE 1E143 ; 3.0 ; ; 3 # Nd NYIAKENG PUACHUE HMONG DIGIT THREE 1E2F3 ; 3.0 ; ; 3 # Nd WANCHO DIGIT THREE 1E4F3 ; 3.0 ; ; 3 # Nd NAG MUNDARI DIGIT THREE -1E5F4 ; 3.0 ; ; 3 # Nd OL ONAL DIGIT THREE 1E8C9 ; 3.0 ; ; 3 # No MENDE KIKAKUI DIGIT THREE 1E953 ; 3.0 ; ; 3 # Nd ADLAM DIGIT THREE 1EC73 ; 3.0 ; ; 3 # No INDIC SIYAQ NUMBER THREE @@ -950,6 +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 @@ -1003,7 +1004,6 @@ FF14 ; 4.0 ; ; 4 # Nd FULLWIDTH DIGIT FOUR 1E144 ; 4.0 ; ; 4 # Nd NYIAKENG PUACHUE HMONG DIGIT FOUR 1E2F4 ; 4.0 ; ; 4 # Nd WANCHO DIGIT FOUR 1E4F4 ; 4.0 ; ; 4 # Nd NAG MUNDARI DIGIT FOUR -1E5F5 ; 4.0 ; ; 4 # Nd OL ONAL DIGIT FOUR 1E8CA ; 4.0 ; ; 4 # No MENDE KIKAKUI DIGIT FOUR 1E954 ; 4.0 ; ; 4 # Nd ADLAM DIGIT FOUR 1EC74 ; 4.0 ; ; 4 # No INDIC SIYAQ NUMBER FOUR @@ -1100,6 +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 @@ -1152,7 +1153,6 @@ FF15 ; 5.0 ; ; 5 # Nd FULLWIDTH DIGIT FIVE 1E145 ; 5.0 ; ; 5 # Nd NYIAKENG PUACHUE HMONG DIGIT FIVE 1E2F5 ; 5.0 ; ; 5 # Nd WANCHO DIGIT FIVE 1E4F5 ; 5.0 ; ; 5 # Nd NAG MUNDARI DIGIT FIVE -1E5F6 ; 5.0 ; ; 5 # Nd OL ONAL DIGIT FIVE 1E8CB ; 5.0 ; ; 5 # No MENDE KIKAKUI DIGIT FIVE 1E955 ; 5.0 ; ; 5 # Nd ADLAM DIGIT FIVE 1EC75 ; 5.0 ; ; 5 # No INDIC SIYAQ NUMBER FIVE @@ -1238,6 +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 @@ -1284,7 +1285,6 @@ FF16 ; 6.0 ; ; 6 # Nd FULLWIDTH DIGIT SIX 1E146 ; 6.0 ; ; 6 # Nd NYIAKENG PUACHUE HMONG DIGIT SIX 1E2F6 ; 6.0 ; ; 6 # Nd WANCHO DIGIT SIX 1E4F6 ; 6.0 ; ; 6 # Nd NAG MUNDARI DIGIT SIX -1E5F7 ; 6.0 ; ; 6 # Nd OL ONAL DIGIT SIX 1E8CC ; 6.0 ; ; 6 # No MENDE KIKAKUI DIGIT SIX 1E956 ; 6.0 ; ; 6 # Nd ADLAM DIGIT SIX 1EC76 ; 6.0 ; ; 6 # No INDIC SIYAQ NUMBER SIX @@ -1369,6 +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 @@ -1414,7 +1415,6 @@ FF17 ; 7.0 ; ; 7 # Nd FULLWIDTH DIGIT SEVEN 1E147 ; 7.0 ; ; 7 # Nd NYIAKENG PUACHUE HMONG DIGIT SEVEN 1E2F7 ; 7.0 ; ; 7 # Nd WANCHO DIGIT SEVEN 1E4F7 ; 7.0 ; ; 7 # Nd NAG MUNDARI DIGIT SEVEN -1E5F8 ; 7.0 ; ; 7 # Nd OL ONAL DIGIT SEVEN 1E8CD ; 7.0 ; ; 7 # No MENDE KIKAKUI DIGIT SEVEN 1E957 ; 7.0 ; ; 7 # Nd ADLAM DIGIT SEVEN 1EC77 ; 7.0 ; ; 7 # No INDIC SIYAQ NUMBER SEVEN @@ -1496,6 +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 @@ -1541,7 +1542,6 @@ FF18 ; 8.0 ; ; 8 # Nd FULLWIDTH DIGIT EIGHT 1E148 ; 8.0 ; ; 8 # Nd NYIAKENG PUACHUE HMONG DIGIT EIGHT 1E2F8 ; 8.0 ; ; 8 # Nd WANCHO DIGIT EIGHT 1E4F8 ; 8.0 ; ; 8 # Nd NAG MUNDARI DIGIT EIGHT -1E5F9 ; 8.0 ; ; 8 # Nd OL ONAL DIGIT EIGHT 1E8CE ; 8.0 ; ; 8 # No MENDE KIKAKUI DIGIT EIGHT 1E958 ; 8.0 ; ; 8 # Nd ADLAM DIGIT EIGHT 1EC78 ; 8.0 ; ; 8 # No INDIC SIYAQ NUMBER EIGHT @@ -1625,6 +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 @@ -1670,7 +1671,6 @@ FF19 ; 9.0 ; ; 9 # Nd FULLWIDTH DIGIT NINE 1E149 ; 9.0 ; ; 9 # Nd NYIAKENG PUACHUE HMONG DIGIT NINE 1E2F9 ; 9.0 ; ; 9 # Nd WANCHO DIGIT NINE 1E4F9 ; 9.0 ; ; 9 # Nd NAG MUNDARI DIGIT NINE -1E5FA ; 9.0 ; ; 9 # Nd OL ONAL DIGIT NINE 1E8CF ; 9.0 ; ; 9 # No MENDE KIKAKUI DIGIT NINE 1E959 ; 9.0 ; ; 9 # Nd ADLAM DIGIT NINE 1EC79 ; 9.0 ; ; 9 # No INDIC SIYAQ NUMBER NINE diff --git a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java index fa1e9bc183..880612bf61 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"), @@ -467,6 +468,7 @@ public enum Block_Values implements Named { Syloti_Nagri("Syloti_Nagri"), Symbols_And_Pictographs_Extended_A("Symbols_And_Pictographs_Ext_A"), Symbols_For_Legacy_Computing("Symbols_For_Legacy_Computing"), + Symbols_For_Legacy_Computing_Supplement("Symbols_For_Legacy_Computing_Sup"), Syriac("Syriac"), Syriac_Supplement("Syriac_Sup"), Tagalog("Tagalog"), @@ -1740,6 +1742,7 @@ 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 ae5eb0f842..c83570084c 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 @@ -288,6 +289,7 @@ Sutton_SignWriting ; Sutton_SignWriting Syloti_Nagri ; Syloti_Nagri Symbols_And_Pictographs_Ext_A ; Symbols_And_Pictographs_Extended_A Symbols_For_Legacy_Computing ; Symbols_For_Legacy_Computing +Symbols_For_Legacy_Computing_Sup ; Symbols_For_Legacy_Computing_Supplement Syriac ; Syriac Syriac_Sup ; Syriac_Supplement Tagalog ; Tagalog