diff --git a/unicodetools/data/ucd/dev/CaseFolding.txt b/unicodetools/data/ucd/dev/CaseFolding.txt index 2f1047b36..ccba5e478 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: 2023-11-02, 18:04:12 GMT +# Date: 2023-12-14, 01:49:09 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1244,6 +1244,8 @@ 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 +A7D2; C; A7D3; # LATIN CAPITAL LETTER DOUBLE THORN +A7D4; C; A7D5; # LATIN CAPITAL LETTER DOUBLE WYNN A7D6; C; A7D7; # LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8; C; A7D9; # LATIN CAPITAL LETTER SIGMOID S A7DA; C; A7DB; # LATIN CAPITAL LETTER LAMBDA diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index d0f51612e..eb682c91f 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: 2023-11-10, 22:24:48 GMT +# Date: 2023-12-14, 01:49:11 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -2018,6 +2018,8 @@ FDFE..FDFF ; 14.0 # [2] ARABIC LIGATURE SUBHAANAHU WA TAAALAA..ARABIC LIGAT 2427..2429 ; 16.0 # [3] SYMBOL FOR DELETE SQUARE CHECKER BOARD FORM..SYMBOL FOR DELETE MEDIUM SHADE FORM 31E4..31E5 ; 16.0 # [2] CJK STROKE HZXG..CJK STROKE SZP A7CB..A7CD ; 16.0 # [3] LATIN CAPITAL LETTER RAMS HORN..LATIN SMALL LETTER S WITH DIAGONAL STROKE +A7D2 ; 16.0 # LATIN CAPITAL LETTER DOUBLE THORN +A7D4 ; 16.0 # LATIN CAPITAL LETTER DOUBLE WYNN A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER LAMBDA WITH 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 @@ -2058,6 +2060,6 @@ A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L 1FAE9 ; 16.0 # FACE WITH BAGS UNDER EYES 1FBCB..1FBEF ; 16.0 # [37] WHITE CROSS MARK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 1192 +# Total code points: 1194 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 118350283..a7b70a13c 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: 2023-11-10, 22:25:26 GMT +# Date: 2023-12-14, 01:49:31 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -834,9 +834,7 @@ 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..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..A7DC ; Alphabetic # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7D0..A7DC ; Alphabetic # L& [13] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; Alphabetic # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; Alphabetic # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; Alphabetic # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -1440,7 +1438,7 @@ 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: 138766 +# Total code points: 138768 # ================================================ @@ -2750,6 +2748,8 @@ A7C4..A7C7 ; Uppercase # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..L 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 +A7D2 ; Uppercase # L& LATIN CAPITAL LETTER DOUBLE THORN +A7D4 ; Uppercase # L& LATIN CAPITAL LETTER DOUBLE WYNN A7D6 ; Uppercase # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Uppercase # L& LATIN CAPITAL LETTER SIGMOID S A7DA ; Uppercase # L& LATIN CAPITAL LETTER LAMBDA @@ -2802,7 +2802,7 @@ 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: 1978 +# Total code points: 1980 # ================================================ @@ -2911,9 +2911,7 @@ 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..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..A7DC ; Cased # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7D0..A7DC ; Cased # L& [13] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; Cased # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; Cased # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F8..A7F9 ; Cased # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -2987,7 +2985,7 @@ 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: 4578 +# Total code points: 4580 # ================================================ @@ -4110,6 +4108,8 @@ A7C4..A7C7 ; Changes_When_Lowercased # L& [4] LATIN CAPITAL LETTER C WITH P 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 +A7D2 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER DOUBLE THORN +A7D4 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER DOUBLE WYNN A7D6 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER SIGMOID S A7DA ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER LAMBDA @@ -4128,7 +4128,7 @@ FF21..FF3A ; Changes_When_Lowercased # L& [26] FULLWIDTH LATIN CAPITAL LETTE 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: 1460 +# Total code points: 1462 # ================================================ @@ -4747,6 +4747,8 @@ A7C8 ; Changes_When_Uppercased # L& LATIN SMALL LETTER D WITH SHO 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 +A7D3 ; Changes_When_Uppercased # L& LATIN SMALL LETTER DOUBLE THORN +A7D5 ; Changes_When_Uppercased # L& LATIN SMALL LETTER DOUBLE WYNN A7D7 ; Changes_When_Uppercased # L& LATIN SMALL LETTER MIDDLE SCOTS S A7D9 ; Changes_When_Uppercased # L& LATIN SMALL LETTER SIGMOID S A7DB ; Changes_When_Uppercased # L& LATIN SMALL LETTER LAMBDA @@ -4768,7 +4770,7 @@ FF41..FF5A ; Changes_When_Uppercased # L& [26] FULLWIDTH LATIN SMALL LETTER 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: 1552 +# Total code points: 1554 # ================================================ @@ -5386,6 +5388,8 @@ A7C8 ; Changes_When_Titlecased # L& LATIN SMALL LETTER D WITH SHO 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 +A7D3 ; Changes_When_Titlecased # L& LATIN SMALL LETTER DOUBLE THORN +A7D5 ; Changes_When_Titlecased # L& LATIN SMALL LETTER DOUBLE WYNN A7D7 ; Changes_When_Titlecased # L& LATIN SMALL LETTER MIDDLE SCOTS S A7D9 ; Changes_When_Titlecased # L& LATIN SMALL LETTER SIGMOID S A7DB ; Changes_When_Titlecased # L& LATIN SMALL LETTER LAMBDA @@ -5407,7 +5411,7 @@ FF41..FF5A ; Changes_When_Titlecased # L& [26] FULLWIDTH LATIN SMALL LETTER 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: 1479 +# Total code points: 1481 # ================================================ @@ -6022,6 +6026,8 @@ A7C4..A7C7 ; Changes_When_Casefolded # L& [4] LATIN CAPITAL LETTER C WITH P 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 +A7D2 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER DOUBLE THORN +A7D4 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER DOUBLE WYNN A7D6 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER SIGMOID S A7DA ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER LAMBDA @@ -6043,7 +6049,7 @@ FF21..FF3A ; Changes_When_Casefolded # L& [26] FULLWIDTH LATIN CAPITAL LETTE 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: 1533 +# Total code points: 1535 # ================================================ @@ -6156,8 +6162,7 @@ A78B..A78D ; Changes_When_Casemapped # L& [3] LATIN CAPITAL LETTER SALTILLO 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..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..A7DC ; Changes_When_Casemapped # L& [7] LATIN CAPITAL LETTER MIDDLE SCOTS S..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7D0..A7DC ; Changes_When_Casemapped # L& [13] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F5..A7F6 ; Changes_When_Casemapped # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H AB53 ; Changes_When_Casemapped # L& LATIN SMALL LETTER CHI AB70..ABBF ; Changes_When_Casemapped # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA @@ -6184,7 +6189,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 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: 2981 +# Total code points: 2985 # ================================================ @@ -6561,9 +6566,7 @@ 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..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..A7DC ; ID_Start # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7D0..A7DC ; ID_Start # L& [13] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; ID_Start # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; ID_Start # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; ID_Start # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -6960,7 +6963,7 @@ 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: 137276 +# Total code points: 137278 # ================================================ @@ -7645,9 +7648,7 @@ 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..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..A7DC ; ID_Continue # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7D0..A7DC ; ID_Continue # L& [13] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; ID_Continue # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; ID_Continue # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; ID_Continue # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -8367,7 +8368,7 @@ 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: 140548 +# Total code points: 140550 # ================================================ @@ -8740,9 +8741,7 @@ 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..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..A7DC ; XID_Start # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7D0..A7DC ; XID_Start # L& [13] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; XID_Start # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; XID_Start # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; XID_Start # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -9144,7 +9143,7 @@ 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: 137253 +# Total code points: 137255 # ================================================ @@ -9824,9 +9823,7 @@ 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..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..A7DC ; XID_Continue # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7D0..A7DC ; XID_Continue # L& [13] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; XID_Continue # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; XID_Continue # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; XID_Continue # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -10552,7 +10549,7 @@ 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: 140529 +# Total code points: 140531 # ================================================ @@ -11957,9 +11954,7 @@ A789..A78A ; Grapheme_Base # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER 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..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..A7DC ; Grapheme_Base # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7D0..A7DC ; Grapheme_Base # L& [13] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; Grapheme_Base # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; Grapheme_Base # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; Grapheme_Base # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -12800,7 +12795,7 @@ 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: 148770 +# Total code points: 148772 # ================================================ diff --git a/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt b/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt index 797dfb763..adce9c2b7 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: 2023-11-10, 20:57:25 GMT +# Date: 2023-12-14, 01:49:36 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 @@ -5449,6 +5449,8 @@ A7C9 ; NFKC_CF; A7CA # L& LATIN CAPITAL LETTER S WITH S 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 +A7D2 ; NFKC_CF; A7D3 # L& LATIN CAPITAL LETTER DOUBLE THORN +A7D4 ; NFKC_CF; A7D5 # L& LATIN CAPITAL LETTER DOUBLE WYNN A7D6 ; NFKC_CF; A7D7 # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; NFKC_CF; A7D9 # L& LATIN CAPITAL LETTER SIGMOID S A7DA ; NFKC_CF; A7DB # L& LATIN CAPITAL LETTER LAMBDA @@ -9148,7 +9150,7 @@ E0080..E00FF ; NFKC_CF; # Cn [128] .... -# Total code points: 10554 +# Total code points: 10556 # ================================================ @@ -11583,6 +11585,8 @@ A7C9 ; NFKC_SCF; A7CA # L& LATIN CAPITAL LETTER S WITH 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 +A7D2 ; NFKC_SCF; A7D3 # L& LATIN CAPITAL LETTER DOUBLE THORN +A7D4 ; NFKC_SCF; A7D5 # L& LATIN CAPITAL LETTER DOUBLE WYNN A7D6 ; NFKC_SCF; A7D7 # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; NFKC_SCF; A7D9 # L& LATIN CAPITAL LETTER SIGMOID S A7DA ; NFKC_SCF; A7DB # L& LATIN CAPITAL LETTER LAMBDA @@ -15282,7 +15286,7 @@ E0080..E00FF ; NFKC_SCF; # Cn [128] .... -# Total code points: 10516 +# Total code points: 10518 # ================================================ @@ -16053,6 +16057,8 @@ A7C4..A7C7 ; Changes_When_NFKC_Casefolded # L& [4] LATIN CAPITAL LETTER C W 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 +A7D2 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER DOUBLE THORN +A7D4 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER DOUBLE WYNN A7D6 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER SIGMOID S A7DA ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER LAMBDA @@ -16300,6 +16306,6 @@ E0080..E00FF ; Changes_When_NFKC_Casefolded # Cn [128] .... -# Total code points: 10554 +# Total code points: 10556 # EOF diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index a2faf7b49..6aed8f304 100644 --- a/unicodetools/data/ucd/dev/EastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/EastAsianWidth.txt @@ -1,5 +1,5 @@ # EastAsianWidth-16.0.0.txt -# Date: 2023-11-10, 22:25:47 GMT +# Date: 2023-12-14, 01:49:38 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 @@ -1545,9 +1545,7 @@ A789..A78A ; N # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQ 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..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..A7DC ; N # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7D0..A7DC ; N # L& [13] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; N # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; N # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; N # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 7b47514bc..03b2dfd7e 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,5 @@ # LineBreak-16.0.0.txt -# Date: 2023-11-10, 22:25:50 GMT +# Date: 2023-12-14, 04:00:57 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1580,9 +1580,7 @@ A789..A78A ; AL # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQ 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..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..A7DC ; AL # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7D0..A7DC ; AL # L& [13] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; AL # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; AL # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; AL # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 73b0ec242..e1a7e7629 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,5 +1,5 @@ # Scripts-16.0.0.txt -# Date: 2023-11-10, 22:26:58 GMT +# Date: 2023-12-14, 04:23:12 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 @@ -677,9 +677,7 @@ A771..A787 ; Latin # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSU 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..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..A7DC ; Latin # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7D0..A7DC ; Latin # L& [13] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; Latin # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; Latin # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; Latin # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -702,7 +700,7 @@ 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: 1487 +# Total code points: 1489 # ================================================ diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 4376ff723..4215f744c 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -14278,8 +14278,10 @@ 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;;;;; -A7D5;LATIN SMALL LETTER DOUBLE WYNN;Ll;0;L;;;;;N;;;;; +A7D2;LATIN CAPITAL LETTER DOUBLE THORN;Lu;0;L;;;;;N;;;;A7D3; +A7D3;LATIN SMALL LETTER DOUBLE THORN;Ll;0;L;;;;;N;;;A7D2;;A7D2 +A7D4;LATIN CAPITAL LETTER DOUBLE WYNN;Lu;0;L;;;;;N;;;;A7D5; +A7D5;LATIN SMALL LETTER DOUBLE WYNN;Ll;0;L;;;;;N;;;A7D4;;A7D4 A7D6;LATIN CAPITAL LETTER MIDDLE SCOTS S;Lu;0;L;;;;;N;;;;A7D7; A7D7;LATIN SMALL LETTER MIDDLE SCOTS S;Ll;0;L;;;;;N;;;A7D6;;A7D6 A7D8;LATIN CAPITAL LETTER SIGMOID S;Lu;0;L;;;;;N;;;;A7D9; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index 005f57218..aae74b202 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ # VerticalOrientation-16.0.0.txt -# Date: 2023-11-10, 22:27:08 GMT +# Date: 2023-12-14, 01:50:07 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 @@ -1357,9 +1357,7 @@ A789..A78A ; R # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQ 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..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..A7DC ; R # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7D0..A7DC ; R # L& [13] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; R # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; R # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; R # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I diff --git a/unicodetools/data/ucd/dev/auxiliary/LineBreakTest.html b/unicodetools/data/ucd/dev/auxiliary/LineBreakTest.html index 6e3c42160..58ae262e3 100644 --- a/unicodetools/data/ucd/dev/auxiliary/LineBreakTest.html +++ b/unicodetools/data/ucd/dev/auxiliary/LineBreakTest.html @@ -7,7 +7,7 @@

Line_Break Chart

Unicode Version: 16.0.0

-

Date: 2023-11-03, 21:06:18 GMT

+

Date: 2023-12-14, 04:00:58 GMT

This page illustrates the application of the Line_Break specification. The material here is informative, not normative.

The first chart shows where breaks would appear between different sample characters or strings. The sample characters are chosen mechanically to represent the different properties used by the specification.

Each cell shows the break-status for the position between the character(s) in its row header and the character(s) in its column header. The × symbol indicates no break, while the ÷ symbol indicated a break. The cells with × are also shaded to make it easier to scan the table. For example, in the cell at the intersection of the row headed by “CR” and the column headed by “LF”, there is a × symbol, indicating that there is no break between CR and LF.

Some column headers may be composed, reflecting “treat as” or “ignore” rules.

If your browser handles titles (tooltips), then hovering the mouse over the row header will show a sample character of that type. Hovering over a column header will show the sample character, plus its abbreviated general category and script. Hovering over the intersected cells shows the rule number that produces the break-status. For example, hovering over the cell at the intersection of H3 and JT shows ×, with the rule 26.03. Checking below the table, rule 26.03 is “JT | H3 × JT”, which is the one that applies to that case. Note that a rule is invoked only when no lower-numbered rules have applied.

diff --git a/unicodetools/data/ucd/dev/auxiliary/LineBreakTest.txt b/unicodetools/data/ucd/dev/auxiliary/LineBreakTest.txt index 2cae631d7..3fbdcdccb 100644 --- a/unicodetools/data/ucd/dev/auxiliary/LineBreakTest.txt +++ b/unicodetools/data/ucd/dev/auxiliary/LineBreakTest.txt @@ -1,5 +1,5 @@ # LineBreakTest-16.0.0.txt -# Date: 2023-11-03, 21:06:19 GMT +# Date: 2023-12-14, 04:00:58 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 diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 9138d7847..bc046b984 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: 2023-11-10, 22:27:00 GMT +# Date: 2023-12-14, 01:50:05 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 @@ -1930,6 +1930,8 @@ A7C4..A7C7 ; Upper # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN 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 +A7D2 ; Upper # L& LATIN CAPITAL LETTER DOUBLE THORN +A7D4 ; Upper # L& LATIN CAPITAL LETTER DOUBLE WYNN A7D6 ; Upper # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Upper # L& LATIN CAPITAL LETTER SIGMOID S A7DA ; Upper # L& LATIN CAPITAL LETTER LAMBDA @@ -1982,7 +1984,7 @@ 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: 1963 +# Total code points: 1965 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index 80b411c60..5e79167a7 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: 2023-11-10, 22:27:08 GMT +# Date: 2023-12-14, 01:50:07 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 @@ -1003,9 +1003,7 @@ A789..A78A ; ALetter # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT 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..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..A7DC ; ALetter # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7D0..A7DC ; ALetter # L& [13] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; ALetter # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; ALetter # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; ALetter # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -1355,7 +1353,7 @@ 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: 29799 +# Total code points: 29801 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 03c8c7701..87c10b0f2 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: 2023-11-10, 22:25:22 GMT +# Date: 2023-12-14, 01:49:30 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -663,9 +663,7 @@ A789..A78A ; L # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS 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..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..A7DC ; L # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7D0..A7DC ; L # L& [13] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; L # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; L # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; L # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -1218,7 +1216,7 @@ 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 819344 code points not listed here. +# The above property value applies to 819342 code points not listed here. # Total code points: 1095518 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index b80bb140e..de1ca39af 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: 2023-11-10, 22:25:25 GMT +# Date: 2023-12-14, 01:49:31 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1094,9 +1094,7 @@ A789..A78A ; 0 # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS 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..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..A7DC ; 0 # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7D0..A7DC ; 0 # L& [13] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; 0 # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; 0 # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; 0 # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -2059,7 +2057,7 @@ 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 825574 code points not listed here. +# The above property value applies to 825572 code points not listed here. # Total code points: 1113178 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index d06e0e6e8..f8eb7b1b3 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: 2023-11-10, 22:25:29 GMT +# Date: 2023-12-14, 01:49:33 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 @@ -1182,9 +1182,7 @@ A789..A78A ; N # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS 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..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..A7DC ; N # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7D0..A7DC ; N # L& [13] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; N # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; N # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; N # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -2102,7 +2100,7 @@ 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 765092 code points not listed here. +# The above property value applies to 765090 code points not listed here. # Total code points: 792608 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index 44fd2035f..a929e258a 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: 2023-11-10, 22:25:30 GMT +# Date: 2023-12-14, 01:49:34 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -295,8 +295,6 @@ A4C7..A4CF ; Cn # [9] .. A62C..A63F ; Cn # [20] .. A6F8..A6FF ; Cn # [8] .. A7CE..A7CF ; Cn # [2] .. -A7D2 ; Cn # -A7D4 ; Cn # A7DD..A7F1 ; Cn # [21] .. A82D..A82F ; Cn # [3] .. A83A..A83F ; Cn # [6] .. @@ -746,7 +744,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 823526 +# Total code points: 823524 # ================================================ @@ -1355,6 +1353,8 @@ A7C4..A7C7 ; Lu # [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPIT 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 +A7D2 ; Lu # LATIN CAPITAL LETTER DOUBLE THORN +A7D4 ; Lu # LATIN CAPITAL LETTER DOUBLE WYNN A7D6 ; Lu # LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Lu # LATIN CAPITAL LETTER SIGMOID S A7DA ; Lu # LATIN CAPITAL LETTER LAMBDA @@ -1404,7 +1404,7 @@ 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: 1858 +# Total code points: 1860 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 779b3bbe8..ee662317a 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: 2023-11-10, 22:25:34 GMT +# Date: 2023-12-14, 04:00:52 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 @@ -69,8 +69,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 761646 code points not listed here. -# Total code points: 899114 +# The above property value applies to 761644 code points not listed here. +# Total code points: 899112 # ================================================ @@ -1141,9 +1141,7 @@ A789..A78A ; AL # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUAL 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..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..A7DC ; AL # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7D0..A7DC ; AL # L& [13] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; AL # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; AL # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; AL # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -1610,7 +1608,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1FB00..1FB92 ; AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBEF ; AL # So [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 22690 +# Total code points: 22692 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 145e66ed9..99f73ed67 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: 2023-11-10, 22:25:34 GMT +# Date: 2023-12-14, 01:49:35 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 @@ -14251,7 +14251,9 @@ 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 +A7D2 ; LATIN CAPITAL LETTER DOUBLE THORN A7D3 ; LATIN SMALL LETTER DOUBLE THORN +A7D4 ; LATIN CAPITAL LETTER DOUBLE WYNN A7D5 ; LATIN SMALL LETTER DOUBLE WYNN A7D6 ; LATIN CAPITAL LETTER MIDDLE SCOTS S A7D7 ; LATIN SMALL LETTER MIDDLE SCOTS S @@ -45368,6 +45370,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 151005 +# Total code points: 151007 # EOF