From 0ec91c3fc2fe3a51cb0f6d15d7c5f3af16a70c65 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 2 Apr 2024 17:19:08 +0200 Subject: [PATCH 01/12] UnicodeData.txt lines from L2/22-218R3 --- unicodetools/data/ucd/dev/UnicodeData.txt | 40 +++++++++++++++++++++++ 1 file changed, 40 insertions(+) diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 08593a319..576b7323b 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -1,3 +1,43 @@ +16D80;CHISOI LETTER A;Lo;0;L;;;;;N;;;;; +16D81;CHISOI LETTER BA;Lo;0;L;;;;;N;;;;; +16D82;CHISOI LETTER AI;Lo;0;L;;;;;N;;;;; +16D83;CHISOI LETTER AA;Lo;0;L;;;;;N;;;;; +16D84;CHISOI LETTER GA;Lo;0;L;;;;;N;;;;; +16D85;CHISOI LETTER TA;Lo;0;L;;;;;N;;;;; +16D86;CHISOI LETTER E;Lo;0;L;;;;;N;;;;; +16D87;CHISOI LETTER SA;Lo;0;L;;;;;N;;;;; +16D88;CHISOI LETTER NA;Lo;0;L;;;;;N;;;;; +16D89;CHISOI LETTER I;Lo;0;L;;;;;N;;;;; +16D8A;CHISOI LETTER KA;Lo;0;L;;;;;N;;;;; +16D8B;CHISOI LETTER RA;Lo;0;L;;;;;N;;;;; +16D8C;CHISOI LETTER MA;Lo;0;L;;;;;N;;;;; +16D8D;CHISOI LETTER HA;Lo;0;L;;;;;N;;;;; +16D8E;CHISOI LETTER RRA;Lo;0;L;;;;;N;;;;; +16D8F;CHISOI LETTER U;Lo;0;L;;;;;N;;;;; +16D90;CHISOI LETTER DA;Lo;0;L;;;;;N;;;;; +16D91;CHISOI LETTER LA;Lo;0;L;;;;;N;;;;; +16D92;CHISOI LETTER O;Lo;0;L;;;;;N;;;;; +16D93;CHISOI LETTER NYA;Lo;0;L;;;;;N;;;;; +16D94;CHISOI LETTER NGA;Lo;0;L;;;;;N;;;;; +16D95;CHISOI LETTER CA;Lo;0;L;;;;;N;;;;; +16D96;CHISOI LETTER JA;Lo;0;L;;;;;N;;;;; +16D97;CHISOI LETTER PA;Lo;0;L;;;;;N;;;;; +16D98;CHISOI SIGN ANUSVARA;Mn;0;NSM;;;;;N;;;;; +16D99;CHISOI LETTER YA;Lo;0;L;;;;;N;;;;; +16D9A;CHISOI LETTER DDA;Lo;0;L;;;;;N;;;;; +16D9B;CHISOI LETTER TTA;Lo;0;L;;;;;N;;;;; +16D9C;CHISOI LETTER JARAHA;Lo;0;L;;;;;N;;;;; +16D9D;CHISOI SIGN SISO;Mn;9;NSM;;;;;N;;;;; +16DA0;CHISOI DIGIT ZERO;Nd;0;L;;0;0;0;N;;;;; +16DA1;CHISOI DIGIT ONE;Nd;0;L;;1;1;1;N;;;;; +16DA2;CHISOI DIGIT TWO;Nd;0;L;;2;2;2;N;;;;; +16DA3;CHISOI DIGIT THREE;Nd;0;L;;3;3;3;N;;;;; +16DA4;CHISOI DIGIT FOUR;Nd;0;L;;4;4;4;N;;;;; +16DA5;CHISOI DIGIT FIVE;Nd;0;L;;5;5;5;N;;;;; +16DA6;CHISOI DIGIT SIX;Nd;0;L;;6;6;6;N;;;;; +16DA7;CHISOI DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;; +16DA8;CHISOI DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;; +16DA9;CHISOI DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; 0000;;Cc;0;BN;;;;;N;NULL;;;; 0001;;Cc;0;BN;;;;;N;START OF HEADING;;;; 0002;;Cc;0;BN;;;;;N;START OF TEXT;;;; From de8ec6bf15efd0579d6094bb8220144fb80a9937 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 2 Apr 2024 17:20:33 +0200 Subject: [PATCH 02/12] LineBreak.txt lines from L2/22-218R3 --- unicodetools/data/ucd/dev/LineBreak.txt | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 1d8bd89ec..7a908a922 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,3 +1,8 @@ +16D80..16D97;AL # Lo [25] CHISOI LETTER A..CHISOI LETTER PA +16D98 ;CM # Mn [01] CHISOI SIGN ANUSVARA +16D99..16D9C;AL # Lo [04] CHISOI LETTER YA..CHISOI LETTER JARAHA +16D9D ;CM # Mn [01] CHISOI SIGN SISO +16DA0..16DA9;NU # Nd [09] CHISOI DIGIT ZERO..CHISOI DIGIT NINE # LineBreak-16.0.0.txt # Date: 2024-02-02, 23:11:30 GMT # © 2024 Unicode®, Inc. From f50a2840bbc121b90a966cae7c5a260b3ec723ff Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 2 Apr 2024 17:22:04 +0200 Subject: [PATCH 03/12] Scripts.txt --- unicodetools/data/ucd/dev/Scripts.txt | 1 + 1 file changed, 1 insertion(+) diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 2e0b4fd4b..c199f3ab6 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,3 +1,4 @@ +16D80..16DA9;Chisoi # Scripts-16.0.0.txt # Date: 2024-02-02, 23:11:49 GMT # © 2024 Unicode®, Inc. From 4df1a1cb89a3a036099b306c138d1579727fd082 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 2 Apr 2024 17:32:31 +0200 Subject: [PATCH 04/12] new block --- unicodetools/data/ucd/dev/Blocks.txt | 1 + .../src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt | 1 + 2 files changed, 2 insertions(+) diff --git a/unicodetools/data/ucd/dev/Blocks.txt b/unicodetools/data/ucd/dev/Blocks.txt index 733274fab..88e1079b6 100644 --- a/unicodetools/data/ucd/dev/Blocks.txt +++ b/unicodetools/data/ucd/dev/Blocks.txt @@ -302,6 +302,7 @@ FFF0..FFFF; Specials 16AD0..16AFF; Bassa Vah 16B00..16B8F; Pahawh Hmong 16D40..16D7F; Kirat Rai +16D80..16DAF; Chisoi 16E40..16E9F; Medefaidrin 16F00..16F9F; Miao 16FE0..16FFF; Ideographic Symbols and Punctuation 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 eaa03a0f7..a1842890b 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt @@ -42,6 +42,7 @@ Cham ; Cham Cherokee ; Cherokee Cherokee_Sup ; Cherokee_Supplement Chess_Symbols ; Chess_Symbols +Chisoi ; Chisoi Chorasmian ; Chorasmian CJK_Compat ; CJK_Compatibility CJK_Compat_Forms ; CJK_Compatibility_Forms From 8385656a7e5e0f1ffaab96e454dab6e5ae069f7a Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 2 Apr 2024 17:33:45 +0200 Subject: [PATCH 05/12] Danda scx --- unicodetools/data/ucd/dev/ScriptExtensions.txt | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/unicodetools/data/ucd/dev/ScriptExtensions.txt b/unicodetools/data/ucd/dev/ScriptExtensions.txt index f9d4b550e..201aec28a 100644 --- a/unicodetools/data/ucd/dev/ScriptExtensions.txt +++ b/unicodetools/data/ucd/dev/ScriptExtensions.txt @@ -86,8 +86,8 @@ 06D4 ; Arab Rohg # Po ARABIC FULL STOP 0951 ; Beng Deva Gran Gujr Guru Knda Latn Mlym Orya Shrd Taml Telu Tirh #Mn DEVANAGARI STRESS SIGN UDATTA 0952 ; Beng Deva Gran Gujr Guru Knda Latn Mlym Orya Taml Telu Tirh #Mn DEVANAGARI STRESS SIGN ANUDATTA -0964 ; Beng Deva Dogr Gong Gonm Gran Gujr Guru Knda Mahj Mlym Nand Onao Orya Sind Sinh Sylo Takr Taml Telu Tirh #Po DEVANAGARI DANDA -0965 ; Beng Deva Dogr Gong Gonm Gran Gujr Gukh Guru Knda Limb Mahj Mlym Nand Onao Orya Sind Sinh Sylo Takr Taml Telu Tirh #Po DEVANAGARI DOUBLE DANDA +0964 ; Beng Deva Dogr Gong Gonm Gran Gujr Guru Knda Mahj Mlym Nand Onao Orya Sind Sinh Sylo Takr Taml Telu Tirh Chis #Po DEVANAGARI DANDA +0965 ; Beng Deva Dogr Gong Gonm Gran Gujr Gukh Guru Knda Limb Mahj Mlym Nand Onao Orya Sind Sinh Sylo Takr Taml Telu Tirh Chis #Po DEVANAGARI DOUBLE DANDA 0966..096F ; Deva Dogr Kthi Mahj # Nd [10] DEVANAGARI DIGIT ZERO..DEVANAGARI DIGIT NINE 09E6..09EF ; Beng Cakm Sylo # Nd [10] BENGALI DIGIT ZERO..BENGALI DIGIT NINE 0A66..0A6F ; Guru Mult # Nd [10] GURMUKHI DIGIT ZERO..GURMUKHI DIGIT NINE From e1efb856d7a9f3a33182e89ec5831b4bc4e05866 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 2 Apr 2024 17:37:32 +0200 Subject: [PATCH 06/12] Alphabetic for the anusvara, Diacritic for the virama --- unicodetools/data/ucd/dev/PropList.txt | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt index 1e3e2912b..28e095016 100644 --- a/unicodetools/data/ucd/dev/PropList.txt +++ b/unicodetools/data/ucd/dev/PropList.txt @@ -430,6 +430,7 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L # ================================================ +16D98; Other_Alphabetic 0345 ; Other_Alphabetic # Mn COMBINING GREEK YPOGEGRAMMENI 0363..036F ; Other_Alphabetic # Mn [13] COMBINING LATIN SMALL LETTER A..COMBINING LATIN SMALL LETTER X 05B0..05BD ; Other_Alphabetic # Mn [14] HEBREW POINT SHEVA..HEBREW POINT METEG @@ -880,7 +881,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM # Total code points: 106477 # ================================================ - +16D9D ; Diacritic 005E ; Diacritic # Sk CIRCUMFLEX ACCENT 0060 ; Diacritic # Sk GRAVE ACCENT 00A8 ; Diacritic # Sk DIAERESIS From b82bf1dd1146b04e1dd9368b059f51c13a0227f5 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 2 Apr 2024 17:42:26 +0200 Subject: [PATCH 07/12] Regenerate UCD --- unicodetools/data/ucd/dev/DerivedAge.txt | 6 +- .../data/ucd/dev/DerivedCoreProperties.txt | 48 ++++++++--- unicodetools/data/ucd/dev/EastAsianWidth.txt | 7 +- unicodetools/data/ucd/dev/LineBreak.txt | 12 +-- .../data/ucd/dev/NormalizationTest.txt | 4 +- unicodetools/data/ucd/dev/PropList.txt | 11 +-- .../data/ucd/dev/PropertyValueAliases.txt | 4 +- .../data/ucd/dev/ScriptExtensions.txt | 6 +- unicodetools/data/ucd/dev/Scripts.txt | 14 +++- unicodetools/data/ucd/dev/UnicodeData.txt | 80 +++++++++---------- .../data/ucd/dev/VerticalOrientation.txt | 7 +- .../dev/auxiliary/GraphemeBreakProperty.txt | 6 +- .../dev/auxiliary/SentenceBreakProperty.txt | 13 ++- .../ucd/dev/auxiliary/WordBreakProperty.txt | 13 ++- .../ucd/dev/extracted/DerivedBidiClass.txt | 13 ++- .../dev/extracted/DerivedCombiningClass.txt | 13 ++- .../dev/extracted/DerivedEastAsianWidth.txt | 9 ++- .../dev/extracted/DerivedGeneralCategory.txt | 19 +++-- .../ucd/dev/extracted/DerivedJoiningType.txt | 6 +- .../ucd/dev/extracted/DerivedLineBreak.txt | 17 ++-- .../data/ucd/dev/extracted/DerivedName.txt | 44 +++++++++- .../ucd/dev/extracted/DerivedNumericType.txt | 5 +- .../dev/extracted/DerivedNumericValues.txt | 32 +++++--- 23 files changed, 267 insertions(+), 122 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index d116dccaa..7ae53688c 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: 2024-02-02, 23:11:18 GMT +# Date: 2024-04-02, 15:38:25 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -2043,6 +2043,8 @@ A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L 13460..143FA ; 16.0 # [3995] EGYPTIAN HIEROGLYPH-13460..EGYPTIAN HIEROGLYPH-143FA 16100..16139 ; 16.0 # [58] GURUNG KHEMA LETTER A..GURUNG KHEMA DIGIT NINE 16D40..16D79 ; 16.0 # [58] KIRAT RAI SIGN ANUSVARA..KIRAT RAI DIGIT NINE +16D80..16D9D ; 16.0 # [30] CHISOI LETTER A..CHISOI SIGN SISO +16DA0..16DA9 ; 16.0 # [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 18CFF ; 16.0 # KHITAN SMALL SCRIPT CHARACTER-18CFF 1CC00..1CCF9 ; 16.0 # [250] UP-POINTING GO-KART..OUTLINED DIGIT NINE 1CD00..1CEB3 ; 16.0 # [436] BLOCK OCTANT-3..BLACK RIGHT TRIANGLE CARET @@ -2059,6 +2061,6 @@ 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: 5187 +# Total code points: 5227 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 1e054c4f2..857c0d3d9 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: 2024-02-02, 23:11:24 GMT +# Date: 2024-04-02, 15:39:03 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1310,6 +1310,9 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 16D40..16D42 ; Alphabetic # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA 16D43..16D6A ; Alphabetic # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU 16D6B..16D6C ; Alphabetic # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D80..16D97 ; Alphabetic # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D98 ; Alphabetic # Mn CHISOI SIGN ANUSVARA +16D99..16D9C ; Alphabetic # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA 16E40..16E7F ; Alphabetic # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16F00..16F4A ; Alphabetic # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F4F ; Alphabetic # Mn MIAO SIGN CONSONANT MODIFIER BAR @@ -1441,7 +1444,7 @@ 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: 142761 +# Total code points: 142790 # ================================================ @@ -3458,6 +3461,8 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 16B40..16B43 ; Case_Ignorable # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM 16D40..16D42 ; Case_Ignorable # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA 16D6B..16D6C ; Case_Ignorable # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D98 ; Case_Ignorable # Mn CHISOI SIGN ANUSVARA +16D9D ; Case_Ignorable # Mn CHISOI SIGN SISO 16F4F ; Case_Ignorable # Mn MIAO SIGN CONSONANT MODIFIER BAR 16F8F..16F92 ; Case_Ignorable # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16F93..16F9F ; Case_Ignorable # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 @@ -3505,7 +3510,7 @@ 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: 2749 +# Total code points: 2751 # ================================================ @@ -6846,6 +6851,8 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 16D40..16D42 ; ID_Start # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA 16D43..16D6A ; ID_Start # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU 16D6B..16D6C ; ID_Start # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D80..16D97 ; ID_Start # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D99..16D9C ; ID_Start # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA 16E40..16E7F ; ID_Start # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16F00..16F4A ; ID_Start # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F50 ; ID_Start # Lo MIAO LETTER NASALIZATION @@ -6962,7 +6969,7 @@ 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: 141271 +# Total code points: 141299 # ================================================ @@ -8211,6 +8218,11 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 16D43..16D6A ; ID_Continue # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU 16D6B..16D6C ; ID_Continue # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16D70..16D79 ; ID_Continue # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16D80..16D97 ; ID_Continue # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D98 ; ID_Continue # Mn CHISOI SIGN ANUSVARA +16D99..16D9C ; ID_Continue # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA +16D9D ; ID_Continue # Mn CHISOI SIGN SISO +16DA0..16DA9 ; ID_Continue # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 16E40..16E7F ; ID_Continue # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16F00..16F4A ; ID_Continue # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F4F ; ID_Continue # Mn MIAO SIGN CONSONANT MODIFIER BAR @@ -8370,7 +8382,7 @@ 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: 144543 +# Total code points: 144583 # ================================================ @@ -9032,6 +9044,8 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 16D40..16D42 ; XID_Start # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA 16D43..16D6A ; XID_Start # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU 16D6B..16D6C ; XID_Start # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D80..16D97 ; XID_Start # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D99..16D9C ; XID_Start # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA 16E40..16E7F ; XID_Start # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16F00..16F4A ; XID_Start # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F50 ; XID_Start # Lo MIAO LETTER NASALIZATION @@ -9148,7 +9162,7 @@ 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: 141248 +# Total code points: 141276 # ================================================ @@ -10398,6 +10412,11 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 16D43..16D6A ; XID_Continue # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU 16D6B..16D6C ; XID_Continue # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16D70..16D79 ; XID_Continue # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16D80..16D97 ; XID_Continue # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D98 ; XID_Continue # Mn CHISOI SIGN ANUSVARA +16D99..16D9C ; XID_Continue # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA +16D9D ; XID_Continue # Mn CHISOI SIGN SISO +16DA0..16DA9 ; XID_Continue # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 16E40..16E7F ; XID_Continue # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16F00..16F4A ; XID_Continue # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F4F ; XID_Continue # Mn MIAO SIGN CONSONANT MODIFIER BAR @@ -10557,7 +10576,7 @@ 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: 144524 +# Total code points: 144564 # ================================================ @@ -10988,6 +11007,8 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 1612D..1612F ; Grapheme_Extend # Mn [3] GURUNG KHEMA SIGN ANUSVARA..GURUNG KHEMA SIGN THOLHOMA 16AF0..16AF4 ; Grapheme_Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Grapheme_Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16D98 ; Grapheme_Extend # Mn CHISOI SIGN ANUSVARA +16D9D ; Grapheme_Extend # Mn CHISOI SIGN SISO 16F4F ; Grapheme_Extend # Mn MIAO SIGN CONSONANT MODIFIER BAR 16F8F..16F92 ; Grapheme_Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16FE4 ; Grapheme_Extend # Mn KHITAN SMALL SCRIPT FILLER @@ -11024,7 +11045,7 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. E0020..E007F ; Grapheme_Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2185 +# Total code points: 2187 # ================================================ @@ -12596,6 +12617,9 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 16D6B..16D6C ; Grapheme_Base # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16D6D..16D6F ; Grapheme_Base # Po [3] KIRAT RAI SIGN YUPI..KIRAT RAI DOUBLE DANDA 16D70..16D79 ; Grapheme_Base # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16D80..16D97 ; Grapheme_Base # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D99..16D9C ; Grapheme_Base # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA +16DA0..16DA9 ; Grapheme_Base # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 16E40..16E7F ; Grapheme_Base # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; Grapheme_Base # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E97..16E9A ; Grapheme_Base # Po [4] MEDEFAIDRIN COMMA..MEDEFAIDRIN EXCLAMATION OH @@ -12811,7 +12835,7 @@ 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: 152740 +# Total code points: 152778 # ================================================ @@ -12883,8 +12907,9 @@ ABED ; Grapheme_Link # Mn MEETEI MAYEK APUN IYEK 11F41 ; Grapheme_Link # Mc KAWI SIGN KILLER 11F42 ; Grapheme_Link # Mn KAWI CONJOINER 1612F ; Grapheme_Link # Mn GURUNG KHEMA SIGN THOLHOMA +16D9D ; Grapheme_Link # Mn CHISOI SIGN SISO -# Total code points: 69 +# Total code points: 70 # ================================================ @@ -13110,6 +13135,7 @@ FE20..FE2F ; InCB; Extend # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING 1612F ; InCB; Extend # Mn GURUNG KHEMA SIGN THOLHOMA 16AF0..16AF4 ; InCB; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; InCB; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16D9D ; InCB; Extend # Mn CHISOI SIGN SISO 16FF0..16FF1 ; InCB; Extend # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY 1BC9E ; InCB; Extend # Mn DUPLOYAN DOUBLE MARK 1D165..1D166 ; InCB; Extend # Mc [2] MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING SPRECHGESANG STEM @@ -13133,6 +13159,6 @@ FE20..FE2F ; InCB; Extend # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING 1E8D0..1E8D6 ; InCB; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; InCB; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA -# Total code points: 908 +# Total code points: 909 # EOF diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index dccf9c5a7..b44336dad 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: 2024-02-02, 23:11:29 GMT +# Date: 2024-04-02, 15:39:12 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -2342,6 +2342,11 @@ FFFD ; A # So REPLACEMENT CHARACTER 16D6B..16D6C ; N # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16D6D..16D6F ; N # Po [3] KIRAT RAI SIGN YUPI..KIRAT RAI DOUBLE DANDA 16D70..16D79 ; N # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16D80..16D97 ; N # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D98 ; N # Mn CHISOI SIGN ANUSVARA +16D99..16D9C ; N # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA +16D9D ; N # Mn CHISOI SIGN SISO +16DA0..16DA9 ; N # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 16E40..16E7F ; N # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; N # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E97..16E9A ; N # Po [4] MEDEFAIDRIN COMMA..MEDEFAIDRIN EXCLAMATION OH diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 7a908a922..42a56ef64 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,10 +1,5 @@ -16D80..16D97;AL # Lo [25] CHISOI LETTER A..CHISOI LETTER PA -16D98 ;CM # Mn [01] CHISOI SIGN ANUSVARA -16D99..16D9C;AL # Lo [04] CHISOI LETTER YA..CHISOI LETTER JARAHA -16D9D ;CM # Mn [01] CHISOI SIGN SISO -16DA0..16DA9;NU # Nd [09] CHISOI DIGIT ZERO..CHISOI DIGIT NINE # LineBreak-16.0.0.txt -# Date: 2024-02-02, 23:11:30 GMT +# Date: 2024-04-02, 15:39:14 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -3253,6 +3248,11 @@ FFFD ; AI # So REPLACEMENT CHARACTER 16D6D ; AL # Po KIRAT RAI SIGN YUPI 16D6E..16D6F ; BA # Po [2] KIRAT RAI DANDA..KIRAT RAI DOUBLE DANDA 16D70..16D79 ; NU # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16D80..16D97 ; AL # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D98 ; CM # Mn CHISOI SIGN ANUSVARA +16D99..16D9C ; AL # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA +16D9D ; CM # Mn CHISOI SIGN SISO +16DA0..16DA9 ; NU # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 16E40..16E7F ; AL # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; AL # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E97..16E98 ; BA # Po [2] MEDEFAIDRIN COMMA..MEDEFAIDRIN FULL STOP diff --git a/unicodetools/data/ucd/dev/NormalizationTest.txt b/unicodetools/data/ucd/dev/NormalizationTest.txt index 1e88cecdf..5bea6191a 100644 --- a/unicodetools/data/ucd/dev/NormalizationTest.txt +++ b/unicodetools/data/ucd/dev/NormalizationTest.txt @@ -1,5 +1,5 @@ # NormalizationTest-16.0.0.txt -# Date: 2024-02-02, 23:11:32 GMT +# Date: 2024-04-02, 15:39:20 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -18832,6 +18832,8 @@ FFEE;FFEE;FFEE;25CB;25CB; # (￮; ￮; ￮; ○; ○; ) HALFWIDTH WHITE CIRCLE 0061 16B35 0315 0300 05AE 0062;0061 05AE 16B35 0300 0315 0062;0061 05AE 16B35 0300 0315 0062;0061 05AE 16B35 0300 0315 0062;0061 05AE 16B35 0300 0315 0062; # (a◌𖬵◌̕◌̀◌֮b; a◌֮◌𖬵◌̀◌̕b; a◌֮◌𖬵◌̀◌̕b; a◌֮◌𖬵◌̀◌̕b; a◌֮◌𖬵◌̀◌̕b; ) LATIN SMALL LETTER A, PAHAWH HMONG MARK CIM HOM, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B 0061 0315 0300 05AE 16B36 0062;00E0 05AE 16B36 0315 0062;0061 05AE 0300 16B36 0315 0062;00E0 05AE 16B36 0315 0062;0061 05AE 0300 16B36 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, PAHAWH HMONG MARK CIM TAUM, LATIN SMALL LETTER B 0061 16B36 0315 0300 05AE 0062;0061 05AE 16B36 0300 0315 0062;0061 05AE 16B36 0300 0315 0062;0061 05AE 16B36 0300 0315 0062;0061 05AE 16B36 0300 0315 0062; # (a◌𖬶◌̕◌̀◌֮b; a◌֮◌𖬶◌̀◌̕b; a◌֮◌𖬶◌̀◌̕b; a◌֮◌𖬶◌̀◌̕b; a◌֮◌𖬶◌̀◌̕b; ) LATIN SMALL LETTER A, PAHAWH HMONG MARK CIM TAUM, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B +0061 05B0 094D 3099 16D9D 0062;0061 3099 094D 16D9D 05B0 0062;0061 3099 094D 16D9D 05B0 0062;0061 3099 094D 16D9D 05B0 0062;0061 3099 094D 16D9D 05B0 0062; # (a◌ְ◌्◌゙◌𖶝b; a◌゙◌्◌𖶝◌ְb; a◌゙◌्◌𖶝◌ְb; a◌゙◌्◌𖶝◌ְb; a◌゙◌्◌𖶝◌ְb; ) LATIN SMALL LETTER A, HEBREW POINT SHEVA, DEVANAGARI SIGN VIRAMA, COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK, CHISOI SIGN SISO, LATIN SMALL LETTER B +0061 16D9D 05B0 094D 3099 0062;0061 3099 16D9D 094D 05B0 0062;0061 3099 16D9D 094D 05B0 0062;0061 3099 16D9D 094D 05B0 0062;0061 3099 16D9D 094D 05B0 0062; # (a◌𖶝◌ְ◌्◌゙b; a◌゙◌𖶝◌्◌ְb; a◌゙◌𖶝◌्◌ְb; a◌゙◌𖶝◌्◌ְb; a◌゙◌𖶝◌्◌ְb; ) LATIN SMALL LETTER A, CHISOI SIGN SISO, HEBREW POINT SHEVA, DEVANAGARI SIGN VIRAMA, COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK, LATIN SMALL LETTER B 0061 093C 16FF0 0334 16FF0 0062;0061 0334 16FF0 16FF0 093C 0062;0061 0334 16FF0 16FF0 093C 0062;0061 0334 16FF0 16FF0 093C 0062;0061 0334 16FF0 16FF0 093C 0062; # (a◌𖿰़◌̴𖿰b; a◌̴𖿰𖿰◌़b; a◌̴𖿰𖿰◌़b; a◌̴𖿰𖿰◌़b; a◌̴𖿰𖿰◌़b; ) LATIN SMALL LETTER A, DEVANAGARI SIGN NUKTA, VIETNAMESE ALTERNATE READING MARK CA, COMBINING TILDE OVERLAY, VIETNAMESE ALTERNATE READING MARK CA, LATIN SMALL LETTER B 0061 16FF0 093C 16FF0 0334 0062;0061 0334 16FF0 16FF0 093C 0062;0061 0334 16FF0 16FF0 093C 0062;0061 0334 16FF0 16FF0 093C 0062;0061 0334 16FF0 16FF0 093C 0062; # (a𖿰◌𖿰़◌̴b; a◌̴𖿰𖿰◌़b; a◌̴𖿰𖿰◌़b; a◌̴𖿰𖿰◌़b; a◌̴𖿰𖿰◌़b; ) LATIN SMALL LETTER A, VIETNAMESE ALTERNATE READING MARK CA, DEVANAGARI SIGN NUKTA, VIETNAMESE ALTERNATE READING MARK CA, COMBINING TILDE OVERLAY, LATIN SMALL LETTER B 0061 093C 16FF0 0334 16FF1 0062;0061 0334 16FF0 16FF1 093C 0062;0061 0334 16FF0 16FF1 093C 0062;0061 0334 16FF0 16FF1 093C 0062;0061 0334 16FF0 16FF1 093C 0062; # (a◌𖿰़◌̴𖿱b; a◌̴𖿰𖿱◌़b; a◌̴𖿰𖿱◌़b; a◌̴𖿰𖿱◌़b; a◌̴𖿰𖿱◌़b; ) LATIN SMALL LETTER A, DEVANAGARI SIGN NUKTA, VIETNAMESE ALTERNATE READING MARK CA, COMBINING TILDE OVERLAY, VIETNAMESE ALTERNATE READING MARK NHAY, LATIN SMALL LETTER B diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt index 28e095016..bf70588aa 100644 --- a/unicodetools/data/ucd/dev/PropList.txt +++ b/unicodetools/data/ucd/dev/PropList.txt @@ -1,5 +1,5 @@ # PropList-16.0.0.txt -# Date: 2024-03-12, 13:28:44 GMT +# Date: 2024-04-02, 15:39:29 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -430,7 +430,6 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L # ================================================ -16D98; Other_Alphabetic 0345 ; Other_Alphabetic # Mn COMBINING GREEK YPOGEGRAMMENI 0363..036F ; Other_Alphabetic # Mn [13] COMBINING LATIN SMALL LETTER A..COMBINING LATIN SMALL LETTER X 05B0..05BD ; Other_Alphabetic # Mn [14] HEBREW POINT SHEVA..HEBREW POINT METEG @@ -835,6 +834,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 1611E..16129 ; Other_Alphabetic # Mn [12] GURUNG KHEMA VOWEL SIGN AA..GURUNG KHEMA VOWEL LENGTH MARK 1612A..1612C ; Other_Alphabetic # Mc [3] GURUNG KHEMA CONSONANT SIGN MEDIAL YA..GURUNG KHEMA CONSONANT SIGN MEDIAL HA 1612D..1612E ; Other_Alphabetic # Mn [2] GURUNG KHEMA SIGN ANUSVARA..GURUNG KHEMA CONSONANT SIGN MEDIAL RA +16D98 ; Other_Alphabetic # Mn CHISOI SIGN ANUSVARA 16F4F ; Other_Alphabetic # Mn MIAO SIGN CONSONANT MODIFIER BAR 16F51..16F87 ; Other_Alphabetic # Mc [55] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN UI 16F8F..16F92 ; Other_Alphabetic # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW @@ -851,7 +851,7 @@ 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: 1495 +# Total code points: 1496 # ================================================ @@ -881,7 +881,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM # Total code points: 106477 # ================================================ -16D9D ; Diacritic + 005E ; Diacritic # Sk CIRCUMFLEX ACCENT 0060 ; Diacritic # Sk GRAVE ACCENT 00A8 ; Diacritic # Sk DIAERESIS @@ -1121,6 +1121,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON 16AF0..16AF4 ; Diacritic # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Diacritic # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16D6B..16D6C ; Diacritic # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D9D ; Diacritic # Mn CHISOI SIGN SISO 16F8F..16F92 ; Diacritic # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16F93..16F9F ; Diacritic # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 16FF0..16FF1 ; Diacritic # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY @@ -1143,7 +1144,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON 1E944..1E946 ; Diacritic # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK 1E948..1E94A ; Diacritic # Mn [3] ADLAM CONSONANT MODIFIER..ADLAM NUKTA -# Total code points: 1178 +# Total code points: 1179 # ================================================ diff --git a/unicodetools/data/ucd/dev/PropertyValueAliases.txt b/unicodetools/data/ucd/dev/PropertyValueAliases.txt index 9c262e97c..86c62b2a8 100644 --- a/unicodetools/data/ucd/dev/PropertyValueAliases.txt +++ b/unicodetools/data/ucd/dev/PropertyValueAliases.txt @@ -1,5 +1,5 @@ # PropertyValueAliases-16.0.0.txt -# Date: 2024-03-12, 12:14:23 GMT +# Date: 2024-04-02, 15:39:31 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -196,6 +196,7 @@ blk; Cham ; Cham blk; Cherokee ; Cherokee blk; Cherokee_Sup ; Cherokee_Supplement blk; Chess_Symbols ; Chess_Symbols +blk; Chisoi ; Chisoi blk; Chorasmian ; Chorasmian blk; CJK ; CJK_Unified_Ideographs blk; CJK_Compat ; CJK_Compatibility @@ -1329,6 +1330,7 @@ sc ; Cans ; Canadian_Aboriginal sc ; Cari ; Carian sc ; Cham ; Cham sc ; Cher ; Cherokee +sc ; Chis ; Chisoi sc ; Chrs ; Chorasmian sc ; Copt ; Coptic ; Qaac sc ; Cpmn ; Cypro_Minoan diff --git a/unicodetools/data/ucd/dev/ScriptExtensions.txt b/unicodetools/data/ucd/dev/ScriptExtensions.txt index 201aec28a..022fa5ecb 100644 --- a/unicodetools/data/ucd/dev/ScriptExtensions.txt +++ b/unicodetools/data/ucd/dev/ScriptExtensions.txt @@ -1,5 +1,5 @@ # ScriptExtensions-16.0.0.txt -# Date: 2024-03-15, 12:16:00 GMT +# Date: 2024-04-02, 15:39:49 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -86,8 +86,8 @@ 06D4 ; Arab Rohg # Po ARABIC FULL STOP 0951 ; Beng Deva Gran Gujr Guru Knda Latn Mlym Orya Shrd Taml Telu Tirh #Mn DEVANAGARI STRESS SIGN UDATTA 0952 ; Beng Deva Gran Gujr Guru Knda Latn Mlym Orya Taml Telu Tirh #Mn DEVANAGARI STRESS SIGN ANUDATTA -0964 ; Beng Deva Dogr Gong Gonm Gran Gujr Guru Knda Mahj Mlym Nand Onao Orya Sind Sinh Sylo Takr Taml Telu Tirh Chis #Po DEVANAGARI DANDA -0965 ; Beng Deva Dogr Gong Gonm Gran Gujr Gukh Guru Knda Limb Mahj Mlym Nand Onao Orya Sind Sinh Sylo Takr Taml Telu Tirh Chis #Po DEVANAGARI DOUBLE DANDA +0964 ; Beng Chis Deva Dogr Gong Gonm Gran Gujr Guru Knda Mahj Mlym Nand Onao Orya Sind Sinh Sylo Takr Taml Telu Tirh #Po DEVANAGARI DANDA +0965 ; Beng Chis Deva Dogr Gong Gonm Gran Gujr Gukh Guru Knda Limb Mahj Mlym Nand Onao Orya Sind Sinh Sylo Takr Taml Telu Tirh #Po DEVANAGARI DOUBLE DANDA 0966..096F ; Deva Dogr Kthi Mahj # Nd [10] DEVANAGARI DIGIT ZERO..DEVANAGARI DIGIT NINE 09E6..09EF ; Beng Cakm Sylo # Nd [10] BENGALI DIGIT ZERO..BENGALI DIGIT NINE 0A66..0A6F ; Guru Mult # Nd [10] GURMUKHI DIGIT ZERO..GURMUKHI DIGIT NINE diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index c199f3ab6..3035f20b4 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,6 +1,5 @@ -16D80..16DA9;Chisoi # Scripts-16.0.0.txt -# Date: 2024-02-02, 23:11:49 GMT +# Date: 2024-04-02, 15:39:49 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -3126,4 +3125,15 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI # Total code points: 80 +# ================================================ + +16D80..16D97 ; Chisoi # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D98 ; Chisoi # Mn CHISOI SIGN ANUSVARA +16D99..16D9C ; Chisoi # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA +16D9D ; Chisoi # Mn CHISOI SIGN SISO +16D9E..16D9F ; Chisoi # Cn [2] .. +16DA0..16DA9 ; Chisoi # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE + +# Total code points: 42 + # EOF diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 576b7323b..6f686a687 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -1,43 +1,3 @@ -16D80;CHISOI LETTER A;Lo;0;L;;;;;N;;;;; -16D81;CHISOI LETTER BA;Lo;0;L;;;;;N;;;;; -16D82;CHISOI LETTER AI;Lo;0;L;;;;;N;;;;; -16D83;CHISOI LETTER AA;Lo;0;L;;;;;N;;;;; -16D84;CHISOI LETTER GA;Lo;0;L;;;;;N;;;;; -16D85;CHISOI LETTER TA;Lo;0;L;;;;;N;;;;; -16D86;CHISOI LETTER E;Lo;0;L;;;;;N;;;;; -16D87;CHISOI LETTER SA;Lo;0;L;;;;;N;;;;; -16D88;CHISOI LETTER NA;Lo;0;L;;;;;N;;;;; -16D89;CHISOI LETTER I;Lo;0;L;;;;;N;;;;; -16D8A;CHISOI LETTER KA;Lo;0;L;;;;;N;;;;; -16D8B;CHISOI LETTER RA;Lo;0;L;;;;;N;;;;; -16D8C;CHISOI LETTER MA;Lo;0;L;;;;;N;;;;; -16D8D;CHISOI LETTER HA;Lo;0;L;;;;;N;;;;; -16D8E;CHISOI LETTER RRA;Lo;0;L;;;;;N;;;;; -16D8F;CHISOI LETTER U;Lo;0;L;;;;;N;;;;; -16D90;CHISOI LETTER DA;Lo;0;L;;;;;N;;;;; -16D91;CHISOI LETTER LA;Lo;0;L;;;;;N;;;;; -16D92;CHISOI LETTER O;Lo;0;L;;;;;N;;;;; -16D93;CHISOI LETTER NYA;Lo;0;L;;;;;N;;;;; -16D94;CHISOI LETTER NGA;Lo;0;L;;;;;N;;;;; -16D95;CHISOI LETTER CA;Lo;0;L;;;;;N;;;;; -16D96;CHISOI LETTER JA;Lo;0;L;;;;;N;;;;; -16D97;CHISOI LETTER PA;Lo;0;L;;;;;N;;;;; -16D98;CHISOI SIGN ANUSVARA;Mn;0;NSM;;;;;N;;;;; -16D99;CHISOI LETTER YA;Lo;0;L;;;;;N;;;;; -16D9A;CHISOI LETTER DDA;Lo;0;L;;;;;N;;;;; -16D9B;CHISOI LETTER TTA;Lo;0;L;;;;;N;;;;; -16D9C;CHISOI LETTER JARAHA;Lo;0;L;;;;;N;;;;; -16D9D;CHISOI SIGN SISO;Mn;9;NSM;;;;;N;;;;; -16DA0;CHISOI DIGIT ZERO;Nd;0;L;;0;0;0;N;;;;; -16DA1;CHISOI DIGIT ONE;Nd;0;L;;1;1;1;N;;;;; -16DA2;CHISOI DIGIT TWO;Nd;0;L;;2;2;2;N;;;;; -16DA3;CHISOI DIGIT THREE;Nd;0;L;;3;3;3;N;;;;; -16DA4;CHISOI DIGIT FOUR;Nd;0;L;;4;4;4;N;;;;; -16DA5;CHISOI DIGIT FIVE;Nd;0;L;;5;5;5;N;;;;; -16DA6;CHISOI DIGIT SIX;Nd;0;L;;6;6;6;N;;;;; -16DA7;CHISOI DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;; -16DA8;CHISOI DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;; -16DA9;CHISOI DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; 0000;;Cc;0;BN;;;;;N;NULL;;;; 0001;;Cc;0;BN;;;;;N;START OF HEADING;;;; 0002;;Cc;0;BN;;;;;N;START OF TEXT;;;; @@ -30075,6 +30035,46 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 16D77;KIRAT RAI DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;; 16D78;KIRAT RAI DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;; 16D79;KIRAT RAI DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; +16D80;CHISOI LETTER A;Lo;0;L;;;;;N;;;;; +16D81;CHISOI LETTER BA;Lo;0;L;;;;;N;;;;; +16D82;CHISOI LETTER AI;Lo;0;L;;;;;N;;;;; +16D83;CHISOI LETTER AA;Lo;0;L;;;;;N;;;;; +16D84;CHISOI LETTER GA;Lo;0;L;;;;;N;;;;; +16D85;CHISOI LETTER TA;Lo;0;L;;;;;N;;;;; +16D86;CHISOI LETTER E;Lo;0;L;;;;;N;;;;; +16D87;CHISOI LETTER SA;Lo;0;L;;;;;N;;;;; +16D88;CHISOI LETTER NA;Lo;0;L;;;;;N;;;;; +16D89;CHISOI LETTER I;Lo;0;L;;;;;N;;;;; +16D8A;CHISOI LETTER KA;Lo;0;L;;;;;N;;;;; +16D8B;CHISOI LETTER RA;Lo;0;L;;;;;N;;;;; +16D8C;CHISOI LETTER MA;Lo;0;L;;;;;N;;;;; +16D8D;CHISOI LETTER HA;Lo;0;L;;;;;N;;;;; +16D8E;CHISOI LETTER RRA;Lo;0;L;;;;;N;;;;; +16D8F;CHISOI LETTER U;Lo;0;L;;;;;N;;;;; +16D90;CHISOI LETTER DA;Lo;0;L;;;;;N;;;;; +16D91;CHISOI LETTER LA;Lo;0;L;;;;;N;;;;; +16D92;CHISOI LETTER O;Lo;0;L;;;;;N;;;;; +16D93;CHISOI LETTER NYA;Lo;0;L;;;;;N;;;;; +16D94;CHISOI LETTER NGA;Lo;0;L;;;;;N;;;;; +16D95;CHISOI LETTER CA;Lo;0;L;;;;;N;;;;; +16D96;CHISOI LETTER JA;Lo;0;L;;;;;N;;;;; +16D97;CHISOI LETTER PA;Lo;0;L;;;;;N;;;;; +16D98;CHISOI SIGN ANUSVARA;Mn;0;NSM;;;;;N;;;;; +16D99;CHISOI LETTER YA;Lo;0;L;;;;;N;;;;; +16D9A;CHISOI LETTER DDA;Lo;0;L;;;;;N;;;;; +16D9B;CHISOI LETTER TTA;Lo;0;L;;;;;N;;;;; +16D9C;CHISOI LETTER JARAHA;Lo;0;L;;;;;N;;;;; +16D9D;CHISOI SIGN SISO;Mn;9;NSM;;;;;N;;;;; +16DA0;CHISOI DIGIT ZERO;Nd;0;L;;0;0;0;N;;;;; +16DA1;CHISOI DIGIT ONE;Nd;0;L;;1;1;1;N;;;;; +16DA2;CHISOI DIGIT TWO;Nd;0;L;;2;2;2;N;;;;; +16DA3;CHISOI DIGIT THREE;Nd;0;L;;3;3;3;N;;;;; +16DA4;CHISOI DIGIT FOUR;Nd;0;L;;4;4;4;N;;;;; +16DA5;CHISOI DIGIT FIVE;Nd;0;L;;5;5;5;N;;;;; +16DA6;CHISOI DIGIT SIX;Nd;0;L;;6;6;6;N;;;;; +16DA7;CHISOI DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;; +16DA8;CHISOI DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;; +16DA9;CHISOI DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; 16E40;MEDEFAIDRIN CAPITAL LETTER M;Lu;0;L;;;;;N;;;;16E60; 16E41;MEDEFAIDRIN CAPITAL LETTER S;Lu;0;L;;;;;N;;;;16E61; 16E42;MEDEFAIDRIN CAPITAL LETTER V;Lu;0;L;;;;;N;;;;16E62; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index 187a0888d..31420c03b 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: 2024-02-02, 23:11:51 GMT +# Date: 2024-04-02, 15:39:55 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -2173,6 +2173,11 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 16D6B..16D6C ; R # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16D6D..16D6F ; R # Po [3] KIRAT RAI SIGN YUPI..KIRAT RAI DOUBLE DANDA 16D70..16D79 ; R # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16D80..16D97 ; R # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D98 ; R # Mn CHISOI SIGN ANUSVARA +16D99..16D9C ; R # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA +16D9D ; R # Mn CHISOI SIGN SISO +16DA0..16DA9 ; R # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 16E40..16E7F ; R # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; R # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E97..16E9A ; R # Po [4] MEDEFAIDRIN COMMA..MEDEFAIDRIN EXCLAMATION OH diff --git a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt index 1241b2d2b..8b2078d9e 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: 2024-02-02, 23:11:29 GMT +# Date: 2024-04-02, 15:39:13 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -453,6 +453,8 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1612D..1612F ; Extend # Mn [3] GURUNG KHEMA SIGN ANUSVARA..GURUNG KHEMA SIGN THOLHOMA 16AF0..16AF4 ; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16D98 ; Extend # Mn CHISOI SIGN ANUSVARA +16D9D ; Extend # Mn CHISOI SIGN SISO 16F4F ; Extend # Mn MIAO SIGN CONSONANT MODIFIER BAR 16F8F..16F92 ; Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16FE4 ; Extend # Mn KHITAN SMALL SCRIPT FILLER @@ -490,7 +492,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2190 +# Total code points: 2192 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index cec52074f..b341d14f3 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: 2024-02-02, 23:11:49 GMT +# Date: 2024-04-02, 15:39:51 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -549,6 +549,8 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1612D..1612F ; Extend # Mn [3] GURUNG KHEMA SIGN ANUSVARA..GURUNG KHEMA SIGN THOLHOMA 16AF0..16AF4 ; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16D98 ; Extend # Mn CHISOI SIGN ANUSVARA +16D9D ; Extend # Mn CHISOI SIGN SISO 16F4F ; Extend # Mn MIAO SIGN CONSONANT MODIFIER BAR 16F51..16F87 ; Extend # Mc [55] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN UI 16F8F..16F92 ; Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW @@ -586,7 +588,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2601 +# Total code points: 2603 # ================================================ @@ -2505,6 +2507,8 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 16D40..16D42 ; OLetter # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA 16D43..16D6A ; OLetter # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU 16D6B..16D6C ; OLetter # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D80..16D97 ; OLetter # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D99..16D9C ; OLetter # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA 16F00..16F4A ; OLetter # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F50 ; OLetter # Lo MIAO LETTER NASALIZATION 16F93..16F9F ; OLetter # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 @@ -2585,7 +2589,7 @@ 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: 136910 +# Total code points: 136938 # ================================================ @@ -2659,6 +2663,7 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 16AC0..16AC9 ; Numeric # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16B50..16B59 ; Numeric # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 16D70..16D79 ; Numeric # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16DA0..16DA9 ; Numeric # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 1CCF0..1CCF9 ; Numeric # Nd [10] OUTLINED DIGIT ZERO..OUTLINED DIGIT NINE 1D7CE..1D7FF ; Numeric # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E140..1E149 ; Numeric # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE @@ -2668,7 +2673,7 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Numeric # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 774 +# Total code points: 784 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index fd760073c..6f115d5a2 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: 2024-02-22, 15:58:24 GMT +# Date: 2024-04-02, 15:39:55 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -585,6 +585,8 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1612D..1612F ; Extend # Mn [3] GURUNG KHEMA SIGN ANUSVARA..GURUNG KHEMA SIGN THOLHOMA 16AF0..16AF4 ; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16D98 ; Extend # Mn CHISOI SIGN ANUSVARA +16D9D ; Extend # Mn CHISOI SIGN SISO 16F4F ; Extend # Mn MIAO SIGN CONSONANT MODIFIER BAR 16F51..16F87 ; Extend # Mc [55] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN UI 16F8F..16F92 ; Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW @@ -623,7 +625,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2605 +# Total code points: 2607 # ================================================ @@ -1257,6 +1259,8 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 16D40..16D42 ; ALetter # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA 16D43..16D6A ; ALetter # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU 16D6B..16D6C ; ALetter # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D80..16D97 ; ALetter # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D99..16D9C ; ALetter # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA 16E40..16E7F ; ALetter # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16F00..16F4A ; ALetter # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F50 ; ALetter # Lo MIAO LETTER NASALIZATION @@ -1355,7 +1359,7 @@ 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: 33793 +# Total code points: 33821 # ================================================ @@ -1474,6 +1478,7 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 16AC0..16AC9 ; Numeric # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16B50..16B59 ; Numeric # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 16D70..16D79 ; Numeric # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16DA0..16DA9 ; Numeric # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 1CCF0..1CCF9 ; Numeric # Nd [10] OUTLINED DIGIT ZERO..OUTLINED DIGIT NINE 1D7CE..1D7FF ; Numeric # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E140..1E149 ; Numeric # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE @@ -1483,7 +1488,7 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Numeric # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 773 +# Total code points: 783 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index d991ed1b8..d1ea3728f 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: 2024-02-02, 23:11:23 GMT +# Date: 2024-04-02, 15:39:00 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1093,6 +1093,9 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 16D6B..16D6C ; L # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16D6D..16D6F ; L # Po [3] KIRAT RAI SIGN YUPI..KIRAT RAI DOUBLE DANDA 16D70..16D79 ; L # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16D80..16D97 ; L # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D99..16D9C ; L # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA +16DA0..16DA9 ; L # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 16E40..16E7F ; L # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; L # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E97..16E9A ; L # Po [4] MEDEFAIDRIN COMMA..MEDEFAIDRIN EXCLAMATION OH @@ -1219,8 +1222,8 @@ 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 815349 code points not listed here. -# Total code points: 1095518 +# The above property value applies to 815309 code points not listed here. +# Total code points: 1095516 # ================================================ @@ -2376,6 +2379,8 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 1612D..1612F ; NSM # Mn [3] GURUNG KHEMA SIGN ANUSVARA..GURUNG KHEMA SIGN THOLHOMA 16AF0..16AF4 ; NSM # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; NSM # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16D98 ; NSM # Mn CHISOI SIGN ANUSVARA +16D9D ; NSM # Mn CHISOI SIGN SISO 16F4F ; NSM # Mn MIAO SIGN CONSONANT MODIFIER BAR 16F8F..16F92 ; NSM # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16FE4 ; NSM # Mn KHITAN SMALL SCRIPT FILLER @@ -2408,7 +2413,7 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 1E944..1E94A ; NSM # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2028 +# Total code points: 2030 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index 639fce0ae..1b50a86a6 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: 2024-02-02, 23:11:23 GMT +# Date: 2024-04-02, 15:39:03 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1826,6 +1826,10 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 16D6B..16D6C ; 0 # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16D6D..16D6F ; 0 # Po [3] KIRAT RAI SIGN YUPI..KIRAT RAI DOUBLE DANDA 16D70..16D79 ; 0 # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16D80..16D97 ; 0 # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D98 ; 0 # Mn CHISOI SIGN ANUSVARA +16D99..16D9C ; 0 # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA +16DA0..16DA9 ; 0 # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 16E40..16E7F ; 0 # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; 0 # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E97..16E9A ; 0 # Po [4] MEDEFAIDRIN COMMA..MEDEFAIDRIN EXCLAMATION OH @@ -2060,8 +2064,8 @@ 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 821579 code points not listed here. -# Total code points: 1113178 +# The above property value applies to 821539 code points not listed here. +# Total code points: 1113177 # ================================================ @@ -2198,8 +2202,9 @@ ABED ; 9 # Mn MEETEI MAYEK APUN IYEK 11F41 ; 9 # Mc KAWI SIGN KILLER 11F42 ; 9 # Mn KAWI CONJOINER 1612F ; 9 # Mn GURUNG KHEMA SIGN THOLHOMA +16D9D ; 9 # Mn CHISOI SIGN SISO -# Total code points: 69 +# Total code points: 70 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index 44585c48d..52df74d49 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: 2024-02-02, 23:11:25 GMT +# Date: 2024-04-02, 15:39:06 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1864,6 +1864,11 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 16D6B..16D6C ; N # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16D6D..16D6F ; N # Po [3] KIRAT RAI SIGN YUPI..KIRAT RAI DOUBLE DANDA 16D70..16D79 ; N # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16D80..16D97 ; N # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D98 ; N # Mn CHISOI SIGN ANUSVARA +16D99..16D9C ; N # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA +16D9D ; N # Mn CHISOI SIGN SISO +16DA0..16DA9 ; N # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 16E40..16E7F ; N # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; N # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E97..16E9A ; N # Po [4] MEDEFAIDRIN COMMA..MEDEFAIDRIN EXCLAMATION OH @@ -2103,7 +2108,7 @@ 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 761097 code points not listed here. +# The above property value applies to 761057 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 b9105da02..26e3bd956 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: 2024-02-02, 23:11:25 GMT +# Date: 2024-04-02, 15:39:06 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -572,7 +572,9 @@ FFFE..FFFF ; Cn # [2] .. 16B62 ; Cn # 16B78..16B7C ; Cn # [5] .. 16B90..16D3F ; Cn # [432] .. -16D7A..16E3F ; Cn # [198] .. +16D7A..16D7F ; Cn # [6] .. +16D9E..16D9F ; Cn # [2] .. +16DAA..16E3F ; Cn # [150] .. 16E9B..16EFF ; Cn # [101] .. 16F4B..16F4E ; Cn # [4] .. 16F88..16F8E ; Cn # [7] .. @@ -747,7 +749,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819531 +# Total code points: 819491 # ================================================ @@ -2637,6 +2639,8 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 16B63..16B77 ; Lo # [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; Lo # [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ 16D43..16D6A ; Lo # [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU +16D80..16D97 ; Lo # [24] CHISOI LETTER A..CHISOI LETTER PA +16D99..16D9C ; Lo # [4] CHISOI LETTER YA..CHISOI LETTER JARAHA 16F00..16F4A ; Lo # [75] MIAO LETTER PA..MIAO LETTER RTE 16F50 ; Lo # MIAO LETTER NASALIZATION 17000..187F7 ; Lo # [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 @@ -2708,7 +2712,7 @@ 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: 136479 +# Total code points: 136507 # ================================================ @@ -3040,6 +3044,8 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 1612D..1612F ; Mn # [3] GURUNG KHEMA SIGN ANUSVARA..GURUNG KHEMA SIGN THOLHOMA 16AF0..16AF4 ; Mn # [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Mn # [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16D98 ; Mn # CHISOI SIGN ANUSVARA +16D9D ; Mn # CHISOI SIGN SISO 16F4F ; Mn # MIAO SIGN CONSONANT MODIFIER BAR 16F8F..16F92 ; Mn # [4] MIAO TONE RIGHT..MIAO TONE BELOW 16FE4 ; Mn # KHITAN SMALL SCRIPT FILLER @@ -3072,7 +3078,7 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 1E944..1E94A ; Mn # [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; Mn # [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2020 +# Total code points: 2022 # ================================================ @@ -3350,6 +3356,7 @@ FF10..FF19 ; Nd # [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 16AC0..16AC9 ; Nd # [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16B50..16B59 ; Nd # [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 16D70..16D79 ; Nd # [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16DA0..16DA9 ; Nd # [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 1CCF0..1CCF9 ; Nd # [10] OUTLINED DIGIT ZERO..OUTLINED DIGIT NINE 1D7CE..1D7FF ; Nd # [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E140..1E149 ; Nd # [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE @@ -3359,7 +3366,7 @@ FF10..FF19 ; Nd # [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E950..1E959 ; Nd # [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Nd # [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 760 +# Total code points: 770 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt index 6407d5c0d..b92350cf9 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: 2024-02-02, 23:11:26 GMT +# Date: 2024-04-02, 15:39:07 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -544,6 +544,8 @@ FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATI 1612D..1612F ; T # Mn [3] GURUNG KHEMA SIGN ANUSVARA..GURUNG KHEMA SIGN THOLHOMA 16AF0..16AF4 ; T # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; T # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16D98 ; T # Mn CHISOI SIGN ANUSVARA +16D9D ; T # Mn CHISOI SIGN SISO 16F4F ; T # Mn MIAO SIGN CONSONANT MODIFIER BAR 16F8F..16F92 ; T # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16FE4 ; T # Mn KHITAN SMALL SCRIPT FILLER @@ -581,6 +583,6 @@ 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: 2185 +# Total code points: 2187 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 3a3ecf9c1..c3f95539b 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: 2024-02-02, 23:11:26 GMT +# Date: 2024-04-02, 15:39:08 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -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 757651 code points not listed here. -# Total code points: 895119 +# The above property value applies to 757611 code points not listed here. +# Total code points: 895079 # ================================================ @@ -544,6 +544,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 16AC0..16AC9 ; NU # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16B50..16B59 ; NU # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 16D70..16D79 ; NU # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16DA0..16DA9 ; NU # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 1CCF0..1CCF9 ; NU # Nd [10] OUTLINED DIGIT ZERO..OUTLINED DIGIT NINE 1D7CE..1D7FF ; NU # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E140..1E149 ; NU # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE @@ -553,7 +554,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 1E950..1E959 ; NU # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; NU # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 694 +# Total code points: 704 # ================================================ @@ -1438,6 +1439,8 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 16D43..16D6A ; AL # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU 16D6B..16D6C ; AL # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16D6D ; AL # Po KIRAT RAI SIGN YUPI +16D80..16D97 ; AL # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D99..16D9C ; AL # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA 16E40..16E7F ; AL # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; AL # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E99..16E9A ; AL # Po [2] MEDEFAIDRIN SYMBOL AIVA..MEDEFAIDRIN EXCLAMATION OH @@ -1611,7 +1614,7 @@ 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: 26685 +# Total code points: 26713 # ================================================ @@ -2343,6 +2346,8 @@ FFF9..FFFB ; CM # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTAT 1612D..1612F ; CM # Mn [3] GURUNG KHEMA SIGN ANUSVARA..GURUNG KHEMA SIGN THOLHOMA 16AF0..16AF4 ; CM # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; CM # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16D98 ; CM # Mn CHISOI SIGN ANUSVARA +16D9D ; CM # Mn CHISOI SIGN SISO 16F4F ; CM # Mn MIAO SIGN CONSONANT MODIFIER BAR 16F51..16F87 ; CM # Mc [55] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN UI 16F8F..16F92 ; CM # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW @@ -2382,7 +2387,7 @@ E0001 ; CM # Cf LANGUAGE TAG E0020..E007F ; CM # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; CM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2479 +# Total code points: 2481 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 4778d471e..224d78146 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: 2024-02-02, 23:11:26 GMT +# Date: 2024-04-02, 15:39:08 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -36706,6 +36706,46 @@ FFFD ; REPLACEMENT CHARACTER 16D77 ; KIRAT RAI DIGIT SEVEN 16D78 ; KIRAT RAI DIGIT EIGHT 16D79 ; KIRAT RAI DIGIT NINE +16D80 ; CHISOI LETTER A +16D81 ; CHISOI LETTER BA +16D82 ; CHISOI LETTER AI +16D83 ; CHISOI LETTER AA +16D84 ; CHISOI LETTER GA +16D85 ; CHISOI LETTER TA +16D86 ; CHISOI LETTER E +16D87 ; CHISOI LETTER SA +16D88 ; CHISOI LETTER NA +16D89 ; CHISOI LETTER I +16D8A ; CHISOI LETTER KA +16D8B ; CHISOI LETTER RA +16D8C ; CHISOI LETTER MA +16D8D ; CHISOI LETTER HA +16D8E ; CHISOI LETTER RRA +16D8F ; CHISOI LETTER U +16D90 ; CHISOI LETTER DA +16D91 ; CHISOI LETTER LA +16D92 ; CHISOI LETTER O +16D93 ; CHISOI LETTER NYA +16D94 ; CHISOI LETTER NGA +16D95 ; CHISOI LETTER CA +16D96 ; CHISOI LETTER JA +16D97 ; CHISOI LETTER PA +16D98 ; CHISOI SIGN ANUSVARA +16D99 ; CHISOI LETTER YA +16D9A ; CHISOI LETTER DDA +16D9B ; CHISOI LETTER TTA +16D9C ; CHISOI LETTER JARAHA +16D9D ; CHISOI SIGN SISO +16DA0 ; CHISOI DIGIT ZERO +16DA1 ; CHISOI DIGIT ONE +16DA2 ; CHISOI DIGIT TWO +16DA3 ; CHISOI DIGIT THREE +16DA4 ; CHISOI DIGIT FOUR +16DA5 ; CHISOI DIGIT FIVE +16DA6 ; CHISOI DIGIT SIX +16DA7 ; CHISOI DIGIT SEVEN +16DA8 ; CHISOI DIGIT EIGHT +16DA9 ; CHISOI DIGIT NINE 16E40 ; MEDEFAIDRIN CAPITAL LETTER M 16E41 ; MEDEFAIDRIN CAPITAL LETTER S 16E42 ; MEDEFAIDRIN CAPITAL LETTER V @@ -45369,6 +45409,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 155000 +# Total code points: 155040 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedNumericType.txt b/unicodetools/data/ucd/dev/extracted/DerivedNumericType.txt index 2ad2b4a20..fc222c607 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: 2024-02-02, 23:11:28 GMT +# Date: 2024-04-02, 15:39:11 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -284,6 +284,7 @@ FF10..FF19 ; Decimal # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 16AC0..16AC9 ; Decimal # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16B50..16B59 ; Decimal # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 16D70..16D79 ; Decimal # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16DA0..16DA9 ; Decimal # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 1CCF0..1CCF9 ; Decimal # Nd [10] OUTLINED DIGIT ZERO..OUTLINED DIGIT NINE 1D7CE..1D7FF ; Decimal # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E140..1E149 ; Decimal # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE @@ -293,6 +294,6 @@ FF10..FF19 ; Decimal # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E950..1E959 ; Decimal # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Decimal # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 760 +# Total code points: 770 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedNumericValues.txt b/unicodetools/data/ucd/dev/extracted/DerivedNumericValues.txt index 1ab64dc7f..3fcc9d509 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: 2024-03-08, 02:06:23 GMT +# Date: 2024-04-02, 15:39:12 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -116,6 +116,7 @@ FF10 ; 0.0 ; ; 0 # Nd FULLWIDTH DIGIT ZERO 16AC0 ; 0.0 ; ; 0 # Nd TANGSA DIGIT ZERO 16B50 ; 0.0 ; ; 0 # Nd PAHAWH HMONG DIGIT ZERO 16D70 ; 0.0 ; ; 0 # Nd KIRAT RAI DIGIT ZERO +16DA0 ; 0.0 ; ; 0 # Nd CHISOI DIGIT ZERO 16E80 ; 0.0 ; ; 0 # No MEDEFAIDRIN DIGIT ZERO 1CCF0 ; 0.0 ; ; 0 # Nd OUTLINED DIGIT ZERO 1D2C0 ; 0.0 ; ; 0 # No KAKTOVIK NUMERAL ZERO @@ -134,7 +135,7 @@ FF10 ; 0.0 ; ; 0 # Nd FULLWIDTH DIGIT ZERO 1F10B..1F10C ; 0.0 ; ; 0 # No [2] DINGBAT CIRCLED SANS-SERIF DIGIT ZERO..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO 1FBF0 ; 0.0 ; ; 0 # Nd SEGMENTED DIGIT ZERO -# Total code points: 96 +# Total code points: 97 # ================================================ @@ -542,6 +543,7 @@ FF11 ; 1.0 ; ; 1 # Nd FULLWIDTH DIGIT ONE 16AC1 ; 1.0 ; ; 1 # Nd TANGSA DIGIT ONE 16B51 ; 1.0 ; ; 1 # Nd PAHAWH HMONG DIGIT ONE 16D71 ; 1.0 ; ; 1 # Nd KIRAT RAI DIGIT ONE +16DA1 ; 1.0 ; ; 1 # Nd CHISOI DIGIT ONE 16E81 ; 1.0 ; ; 1 # No MEDEFAIDRIN DIGIT ONE 16E94 ; 1.0 ; ; 1 # No MEDEFAIDRIN DIGIT ONE ALTERNATE FORM 1CCF1 ; 1.0 ; ; 1 # Nd OUTLINED DIGIT ONE @@ -569,7 +571,7 @@ FF11 ; 1.0 ; ; 1 # Nd FULLWIDTH DIGIT ONE 1FBF1 ; 1.0 ; ; 1 # Nd SEGMENTED DIGIT ONE 2092A ; 1.0 ; ; 1 # Lo CJK UNIFIED IDEOGRAPH-2092A -# Total code points: 152 +# Total code points: 153 # ================================================ @@ -704,6 +706,7 @@ FF12 ; 2.0 ; ; 2 # Nd FULLWIDTH DIGIT TWO 16AC2 ; 2.0 ; ; 2 # Nd TANGSA DIGIT TWO 16B52 ; 2.0 ; ; 2 # Nd PAHAWH HMONG DIGIT TWO 16D72 ; 2.0 ; ; 2 # Nd KIRAT RAI DIGIT TWO +16DA2 ; 2.0 ; ; 2 # Nd CHISOI DIGIT TWO 16E82 ; 2.0 ; ; 2 # No MEDEFAIDRIN DIGIT TWO 16E95 ; 2.0 ; ; 2 # No MEDEFAIDRIN DIGIT TWO ALTERNATE FORM 1CCF2 ; 2.0 ; ; 2 # Nd OUTLINED DIGIT TWO @@ -731,7 +734,7 @@ FF12 ; 2.0 ; ; 2 # Nd FULLWIDTH DIGIT TWO 1FBF2 ; 2.0 ; ; 2 # Nd SEGMENTED DIGIT TWO 22390 ; 2.0 ; ; 2 # Lo CJK UNIFIED IDEOGRAPH-22390 -# Total code points: 154 +# Total code points: 155 # ================================================ @@ -858,6 +861,7 @@ FF13 ; 3.0 ; ; 3 # Nd FULLWIDTH DIGIT THREE 16AC3 ; 3.0 ; ; 3 # Nd TANGSA DIGIT THREE 16B53 ; 3.0 ; ; 3 # Nd PAHAWH HMONG DIGIT THREE 16D73 ; 3.0 ; ; 3 # Nd KIRAT RAI DIGIT THREE +16DA3 ; 3.0 ; ; 3 # Nd CHISOI DIGIT THREE 16E83 ; 3.0 ; ; 3 # No MEDEFAIDRIN DIGIT THREE 16E96 ; 3.0 ; ; 3 # No MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 1CCF3 ; 3.0 ; ; 3 # Nd OUTLINED DIGIT THREE @@ -887,7 +891,7 @@ FF13 ; 3.0 ; ; 3 # Nd FULLWIDTH DIGIT THREE 22998 ; 3.0 ; ; 3 # Lo CJK UNIFIED IDEOGRAPH-22998 23B1B ; 3.0 ; ; 3 # Lo CJK UNIFIED IDEOGRAPH-23B1B -# Total code points: 152 +# Total code points: 153 # ================================================ @@ -1009,6 +1013,7 @@ FF14 ; 4.0 ; ; 4 # Nd FULLWIDTH DIGIT FOUR 16AC4 ; 4.0 ; ; 4 # Nd TANGSA DIGIT FOUR 16B54 ; 4.0 ; ; 4 # Nd PAHAWH HMONG DIGIT FOUR 16D74 ; 4.0 ; ; 4 # Nd KIRAT RAI DIGIT FOUR +16DA4 ; 4.0 ; ; 4 # Nd CHISOI DIGIT FOUR 16E84 ; 4.0 ; ; 4 # No MEDEFAIDRIN DIGIT FOUR 1CCF4 ; 4.0 ; ; 4 # Nd OUTLINED DIGIT FOUR 1D2C4 ; 4.0 ; ; 4 # No KAKTOVIK NUMERAL FOUR @@ -1036,7 +1041,7 @@ FF14 ; 4.0 ; ; 4 # Nd FULLWIDTH DIGIT FOUR 200E2 ; 4.0 ; ; 4 # Lo CJK UNIFIED IDEOGRAPH-200E2 2626D ; 4.0 ; ; 4 # Lo CJK UNIFIED IDEOGRAPH-2626D -# Total code points: 143 +# Total code points: 144 # ================================================ @@ -1161,6 +1166,7 @@ FF15 ; 5.0 ; ; 5 # Nd FULLWIDTH DIGIT FIVE 16AC5 ; 5.0 ; ; 5 # Nd TANGSA DIGIT FIVE 16B55 ; 5.0 ; ; 5 # Nd PAHAWH HMONG DIGIT FIVE 16D75 ; 5.0 ; ; 5 # Nd KIRAT RAI DIGIT FIVE +16DA5 ; 5.0 ; ; 5 # Nd CHISOI DIGIT FIVE 16E85 ; 5.0 ; ; 5 # No MEDEFAIDRIN DIGIT FIVE 1CCF5 ; 5.0 ; ; 5 # Nd OUTLINED DIGIT FIVE 1D2C5 ; 5.0 ; ; 5 # No KAKTOVIK NUMERAL FIVE @@ -1187,7 +1193,7 @@ FF15 ; 5.0 ; ; 5 # Nd FULLWIDTH DIGIT FIVE 1FBF5 ; 5.0 ; ; 5 # Nd SEGMENTED DIGIT FIVE 20121 ; 5.0 ; ; 5 # Lo CJK UNIFIED IDEOGRAPH-20121 -# Total code points: 141 +# Total code points: 142 # ================================================ @@ -1299,6 +1305,7 @@ FF16 ; 6.0 ; ; 6 # Nd FULLWIDTH DIGIT SIX 16AC6 ; 6.0 ; ; 6 # Nd TANGSA DIGIT SIX 16B56 ; 6.0 ; ; 6 # Nd PAHAWH HMONG DIGIT SIX 16D76 ; 6.0 ; ; 6 # Nd KIRAT RAI DIGIT SIX +16DA6 ; 6.0 ; ; 6 # Nd CHISOI DIGIT SIX 16E86 ; 6.0 ; ; 6 # No MEDEFAIDRIN DIGIT SIX 1CCF6 ; 6.0 ; ; 6 # Nd OUTLINED DIGIT SIX 1D2C6 ; 6.0 ; ; 6 # No KAKTOVIK NUMERAL SIX @@ -1323,7 +1330,7 @@ FF16 ; 6.0 ; ; 6 # Nd FULLWIDTH DIGIT SIX 1FBF6 ; 6.0 ; ; 6 # Nd SEGMENTED DIGIT SIX 20AEA ; 6.0 ; ; 6 # Lo CJK UNIFIED IDEOGRAPH-20AEA -# Total code points: 125 +# Total code points: 126 # ================================================ @@ -1433,6 +1440,7 @@ FF17 ; 7.0 ; ; 7 # Nd FULLWIDTH DIGIT SEVEN 16AC7 ; 7.0 ; ; 7 # Nd TANGSA DIGIT SEVEN 16B57 ; 7.0 ; ; 7 # Nd PAHAWH HMONG DIGIT SEVEN 16D77 ; 7.0 ; ; 7 # Nd KIRAT RAI DIGIT SEVEN +16DA7 ; 7.0 ; ; 7 # Nd CHISOI DIGIT SEVEN 16E87 ; 7.0 ; ; 7 # No MEDEFAIDRIN DIGIT SEVEN 1CCF7 ; 7.0 ; ; 7 # Nd OUTLINED DIGIT SEVEN 1D2C7 ; 7.0 ; ; 7 # No KAKTOVIK NUMERAL SEVEN @@ -1457,7 +1465,7 @@ FF17 ; 7.0 ; ; 7 # Nd FULLWIDTH DIGIT SEVEN 1FBF7 ; 7.0 ; ; 7 # Nd SEGMENTED DIGIT SEVEN 20001 ; 7.0 ; ; 7 # Lo CJK UNIFIED IDEOGRAPH-20001 -# Total code points: 125 +# Total code points: 126 # ================================================ @@ -1564,6 +1572,7 @@ FF18 ; 8.0 ; ; 8 # Nd FULLWIDTH DIGIT EIGHT 16AC8 ; 8.0 ; ; 8 # Nd TANGSA DIGIT EIGHT 16B58 ; 8.0 ; ; 8 # Nd PAHAWH HMONG DIGIT EIGHT 16D78 ; 8.0 ; ; 8 # Nd KIRAT RAI DIGIT EIGHT +16DA8 ; 8.0 ; ; 8 # Nd CHISOI DIGIT EIGHT 16E88 ; 8.0 ; ; 8 # No MEDEFAIDRIN DIGIT EIGHT 1CCF8 ; 8.0 ; ; 8 # Nd OUTLINED DIGIT EIGHT 1D2C8 ; 8.0 ; ; 8 # No KAKTOVIK NUMERAL EIGHT @@ -1587,7 +1596,7 @@ FF18 ; 8.0 ; ; 8 # Nd FULLWIDTH DIGIT EIGHT 1F109 ; 8.0 ; ; 8 # No DIGIT EIGHT COMMA 1FBF8 ; 8.0 ; ; 8 # Nd SEGMENTED DIGIT EIGHT -# Total code points: 120 +# Total code points: 121 # ================================================ @@ -1697,6 +1706,7 @@ FF19 ; 9.0 ; ; 9 # Nd FULLWIDTH DIGIT NINE 16AC9 ; 9.0 ; ; 9 # Nd TANGSA DIGIT NINE 16B59 ; 9.0 ; ; 9 # Nd PAHAWH HMONG DIGIT NINE 16D79 ; 9.0 ; ; 9 # Nd KIRAT RAI DIGIT NINE +16DA9 ; 9.0 ; ; 9 # Nd CHISOI DIGIT NINE 16E89 ; 9.0 ; ; 9 # No MEDEFAIDRIN DIGIT NINE 1CCF9 ; 9.0 ; ; 9 # Nd OUTLINED DIGIT NINE 1D2C9 ; 9.0 ; ; 9 # No KAKTOVIK NUMERAL NINE @@ -1721,7 +1731,7 @@ FF19 ; 9.0 ; ; 9 # Nd FULLWIDTH DIGIT NINE 1FBF9 ; 9.0 ; ; 9 # Nd SEGMENTED DIGIT NINE 2F890 ; 9.0 ; ; 9 # Lo CJK COMPATIBILITY IDEOGRAPH-2F890 -# Total code points: 126 +# Total code points: 127 # ================================================ From ee5dfcda0e6c12b76e006ae31c52a6fa595d3f0b Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Sat, 8 Jun 2024 02:55:23 +0200 Subject: [PATCH 08/12] GenerateEnums --- .../src/main/java/org/unicode/props/UcdPropertyValues.java | 2 ++ 1 file changed, 2 insertions(+) diff --git a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java index 37020e727..7cf0d7185 100644 --- a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java +++ b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java @@ -220,6 +220,7 @@ public enum Block_Values implements Named { Cherokee("Cherokee"), Cherokee_Supplement("Cherokee_Sup"), Chess_Symbols("Chess_Symbols"), + Chisoi("Chisoi"), Chorasmian("Chorasmian"), CJK_Unified_Ideographs("CJK"), CJK_Compatibility("CJK_Compat"), @@ -1829,6 +1830,7 @@ public enum Script_Values implements Named { Carian("Cari"), Cham("Cham"), Cherokee("Cher"), + Chisoi("Chis"), Chorasmian("Chrs"), Coptic("Copt", "Qaac"), Cypro_Minoan("Cpmn"), From c3c4b51965fd20d742a96592a9fe2a5c3a692ae4 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Thu, 25 Jul 2024 20:08:42 +0200 Subject: [PATCH 09/12] mind the gap --- unicodetools/data/ucd/dev/Scripts.txt | 1 - 1 file changed, 1 deletion(-) diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 2073f5817..838430751 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -3131,7 +3131,6 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI 16D98 ; Chisoi # Mn CHISOI SIGN ANUSVARA 16D99..16D9C ; Chisoi # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA 16D9D ; Chisoi # Mn CHISOI SIGN SISO -16D9E..16D9F ; Chisoi # Cn [2] .. 16DA0..16DA9 ; Chisoi # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE # Total code points: 42 From 308d60398f7d56c99787a52f358e1e57e34b0d4d Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Thu, 25 Jul 2024 20:13:39 +0200 Subject: [PATCH 10/12] Regenerate UCD --- unicodetools/data/ucd/dev/Scripts.txt | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 838430751..17ef0d593 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: 2024-06-06, 09:45:21 GMT +# Date: 2024-07-25, 18:11:18 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -3133,6 +3133,6 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI 16D9D ; Chisoi # Mn CHISOI SIGN SISO 16DA0..16DA9 ; Chisoi # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE -# Total code points: 42 +# Total code points: 40 # EOF From 8ccee45be4cb7b77a23adac10c8407a93088217e Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 15 Oct 2024 14:24:36 +0200 Subject: [PATCH 11/12] InMeowC from KenW --- .../data/ucd/dev/IndicPositionalCategory.txt | 2 ++ .../data/ucd/dev/IndicSyllabicCategory.txt | 17 +++++++++++++++++ 2 files changed, 19 insertions(+) diff --git a/unicodetools/data/ucd/dev/IndicPositionalCategory.txt b/unicodetools/data/ucd/dev/IndicPositionalCategory.txt index 7379b43e5..542c8d464 100644 --- a/unicodetools/data/ucd/dev/IndicPositionalCategory.txt +++ b/unicodetools/data/ucd/dev/IndicPositionalCategory.txt @@ -1,3 +1,5 @@ +16D98;Top +16D9D;Bottom # IndicPositionalCategory-16.0.0.txt # Date: 2024-04-30, 21:48:21 GMT # © 2024 Unicode®, Inc. diff --git a/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt b/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt index dc0760462..91f3d5bb1 100644 --- a/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt +++ b/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt @@ -1,3 +1,20 @@ +16D80;Vowel +16D81;Consonant +16D82;Vowel +16D83;Vowel +16D84..16D85;Consonant +16D86;Vowel +16D87..16D88;Consonant +16D89;Vowel +16D8A..16D8E;Consonant +16D8F;Vowel +16D90..16D91;Consonant +16D92;Vowel +16D93..16D97;Consonant +16D98;Bindu +16D99..16D9C;Consonant +16D9D;Pure_Killer +16DA0..16DA9;Number # IndicSyllabicCategory-16.0.0.txt # Date: 2024-04-30, 21:48:21 GMT # © 2024 Unicode®, Inc. From 835c7133f62cafcb0bd0562fbd9dd755f1fe842c Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 15 Oct 2024 14:30:26 +0200 Subject: [PATCH 12/12] Regenerate UCD --- .../data/ucd/dev/IndicPositionalCategory.txt | 8 ++-- .../data/ucd/dev/IndicSyllabicCategory.txt | 37 +++++++++---------- 2 files changed, 22 insertions(+), 23 deletions(-) diff --git a/unicodetools/data/ucd/dev/IndicPositionalCategory.txt b/unicodetools/data/ucd/dev/IndicPositionalCategory.txt index 542c8d464..3b7a5f637 100644 --- a/unicodetools/data/ucd/dev/IndicPositionalCategory.txt +++ b/unicodetools/data/ucd/dev/IndicPositionalCategory.txt @@ -1,7 +1,5 @@ -16D98;Top -16D9D;Bottom -# IndicPositionalCategory-16.0.0.txt -# Date: 2024-04-30, 21:48:21 GMT +# IndicPositionalCategory-17.0.0.txt +# Date: 2024-10-15, 12:29:44 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -615,6 +613,7 @@ ABE5 ; Top # Mn MEETEI MAYEK VOWEL SIGN ANAP 11F5A ; Top # Mn KAWI SIGN NUKTA 1611E..16129 ; Top # Mn [12] GURUNG KHEMA VOWEL SIGN AA..GURUNG KHEMA VOWEL LENGTH MARK 1612D ; Top # Mn GURUNG KHEMA SIGN ANUSVARA +16D98 ; Top # Mn CHISOI SIGN ANUSVARA # Indic_Positional_Category=Bottom @@ -769,6 +768,7 @@ ABED ; Bottom # Mn MEETEI MAYEK APUN IYEK 11EF4 ; Bottom # Mn MAKASAR VOWEL SIGN U 11F38..11F3A ; Bottom # Mn [3] KAWI VOWEL SIGN U..KAWI VOWEL SIGN VOCALIC R 1612E..1612F ; Bottom # Mn [2] GURUNG KHEMA CONSONANT SIGN MEDIAL RA..GURUNG KHEMA SIGN THOLHOMA +16D9D ; Bottom # Mn CHISOI SIGN SISO # Indic_Positional_Category=Top_And_Bottom diff --git a/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt b/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt index 91f3d5bb1..53884d4f5 100644 --- a/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt +++ b/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt @@ -1,22 +1,5 @@ -16D80;Vowel -16D81;Consonant -16D82;Vowel -16D83;Vowel -16D84..16D85;Consonant -16D86;Vowel -16D87..16D88;Consonant -16D89;Vowel -16D8A..16D8E;Consonant -16D8F;Vowel -16D90..16D91;Consonant -16D92;Vowel -16D93..16D97;Consonant -16D98;Bindu -16D99..16D9C;Consonant -16D9D;Pure_Killer -16DA0..16DA9;Number -# IndicSyllabicCategory-16.0.0.txt -# Date: 2024-04-30, 21:48:21 GMT +# IndicSyllabicCategory-17.0.0.txt +# Date: 2024-10-15, 12:29:44 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -157,6 +140,7 @@ A980..A981 ; Bindu # Mn [2] JAVANESE SIGN PANYANGGA..JAVANESE SIGN CECAK 11F00..11F01 ; Bindu # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA 1612D ; Bindu # Mn GURUNG KHEMA SIGN ANUSVARA 16D40..16D41 ; Bindu # Lm [2] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN TONPI +16D98 ; Bindu # Mn CHISOI SIGN ANUSVARA # ================================================ @@ -355,6 +339,7 @@ ABED ; Pure_Killer # Mn MEETEI MAYEK APUN IYEK 11F41 ; Pure_Killer # Mc KAWI SIGN KILLER 1612F ; Pure_Killer # Mn GURUNG KHEMA SIGN THOLHOMA 16D6B..16D6C ; Pure_Killer # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D9D ; Pure_Killer # Mn CHISOI SIGN SISO # ================================================ @@ -784,6 +769,12 @@ A866 ; Vowel # Lo PHAGS-PA LETTER EE A922..A925 ; Vowel # Lo [4] KAYAH LI LETTER A..KAYAH LI LETTER OO A926..A92A ; Vowel # Mn [5] KAYAH LI VOWEL UE..KAYAH LI VOWEL O 11150..11154 ; Vowel # Lo [5] MAHAJANI LETTER A..MAHAJANI LETTER O +16D80 ; Vowel # Lo CHISOI LETTER A +16D82..16D83 ; Vowel # Lo [2] CHISOI LETTER AI..CHISOI LETTER AA +16D86 ; Vowel # Lo CHISOI LETTER E +16D89 ; Vowel # Lo CHISOI LETTER I +16D8F ; Vowel # Lo CHISOI LETTER U +16D92 ; Vowel # Lo CHISOI LETTER O # ================================================ @@ -982,6 +973,13 @@ ABD2..ABDA ; Consonant # Lo [9] MEETEI MAYEK LETTER GOK..MEETEI MAYEK LETTE 11F12..11F33 ; Consonant # Lo [34] KAWI LETTER KA..KAWI LETTER JNYA 16101..1611D ; Consonant # Lo [29] GURUNG KHEMA LETTER KA..GURUNG KHEMA LETTER SA 16D43..16D62 ; Consonant # Lo [32] KIRAT RAI LETTER A..KIRAT RAI LETTER HA +16D81 ; Consonant # Lo CHISOI LETTER BA +16D84..16D85 ; Consonant # Lo [2] CHISOI LETTER GA..CHISOI LETTER TA +16D87..16D88 ; Consonant # Lo [2] CHISOI LETTER SA..CHISOI LETTER NA +16D8A..16D8E ; Consonant # Lo [5] CHISOI LETTER KA..CHISOI LETTER RRA +16D90..16D91 ; Consonant # Lo [2] CHISOI LETTER DA..CHISOI LETTER LA +16D93..16D97 ; Consonant # Lo [5] CHISOI LETTER NYA..CHISOI LETTER PA +16D99..16D9C ; Consonant # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA # ================================================ @@ -1396,6 +1394,7 @@ ABF0..ABF9 ; Number # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NI 11F50..11F59 ; Number # Nd [10] KAWI DIGIT ZERO..KAWI DIGIT NINE 16130..16139 ; Number # Nd [10] GURUNG KHEMA DIGIT ZERO..GURUNG KHEMA DIGIT NINE 16D70..16D79 ; Number # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16DA0..16DA9 ; Number # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE # ================================================