From 93c39cccbbb15d232d3e260769b1ee381f0f99a2 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 25 Oct 2023 13:09:27 +0200 Subject: [PATCH 01/10] UnicodeData.txt from L2/23-207 --- unicodetools/data/ucd/dev/UnicodeData.txt | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 20da9b7d8..305212e3a 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -1,3 +1,24 @@ +1CEC0;HEBE;So;0;ON;;;;;N;;;;; +1CEC1;IRIS;So;0;ON;;;;;N;;;;; +1CEC2;FLORA;So;0;ON;;;;;N;;;;; +1CEC3;METIS;So;0;ON;;;;;N;;;;; +1CEC4;PARTHENOPE;So;0;ON;;;;;N;;;;; +1CEC5;VICTORIA;So;0;ON;;;;;N;;;;; +1CEC6;EGERIA;So;0;ON;;;;;N;;;;; +1CEC7;IRENE;So;0;ON;;;;;N;;;;; +1CEC8;EUNOMIA;So;0;ON;;;;;N;;;;; +1CEC9;PSYCHE;So;0;ON;;;;;N;;;;; +1CECA;THETIS;So;0;ON;;;;;N;;;;; +1CECB;MELPOMENE;So;0;ON;;;;;N;;;;; +1CECC;FORTUNA;So;0;ON;;;;;N;;;;; +1CECD;ASTRONOMICAL SYMBOL FOR ASTEROID PROSERPINA;So;0;ON;;;;;N;;;;; +1CECE;BELLONA;So;0;ON;;;;;N;;;;; +1CECF;AMPHITRITE;So;0;ON;;;;;N;;;;; +1CED0;LEUKOTHEA;So;0;ON;;;;;N;;;;; +1F777;VESTA FORM TWO;So;0;ON;;;;;N;;;;; +1F778;ASTRAEA FORM TWO;So;0;ON;;;;;N;;;;; +1F779;HYGIEA FORM TWO;So;0;ON;;;;;N;;;;; +1F77A;PARTHENOPE FORM TWO;So;0;ON;;;;;N;;;;; 0000;;Cc;0;BN;;;;;N;NULL;;;; 0001;;Cc;0;BN;;;;;N;START OF HEADING;;;; 0002;;Cc;0;BN;;;;;N;START OF TEXT;;;; From 3b6269bc396d24e02f5c88987ee7a4eae24aa37d Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 25 Oct 2023 13:23:00 +0200 Subject: [PATCH 02/10] LB is a mess around here, but this should probably be AL. --- unicodetools/data/ucd/dev/LineBreak.txt | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index daea5c0ac..a57889dba 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,5 @@ # LineBreak-16.0.0.txt -# Date: 2023-10-24, 21:03:44 GMT +# Date: 2023-10-25, 11:17:05 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 @@ -3249,6 +3249,7 @@ FFFD ; AI # So REPLACEMENT CHARACTER 1BC9F ; BA # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3 ; CM # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP 1CEB0..1CEB3 ; AL # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET +1CEC0..1CED0 ; AL # So [17] HEBE..LEUKOTHEA 1CF00..1CF2D ; CM # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT 1CF30..1CF46 ; CM # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1CF50..1CFC3 ; AL # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK @@ -3533,7 +3534,7 @@ FFFD ; AI # So REPLACEMENT CHARACTER 1F6FD..1F6FF ; ID # Cn [3] .. 1F700..1F773 ; AL # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE 1F774..1F776 ; ID # So [3] LOT OF FORTUNE..LUNAR ECLIPSE -1F777..1F77A ; ID # Cn [4] .. +1F777..1F77A ; AL 1F77B..1F77F ; ID # So [5] HAUMEA..ORCUS 1F780..1F7D4 ; AL # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR 1F7D5..1F7D9 ; ID # So [5] CIRCLED TRIANGLE..NINE POINTED WHITE STAR From 71604eb616d1f1d0cbee47f3ace9c1a01a91d848 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 25 Oct 2023 13:24:56 +0200 Subject: [PATCH 03/10] Scripts.txt --- unicodetools/data/ucd/dev/Scripts.txt | 2 ++ 1 file changed, 2 insertions(+) diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 376dac297..9b9f71d4c 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,3 +1,5 @@ +1CEC0..1CED0; Common +1F777..1F77A; Common # Scripts-16.0.0.txt # Date: 2023-10-24, 21:04:04 GMT # © 2023 Unicode®, Inc. From f422e006e30139d76d2f934ee8f08bc1600f39b5 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 25 Oct 2023 13:26:43 +0200 Subject: [PATCH 04/10] 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 6dcbf10c7..4fa48d1cd 100644 --- a/unicodetools/data/ucd/dev/Blocks.txt +++ b/unicodetools/data/ucd/dev/Blocks.txt @@ -313,6 +313,7 @@ FFF0..FFFF; Specials 1BC00..1BC9F; Duployan 1BCA0..1BCAF; Shorthand Format Controls 1CC00..1CEBF; Symbols for Legacy Computing Supplement +1CEC0..1CEFF; Miscellaneous Symbols Supplement 1CF00..1CFCF; Znamenny Musical Notation 1D000..1D0FF; Byzantine Musical Symbols 1D100..1D1FF; Musical Symbols 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 c83570084..f789afdd4 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt @@ -202,6 +202,7 @@ Miao ; Miao Misc_Math_Symbols_A ; Miscellaneous_Mathematical_Symbols_A Misc_Math_Symbols_B ; Miscellaneous_Mathematical_Symbols_B Misc_Symbols ; Miscellaneous_Symbols +Misc_Symbols_Sup ; Miscellaneous_Symbols_Supplement Misc_Arrows ; Miscellaneous_Symbols_And_Arrows Misc_Pictographs ; Miscellaneous_Symbols_And_Pictographs Misc_Technical ; Miscellaneous_Technical From 447c37afd6aadb44cd002ab9064794eae769f170 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 25 Oct 2023 13:28:40 +0200 Subject: [PATCH 05/10] Regenerate UCD --- unicodetools/data/ucd/dev/DerivedAge.txt | 6 ++- .../data/ucd/dev/DerivedCoreProperties.txt | 8 ++-- unicodetools/data/ucd/dev/EastAsianWidth.txt | 6 +-- unicodetools/data/ucd/dev/LineBreak.txt | 4 +- .../data/ucd/dev/PropertyValueAliases.txt | 3 +- unicodetools/data/ucd/dev/Scripts.txt | 10 ++--- unicodetools/data/ucd/dev/UnicodeData.txt | 42 +++++++++---------- .../data/ucd/dev/VerticalOrientation.txt | 7 ++-- .../ucd/dev/extracted/DerivedBidiClass.txt | 12 +++--- .../dev/extracted/DerivedCombiningClass.txt | 8 ++-- .../dev/extracted/DerivedEastAsianWidth.txt | 8 ++-- .../dev/extracted/DerivedGeneralCategory.txt | 14 +++---- .../ucd/dev/extracted/DerivedLineBreak.txt | 14 ++++--- .../data/ucd/dev/extracted/DerivedName.txt | 25 ++++++++++- 14 files changed, 95 insertions(+), 72 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index a0de787d6..2465ffb01 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-16.0.0.txt -# Date: 2023-10-24, 21:03:11 GMT +# Date: 2023-10-25, 11:27:37 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 @@ -2024,10 +2024,12 @@ A7CB..A7CD ; 16.0 # [3] LATIN CAPITAL LETTER RAMS HORN..LATIN SMALL LETTER 11BC0..11BE1 ; 16.0 # [34] SUNUWAR LETTER DEVI..SUNUWAR SIGN PVO 11BF0..11BF9 ; 16.0 # [10] SUNUWAR DIGIT ZERO..SUNUWAR DIGIT NINE 1CEB0..1CEB3 ; 16.0 # [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET +1CEC0..1CED0 ; 16.0 # [17] HEBE..LEUKOTHEA 1E5D0..1E5FA ; 16.0 # [43] OL ONAL LETTER O..OL ONAL DIGIT NINE 1E5FF ; 16.0 # OL ONAL ABBREVIATION SIGN +1F777..1F77A ; 16.0 # [4] VESTA FORM TWO..PARTHENOPE FORM TWO 1F8B2 ; 16.0 # RIGHTWARDS ARROW WITH LOWER HOOK -# Total code points: 246 +# Total code points: 267 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 5d2157ef5..764ef3ac3 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-16.0.0.txt -# Date: 2023-10-24, 21:03:37 GMT +# Date: 2023-10-25, 11:28:08 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 @@ -12452,6 +12452,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1BC9C ; Grapheme_Base # So DUPLOYAN SIGN O WITH CROSS 1BC9F ; Grapheme_Base # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1CEB0..1CEB3 ; Grapheme_Base # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET +1CEC0..1CED0 ; Grapheme_Base # So [17] HEBE..LEUKOTHEA 1CF50..1CFC3 ; Grapheme_Base # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK 1D000..1D0F5 ; Grapheme_Base # So [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126 ; Grapheme_Base # So [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 @@ -12606,8 +12607,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1F400..1F6D7 ; Grapheme_Base # So [728] RAT..ELEVATOR 1F6DC..1F6EC ; Grapheme_Base # So [17] WIRELESS..AIRPLANE ARRIVING 1F6F0..1F6FC ; Grapheme_Base # So [13] SATELLITE..ROLLER SKATE -1F700..1F776 ; Grapheme_Base # So [119] ALCHEMICAL SYMBOL FOR QUINTESSENCE..LUNAR ECLIPSE -1F77B..1F7D9 ; Grapheme_Base # So [95] HAUMEA..NINE POINTED WHITE STAR +1F700..1F7D9 ; Grapheme_Base # So [218] ALCHEMICAL SYMBOL FOR QUINTESSENCE..NINE POINTED WHITE STAR 1F7E0..1F7EB ; Grapheme_Base # So [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE 1F7F0 ; Grapheme_Base # So HEAVY EQUALS SIGN 1F800..1F80B ; Grapheme_Base # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD @@ -12638,7 +12638,7 @@ 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: 147850 +# Total code points: 147871 # ================================================ diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index add68d076..87b2b9c26 100644 --- a/unicodetools/data/ucd/dev/EastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/EastAsianWidth.txt @@ -1,5 +1,5 @@ # EastAsianWidth-16.0.0.txt -# Date: 2023-10-24, 21:03:43 GMT +# Date: 2023-10-25, 11:28:17 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -2344,6 +2344,7 @@ FFFD ; A # So REPLACEMENT CHARACTER 1BC9F ; N # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3 ; N # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP 1CEB0..1CEB3 ; N # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET +1CEC0..1CED0 ; N # So [17] HEBE..LEUKOTHEA 1CF00..1CF2D ; N # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT 1CF30..1CF46 ; N # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1CF50..1CFC3 ; N # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK @@ -2586,8 +2587,7 @@ FFFD ; A # So REPLACEMENT CHARACTER 1F6EB..1F6EC ; W # So [2] AIRPLANE DEPARTURE..AIRPLANE ARRIVING 1F6F0..1F6F3 ; N # So [4] SATELLITE..PASSENGER SHIP 1F6F4..1F6FC ; W # So [9] SCOOTER..ROLLER SKATE -1F700..1F776 ; N # So [119] ALCHEMICAL SYMBOL FOR QUINTESSENCE..LUNAR ECLIPSE -1F77B..1F77F ; N # So [5] HAUMEA..ORCUS +1F700..1F77F ; N # So [128] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ORCUS 1F780..1F7D9 ; N # So [90] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..NINE POINTED WHITE STAR 1F7E0..1F7EB ; W # So [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE 1F7F0 ; W # So HEAVY EQUALS SIGN diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index a57889dba..c7a5cc956 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,5 @@ # LineBreak-16.0.0.txt -# Date: 2023-10-25, 11:17:05 GMT +# Date: 2023-10-25, 11:28:18 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 @@ -3534,7 +3534,7 @@ FFFD ; AI # So REPLACEMENT CHARACTER 1F6FD..1F6FF ; ID # Cn [3] .. 1F700..1F773 ; AL # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE 1F774..1F776 ; ID # So [3] LOT OF FORTUNE..LUNAR ECLIPSE -1F777..1F77A ; AL +1F777..1F77A ; AL # So [4] VESTA FORM TWO..PARTHENOPE FORM TWO 1F77B..1F77F ; ID # So [5] HAUMEA..ORCUS 1F780..1F7D4 ; AL # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR 1F7D5..1F7D9 ; ID # So [5] CIRCLED TRIANGLE..NINE POINTED WHITE STAR diff --git a/unicodetools/data/ucd/dev/PropertyValueAliases.txt b/unicodetools/data/ucd/dev/PropertyValueAliases.txt index 0e34fbc04..bd1eaf82d 100644 --- a/unicodetools/data/ucd/dev/PropertyValueAliases.txt +++ b/unicodetools/data/ucd/dev/PropertyValueAliases.txt @@ -1,5 +1,5 @@ # PropertyValueAliases-16.0.0.txt -# Date: 2023-10-24, 21:03:50 GMT +# Date: 2023-10-25, 11:28:24 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 @@ -357,6 +357,7 @@ blk; Misc_Math_Symbols_A ; Miscellaneous_Mathematical_Symbols_A blk; Misc_Math_Symbols_B ; Miscellaneous_Mathematical_Symbols_B blk; Misc_Pictographs ; Miscellaneous_Symbols_And_Pictographs blk; Misc_Symbols ; Miscellaneous_Symbols +blk; Misc_Symbols_Sup ; Miscellaneous_Symbols_Supplement blk; Misc_Technical ; Miscellaneous_Technical blk; Modi ; Modi blk; Modifier_Letters ; Spacing_Modifier_Letters diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 9b9f71d4c..ce672eed4 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,7 +1,5 @@ -1CEC0..1CED0; Common -1F777..1F77A; Common # Scripts-16.0.0.txt -# Date: 2023-10-24, 21:04:04 GMT +# Date: 2023-10-25, 11:28:35 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 @@ -525,6 +523,7 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR 102E1..102FB ; Common # No [27] COPTIC EPACT DIGIT ONE..COPTIC EPACT NUMBER NINE HUNDRED 1BCA0..1BCA3 ; Common # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP 1CEB0..1CEB3 ; Common # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET +1CEC0..1CED0 ; Common # So [17] HEBE..LEUKOTHEA 1CF50..1CFC3 ; Common # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK 1D000..1D0F5 ; Common # So [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126 ; Common # So [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 @@ -608,8 +607,7 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR 1F400..1F6D7 ; Common # So [728] RAT..ELEVATOR 1F6DC..1F6EC ; Common # So [17] WIRELESS..AIRPLANE ARRIVING 1F6F0..1F6FC ; Common # So [13] SATELLITE..ROLLER SKATE -1F700..1F776 ; Common # So [119] ALCHEMICAL SYMBOL FOR QUINTESSENCE..LUNAR ECLIPSE -1F77B..1F7D9 ; Common # So [95] HAUMEA..NINE POINTED WHITE STAR +1F700..1F7D9 ; Common # So [218] ALCHEMICAL SYMBOL FOR QUINTESSENCE..NINE POINTED WHITE STAR 1F7E0..1F7EB ; Common # So [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE 1F7F0 ; Common # So HEAVY EQUALS SIGN 1F800..1F80B ; Common # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD @@ -633,7 +631,7 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR E0001 ; Common # Cf LANGUAGE TAG E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG -# Total code points: 8311 +# Total code points: 8332 # ================================================ diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 305212e3a..abae2b7f5 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -1,24 +1,3 @@ -1CEC0;HEBE;So;0;ON;;;;;N;;;;; -1CEC1;IRIS;So;0;ON;;;;;N;;;;; -1CEC2;FLORA;So;0;ON;;;;;N;;;;; -1CEC3;METIS;So;0;ON;;;;;N;;;;; -1CEC4;PARTHENOPE;So;0;ON;;;;;N;;;;; -1CEC5;VICTORIA;So;0;ON;;;;;N;;;;; -1CEC6;EGERIA;So;0;ON;;;;;N;;;;; -1CEC7;IRENE;So;0;ON;;;;;N;;;;; -1CEC8;EUNOMIA;So;0;ON;;;;;N;;;;; -1CEC9;PSYCHE;So;0;ON;;;;;N;;;;; -1CECA;THETIS;So;0;ON;;;;;N;;;;; -1CECB;MELPOMENE;So;0;ON;;;;;N;;;;; -1CECC;FORTUNA;So;0;ON;;;;;N;;;;; -1CECD;ASTRONOMICAL SYMBOL FOR ASTEROID PROSERPINA;So;0;ON;;;;;N;;;;; -1CECE;BELLONA;So;0;ON;;;;;N;;;;; -1CECF;AMPHITRITE;So;0;ON;;;;;N;;;;; -1CED0;LEUKOTHEA;So;0;ON;;;;;N;;;;; -1F777;VESTA FORM TWO;So;0;ON;;;;;N;;;;; -1F778;ASTRAEA FORM TWO;So;0;ON;;;;;N;;;;; -1F779;HYGIEA FORM TWO;So;0;ON;;;;;N;;;;; -1F77A;PARTHENOPE FORM TWO;So;0;ON;;;;;N;;;;; 0000;;Cc;0;BN;;;;;N;NULL;;;; 0001;;Cc;0;BN;;;;;N;START OF HEADING;;;; 0002;;Cc;0;BN;;;;;N;START OF TEXT;;;; @@ -28202,6 +28181,23 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1CEB1;KEYHOLE;So;0;ON;;;;;N;;;;; 1CEB2;OLD PERSONAL COMPUTER WITH MONITOR IN PORTRAIT ORIENTATION;So;0;ON;;;;;N;;;;; 1CEB3;BLACK RIGHT TRIANGLE CARET;So;0;ON;;;;;N;;;;; +1CEC0;HEBE;So;0;ON;;;;;N;;;;; +1CEC1;IRIS;So;0;ON;;;;;N;;;;; +1CEC2;FLORA;So;0;ON;;;;;N;;;;; +1CEC3;METIS;So;0;ON;;;;;N;;;;; +1CEC4;PARTHENOPE;So;0;ON;;;;;N;;;;; +1CEC5;VICTORIA;So;0;ON;;;;;N;;;;; +1CEC6;EGERIA;So;0;ON;;;;;N;;;;; +1CEC7;IRENE;So;0;ON;;;;;N;;;;; +1CEC8;EUNOMIA;So;0;ON;;;;;N;;;;; +1CEC9;PSYCHE;So;0;ON;;;;;N;;;;; +1CECA;THETIS;So;0;ON;;;;;N;;;;; +1CECB;MELPOMENE;So;0;ON;;;;;N;;;;; +1CECC;FORTUNA;So;0;ON;;;;;N;;;;; +1CECD;ASTRONOMICAL SYMBOL FOR ASTEROID PROSERPINA;So;0;ON;;;;;N;;;;; +1CECE;BELLONA;So;0;ON;;;;;N;;;;; +1CECF;AMPHITRITE;So;0;ON;;;;;N;;;;; +1CED0;LEUKOTHEA;So;0;ON;;;;;N;;;;; 1CF00;ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT;Mn;0;NSM;;;;;N;;;;; 1CF01;ZNAMENNY COMBINING MARK NIZKO S KRYZHEM ON LEFT;Mn;0;NSM;;;;;N;;;;; 1CF02;ZNAMENNY COMBINING MARK TSATA ON LEFT;Mn;0;NSM;;;;;N;;;;; @@ -33365,6 +33361,10 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1F774;LOT OF FORTUNE;So;0;ON;;;;;N;;;;; 1F775;OCCULTATION;So;0;ON;;;;;N;;;;; 1F776;LUNAR ECLIPSE;So;0;ON;;;;;N;;;;; +1F777;VESTA FORM TWO;So;0;ON;;;;;N;;;;; +1F778;ASTRAEA FORM TWO;So;0;ON;;;;;N;;;;; +1F779;HYGIEA FORM TWO;So;0;ON;;;;;N;;;;; +1F77A;PARTHENOPE FORM TWO;So;0;ON;;;;;N;;;;; 1F77B;HAUMEA;So;0;ON;;;;;N;;;;; 1F77C;MAKEMAKE;So;0;ON;;;;;N;;;;; 1F77D;GONGGONG;So;0;ON;;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index 08b73924c..788141c3f 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ # VerticalOrientation-16.0.0.txt -# Date: 2023-10-24, 21:04:08 GMT +# Date: 2023-10-25, 11:28:38 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 @@ -2189,6 +2189,7 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 1BC9F ; R # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3 ; R # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP 1CEB0..1CEB3 ; R # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET +1CEC0..1CED0 ; R # So [17] HEBE..LEUKOTHEA 1CF00..1CF2D ; U # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT 1CF2E..1CF2F ; U # Cn [2] .. 1CF30..1CF46 ; U # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG @@ -2401,9 +2402,7 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 1F6ED..1F6EF ; U # Cn [3] .. 1F6F0..1F6FC ; U # So [13] SATELLITE..ROLLER SKATE 1F6FD..1F6FF ; U # Cn [3] .. -1F700..1F776 ; U # So [119] ALCHEMICAL SYMBOL FOR QUINTESSENCE..LUNAR ECLIPSE -1F777..1F77A ; U # Cn [4] .. -1F77B..1F77F ; U # So [5] HAUMEA..ORCUS +1F700..1F77F ; U # So [128] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ORCUS 1F780..1F7D9 ; U # So [90] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..NINE POINTED WHITE STAR 1F7DA..1F7DF ; U # Cn [6] .. 1F7E0..1F7EB ; U # So [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index b3216b731..6c876a419 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-16.0.0.txt -# Date: 2023-10-24, 21:03:35 GMT +# Date: 2023-10-25, 11:28:05 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 @@ -1192,8 +1192,8 @@ 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 820290 code points not listed here. -# Total code points: 1096260 +# The above property value applies to 820269 code points not listed here. +# Total code points: 1096239 # ================================================ @@ -1919,6 +1919,7 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE 11FE1..11FF1 ; ON # So [17] TAMIL SIGN PAARAM..TAMIL SIGN VAKAIYARAA 16FE2 ; ON # Po OLD CHINESE HOOK MARK 1CEB0..1CEB3 ; ON # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET +1CEC0..1CED0 ; ON # So [17] HEBE..LEUKOTHEA 1D1E9..1D1EA ; ON # So [2] MUSICAL SYMBOL SORI..MUSICAL SYMBOL KORON 1D200..1D241 ; ON # So [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54 1D245 ; ON # So GREEK MUSICAL LEIMMA @@ -1946,8 +1947,7 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE 1F400..1F6D7 ; ON # So [728] RAT..ELEVATOR 1F6DC..1F6EC ; ON # So [17] WIRELESS..AIRPLANE ARRIVING 1F6F0..1F6FC ; ON # So [13] SATELLITE..ROLLER SKATE -1F700..1F776 ; ON # So [119] ALCHEMICAL SYMBOL FOR QUINTESSENCE..LUNAR ECLIPSE -1F77B..1F7D9 ; ON # So [95] HAUMEA..NINE POINTED WHITE STAR +1F700..1F7D9 ; ON # So [218] ALCHEMICAL SYMBOL FOR QUINTESSENCE..NINE POINTED WHITE STAR 1F7E0..1F7EB ; ON # So [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE 1F7F0 ; ON # So HEAVY EQUALS SIGN 1F800..1F80B ; ON # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD @@ -1968,7 +1968,7 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE 1FB00..1FB92 ; ON # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; ON # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON -# Total code points: 6040 +# Total code points: 6061 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index c3ef6239a..c67ec000a 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-16.0.0.txt -# Date: 2023-10-24, 21:03:36 GMT +# Date: 2023-10-25, 11:28:08 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 @@ -1828,6 +1828,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1BC9F ; 0 # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3 ; 0 # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP 1CEB0..1CEB3 ; 0 # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET +1CEC0..1CED0 ; 0 # So [17] HEBE..LEUKOTHEA 1CF00..1CF2D ; 0 # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT 1CF30..1CF46 ; 0 # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1CF50..1CFC3 ; 0 # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK @@ -1989,8 +1990,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1F400..1F6D7 ; 0 # So [728] RAT..ELEVATOR 1F6DC..1F6EC ; 0 # So [17] WIRELESS..AIRPLANE ARRIVING 1F6F0..1F6FC ; 0 # So [13] SATELLITE..ROLLER SKATE -1F700..1F776 ; 0 # So [119] ALCHEMICAL SYMBOL FOR QUINTESSENCE..LUNAR ECLIPSE -1F77B..1F7D9 ; 0 # So [95] HAUMEA..NINE POINTED WHITE STAR +1F700..1F7D9 ; 0 # So [218] ALCHEMICAL SYMBOL FOR QUINTESSENCE..NINE POINTED WHITE STAR 1F7E0..1F7EB ; 0 # So [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE 1F7F0 ; 0 # So HEAVY EQUALS SIGN 1F800..1F80B ; 0 # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD @@ -2026,7 +2026,7 @@ 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 826520 code points not listed here. +# The above property value applies to 826499 code points not listed here. # Total code points: 1113182 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index b9c329c1d..41946f543 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-16.0.0.txt -# Date: 2023-10-24, 21:03:39 GMT +# Date: 2023-10-25, 11:28:11 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 @@ -1847,6 +1847,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 1BC9F ; N # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3 ; N # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP 1CEB0..1CEB3 ; N # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET +1CEC0..1CED0 ; N # So [17] HEBE..LEUKOTHEA 1CF00..1CF2D ; N # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT 1CF30..1CF46 ; N # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1CF50..1CFC3 ; N # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK @@ -2046,8 +2047,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 1F6D3..1F6D4 ; N # So [2] STUPA..PAGODA 1F6E0..1F6EA ; N # So [11] HAMMER AND WRENCH..NORTHEAST-POINTING AIRPLANE 1F6F0..1F6F3 ; N # So [4] SATELLITE..PASSENGER SHIP -1F700..1F776 ; N # So [119] ALCHEMICAL SYMBOL FOR QUINTESSENCE..LUNAR ECLIPSE -1F77B..1F7D9 ; N # So [95] HAUMEA..NINE POINTED WHITE STAR +1F700..1F7D9 ; N # So [218] ALCHEMICAL SYMBOL FOR QUINTESSENCE..NINE POINTED WHITE STAR 1F800..1F80B ; N # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD 1F810..1F847 ; N # So [56] LEFTWARDS ARROW WITH SMALL EQUILATERAL ARROWHEAD..DOWNWARDS HEAVY ARROW 1F850..1F859 ; N # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW @@ -2065,7 +2065,7 @@ 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 766038 code points not listed here. +# The above property value applies to 766017 code points not listed here. # Total code points: 792618 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index 2a5ac8419..c080ad50f 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-16.0.0.txt -# Date: 2023-10-24, 21:03:39 GMT +# Date: 2023-10-25, 11:28:11 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 @@ -583,7 +583,8 @@ FFFE..FFFF ; Cn # [2] .. 1BC89..1BC8F ; Cn # [7] .. 1BC9A..1BC9B ; Cn # [2] .. 1BCA4..1CEAF ; Cn # [4620] .. -1CEB4..1CEFF ; Cn # [76] .. +1CEB4..1CEBF ; Cn # [12] .. +1CED1..1CEFF ; Cn # [47] .. 1CF2E..1CF2F ; Cn # [2] .. 1CF47..1CF4F ; Cn # [9] .. 1CFC4..1CFFF ; Cn # [60] .. @@ -697,7 +698,6 @@ FFFE..FFFF ; Cn # [2] .. 1F6D8..1F6DB ; Cn # [4] .. 1F6ED..1F6EF ; Cn # [3] .. 1F6FD..1F6FF ; Cn # [3] .. -1F777..1F77A ; Cn # [4] .. 1F7DA..1F7DF ; Cn # [6] .. 1F7EC..1F7EF ; Cn # [4] .. 1F7F1..1F7FF ; Cn # [15] .. @@ -734,7 +734,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 824472 +# Total code points: 824451 # ================================================ @@ -4173,6 +4173,7 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 16B45 ; So # PAHAWH HMONG SIGN CIM TSOV ROG 1BC9C ; So # DUPLOYAN SIGN O WITH CROSS 1CEB0..1CEB3 ; So # [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET +1CEC0..1CED0 ; So # [17] HEBE..LEUKOTHEA 1CF50..1CFC3 ; So # [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK 1D000..1D0F5 ; So # [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126 ; So # [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 @@ -4208,8 +4209,7 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1F400..1F6D7 ; So # [728] RAT..ELEVATOR 1F6DC..1F6EC ; So # [17] WIRELESS..AIRPLANE ARRIVING 1F6F0..1F6FC ; So # [13] SATELLITE..ROLLER SKATE -1F700..1F776 ; So # [119] ALCHEMICAL SYMBOL FOR QUINTESSENCE..LUNAR ECLIPSE -1F77B..1F7D9 ; So # [95] HAUMEA..NINE POINTED WHITE STAR +1F700..1F7D9 ; So # [218] ALCHEMICAL SYMBOL FOR QUINTESSENCE..NINE POINTED WHITE STAR 1F7E0..1F7EB ; So # [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE 1F7F0 ; So # HEAVY EQUALS SIGN 1F800..1F80B ; So # [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD @@ -4230,7 +4230,7 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1FB00..1FB92 ; So # [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; So # [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON -# Total code points: 6644 +# Total code points: 6665 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 0581bb420..bdce4e1f1 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-16.0.0.txt -# Date: 2023-10-24, 21:03:41 GMT +# Date: 2023-10-25, 11:28:13 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -68,8 +68,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 762480 code points not listed here. -# Total code points: 899948 +# The above property value applies to 762463 code points not listed here. +# Total code points: 899931 # ================================================ @@ -1446,6 +1446,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1BC90..1BC99 ; AL # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW 1BC9C ; AL # So DUPLOYAN SIGN O WITH CROSS 1CEB0..1CEB3 ; AL # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET +1CEC0..1CED0 ; AL # So [17] HEBE..LEUKOTHEA 1CF50..1CFC3 ; AL # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK 1D000..1D0F5 ; AL # So [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126 ; AL # So [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 @@ -1588,6 +1589,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1F650..1F675 ; AL # So [38] NORTH WEST POINTING LEAF..SWASH AMPERSAND ORNAMENT 1F67C..1F67F ; AL # So [4] VERY HEAVY SOLIDUS..REVERSE CHECKER BOARD 1F700..1F773 ; AL # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE +1F777..1F77A ; AL # So [4] VESTA FORM TWO..PARTHENOPE FORM TWO 1F780..1F7D4 ; AL # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR 1F800..1F80B ; AL # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD 1F810..1F847 ; AL # So [56] LEFTWARDS ARROW WITH SMALL EQUILATERAL ARROWHEAD..DOWNWARDS HEAVY ARROW @@ -1600,7 +1602,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1FB00..1FB92 ; AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; AL # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON -# Total code points: 21915 +# Total code points: 21936 # ================================================ @@ -1843,8 +1845,8 @@ FFE4 ; ID # So FULLWIDTH BROKEN BAR 30000..3134A ; ID # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; ID # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# The above property value applies to 61977 code points not listed here. -# Total code points: 172567 +# The above property value applies to 61973 code points not listed here. +# Total code points: 172563 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index b9437c06f..3cae3b912 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-16.0.0.txt -# Date: 2023-10-24, 21:03:41 GMT +# Date: 2023-10-25, 11:28:14 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 @@ -37980,6 +37980,23 @@ FFFD ; REPLACEMENT CHARACTER 1CEB1 ; KEYHOLE 1CEB2 ; OLD PERSONAL COMPUTER WITH MONITOR IN PORTRAIT ORIENTATION 1CEB3 ; BLACK RIGHT TRIANGLE CARET +1CEC0 ; HEBE +1CEC1 ; IRIS +1CEC2 ; FLORA +1CEC3 ; METIS +1CEC4 ; PARTHENOPE +1CEC5 ; VICTORIA +1CEC6 ; EGERIA +1CEC7 ; IRENE +1CEC8 ; EUNOMIA +1CEC9 ; PSYCHE +1CECA ; THETIS +1CECB ; MELPOMENE +1CECC ; FORTUNA +1CECD ; ASTRONOMICAL SYMBOL FOR ASTEROID PROSERPINA +1CECE ; BELLONA +1CECF ; AMPHITRITE +1CED0 ; LEUKOTHEA 1CF00 ; ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT 1CF01 ; ZNAMENNY COMBINING MARK NIZKO S KRYZHEM ON LEFT 1CF02 ; ZNAMENNY COMBINING MARK TSATA ON LEFT @@ -43143,6 +43160,10 @@ FFFD ; REPLACEMENT CHARACTER 1F774 ; LOT OF FORTUNE 1F775 ; OCCULTATION 1F776 ; LUNAR ECLIPSE +1F777 ; VESTA FORM TWO +1F778 ; ASTRAEA FORM TWO +1F779 ; HYGIEA FORM TWO +1F77A ; PARTHENOPE FORM TWO 1F77B ; HAUMEA 1F77C ; MAKEMAKE 1F77D ; GONGGONG @@ -44422,6 +44443,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 150059 +# Total code points: 150080 # EOF From 0f5e9a96005c41dfd4c0f8d22aa39d47c33f34f7 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 25 Oct 2023 13:29:09 +0200 Subject: [PATCH 06/10] GenerateEnums --- .../src/main/java/org/unicode/props/UcdPropertyValues.java | 1 + 1 file changed, 1 insertion(+) diff --git a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java index 880612bf6..513f98aa3 100644 --- a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java +++ b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java @@ -382,6 +382,7 @@ public enum Block_Values implements Named { Miscellaneous_Mathematical_Symbols_B("Misc_Math_Symbols_B"), Miscellaneous_Symbols_And_Pictographs("Misc_Pictographs"), Miscellaneous_Symbols("Misc_Symbols"), + Miscellaneous_Symbols_Supplement("Misc_Symbols_Sup"), Miscellaneous_Technical("Misc_Technical"), Modi("Modi"), Spacing_Modifier_Letters("Modifier_Letters"), From 88080d7919d34b08825ff3875e889dc021cf3c02 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Fri, 29 Dec 2023 11:25:25 +0100 Subject: [PATCH 07/10] Miscellaneous symbols supplement to vo=U --- unicodetools/data/ucd/dev/VerticalOrientation.txt | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index 788141c3f..b0ce59646 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -50,6 +50,7 @@ # Kana Extended-A & Small Kana Ext: U+1B100..U+1B16F # Nushu: U+1B170..U+1B2FF # Musical Symbols: U+1CF00..U+1CFCF +# Miscellaneous Symbols Supplement: U+1CEC0..U+1CEFF # Musical Symbols: U+1D000..U+1D1FF # Mayan Numerals: U+1D2E0..U+1D2FF # Symbols & Rods: U+1D300..U+1D37F @@ -2189,7 +2190,7 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 1BC9F ; R # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3 ; R # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP 1CEB0..1CEB3 ; R # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET -1CEC0..1CED0 ; R # So [17] HEBE..LEUKOTHEA +1CEC0..1CEFF ; U # So [17] HEBE..LEUKOTHEA 1CF00..1CF2D ; U # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT 1CF2E..1CF2F ; U # Cn [2] .. 1CF30..1CF46 ; U # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG From 29076944f81c9316b2d1dbe7a6bf79d6d06e783e Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Fri, 29 Dec 2023 11:27:37 +0100 Subject: [PATCH 08/10] Regenerate UCD --- unicodetools/data/ucd/dev/VerticalOrientation.txt | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index b0ce59646..cdb9f4732 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ # VerticalOrientation-16.0.0.txt -# Date: 2023-10-25, 11:28:38 GMT +# Date: 2023-12-29, 10:27:34 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 @@ -50,7 +50,6 @@ # Kana Extended-A & Small Kana Ext: U+1B100..U+1B16F # Nushu: U+1B170..U+1B2FF # Musical Symbols: U+1CF00..U+1CFCF -# Miscellaneous Symbols Supplement: U+1CEC0..U+1CEFF # Musical Symbols: U+1D000..U+1D1FF # Mayan Numerals: U+1D2E0..U+1D2FF # Symbols & Rods: U+1D300..U+1D37F @@ -2190,7 +2189,8 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 1BC9F ; R # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3 ; R # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP 1CEB0..1CEB3 ; R # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET -1CEC0..1CEFF ; U # So [17] HEBE..LEUKOTHEA +1CEC0..1CED0 ; U # So [17] HEBE..LEUKOTHEA +1CED1..1CEFF ; U # Cn [47] .. 1CF00..1CF2D ; U # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT 1CF2E..1CF2F ; U # Cn [2] .. 1CF30..1CF46 ; U # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG From 3530603edd7de1868f03f7a3a405588aca5bfee1 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Fri, 29 Dec 2023 11:32:55 +0100 Subject: [PATCH 09/10] comment --- .../src/main/resources/org/unicode/text/UCD/MakeUnicodeFiles.txt | 1 + 1 file changed, 1 insertion(+) diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/MakeUnicodeFiles.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/MakeUnicodeFiles.txt index db8ebd7b8..4435f4b17 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/MakeUnicodeFiles.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/MakeUnicodeFiles.txt @@ -884,6 +884,7 @@ Format: kenFile skipValue=Rotated # Kana Extended-A & Small Kana Ext: U+1B100..U+1B16F # Nushu: U+1B170..U+1B2FF # Musical Symbols: U+1CF00..U+1CFCF +# Miscellaneous Symbols Supplement: U+1CEC0..U+1CEFF # Musical Symbols: U+1D000..U+1D1FF # Mayan Numerals: U+1D2E0..U+1D2FF # Symbols & Rods: U+1D300..U+1D37F From b0b144ad0665c3ad3805b371ea164fb8d829cc51 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Fri, 29 Dec 2023 11:34:48 +0100 Subject: [PATCH 10/10] Regenerate UCD --- unicodetools/data/ucd/dev/VerticalOrientation.txt | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index cdb9f4732..21a8432c1 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: 2023-12-29, 10:27:34 GMT +# Date: 2023-12-29, 10:34:32 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 @@ -50,6 +50,7 @@ # Kana Extended-A & Small Kana Ext: U+1B100..U+1B16F # Nushu: U+1B170..U+1B2FF # Musical Symbols: U+1CF00..U+1CFCF +# Miscellaneous Symbols Supplement: U+1CEC0..U+1CEFF # Musical Symbols: U+1D000..U+1D1FF # Mayan Numerals: U+1D2E0..U+1D2FF # Symbols & Rods: U+1D300..U+1D37F