From 71bdf25e7fca0ee72e26c20fbe078bb611181ba1 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 24 Oct 2023 09:14:15 +0200 Subject: [PATCH 1/4] UnicodeData.txt from L2/23-252 --- unicodetools/data/ucd/dev/UnicodeData.txt | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index c2c986b26..3b2d4b75f 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -1,3 +1,13 @@ +1CCFA;SNAKE SYMBOL;So;0;ON;;;;;N;;;;; +1CCFB;FLYING SAUCER SYMBOL;So;0;ON;;;;;N;;;;; +1CCFC;NOSE SYMBOL;So;0;ON;;;;;N;;;;; +1CEBA;FRAGILE SYMBOL;So;0;ON;;;;;N;;;;; +1CEBB;OFFICE BUILDING SYMBOL;So;0;ON;;;;;N;;;;; +1CEBC;TREE SYMBOL;So;0;ON;;;;;N;;;;; +1CEBD;APPLE SYMBOL;So;0;ON;;;;;N;;;;; +1CEBE;CHERRY SYMBOL;So;0;ON;;;;;N;;;;; +1CEBF;STRAWBERRY SYMBOL;So;0;ON;;;;;N;;;;; +1FBFA;ALARM BELL SYMBOL;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 ddb5a2763e6cc7d0f164b0f21239513ffa93d31e Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 24 Oct 2023 09:45:29 +0200 Subject: [PATCH 2/4] LB=AL --- unicodetools/data/ucd/dev/LineBreak.txt | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index f826adf12..a0ec1626e 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,5 @@ # LineBreak-16.0.0.txt -# Date: 2023-10-23, 18:45:02 GMT +# Date: 2023-10-24, 07:43:05 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 @@ -3248,7 +3248,9 @@ FFFD ; AI # So REPLACEMENT CHARACTER 1BC9D..1BC9E ; CM # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK 1BC9F ; BA # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3 ; CM # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CCFA..1CCFC ; AL # So [3] SNAKE SYMBOL..NOSE SYMBOL 1CEB0..1CEB3 ; AL # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET +1CEBA..1CEBF ; AL # So [6] FRAGILE SYMBOL..STRAWBERRY SYMBOL 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 @@ -3597,6 +3599,7 @@ FFFD ; AI # So REPLACEMENT CHARACTER 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 1FBF0..1FBF9 ; NU # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE +1FBFA ; AL # So ALARM BELL SYMBOL 1FC00..1FFFD ; ID # Cn [1022] .. 20000..2A6DF ; ID # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF 2A6E0..2A6FF ; ID # Cn [32] .. From 4acab1a777f028ea9faa85ccf2ef04b4235ea89f Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 24 Oct 2023 09:47:47 +0200 Subject: [PATCH 3/4] Scripts.txt --- unicodetools/data/ucd/dev/Scripts.txt | 3 +++ 1 file changed, 3 insertions(+) diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 9c32a15b9..1abf619f0 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,3 +1,6 @@ +1CCFA..1CCFC;Common +1CEBA..1CEBF;Common +1FBFA;Common # Scripts-16.0.0.txt # Date: 2023-10-23, 18:45:30 GMT # © 2023 Unicode®, Inc. From 8446105857e0607c896ce702ce4a2c3538e360da Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 24 Oct 2023 09:51:09 +0200 Subject: [PATCH 4/4] Regenerate UCD --- unicodetools/data/ucd/dev/DerivedAge.txt | 7 +++++-- .../data/ucd/dev/DerivedCoreProperties.txt | 7 +++++-- unicodetools/data/ucd/dev/EastAsianWidth.txt | 5 ++++- unicodetools/data/ucd/dev/Scripts.txt | 10 +++++----- unicodetools/data/ucd/dev/UnicodeData.txt | 20 +++++++++---------- .../data/ucd/dev/VerticalOrientation.txt | 5 ++++- .../ucd/dev/extracted/DerivedBidiClass.txt | 11 ++++++---- .../dev/extracted/DerivedCombiningClass.txt | 7 +++++-- .../dev/extracted/DerivedEastAsianWidth.txt | 7 +++++-- .../dev/extracted/DerivedGeneralCategory.txt | 17 ++++++++++------ .../ucd/dev/extracted/DerivedLineBreak.txt | 11 ++++++---- .../data/ucd/dev/extracted/DerivedName.txt | 14 +++++++++++-- 12 files changed, 80 insertions(+), 41 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index 57dd38b3b..678febc68 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-16.0.0.txt -# Date: 2023-10-23, 18:44:20 GMT +# Date: 2023-10-24, 07:49:54 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -2022,9 +2022,12 @@ FDFE..FDFF ; 14.0 # [2] ARABIC LIGATURE SUBHAANAHU WA TAAALAA..ARABIC LIGAT 116D0..116E3 ; 16.0 # [20] MYANMAR PAO DIGIT ZERO..MYANMAR EASTERN PWO KAREN DIGIT NINE 11BC0..11BE1 ; 16.0 # [34] SUNUWAR LETTER DEVI..SUNUWAR SIGN PVO 11BF0..11BF9 ; 16.0 # [10] SUNUWAR DIGIT ZERO..SUNUWAR DIGIT NINE +1CCFA..1CCFC ; 16.0 # [3] SNAKE SYMBOL..NOSE SYMBOL 1CEB0..1CEB3 ; 16.0 # [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET +1CEBA..1CEBF ; 16.0 # [6] FRAGILE SYMBOL..STRAWBERRY SYMBOL 1F8B2 ; 16.0 # RIGHTWARDS ARROW WITH LOWER HOOK +1FBFA ; 16.0 # ALARM BELL SYMBOL -# Total code points: 199 +# Total code points: 209 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 42df9cdb7..9f5198cc9 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-16.0.0.txt -# Date: 2023-10-23, 18:44:51 GMT +# Date: 2023-10-24, 07:50:24 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 @@ -12432,7 +12432,9 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1BC90..1BC99 ; Grapheme_Base # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW 1BC9C ; Grapheme_Base # So DUPLOYAN SIGN O WITH CROSS 1BC9F ; Grapheme_Base # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP +1CCFA..1CCFC ; Grapheme_Base # So [3] SNAKE SYMBOL..NOSE SYMBOL 1CEB0..1CEB3 ; Grapheme_Base # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET +1CEBA..1CEBF ; Grapheme_Base # So [6] FRAGILE SYMBOL..STRAWBERRY SYMBOL 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 @@ -12605,6 +12607,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1FB00..1FB92 ; Grapheme_Base # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; Grapheme_Base # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON 1FBF0..1FBF9 ; Grapheme_Base # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE +1FBFA ; Grapheme_Base # So ALARM BELL SYMBOL 20000..2A6DF ; Grapheme_Base # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF 2A700..2B739 ; Grapheme_Base # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739 2B740..2B81D ; Grapheme_Base # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D @@ -12615,7 +12618,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 30000..3134A ; Grapheme_Base # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Grapheme_Base # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 147805 +# Total code points: 147815 # ================================================ diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index 1d710c3d3..196e8e50f 100644 --- a/unicodetools/data/ucd/dev/EastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/EastAsianWidth.txt @@ -1,5 +1,5 @@ # EastAsianWidth-16.0.0.txt -# Date: 2023-10-23, 18:45:00 GMT +# Date: 2023-10-24, 07:50:33 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -2343,7 +2343,9 @@ FFFD ; A # So REPLACEMENT CHARACTER 1BC9D..1BC9E ; N # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK 1BC9F ; N # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3 ; N # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CCFA..1CCFC ; N # So [3] SNAKE SYMBOL..NOSE SYMBOL 1CEB0..1CEB3 ; N # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET +1CEBA..1CEBF ; N # So [6] FRAGILE SYMBOL..STRAWBERRY SYMBOL 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 @@ -2610,6 +2612,7 @@ FFFD ; A # So REPLACEMENT CHARACTER 1FB00..1FB92 ; N # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; N # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON 1FBF0..1FBF9 ; N # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE +1FBFA ; N # So ALARM BELL SYMBOL 20000..2A6DF ; W # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF 2A6E0..2A6FF ; W # Cn [32] .. 2A700..2B739 ; W # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739 diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 1abf619f0..e3888ef1a 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,8 +1,5 @@ -1CCFA..1CCFC;Common -1CEBA..1CEBF;Common -1FBFA;Common # Scripts-16.0.0.txt -# Date: 2023-10-23, 18:45:30 GMT +# Date: 2023-10-24, 07:51:02 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -525,7 +522,9 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR 101D0..101FC ; Common # So [45] PHAISTOS DISC SIGN PEDESTRIAN..PHAISTOS DISC SIGN WAVY BAND 102E1..102FB ; Common # No [27] COPTIC EPACT DIGIT ONE..COPTIC EPACT NUMBER NINE HUNDRED 1BCA0..1BCA3 ; Common # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CCFA..1CCFC ; Common # So [3] SNAKE SYMBOL..NOSE SYMBOL 1CEB0..1CEB3 ; Common # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET +1CEBA..1CEBF ; Common # So [6] FRAGILE SYMBOL..STRAWBERRY SYMBOL 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 @@ -631,10 +630,11 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR 1FB00..1FB92 ; Common # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; Common # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON 1FBF0..1FBF9 ; Common # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE +1FBFA ; Common # So ALARM BELL SYMBOL E0001 ; Common # Cf LANGUAGE TAG E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG -# Total code points: 8311 +# Total code points: 8321 # ================================================ diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 3b2d4b75f..27d2d2ea6 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -1,13 +1,3 @@ -1CCFA;SNAKE SYMBOL;So;0;ON;;;;;N;;;;; -1CCFB;FLYING SAUCER SYMBOL;So;0;ON;;;;;N;;;;; -1CCFC;NOSE SYMBOL;So;0;ON;;;;;N;;;;; -1CEBA;FRAGILE SYMBOL;So;0;ON;;;;;N;;;;; -1CEBB;OFFICE BUILDING SYMBOL;So;0;ON;;;;;N;;;;; -1CEBC;TREE SYMBOL;So;0;ON;;;;;N;;;;; -1CEBD;APPLE SYMBOL;So;0;ON;;;;;N;;;;; -1CEBE;CHERRY SYMBOL;So;0;ON;;;;;N;;;;; -1CEBF;STRAWBERRY SYMBOL;So;0;ON;;;;;N;;;;; -1FBFA;ALARM BELL SYMBOL;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;;;; @@ -28184,10 +28174,19 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1BCA1;SHORTHAND FORMAT CONTINUING OVERLAP;Cf;0;BN;;;;;N;;;;; 1BCA2;SHORTHAND FORMAT DOWN STEP;Cf;0;BN;;;;;N;;;;; 1BCA3;SHORTHAND FORMAT UP STEP;Cf;0;BN;;;;;N;;;;; +1CCFA;SNAKE SYMBOL;So;0;ON;;;;;N;;;;; +1CCFB;FLYING SAUCER SYMBOL;So;0;ON;;;;;N;;;;; +1CCFC;NOSE SYMBOL;So;0;ON;;;;;N;;;;; 1CEB0;HORIZONTAL ZIGZAG LINE;So;0;ON;;;;;N;;;;; 1CEB1;KEYHOLE;So;0;ON;;;;;N;;;;; 1CEB2;OLD PERSONAL COMPUTER WITH MONITOR IN PORTRAIT ORIENTATION;So;0;ON;;;;;N;;;;; 1CEB3;BLACK RIGHT TRIANGLE CARET;So;0;ON;;;;;N;;;;; +1CEBA;FRAGILE SYMBOL;So;0;ON;;;;;N;;;;; +1CEBB;OFFICE BUILDING SYMBOL;So;0;ON;;;;;N;;;;; +1CEBC;TREE SYMBOL;So;0;ON;;;;;N;;;;; +1CEBD;APPLE SYMBOL;So;0;ON;;;;;N;;;;; +1CEBE;CHERRY SYMBOL;So;0;ON;;;;;N;;;;; +1CEBF;STRAWBERRY SYMBOL;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;;;;; @@ -34239,6 +34238,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1FBF7;SEGMENTED DIGIT SEVEN;Nd;0;EN; 0037;7;7;7;N;;;;; 1FBF8;SEGMENTED DIGIT EIGHT;Nd;0;EN; 0038;8;8;8;N;;;;; 1FBF9;SEGMENTED DIGIT NINE;Nd;0;EN; 0039;9;9;9;N;;;;; +1FBFA;ALARM BELL SYMBOL;So;0;ON;;;;;N;;;;; 20000;;Lo;0;L;;;;;N;;;;; 2A6DF;;Lo;0;L;;;;;N;;;;; 2A700;;Lo;0;L;;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index 5b43d648e..1f8e6c51c 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ # VerticalOrientation-16.0.0.txt -# Date: 2023-10-23, 18:45:34 GMT +# Date: 2023-10-24, 07:51:07 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -2188,7 +2188,9 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 1BC9D..1BC9E ; R # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK 1BC9F ; R # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3 ; R # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CCFA..1CCFC ; R # So [3] SNAKE SYMBOL..NOSE SYMBOL 1CEB0..1CEB3 ; R # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET +1CEBA..1CEBF ; R # So [6] FRAGILE SYMBOL..STRAWBERRY SYMBOL 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 @@ -2433,6 +2435,7 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 1FB00..1FB92 ; R # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; R # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON 1FBF0..1FBF9 ; R # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE +1FBFA ; R # So ALARM BELL SYMBOL 20000..2A6DF ; U # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF 2A6E0..2A6FF ; U # Cn [32] .. 2A700..2B739 ; U # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739 diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index c84daee40..b2239bcfe 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-16.0.0.txt -# Date: 2023-10-23, 18:44:48 GMT +# Date: 2023-10-24, 07:50:21 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1188,8 +1188,8 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER F0000..FFFFD ; L # Co [65534] .. 100000..10FFFD; L # Co [65534] .. -# The above property value applies to 820337 code points not listed here. -# Total code points: 1096262 +# The above property value applies to 820327 code points not listed here. +# Total code points: 1096252 # ================================================ @@ -1914,7 +1914,9 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE 11FD5..11FDC ; ON # So [8] TAMIL SIGN NEL..TAMIL SIGN MUKKURUNI 11FE1..11FF1 ; ON # So [17] TAMIL SIGN PAARAM..TAMIL SIGN VAKAIYARAA 16FE2 ; ON # Po OLD CHINESE HOOK MARK +1CCFA..1CCFC ; ON # So [3] SNAKE SYMBOL..NOSE SYMBOL 1CEB0..1CEB3 ; ON # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET +1CEBA..1CEBF ; ON # So [6] FRAGILE SYMBOL..STRAWBERRY SYMBOL 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 @@ -1963,8 +1965,9 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE 1FAF0..1FAF8 ; ON # So [9] HAND WITH INDEX FINGER AND THUMB CROSSED..RIGHTWARDS PUSHING HAND 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 +1FBFA ; ON # So ALARM BELL SYMBOL -# Total code points: 6040 +# Total code points: 6050 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index 6073d7d68..0f4179cc3 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-16.0.0.txt -# Date: 2023-10-23, 18:44:51 GMT +# Date: 2023-10-24, 07:50:23 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 @@ -1827,7 +1827,9 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1BC9D ; 0 # Mn DUPLOYAN THICK LETTER SELECTOR 1BC9F ; 0 # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3 ; 0 # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CCFA..1CCFC ; 0 # So [3] SNAKE SYMBOL..NOSE SYMBOL 1CEB0..1CEB3 ; 0 # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET +1CEBA..1CEBF ; 0 # So [6] FRAGILE SYMBOL..STRAWBERRY SYMBOL 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 @@ -2007,6 +2009,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1FB00..1FB92 ; 0 # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; 0 # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON 1FBF0..1FBF9 ; 0 # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE +1FBFA ; 0 # So ALARM BELL SYMBOL 20000..2A6DF ; 0 # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF 2A700..2B739 ; 0 # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739 2B740..2B81D ; 0 # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D @@ -2022,7 +2025,7 @@ 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 826567 code points not listed here. +# The above property value applies to 826557 code points not listed here. # Total code points: 1113184 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index a452d3406..f48bb0c60 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-16.0.0.txt -# Date: 2023-10-23, 18:44:54 GMT +# Date: 2023-10-24, 07:50:26 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 @@ -1846,7 +1846,9 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 1BC9D..1BC9E ; N # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK 1BC9F ; N # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3 ; N # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CCFA..1CCFC ; N # So [3] SNAKE SYMBOL..NOSE SYMBOL 1CEB0..1CEB3 ; N # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET +1CEBA..1CEBF ; N # So [6] FRAGILE SYMBOL..STRAWBERRY SYMBOL 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 @@ -2057,10 +2059,11 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 1FB00..1FB92 ; N # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; N # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON 1FBF0..1FBF9 ; N # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE +1FBFA ; N # So ALARM BELL SYMBOL E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 766085 code points not listed here. +# The above property value applies to 766075 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 5291e0f0c..c83973a6c 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-16.0.0.txt -# Date: 2023-10-23, 18:44:54 GMT +# Date: 2023-10-24, 07:50:27 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 @@ -582,8 +582,10 @@ FFFE..FFFF ; Cn # [2] .. 1BC7D..1BC7F ; Cn # [3] .. 1BC89..1BC8F ; Cn # [7] .. 1BC9A..1BC9B ; Cn # [2] .. -1BCA4..1CEAF ; Cn # [4620] .. -1CEB4..1CEFF ; Cn # [76] .. +1BCA4..1CCF9 ; Cn # [4182] .. +1CCFD..1CEAF ; Cn # [435] .. +1CEB4..1CEB9 ; Cn # [6] .. +1CEC0..1CEFF ; Cn # [64] .. 1CF2E..1CF2F ; Cn # [2] .. 1CF47..1CF4F ; Cn # [9] .. 1CFC4..1CFFF ; Cn # [60] .. @@ -716,7 +718,7 @@ FFFE..FFFF ; Cn # [2] .. 1FAF9..1FAFF ; Cn # [7] .. 1FB93 ; Cn # 1FBCB..1FBEF ; Cn # [37] .. -1FBFA..1FFFF ; Cn # [1030] .. +1FBFB..1FFFF ; Cn # [1029] .. 2A6E0..2A6FF ; Cn # [32] .. 2B73A..2B73F ; Cn # [6] .. 2B81E..2B81F ; Cn # [2] .. @@ -732,7 +734,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 824519 +# Total code points: 824509 # ================================================ @@ -4163,7 +4165,9 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 16B3C..16B3F ; So # [4] PAHAWH HMONG SIGN XYEEM NTXIV..PAHAWH HMONG SIGN XYEEM FAIB 16B45 ; So # PAHAWH HMONG SIGN CIM TSOV ROG 1BC9C ; So # DUPLOYAN SIGN O WITH CROSS +1CCFA..1CCFC ; So # [3] SNAKE SYMBOL..NOSE SYMBOL 1CEB0..1CEB3 ; So # [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET +1CEBA..1CEBF ; So # [6] FRAGILE SYMBOL..STRAWBERRY SYMBOL 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 @@ -4220,8 +4224,9 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1FAF0..1FAF8 ; So # [9] HAND WITH INDEX FINGER AND THUMB CROSSED..RIGHTWARDS PUSHING HAND 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 +1FBFA ; So # ALARM BELL SYMBOL -# Total code points: 6644 +# Total code points: 6654 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 10c5055c3..4dfc8bf50 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-16.0.0.txt -# Date: 2023-10-23, 18:44:56 GMT +# Date: 2023-10-24, 07:50:29 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 762527 code points not listed here. -# Total code points: 899995 +# The above property value applies to 762517 code points not listed here. +# Total code points: 899985 # ================================================ @@ -1444,7 +1444,9 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1BC80..1BC88 ; AL # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL 1BC90..1BC99 ; AL # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW 1BC9C ; AL # So DUPLOYAN SIGN O WITH CROSS +1CCFA..1CCFC ; AL # So [3] SNAKE SYMBOL..NOSE SYMBOL 1CEB0..1CEB3 ; AL # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET +1CEBA..1CEBF ; AL # So [6] FRAGILE SYMBOL..STRAWBERRY SYMBOL 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 @@ -1595,8 +1597,9 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1FA00..1FA53 ; AL # So [84] NEUTRAL CHESS KING..BLACK CHESS KNIGHT-BISHOP 1FB00..1FB92 ; AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; AL # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON +1FBFA ; AL # So ALARM BELL SYMBOL -# Total code points: 21880 +# Total code points: 21890 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 80307982a..bec8ef222 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-16.0.0.txt -# Date: 2023-10-23, 18:44:57 GMT +# Date: 2023-10-24, 07:50:29 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 @@ -37973,10 +37973,19 @@ FFFD ; REPLACEMENT CHARACTER 1BCA1 ; SHORTHAND FORMAT CONTINUING OVERLAP 1BCA2 ; SHORTHAND FORMAT DOWN STEP 1BCA3 ; SHORTHAND FORMAT UP STEP +1CCFA ; SNAKE SYMBOL +1CCFB ; FLYING SAUCER SYMBOL +1CCFC ; NOSE SYMBOL 1CEB0 ; HORIZONTAL ZIGZAG LINE 1CEB1 ; KEYHOLE 1CEB2 ; OLD PERSONAL COMPUTER WITH MONITOR IN PORTRAIT ORIENTATION 1CEB3 ; BLACK RIGHT TRIANGLE CARET +1CEBA ; FRAGILE SYMBOL +1CEBB ; OFFICE BUILDING SYMBOL +1CEBC ; TREE SYMBOL +1CEBD ; APPLE SYMBOL +1CEBE ; CHERRY SYMBOL +1CEBF ; STRAWBERRY SYMBOL 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 @@ -44028,6 +44037,7 @@ FFFD ; REPLACEMENT CHARACTER 1FBF7 ; SEGMENTED DIGIT SEVEN 1FBF8 ; SEGMENTED DIGIT EIGHT 1FBF9 ; SEGMENTED DIGIT NINE +1FBFA ; ALARM BELL SYMBOL 20000..2A6DF ; CJK UNIFIED IDEOGRAPH-* 2A700..2B739 ; CJK UNIFIED IDEOGRAPH-* 2B740..2B81D ; CJK UNIFIED IDEOGRAPH-* @@ -44375,6 +44385,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 150012 +# Total code points: 150022 # EOF