From a73768f4c70c81a48c614a9c525698b0fe8805d3 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 18 Apr 2023 13:13:01 +0200 Subject: [PATCH 1/8] UnicodeData lines from L2/21-234 --- unicodetools/data/ucd/dev/UnicodeData.txt | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index b10c67ba8..7e60d5fb4 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -27980,6 +27980,10 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1BCA1;SHORTHAND FORMAT CONTINUING OVERLAP;Cf;0;BN;;;;;N;;;;; 1BCA2;SHORTHAND FORMAT DOWN STEP;Cf;0;BN;;;;;N;;;;; 1BCA3;SHORTHAND FORMAT UP STEP;Cf;0;BN;;;;;N;;;;; +1CEB0;HORIZONTAL ZIGZAG LINE;So;0;ON;;;;;N;;;;; +1CEB1;KEYHOLE;So;0;ON;;;;;N;;;;; +1CEB2;OLD PERSONAL COMPUTER WITH MONITOR IN PORTRAIT ORIENTATION;So;0;ON;;;;;N;;;;; +1CEB3;BLACK RIGHT TRIANGLE CARET;So;0;ON;;;;;N;;;;; 1CF00;ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT;Mn;0;NSM;;;;;N;;;;; 1CF01;ZNAMENNY COMBINING MARK NIZKO S KRYZHEM ON LEFT;Mn;0;NSM;;;;;N;;;;; 1CF02;ZNAMENNY COMBINING MARK TSATA ON LEFT;Mn;0;NSM;;;;;N;;;;; @@ -33357,6 +33361,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1F8AD;WHITE ARROW SHAFT WIDTH TWO THIRDS;So;0;ON;;;;;N;;;;; 1F8B0;ARROW POINTING UPWARDS THEN NORTH WEST;So;0;ON;;;;;N;;;;; 1F8B1;ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST;So;0;ON;;;;;N;;;;; +1F8B2;RIGHTWARDS ARROW WITH LOWER HOOK;So;0;ON;;;;;N;;;;; 1F900;CIRCLED CROSS FORMEE WITH FOUR DOTS;So;0;ON;;;;;N;;;;; 1F901;CIRCLED CROSS FORMEE WITH TWO DOTS;So;0;ON;;;;;N;;;;; 1F902;CIRCLED CROSS FORMEE;So;0;ON;;;;;N;;;;; From a8149401ce8a60fbd9b770f97c5d3b0b7373caeb Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 18 Apr 2023 13:17:38 +0200 Subject: [PATCH 2/8] lb=AL probably --- unicodetools/data/ucd/dev/LineBreak.txt | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 48516a7a0..3a155d777 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,5 @@ # LineBreak-15.1.0.txt -# Date: 2023-04-15, 00:27:09 GMT +# Date: 2023-04-18, 11:16:11 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 @@ -3225,6 +3225,7 @@ FFFD ; AI # So REPLACEMENT CHARACTER 1BC9D..1BC9E ; CM # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK 1BC9F ; BA # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3 ; CM # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CEB0..1CEB3 ; AL # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET 1CF00..1CF2D ; CM # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT 1CF30..1CF46 ; CM # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1CF50..1CFC3 ; AL # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK @@ -3523,8 +3524,8 @@ FFFD ; AI # So REPLACEMENT CHARACTER 1F888..1F88F ; ID # Cn [8] .. 1F890..1F8AD ; AL # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS 1F8AE..1F8AF ; ID # Cn [2] .. -1F8B0..1F8B1 ; ID # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST -1F8B2..1F8FF ; ID # Cn [78] .. +1F8B0..1F8B2 ; ID # So [3] ARROW POINTING UPWARDS THEN NORTH WEST..RIGHTWARDS ARROW WITH LOWER HOOK +1F8B3..1F8FF ; ID # Cn [77] .. 1F900..1F90B ; AL # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT 1F90C ; EB # So PINCHED FINGERS 1F90D..1F90E ; ID # So [2] WHITE HEART..BROWN HEART From 67e912cba757e3ee86b948cc6879c839d9a88e44 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 18 Apr 2023 13:19:06 +0200 Subject: [PATCH 3/8] Scripts --- 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 9fb6b5abd..6904fb62f 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -24,6 +24,8 @@ # ================================================ +1CEB0..1CEB3;Common +1F8B2;Common 0000..001F ; Common # Cc [32] .. 0020 ; Common # Zs SPACE 0021..0023 ; Common # Po [3] EXCLAMATION MARK..NUMBER SIGN From 2b4d4d2ca9bdce50ab633fef071d9eb854129fe3 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 17 Apr 2023 15:40:23 +0200 Subject: [PATCH 4/8] Blocks, ShortBlockNames --- 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 1bd4d0325..e7869cedb 100644 --- a/unicodetools/data/ucd/dev/Blocks.txt +++ b/unicodetools/data/ucd/dev/Blocks.txt @@ -308,6 +308,7 @@ FFF0..FFFF; Specials 1B170..1B2FF; Nushu 1BC00..1BC9F; Duployan 1BCA0..1BCAF; Shorthand Format Controls +1CC00..1CEBF; Symbols for Legacy Computing Supplement 1CF00..1CFCF; Znamenny Musical Notation 1D000..1D0FF; Byzantine Musical Symbols 1D100..1D1FF; Musical Symbols diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt index c05e737eb..4b89ae4d5 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt @@ -284,6 +284,7 @@ Sutton_SignWriting ; Sutton_SignWriting Syloti_Nagri ; Syloti_Nagri Symbols_And_Pictographs_Ext_A ; Symbols_And_Pictographs_Extended_A Symbols_For_Legacy_Computing ; Symbols_For_Legacy_Computing +Symbols_For_Legacy_Computing_Sup ; Symbols_For_Legacy_Computing_Supplement Syriac ; Syriac Syriac_Sup ; Syriac_Supplement Tagalog ; Tagalog From 51744fd9940a9ba5e4f626728484165f316f8dbd Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 18 Apr 2023 13:21:19 +0200 Subject: [PATCH 5/8] Regenerate UCD --- unicodetools/data/ucd/dev/DerivedAge.txt | 6 ++++-- .../data/ucd/dev/DerivedCoreProperties.txt | 7 ++++--- unicodetools/data/ucd/dev/PropertyValueAliases.txt | 3 ++- unicodetools/data/ucd/dev/Scripts.txt | 9 ++++----- .../data/ucd/dev/extracted/DerivedBidiClass.txt | 11 ++++++----- .../ucd/dev/extracted/DerivedCombiningClass.txt | 7 ++++--- .../ucd/dev/extracted/DerivedEastAsianWidth.txt | 7 ++++--- .../ucd/dev/extracted/DerivedGeneralCategory.txt | 14 ++++++++------ .../data/ucd/dev/extracted/DerivedLineBreak.txt | 13 +++++++------ .../data/ucd/dev/extracted/DerivedName.txt | 9 +++++++-- 10 files changed, 50 insertions(+), 36 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index 40d92c540..70ffba802 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-15.1.0.txt -# Date: 2023-01-05, 20:34:30 GMT +# Date: 2023-04-18, 11:20:12 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1999,7 +1999,9 @@ FDFE..FDFF ; 14.0 # [2] ARABIC LIGATURE SUBHAANAHU WA TAAALAA..ARABIC LIGAT 2FFC..2FFF ; 15.1 # [4] IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER ROTATION 31EF ; 15.1 # IDEOGRAPHIC DESCRIPTION CHARACTER SUBTRACTION +1CEB0..1CEB3 ; 15.1 # [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET +1F8B2 ; 15.1 # RIGHTWARDS ARROW WITH LOWER HOOK -# Total code points: 5 +# Total code points: 10 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 368a1ccf5..3c4f313b0 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-15.1.0.txt -# Date: 2023-01-31, 21:26:32 GMT +# Date: 2023-04-18, 11:20:40 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 @@ -12323,6 +12323,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1BC90..1BC99 ; Grapheme_Base # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW 1BC9C ; Grapheme_Base # So DUPLOYAN SIGN O WITH CROSS 1BC9F ; Grapheme_Base # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP +1CEB0..1CEB3 ; Grapheme_Base # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET 1CF50..1CFC3 ; Grapheme_Base # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK 1D000..1D0F5 ; Grapheme_Base # So [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126 ; Grapheme_Base # So [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 @@ -12482,7 +12483,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1F850..1F859 ; Grapheme_Base # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; Grapheme_Base # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; Grapheme_Base # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F8B0..1F8B1 ; Grapheme_Base # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST +1F8B0..1F8B2 ; Grapheme_Base # So [3] ARROW POINTING UPWARDS THEN NORTH WEST..RIGHTWARDS ARROW WITH LOWER HOOK 1F900..1FA53 ; Grapheme_Base # So [340] CIRCLED CROSS FORMEE WITH FOUR DOTS..BLACK CHESS KNIGHT-BISHOP 1FA60..1FA6D ; Grapheme_Base # So [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER 1FA70..1FA7C ; Grapheme_Base # So [13] BALLET SHOES..CRUTCH @@ -12504,7 +12505,7 @@ 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: 146991 +# Total code points: 146996 # ================================================ diff --git a/unicodetools/data/ucd/dev/PropertyValueAliases.txt b/unicodetools/data/ucd/dev/PropertyValueAliases.txt index cb1263a9f..9cb1826e2 100644 --- a/unicodetools/data/ucd/dev/PropertyValueAliases.txt +++ b/unicodetools/data/ucd/dev/PropertyValueAliases.txt @@ -1,5 +1,5 @@ # PropertyValueAliases-15.1.0.txt -# Date: 2023-01-31, 22:27:07 GMT +# Date: 2023-04-18, 11:20:56 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -437,6 +437,7 @@ blk; Sutton_SignWriting ; Sutton_SignWriting blk; Syloti_Nagri ; Syloti_Nagri blk; Symbols_And_Pictographs_Ext_A ; Symbols_And_Pictographs_Extended_A blk; Symbols_For_Legacy_Computing ; Symbols_For_Legacy_Computing +blk; Symbols_For_Legacy_Computing_Sup ; Symbols_For_Legacy_Computing_Supplement blk; Syriac ; Syriac blk; Syriac_Sup ; Syriac_Supplement blk; Tagalog ; Tagalog diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 6904fb62f..95a5024f0 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,5 +1,5 @@ # Scripts-15.1.0.txt -# Date: 2023-01-05, 20:35:02 GMT +# Date: 2023-04-18, 11:21:16 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 @@ -24,8 +24,6 @@ # ================================================ -1CEB0..1CEB3;Common -1F8B2;Common 0000..001F ; Common # Cc [32] .. 0020 ; Common # Zs SPACE 0021..0023 ; Common # Po [3] EXCLAMATION MARK..NUMBER SIGN @@ -524,6 +522,7 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR 101D0..101FC ; Common # So [45] PHAISTOS DISC SIGN PEDESTRIAN..PHAISTOS DISC SIGN WAVY BAND 102E1..102FB ; Common # No [27] COPTIC EPACT DIGIT ONE..COPTIC EPACT NUMBER NINE HUNDRED 1BCA0..1BCA3 ; Common # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CEB0..1CEB3 ; Common # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET 1CF50..1CFC3 ; Common # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK 1D000..1D0F5 ; Common # So [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126 ; Common # So [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 @@ -616,7 +615,7 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR 1F850..1F859 ; Common # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; Common # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; Common # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F8B0..1F8B1 ; Common # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST +1F8B0..1F8B2 ; Common # So [3] ARROW POINTING UPWARDS THEN NORTH WEST..RIGHTWARDS ARROW WITH LOWER HOOK 1F900..1FA53 ; Common # So [340] CIRCLED CROSS FORMEE WITH FOUR DOTS..BLACK CHESS KNIGHT-BISHOP 1FA60..1FA6D ; Common # So [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER 1FA70..1FA7C ; Common # So [13] BALLET SHOES..CRUTCH @@ -632,7 +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: 8306 +# Total code points: 8311 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 529bf2d41..9bac40ef6 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-15.1.0.txt -# Date: 2023-01-05, 20:34:32 GMT +# Date: 2023-04-18, 11:20:36 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1181,8 +1181,8 @@ 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 821084 code points not listed here. -# Total code points: 1096267 +# The above property value applies to 821079 code points not listed here. +# Total code points: 1096262 # ================================================ @@ -1898,6 +1898,7 @@ 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 +1CEB0..1CEB3 ; ON # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET 1D1E9..1D1EA ; ON # So [2] MUSICAL SYMBOL SORI..MUSICAL SYMBOL KORON 1D200..1D241 ; ON # So [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54 1D245 ; ON # So GREEK MUSICAL LEIMMA @@ -1934,7 +1935,7 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE 1F850..1F859 ; ON # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; ON # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; ON # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F8B0..1F8B1 ; ON # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST +1F8B0..1F8B2 ; ON # So [3] ARROW POINTING UPWARDS THEN NORTH WEST..RIGHTWARDS ARROW WITH LOWER HOOK 1F900..1FA53 ; ON # So [340] CIRCLED CROSS FORMEE WITH FOUR DOTS..BLACK CHESS KNIGHT-BISHOP 1FA60..1FA6D ; ON # So [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER 1FA70..1FA7C ; ON # So [13] BALLET SHOES..CRUTCH @@ -1947,7 +1948,7 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE 1FB00..1FB92 ; ON # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; ON # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON -# Total code points: 6034 +# Total code points: 6039 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index 39794a94e..18f2ab35a 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-15.1.0.txt -# Date: 2023-01-05, 20:34:33 GMT +# Date: 2023-04-18, 11:20:39 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1811,6 +1811,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1BC9D ; 0 # Mn DUPLOYAN THICK LETTER SELECTOR 1BC9F ; 0 # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3 ; 0 # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CEB0..1CEB3 ; 0 # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET 1CF00..1CF2D ; 0 # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT 1CF30..1CF46 ; 0 # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1CF50..1CFC3 ; 0 # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK @@ -1977,7 +1978,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1F850..1F859 ; 0 # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; 0 # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; 0 # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F8B0..1F8B1 ; 0 # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST +1F8B0..1F8B2 ; 0 # So [3] ARROW POINTING UPWARDS THEN NORTH WEST..RIGHTWARDS ARROW WITH LOWER HOOK 1F900..1FA53 ; 0 # So [340] CIRCLED CROSS FORMEE WITH FOUR DOTS..BLACK CHESS KNIGHT-BISHOP 1FA60..1FA6D ; 0 # So [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER 1FA70..1FA7C ; 0 # So [13] BALLET SHOES..CRUTCH @@ -2004,7 +2005,7 @@ 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 827388 code points not listed here. +# The above property value applies to 827383 code points not listed here. # Total code points: 1113190 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index 80dd68b77..e228b590e 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-15.1.0.txt -# Date: 2023-01-05, 20:34:36 GMT +# Date: 2023-04-18, 11:20:42 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 @@ -1829,6 +1829,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 1BC9D..1BC9E ; N # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK 1BC9F ; N # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3 ; N # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CEB0..1CEB3 ; N # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET 1CF00..1CF2D ; N # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT 1CF30..1CF46 ; N # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1CF50..1CFC3 ; N # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK @@ -2030,7 +2031,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 1F850..1F859 ; N # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; N # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; N # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F8B0..1F8B1 ; N # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST +1F8B0..1F8B2 ; N # So [3] ARROW POINTING UPWARDS THEN NORTH WEST..RIGHTWARDS ARROW WITH LOWER HOOK 1F900..1F90B ; N # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT 1F93B ; N # So MODERN PENTATHLON 1F946 ; N # So RIFLE @@ -2042,7 +2043,7 @@ 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 766284 code points not listed here. +# The above property value applies to 766279 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 c17494d8b..3eff49697 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-15.1.0.txt -# Date: 2023-01-05, 20:34:37 GMT +# Date: 2023-04-18, 11:20:43 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -574,7 +574,8 @@ FFFE..FFFF ; Cn # [2] .. 1BC7D..1BC7F ; Cn # [3] .. 1BC89..1BC8F ; Cn # [7] .. 1BC9A..1BC9B ; Cn # [2] .. -1BCA4..1CEFF ; Cn # [4700] .. +1BCA4..1CEAF ; Cn # [4620] .. +1CEB4..1CEFF ; Cn # [76] .. 1CF2E..1CF2F ; Cn # [2] .. 1CF47..1CF4F ; Cn # [9] .. 1CFC4..1CFFF ; Cn # [60] .. @@ -695,7 +696,7 @@ FFFE..FFFF ; Cn # [2] .. 1F85A..1F85F ; Cn # [6] .. 1F888..1F88F ; Cn # [8] .. 1F8AE..1F8AF ; Cn # [2] .. -1F8B2..1F8FF ; Cn # [78] .. +1F8B3..1F8FF ; Cn # [77] .. 1FA54..1FA5F ; Cn # [12] .. 1FA6E..1FA6F ; Cn # [2] .. 1FA7D..1FA7F ; Cn # [3] .. @@ -722,7 +723,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 825340 +# Total code points: 825335 # ================================================ @@ -4134,6 +4135,7 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 16B3C..16B3F ; So # [4] PAHAWH HMONG SIGN XYEEM NTXIV..PAHAWH HMONG SIGN XYEEM FAIB 16B45 ; So # PAHAWH HMONG SIGN CIM TSOV ROG 1BC9C ; So # DUPLOYAN SIGN O WITH CROSS +1CEB0..1CEB3 ; So # [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET 1CF50..1CFC3 ; So # [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK 1D000..1D0F5 ; So # [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126 ; So # [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 @@ -4178,7 +4180,7 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1F850..1F859 ; So # [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; So # [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; So # [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F8B0..1F8B1 ; So # [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST +1F8B0..1F8B2 ; So # [3] ARROW POINTING UPWARDS THEN NORTH WEST..RIGHTWARDS ARROW WITH LOWER HOOK 1F900..1FA53 ; So # [340] CIRCLED CROSS FORMEE WITH FOUR DOTS..BLACK CHESS KNIGHT-BISHOP 1FA60..1FA6D ; So # [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER 1FA70..1FA7C ; So # [13] BALLET SHOES..CRUTCH @@ -4191,7 +4193,7 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1FB00..1FB92 ; So # [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; So # [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON -# Total code points: 6639 +# Total code points: 6644 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 7cd22b063..db0d26322 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-15.1.0.txt -# Date: 2023-01-05, 20:34:38 GMT +# Date: 2023-04-18, 11:20:45 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -67,8 +67,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 762725 code points not listed here. -# Total code points: 900193 +# The above property value applies to 762721 code points not listed here. +# Total code points: 900189 # ================================================ @@ -1473,6 +1473,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1BC80..1BC88 ; AL # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL 1BC90..1BC99 ; AL # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW 1BC9C ; AL # So DUPLOYAN SIGN O WITH CROSS +1CEB0..1CEB3 ; AL # So [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET 1CF50..1CFC3 ; AL # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK 1D000..1D0F5 ; AL # So [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126 ; AL # So [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 @@ -1623,7 +1624,7 @@ 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: 22214 +# Total code points: 22218 # ================================================ @@ -1823,7 +1824,7 @@ FFE4 ; ID # So FULLWIDTH BROKEN BAR 1F7D5..1F7D9 ; ID # So [5] CIRCLED TRIANGLE..NINE POINTED WHITE STAR 1F7E0..1F7EB ; ID # So [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE 1F7F0 ; ID # So HEAVY EQUALS SIGN -1F8B0..1F8B1 ; ID # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST +1F8B0..1F8B2 ; ID # So [3] ARROW POINTING UPWARDS THEN NORTH WEST..RIGHTWARDS ARROW WITH LOWER HOOK 1F90D..1F90E ; ID # So [2] WHITE HEART..BROWN HEART 1F910..1F917 ; ID # So [8] ZIPPER-MOUTH FACE..HUGGING FACE 1F920..1F925 ; ID # So [6] FACE WITH COWBOY HAT..LYING FACE @@ -1852,7 +1853,7 @@ 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 62600 code points not listed here. +# The above property value applies to 62599 code points not listed here. # Total code points: 172470 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 805beab0b..9ef0db5a6 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-15.1.0.txt -# Date: 2023-01-05, 20:34:38 GMT +# Date: 2023-04-18, 11:20:45 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -37779,6 +37779,10 @@ FFFD ; REPLACEMENT CHARACTER 1BCA1 ; SHORTHAND FORMAT CONTINUING OVERLAP 1BCA2 ; SHORTHAND FORMAT DOWN STEP 1BCA3 ; SHORTHAND FORMAT UP STEP +1CEB0 ; HORIZONTAL ZIGZAG LINE +1CEB1 ; KEYHOLE +1CEB2 ; OLD PERSONAL COMPUTER WITH MONITOR IN PORTRAIT ORIENTATION +1CEB3 ; BLACK RIGHT TRIANGLE CARET 1CF00 ; ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT 1CF01 ; ZNAMENNY COMBINING MARK NIZKO S KRYZHEM ON LEFT 1CF02 ; ZNAMENNY COMBINING MARK TSATA ON LEFT @@ -43156,6 +43160,7 @@ FFFD ; REPLACEMENT CHARACTER 1F8AD ; WHITE ARROW SHAFT WIDTH TWO THIRDS 1F8B0 ; ARROW POINTING UPWARDS THEN NORTH WEST 1F8B1 ; ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST +1F8B2 ; RIGHTWARDS ARROW WITH LOWER HOOK 1F900 ; CIRCLED CROSS FORMEE WITH FOUR DOTS 1F901 ; CIRCLED CROSS FORMEE WITH TWO DOTS 1F902 ; CIRCLED CROSS FORMEE @@ -44175,6 +44180,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 149191 +# Total code points: 149196 # EOF From 79d0c279d00a1c42e2d7a824a962300b691f05bf Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 18 Apr 2023 13:26:19 +0200 Subject: [PATCH 6/8] 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 640fa3b1e..9a4d33f3a 100644 --- a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java +++ b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java @@ -462,6 +462,7 @@ public enum Block_Values implements Named { Syloti_Nagri("Syloti_Nagri"), Symbols_And_Pictographs_Extended_A("Symbols_And_Pictographs_Ext_A"), Symbols_For_Legacy_Computing("Symbols_For_Legacy_Computing"), + Symbols_For_Legacy_Computing_Supplement("Symbols_For_Legacy_Computing_Sup"), Syriac("Syriac"), Syriac_Supplement("Syriac_Sup"), Tagalog("Tagalog"), From 2cf790ba0b04ed0e3984f3c8d1f03848941d5514 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 23 Oct 2023 12:05:39 +0200 Subject: [PATCH 7/8] AL for the new arrow --- unicodetools/data/ucd/dev/LineBreak.txt | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 692bcafe6..2983744fc 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -3531,7 +3531,8 @@ FFFD ; AI # So REPLACEMENT CHARACTER 1F888..1F88F ; ID # Cn [8] .. 1F890..1F8AD ; AL # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS 1F8AE..1F8AF ; ID # Cn [2] .. -1F8B0..1F8B2 ; ID # So [3] ARROW POINTING UPWARDS THEN NORTH WEST..RIGHTWARDS ARROW WITH LOWER HOOK +1F8B0..1F8B1 ; ID +1F8B2 ; AL 1F8B3..1F8FF ; ID # Cn [77] .. 1F900..1F90B ; AL # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT 1F90C ; EB # So PINCHED FINGERS From 06e37d575fa97ddab21fc9ff71a6bec67ac6396b Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 23 Oct 2023 12:07:22 +0200 Subject: [PATCH 8/8] Regenerate UCD --- unicodetools/data/ucd/dev/LineBreak.txt | 6 +++--- unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt | 9 +++++---- 2 files changed, 8 insertions(+), 7 deletions(-) diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 2983744fc..c7ee51f2e 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: 2023-10-02, 13:27:40 GMT +# Date: 2023-10-23, 10:06:47 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 @@ -3531,8 +3531,8 @@ FFFD ; AI # So REPLACEMENT CHARACTER 1F888..1F88F ; ID # Cn [8] .. 1F890..1F8AD ; AL # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS 1F8AE..1F8AF ; ID # Cn [2] .. -1F8B0..1F8B1 ; ID -1F8B2 ; AL +1F8B0..1F8B1 ; ID # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST +1F8B2 ; AL # So RIGHTWARDS ARROW WITH LOWER HOOK 1F8B3..1F8FF ; ID # Cn [77] .. 1F900..1F90B ; AL # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT 1F90C ; EB # So PINCHED FINGERS diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 5ad8d89ff..73e0511e7 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: 2023-10-02, 13:27:36 GMT +# Date: 2023-10-23, 10:06:43 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1576,12 +1576,13 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1F850..1F859 ; AL # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; AL # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; AL # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS +1F8B2 ; AL # So RIGHTWARDS ARROW WITH LOWER HOOK 1F900..1F90B ; AL # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT 1FA00..1FA53 ; AL # So [84] NEUTRAL CHESS KING..BLACK CHESS KNIGHT-BISHOP 1FB00..1FB92 ; AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; AL # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON -# Total code points: 21733 +# Total code points: 21734 # ================================================ @@ -1794,7 +1795,7 @@ FFE4 ; ID # So FULLWIDTH BROKEN BAR 1F7D5..1F7D9 ; ID # So [5] CIRCLED TRIANGLE..NINE POINTED WHITE STAR 1F7E0..1F7EB ; ID # So [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE 1F7F0 ; ID # So HEAVY EQUALS SIGN -1F8B0..1F8B2 ; ID # So [3] ARROW POINTING UPWARDS THEN NORTH WEST..RIGHTWARDS ARROW WITH LOWER HOOK +1F8B0..1F8B1 ; ID # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST 1F90D..1F90E ; ID # So [2] WHITE HEART..BROWN HEART 1F910..1F917 ; ID # So [8] ZIPPER-MOUTH FACE..HUGGING FACE 1F920..1F925 ; ID # So [6] FACE WITH COWBOY HAT..LYING FACE @@ -1825,7 +1826,7 @@ FFE4 ; ID # So FULLWIDTH BROKEN BAR 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: 172568 +# Total code points: 172567 # ================================================