From af702b26d5277912a4d3fc0edc79e0d38d9e0bb3 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 9 Oct 2023 15:27:16 +0200 Subject: [PATCH 01/13] UnicodeData.txt from L2/22-260 --- unicodetools/data/ucd/dev/UnicodeData.txt | 2 ++ 1 file changed, 2 insertions(+) diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 8f88960db..74f29fa10 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -1,3 +1,5 @@ +113D2; TULU-TIGALARI GEMINATION MARK;Mn;0;NSM;;;;;N;;;;; +113D3; TULU-TIGALARI SIGN PLUTA;Lo;0;L;;;;;N;;;; 0000;;Cc;0;BN;;;;;N;NULL;;;; 0001;;Cc;0;BN;;;;;N;START OF HEADING;;;; 0002;;Cc;0;BN;;;;;N;START OF TEXT;;;; From 482bd7ab4a8f9b2c3f93ebb2c7c23032f5622021 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 9 Oct 2023 15:32:18 +0200 Subject: [PATCH 02/13] more ; --- unicodetools/data/ucd/dev/UnicodeData.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 74f29fa10..1ef1aa0d6 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -1,5 +1,5 @@ 113D2; TULU-TIGALARI GEMINATION MARK;Mn;0;NSM;;;;;N;;;;; -113D3; TULU-TIGALARI SIGN PLUTA;Lo;0;L;;;;;N;;;; +113D3; TULU-TIGALARI SIGN PLUTA;Lo;0;L;;;;;N;;;;; 0000;;Cc;0;BN;;;;;N;NULL;;;; 0001;;Cc;0;BN;;;;;N;START OF HEADING;;;; 0002;;Cc;0;BN;;;;;N;START OF TEXT;;;; From c80a82654beb2ea3f956f06e09de3fcdf1eb3d33 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 9 Oct 2023 15:36:16 +0200 Subject: [PATCH 03/13] My take on LB, different from Ken's --- unicodetools/data/ucd/dev/LineBreak.txt | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index f0b1a9b41..9e2eaf220 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, 12:16:34 GMT +# Date: 2023-10-09, 13:33:04 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 @@ -2930,6 +2930,8 @@ FFFD ; AI # So REPLACEMENT CHARACTER 11362..11363 ; CM # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL 11366..1136C ; CM # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; CM # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +113D2 ; CM # Mn TULU-TIGALARI GEMINATION MARK +113D3 ; BA # Lo TULU-TIGALARI SIGN PLUTA 11400..11434 ; AL # Lo [53] NEWA LETTER A..NEWA LETTER HA 11435..11437 ; CM # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II 11438..1143F ; CM # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI From 9f87e704a22195aea87d2aac2b7002851efc50e7 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 9 Oct 2023 15:37:37 +0200 Subject: [PATCH 04/13] Scripts.txt --- unicodetools/data/ucd/dev/Scripts.txt | 1 + 1 file changed, 1 insertion(+) diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 13e7f6299..9d64347e4 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,3 +1,4 @@ +113D2..113D3; Tulu_Tigalari # Scripts-16.0.0.txt # Date: 2023-10-02, 12:17:02 GMT # © 2023 Unicode®, Inc. From 8b98925f58ea392e5547543454970f10c32b7cfb Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Fri, 18 Aug 2023 15:33:43 +0200 Subject: [PATCH 05/13] ShortBlockNames and Blocks --- 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 8fa3eaad0..cf8fd1962 100644 --- a/unicodetools/data/ucd/dev/Blocks.txt +++ b/unicodetools/data/ucd/dev/Blocks.txt @@ -258,6 +258,7 @@ FFF0..FFFF; Specials 11280..112AF; Multani 112B0..112FF; Khudawadi 11300..1137F; Grantha +11380..113FF; Tulu-Tigalari 11400..1147F; Newa 11480..114DF; Tirhuta 11580..115FF; Siddham 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 32a6ce8cc..e44f59ac4 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt @@ -308,6 +308,7 @@ Tibetan ; Tibetan Tifinagh ; Tifinagh Tirhuta ; Tirhuta Toto ; Toto +Tulu_Tigalari ; Tulu_Tigalari Transport_And_Map ; Transport_And_Map_Symbols Ugaritic ; Ugaritic UCAS ; Unified_Canadian_Aboriginal_Syllabics From 93ab07f4a242be3c3c217664e29056d718f5235b Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 9 Oct 2023 15:39:08 +0200 Subject: [PATCH 06/13] IndicMeowCategory --- unicodetools/data/ucd/dev/IndicPositionalCategory.txt | 2 ++ unicodetools/data/ucd/dev/IndicSyllabicCategory.txt | 2 ++ 2 files changed, 4 insertions(+) diff --git a/unicodetools/data/ucd/dev/IndicPositionalCategory.txt b/unicodetools/data/ucd/dev/IndicPositionalCategory.txt index 9b5aabfa0..f45756e2c 100644 --- a/unicodetools/data/ucd/dev/IndicPositionalCategory.txt +++ b/unicodetools/data/ucd/dev/IndicPositionalCategory.txt @@ -1,3 +1,5 @@ +# Indic_Positional_Category=Bottom +113D2; Bottom # Mn TULU-TIGALARI GEMINATION MARK # IndicPositionalCategory-16.0.0.txt # Date: 2023-10-02, 22:58:33 GMT # © 2023 Unicode®, Inc. diff --git a/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt b/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt index 5de0d7554..f6aefb0a0 100644 --- a/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt +++ b/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt @@ -1,3 +1,5 @@ +# Indic_Syllabic_Category=Gemination_Mark +113D2; Gemination_Mark # Mn TULU-TIGALARI GEMINATION MARK # IndicSyllabicCategory-16.0.0.txt # Date: 2023-10-02, 22:58:33 GMT # © 2023 Unicode®, Inc. From c32519e66c2d330cac43f92730edf4bd7bb4241e Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 9 Oct 2023 15:40:14 +0200 Subject: [PATCH 07/13] Regenerate UCD --- unicodetools/data/ucd/dev/DerivedAge.txt | 5 ++-- .../data/ucd/dev/DerivedCoreProperties.txt | 28 +++++++++++++------ unicodetools/data/ucd/dev/EastAsianWidth.txt | 4 ++- .../data/ucd/dev/IndicPositionalCategory.txt | 5 ++-- .../data/ucd/dev/IndicSyllabicCategory.txt | 5 ++-- .../data/ucd/dev/PropertyValueAliases.txt | 6 ++-- unicodetools/data/ucd/dev/Scripts.txt | 10 +++++-- unicodetools/data/ucd/dev/UnicodeData.txt | 4 +-- .../data/ucd/dev/VerticalOrientation.txt | 4 ++- .../dev/auxiliary/GraphemeBreakProperty.txt | 5 ++-- .../dev/auxiliary/SentenceBreakProperty.txt | 8 ++++-- .../ucd/dev/auxiliary/WordBreakProperty.txt | 8 ++++-- .../ucd/dev/extracted/DerivedBidiClass.txt | 10 ++++--- .../dev/extracted/DerivedCombiningClass.txt | 6 ++-- .../dev/extracted/DerivedEastAsianWidth.txt | 6 ++-- .../dev/extracted/DerivedGeneralCategory.txt | 13 +++++---- .../ucd/dev/extracted/DerivedJoiningType.txt | 5 ++-- .../ucd/dev/extracted/DerivedLineBreak.txt | 12 ++++---- .../data/ucd/dev/extracted/DerivedName.txt | 6 ++-- 19 files changed, 95 insertions(+), 55 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index 0572b7be6..06ff5f1b7 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: 2023-10-02, 12:16:00 GMT +# Date: 2023-10-09, 13:39:28 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 @@ -2011,7 +2011,8 @@ FDFE..FDFF ; 14.0 # [2] ARABIC LIGATURE SUBHAANAHU WA TAAALAA..ARABIC LIGAT 0897 ; 16.0 # ARABIC PEPET 10EC2..10EC4 ; 16.0 # [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +113D2..113D3 ; 16.0 # [2] TULU-TIGALARI GEMINATION MARK..TULU-TIGALARI SIGN PLUTA -# Total code points: 4 +# Total code points: 6 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 21cf3645d..08e8e25f5 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: 2023-10-02, 12:41:01 GMT +# Date: 2023-10-09, 13:39:48 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 @@ -1122,6 +1122,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 11357 ; Alphabetic # Mc GRANTHA AU LENGTH MARK 1135D..11361 ; Alphabetic # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL 11362..11363 ; Alphabetic # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL +113D3 ; Alphabetic # Lo TULU-TIGALARI SIGN PLUTA 11400..11434 ; Alphabetic # Lo [53] NEWA LETTER A..NEWA LETTER HA 11435..11437 ; Alphabetic # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II 11438..1143F ; Alphabetic # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI @@ -1403,7 +1404,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 30000..3134A ; Alphabetic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Alphabetic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 138390 +# Total code points: 138391 # ================================================ @@ -3331,6 +3332,7 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 11340 ; Case_Ignorable # Mn GRANTHA VOWEL SIGN II 11366..1136C ; Case_Ignorable # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; Case_Ignorable # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +113D2 ; Case_Ignorable # Mn TULU-TIGALARI GEMINATION MARK 11438..1143F ; Case_Ignorable # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI 11442..11444 ; Case_Ignorable # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA 11446 ; Case_Ignorable # Mn NEWA SIGN NUKTA @@ -3441,7 +3443,7 @@ E0001 ; Case_Ignorable # Cf LANGUAGE TAG E0020..E007F ; Case_Ignorable # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2708 +# Total code points: 2709 # ================================================ @@ -6681,6 +6683,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1133D ; ID_Start # Lo GRANTHA SIGN AVAGRAHA 11350 ; ID_Start # Lo GRANTHA OM 1135D..11361 ; ID_Start # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL +113D3 ; ID_Start # Lo TULU-TIGALARI SIGN PLUTA 11400..11434 ; ID_Start # Lo [53] NEWA LETTER A..NEWA LETTER HA 11447..1144A ; ID_Start # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI 1145F..11461 ; ID_Start # Lo [3] NEWA LETTER VEDIC ANUSVARA..NEWA SIGN UPADHMANIYA @@ -6861,7 +6864,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; ID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; ID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 136970 +# Total code points: 136971 # ================================================ @@ -7881,6 +7884,8 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 11362..11363 ; ID_Continue # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL 11366..1136C ; ID_Continue # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; ID_Continue # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +113D2 ; ID_Continue # Mn TULU-TIGALARI GEMINATION MARK +113D3 ; ID_Continue # Lo TULU-TIGALARI SIGN PLUTA 11400..11434 ; ID_Continue # Lo [53] NEWA LETTER A..NEWA LETTER HA 11435..11437 ; ID_Continue # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II 11438..1143F ; ID_Continue # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI @@ -8221,7 +8226,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 140112 +# Total code points: 140114 # ================================================ @@ -8797,6 +8802,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1133D ; XID_Start # Lo GRANTHA SIGN AVAGRAHA 11350 ; XID_Start # Lo GRANTHA OM 1135D..11361 ; XID_Start # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL +113D3 ; XID_Start # Lo TULU-TIGALARI SIGN PLUTA 11400..11434 ; XID_Start # Lo [53] NEWA LETTER A..NEWA LETTER HA 11447..1144A ; XID_Start # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI 1145F..11461 ; XID_Start # Lo [3] NEWA LETTER VEDIC ANUSVARA..NEWA SIGN UPADHMANIYA @@ -8977,7 +8983,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 30000..3134A ; XID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; XID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 136947 +# Total code points: 136948 # ================================================ @@ -9998,6 +10004,8 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 11362..11363 ; XID_Continue # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL 11366..1136C ; XID_Continue # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; XID_Continue # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +113D2 ; XID_Continue # Mn TULU-TIGALARI GEMINATION MARK +113D3 ; XID_Continue # Lo TULU-TIGALARI SIGN PLUTA 11400..11434 ; XID_Continue # Lo [53] NEWA LETTER A..NEWA LETTER HA 11435..11437 ; XID_Continue # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II 11438..1143F ; XID_Continue # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI @@ -10338,7 +10346,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 140093 +# Total code points: 140095 # ================================================ @@ -10675,6 +10683,7 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 11357 ; Grapheme_Extend # Mc GRANTHA AU LENGTH MARK 11366..1136C ; Grapheme_Extend # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; Grapheme_Extend # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +113D2 ; Grapheme_Extend # Mn TULU-TIGALARI GEMINATION MARK 11438..1143F ; Grapheme_Extend # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI 11442..11444 ; Grapheme_Extend # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA 11446 ; Grapheme_Extend # Mn NEWA SIGN NUKTA @@ -10775,7 +10784,7 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. E0020..E007F ; Grapheme_Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2126 +# Total code points: 2127 # ================================================ @@ -12155,6 +12164,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 11350 ; Grapheme_Base # Lo GRANTHA OM 1135D..11361 ; Grapheme_Base # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL 11362..11363 ; Grapheme_Base # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL +113D3 ; Grapheme_Base # Lo TULU-TIGALARI SIGN PLUTA 11400..11434 ; Grapheme_Base # Lo [53] NEWA LETTER A..NEWA LETTER HA 11435..11437 ; Grapheme_Base # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II 11440..11441 ; Grapheme_Base # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU @@ -12529,7 +12539,7 @@ 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: 147616 +# Total code points: 147617 # ================================================ diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index e40596ac2..9b81c7203 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: 2023-10-02, 12:16:33 GMT +# Date: 2023-10-09, 13:39:54 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 @@ -2065,6 +2065,8 @@ FFFD ; A # So REPLACEMENT CHARACTER 11362..11363 ; N # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL 11366..1136C ; N # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; N # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +113D2 ; N # Mn TULU-TIGALARI GEMINATION MARK +113D3 ; N # Lo TULU-TIGALARI SIGN PLUTA 11400..11434 ; N # Lo [53] NEWA LETTER A..NEWA LETTER HA 11435..11437 ; N # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II 11438..1143F ; N # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI diff --git a/unicodetools/data/ucd/dev/IndicPositionalCategory.txt b/unicodetools/data/ucd/dev/IndicPositionalCategory.txt index f45756e2c..b0224ff7e 100644 --- a/unicodetools/data/ucd/dev/IndicPositionalCategory.txt +++ b/unicodetools/data/ucd/dev/IndicPositionalCategory.txt @@ -1,7 +1,5 @@ -# Indic_Positional_Category=Bottom -113D2; Bottom # Mn TULU-TIGALARI GEMINATION MARK # IndicPositionalCategory-16.0.0.txt -# Date: 2023-10-02, 22:58:33 GMT +# Date: 2023-10-09, 13:39:54 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 @@ -704,6 +702,7 @@ ABED ; Bottom # Mn MEETEI MAYEK APUN IYEK 112E3..112E4 ; Bottom # Mn [2] KHUDAWADI VOWEL SIGN U..KHUDAWADI VOWEL SIGN UU 112E9..112EA ; Bottom # Mn [2] KHUDAWADI SIGN NUKTA..KHUDAWADI SIGN VIRAMA 1133B..1133C ; Bottom # Mn [2] COMBINING BINDU BELOW..GRANTHA SIGN NUKTA +113D2 ; Bottom # Mn TULU-TIGALARI GEMINATION MARK 11438..1143D ; Bottom # Mn [6] NEWA VOWEL SIGN U..NEWA VOWEL SIGN VOCALIC LL 11442 ; Bottom # Mn NEWA SIGN VIRAMA 11446 ; Bottom # Mn NEWA SIGN NUKTA diff --git a/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt b/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt index f6aefb0a0..25739e10d 100644 --- a/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt +++ b/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt @@ -1,7 +1,5 @@ -# Indic_Syllabic_Category=Gemination_Mark -113D2; Gemination_Mark # Mn TULU-TIGALARI GEMINATION MARK # IndicSyllabicCategory-16.0.0.txt -# Date: 2023-10-02, 22:58:33 GMT +# Date: 2023-10-09, 13:39:55 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 @@ -1158,6 +1156,7 @@ ABEC ; Tone_Mark # Mc MEETEI MAYEK LUM IYEK 0A71 ; Gemination_Mark # Mn GURMUKHI ADDAK 0AFB ; Gemination_Mark # Mn GUJARATI SIGN SHADDA 11237 ; Gemination_Mark # Mn KHOJKI SIGN SHADDA +113D2 ; Gemination_Mark # Mn TULU-TIGALARI GEMINATION MARK 11A98 ; Gemination_Mark # Mn SOYOMBO GEMINATION MARK # ================================================ diff --git a/unicodetools/data/ucd/dev/PropertyValueAliases.txt b/unicodetools/data/ucd/dev/PropertyValueAliases.txt index 9039e9eb2..d6a9fdf5a 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: 2023-08-07, 15:21:34 GMT +# PropertyValueAliases-16.0.0.txt +# Date: 2023-10-09, 13:39:58 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -463,6 +463,7 @@ blk; Tifinagh ; Tifinagh blk; Tirhuta ; Tirhuta blk; Toto ; Toto blk; Transport_And_Map ; Transport_And_Map_Symbols +blk; Tulu_Tigalari ; Tulu_Tigalari blk; UCAS ; Unified_Canadian_Aboriginal_Syllabics; Canadian_Syllabics blk; UCAS_Ext ; Unified_Canadian_Aboriginal_Syllabics_Extended blk; UCAS_Ext_A ; Unified_Canadian_Aboriginal_Syllabics_Extended_A @@ -1442,6 +1443,7 @@ sc ; Tibt ; Tibetan sc ; Tirh ; Tirhuta sc ; Tnsa ; Tangsa sc ; Toto ; Toto +sc ; Tutg ; Tulu_Tigalari sc ; Ugar ; Ugaritic sc ; Vaii ; Vai sc ; Vith ; Vithkuqi diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 9d64347e4..a44a20482 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,6 +1,5 @@ -113D2..113D3; Tulu_Tigalari # Scripts-16.0.0.txt -# Date: 2023-10-02, 12:17:02 GMT +# Date: 2023-10-09, 13:40:09 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -3032,4 +3031,11 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI # Total code points: 42 +# ================================================ + +113D2 ; Tulu_Tigalari # Mn TULU-TIGALARI GEMINATION MARK +113D3 ; Tulu_Tigalari # Lo TULU-TIGALARI SIGN PLUTA + +# Total code points: 2 + # EOF diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 1ef1aa0d6..e247d28f0 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -1,5 +1,3 @@ -113D2; TULU-TIGALARI GEMINATION MARK;Mn;0;NSM;;;;;N;;;;; -113D3; TULU-TIGALARI SIGN PLUTA;Lo;0;L;;;;;N;;;;; 0000;;Cc;0;BN;;;;;N;NULL;;;; 0001;;Cc;0;BN;;;;;N;START OF HEADING;;;; 0002;;Cc;0;BN;;;;;N;START OF TEXT;;;; @@ -20270,6 +20268,8 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 11372;COMBINING GRANTHA LETTER NA;Mn;230;NSM;;;;;N;;;;; 11373;COMBINING GRANTHA LETTER VI;Mn;230;NSM;;;;;N;;;;; 11374;COMBINING GRANTHA LETTER PA;Mn;230;NSM;;;;;N;;;;; +113D2;TULU-TIGALARI GEMINATION MARK;Mn;0;NSM;;;;;N;;;;; +113D3;TULU-TIGALARI SIGN PLUTA;Lo;0;L;;;;;N;;;;; 11400;NEWA LETTER A;Lo;0;L;;;;;N;;;;; 11401;NEWA LETTER AA;Lo;0;L;;;;;N;;;;; 11402;NEWA LETTER I;Lo;0;L;;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index 89e03f3c2..879be011b 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: 2023-10-02, 12:17:09 GMT +# Date: 2023-10-09, 13:40:12 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 @@ -1889,6 +1889,8 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 11362..11363 ; R # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL 11366..1136C ; R # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; R # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +113D2 ; R # Mn TULU-TIGALARI GEMINATION MARK +113D3 ; R # Lo TULU-TIGALARI SIGN PLUTA 11400..11434 ; R # Lo [53] NEWA LETTER A..NEWA LETTER HA 11435..11437 ; R # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II 11438..1143F ; R # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI diff --git a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt index a33745533..b996448eb 100644 --- a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt @@ -1,5 +1,5 @@ # GraphemeBreakProperty-16.0.0.txt -# Date: 2023-10-02, 12:16:33 GMT +# Date: 2023-10-09, 13:39:54 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 @@ -358,6 +358,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 11357 ; Extend # Mc GRANTHA AU LENGTH MARK 11366..1136C ; Extend # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; Extend # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +113D2 ; Extend # Mn TULU-TIGALARI GEMINATION MARK 11438..1143F ; Extend # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI 11442..11444 ; Extend # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA 11446 ; Extend # Mn NEWA SIGN NUKTA @@ -459,7 +460,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2131 +# Total code points: 2132 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 04638c600..9f4322a7c 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ # SentenceBreakProperty-16.0.0.txt -# Date: 2023-10-02, 12:17:03 GMT +# Date: 2023-10-09, 13:40:10 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 @@ -425,6 +425,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 11362..11363 ; Extend # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL 11366..1136C ; Extend # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; Extend # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +113D2 ; Extend # Mn TULU-TIGALARI GEMINATION MARK 11435..11437 ; Extend # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II 11438..1143F ; Extend # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI 11440..11441 ; Extend # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU @@ -567,7 +568,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2551 +# Total code points: 2552 # ================================================ @@ -2394,6 +2395,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1133D ; OLetter # Lo GRANTHA SIGN AVAGRAHA 11350 ; OLetter # Lo GRANTHA OM 1135D..11361 ; OLetter # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL +113D3 ; OLetter # Lo TULU-TIGALARI SIGN PLUTA 11400..11434 ; OLetter # Lo [53] NEWA LETTER A..NEWA LETTER HA 11447..1144A ; OLetter # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI 1145F..11461 ; OLetter # Lo [3] NEWA LETTER VEDIC ANUSVARA..NEWA SIGN UPADHMANIYA @@ -2537,7 +2539,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; OLetter # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; OLetter # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 132661 +# Total code points: 132662 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index 870eb1937..775c8040b 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-16.0.0.txt -# Date: 2023-10-02, 12:17:10 GMT +# Date: 2023-10-09, 13:40:12 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 @@ -461,6 +461,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 11362..11363 ; Extend # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL 11366..1136C ; Extend # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; Extend # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +113D2 ; Extend # Mn TULU-TIGALARI GEMINATION MARK 11435..11437 ; Extend # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II 11438..1143F ; Extend # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI 11440..11441 ; Extend # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU @@ -604,7 +605,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2555 +# Total code points: 2556 # ================================================ @@ -1154,6 +1155,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1133D ; ALetter # Lo GRANTHA SIGN AVAGRAHA 11350 ; ALetter # Lo GRANTHA OM 1135D..11361 ; ALetter # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL +113D3 ; ALetter # Lo TULU-TIGALARI SIGN PLUTA 11400..11434 ; ALetter # Lo [53] NEWA LETTER A..NEWA LETTER HA 11447..1144A ; ALetter # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI 1145F..11461 ; ALetter # Lo [3] NEWA LETTER VEDIC ANUSVARA..NEWA SIGN UPADHMANIYA @@ -1314,7 +1316,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1F150..1F169 ; ALetter # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; ALetter # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 29493 +# Total code points: 29494 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 425000246..14074b18e 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: 2023-10-02, 12:16:21 GMT +# Date: 2023-10-09, 13:39:47 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 @@ -900,6 +900,7 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 11357 ; L # Mc GRANTHA AU LENGTH MARK 1135D..11361 ; L # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL 11362..11363 ; L # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL +113D3 ; L # Lo TULU-TIGALARI SIGN PLUTA 11400..11434 ; L # Lo [53] NEWA LETTER A..NEWA LETTER HA 11435..11437 ; L # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II 11440..11441 ; L # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU @@ -1182,8 +1183,8 @@ 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 820462 code points not listed here. -# Total code points: 1096267 +# The above property value applies to 820460 code points not listed here. +# Total code points: 1096266 # ================================================ @@ -2255,6 +2256,7 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 11340 ; NSM # Mn GRANTHA VOWEL SIGN II 11366..1136C ; NSM # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; NSM # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +113D2 ; NSM # Mn TULU-TIGALARI GEMINATION MARK 11438..1143F ; NSM # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI 11442..11444 ; NSM # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA 11446 ; NSM # Mn NEWA SIGN NUKTA @@ -2348,7 +2350,7 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 1E944..1E94A ; NSM # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1994 +# Total code points: 1995 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index d2888c80d..11a33ef3d 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: 2023-10-02, 12:41:00 GMT +# Date: 2023-10-09, 13:39:48 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 @@ -1570,6 +1570,8 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 11357 ; 0 # Mc GRANTHA AU LENGTH MARK 1135D..11361 ; 0 # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL 11362..11363 ; 0 # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL +113D2 ; 0 # Mn TULU-TIGALARI GEMINATION MARK +113D3 ; 0 # Lo TULU-TIGALARI SIGN PLUTA 11400..11434 ; 0 # Lo [53] NEWA LETTER A..NEWA LETTER HA 11435..11437 ; 0 # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II 11438..1143F ; 0 # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI @@ -2006,7 +2008,7 @@ 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 826762 code points not listed here. +# The above property value applies to 826760 code points not listed here. # Total code points: 1113189 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index 6776cd4c8..589524f82 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: 2023-10-02, 12:16:27 GMT +# Date: 2023-10-09, 13:39:50 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 @@ -1589,6 +1589,8 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 11362..11363 ; N # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL 11366..1136C ; N # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; N # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +113D2 ; N # Mn TULU-TIGALARI GEMINATION MARK +113D3 ; N # Lo TULU-TIGALARI SIGN PLUTA 11400..11434 ; N # Lo [53] NEWA LETTER A..NEWA LETTER HA 11435..11437 ; N # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II 11438..1143F ; N # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI @@ -2044,7 +2046,7 @@ 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 766280 code points not listed here. +# The above property value applies to 766278 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 b75457c76..eb7d213fb 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: 2023-10-02, 12:16:28 GMT +# Date: 2023-10-09, 13:39:50 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 @@ -476,7 +476,8 @@ FFFE..FFFF ; Cn # [2] .. 11358..1135C ; Cn # [5] .. 11364..11365 ; Cn # [2] .. 1136D..1136F ; Cn # [3] .. -11375..113FF ; Cn # [139] .. +11375..113D1 ; Cn # [93] .. +113D4..113FF ; Cn # [44] .. 1145C ; Cn # 11462..1147F ; Cn # [30] .. 114C8..114CF ; Cn # [8] .. @@ -724,7 +725,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 824714 +# Total code points: 824712 # ================================================ @@ -2524,6 +2525,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 1133D ; Lo # GRANTHA SIGN AVAGRAHA 11350 ; Lo # GRANTHA OM 1135D..11361 ; Lo # [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL +113D3 ; Lo # TULU-TIGALARI SIGN PLUTA 11400..11434 ; Lo # [53] NEWA LETTER A..NEWA LETTER HA 11447..1144A ; Lo # [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI 1145F..11461 ; Lo # [3] NEWA LETTER VEDIC ANUSVARA..NEWA SIGN UPADHMANIYA @@ -2656,7 +2658,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 30000..3134A ; Lo # [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Lo # [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 132237 +# Total code points: 132238 # ================================================ @@ -2916,6 +2918,7 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 11340 ; Mn # GRANTHA VOWEL SIGN II 11366..1136C ; Mn # [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; Mn # [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +113D2 ; Mn # TULU-TIGALARI GEMINATION MARK 11438..1143F ; Mn # [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI 11442..11444 ; Mn # [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA 11446 ; Mn # NEWA SIGN NUKTA @@ -3009,7 +3012,7 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 1E944..1E94A ; Mn # [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; Mn # [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1986 +# Total code points: 1987 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt index 082e7a262..953411919 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt @@ -1,5 +1,5 @@ # DerivedJoiningType-16.0.0.txt -# Date: 2023-10-02, 12:16:29 GMT +# Date: 2023-10-09, 13:39:51 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 @@ -471,6 +471,7 @@ FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATI 11340 ; T # Mn GRANTHA VOWEL SIGN II 11366..1136C ; T # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; T # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +113D2 ; T # Mn TULU-TIGALARI GEMINATION MARK 11438..1143F ; T # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI 11442..11444 ; T # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA 11446 ; T # Mn NEWA SIGN NUKTA @@ -570,6 +571,6 @@ E0001 ; T # Cf LANGUAGE TAG E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2151 +# Total code points: 2152 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index c2f084c5f..ea46db5d8 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, 12:16:29 GMT +# Date: 2023-10-09, 13:39:51 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 762721 code points not listed here. -# Total code points: 900189 +# The above property value applies to 762719 code points not listed here. +# Total code points: 900187 # ================================================ @@ -2200,6 +2200,7 @@ FFF9..FFFB ; CM # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTAT 11362..11363 ; CM # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL 11366..1136C ; CM # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; CM # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +113D2 ; CM # Mn TULU-TIGALARI GEMINATION MARK 11435..11437 ; CM # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II 11438..1143F ; CM # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI 11440..11441 ; CM # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU @@ -2337,7 +2338,7 @@ E0001 ; CM # Cf LANGUAGE TAG E0020..E007F ; CM # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; CM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2430 +# Total code points: 2431 # ================================================ @@ -2463,6 +2464,7 @@ ABEB ; BA # Po MEETEI MAYEK CHEIKHEI 112A9 ; BA # Po MULTANI SECTION MARK 1133D ; BA # Lo GRANTHA SIGN AVAGRAHA 1135D ; BA # Lo GRANTHA SIGN PLUTA +113D3 ; BA # Lo TULU-TIGALARI SIGN PLUTA 1144B..1144E ; BA # Po [4] NEWA DANDA..NEWA GAP FILLER 1145A..1145B ; BA # Po [2] NEWA DOUBLE COMMA..NEWA PLACEHOLDER MARK 115C2..115C3 ; BA # Po [2] SIDDHAM DANDA..SIDDHAM DOUBLE DANDA @@ -2487,7 +2489,7 @@ ABEB ; BA # Po MEETEI MAYEK CHEIKHEI 1BC9F ; BA # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1DA87..1DA8A ; BA # Po [4] SIGNWRITING COMMA..SIGNWRITING COLON -# Total code points: 266 +# Total code points: 267 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 080ce3711..1ad6d8c01 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: 2023-10-02, 12:16:30 GMT +# Date: 2023-10-09, 13:39:52 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -30933,6 +30933,8 @@ FFFD ; REPLACEMENT CHARACTER 11372 ; COMBINING GRANTHA LETTER NA 11373 ; COMBINING GRANTHA LETTER VI 11374 ; COMBINING GRANTHA LETTER PA +113D2 ; TULU-TIGALARI GEMINATION MARK +113D3 ; TULU-TIGALARI SIGN PLUTA 11400 ; NEWA LETTER A 11401 ; NEWA LETTER AA 11402 ; NEWA LETTER I @@ -44180,6 +44182,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 149817 +# Total code points: 149819 # EOF From f434976d6b030a766b3350bb3512460097e54a18 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 9 Oct 2023 15:40:43 +0200 Subject: [PATCH 08/13] GenerateEnums --- .../src/main/java/org/unicode/props/UcdPropertyValues.java | 2 ++ 1 file changed, 2 insertions(+) diff --git a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java index c5eb7e092..a8925f735 100644 --- a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java +++ b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java @@ -488,6 +488,7 @@ public enum Block_Values implements Named { Tirhuta("Tirhuta"), Toto("Toto"), Transport_And_Map_Symbols("Transport_And_Map"), + Tulu_Tigalari("Tulu_Tigalari"), Unified_Canadian_Aboriginal_Syllabics("UCAS", "Canadian_Syllabics"), Unified_Canadian_Aboriginal_Syllabics_Extended("UCAS_Ext"), Unified_Canadian_Aboriginal_Syllabics_Extended_A("UCAS_Ext_A"), @@ -1851,6 +1852,7 @@ public enum Script_Values implements Named { Tirhuta("Tirh"), Tangsa("Tnsa"), Toto("Toto"), + Tulu_Tigalari("Tutg"), Ugaritic("Ugar"), Vai("Vaii"), Vithkuqi("Vith"), From 108a1545d00c08eb4eb83000cbfc7b76c0ef1a56 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 23 Oct 2023 23:42:32 +0200 Subject: [PATCH 09/13] A guess at dia ext --- unicodetools/data/ucd/dev/PropList.txt | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt index 777e8a288..93bc71ab4 100644 --- a/unicodetools/data/ucd/dev/PropList.txt +++ b/unicodetools/data/ucd/dev/PropList.txt @@ -1,3 +1,8 @@ +113D3;Diacritic +113D3;Extender +113D2;Diacritic +113D2;Extender + # PropList-15.1.0.txt # Date: 2023-08-01, 21:56:53 GMT # © 2023 Unicode®, Inc. From 7c03f033db966a8fb8d766c2cc94bfa191d012a0 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 23 Oct 2023 23:44:30 +0200 Subject: [PATCH 10/13] Regenerate UCD --- unicodetools/data/ucd/dev/PropList.txt | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt index 93bc71ab4..15cd9c82b 100644 --- a/unicodetools/data/ucd/dev/PropList.txt +++ b/unicodetools/data/ucd/dev/PropList.txt @@ -1,10 +1,5 @@ -113D3;Diacritic -113D3;Extender -113D2;Diacritic -113D2;Extender - -# PropList-15.1.0.txt -# Date: 2023-08-01, 21:56:53 GMT +# PropList-16.0.0.txt +# Date: 2023-10-23, 21:44:00 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 @@ -1064,6 +1059,8 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON 1134D ; Diacritic # Mc GRANTHA SIGN VIRAMA 11366..1136C ; Diacritic # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; Diacritic # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +113D2 ; Diacritic # Mn TULU-TIGALARI GEMINATION MARK +113D3 ; Diacritic # Lo TULU-TIGALARI SIGN PLUTA 11442 ; Diacritic # Mn NEWA SIGN VIRAMA 11446 ; Diacritic # Mn NEWA SIGN NUKTA 114C2..114C3 ; Diacritic # Mn [2] TIRHUTA SIGN VIRAMA..TIRHUTA SIGN NUKTA @@ -1108,7 +1105,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON 1E944..1E946 ; Diacritic # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK 1E948..1E94A ; Diacritic # Mn [3] ADLAM CONSONANT MODIFIER..ADLAM NUKTA -# Total code points: 1144 +# Total code points: 1146 # ================================================ @@ -1138,6 +1135,8 @@ AAF3..AAF4 ; Extender # Lm [2] MEETEI MAYEK SYLLABLE REPETITION MARK..MEETE FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK 10781..10782 ; Extender # Lm [2] MODIFIER LETTER SUPERSCRIPT TRIANGULAR COLON..MODIFIER LETTER SUPERSCRIPT HALF TRIANGULAR COLON 1135D ; Extender # Lo GRANTHA SIGN PLUTA +113D2 ; Extender # Mn TULU-TIGALARI GEMINATION MARK +113D3 ; Extender # Lo TULU-TIGALARI SIGN PLUTA 115C6..115C8 ; Extender # Po [3] SIDDHAM REPETITION MARK-1..SIDDHAM REPETITION MARK-3 11A98 ; Extender # Mn SOYOMBO GEMINATION MARK 16B42..16B43 ; Extender # Lm [2] PAHAWH HMONG SIGN VOS NRUA..PAHAWH HMONG SIGN IB YAM @@ -1146,7 +1145,7 @@ FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND 1E13C..1E13D ; Extender # Lm [2] NYIAKENG PUACHUE HMONG SIGN XW XW..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E944..1E946 ; Extender # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK -# Total code points: 50 +# Total code points: 52 # ================================================ From 09357c32e40463e3943ed442854cdd74737b184d Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Sun, 5 Nov 2023 10:30:53 -0800 Subject: [PATCH 11/13] Back to lb=ID for the Pluta --- unicodetools/data/ucd/dev/LineBreak.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index d8f748ed4..b67ef37a9 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -2942,7 +2942,7 @@ FFFD ; AI # So REPLACEMENT CHARACTER 11366..1136C ; CM # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; CM # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA 113D2 ; CM # Mn TULU-TIGALARI GEMINATION MARK -113D3 ; BA # Lo TULU-TIGALARI SIGN PLUTA +113D3 ; ID # Lo TULU-TIGALARI SIGN PLUTA 11400..11434 ; AL # Lo [53] NEWA LETTER A..NEWA LETTER HA 11435..11437 ; CM # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II 11438..1143F ; CM # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI From 806d9973f7cd8e0f8bd21bb40372eb4f55d93e9d Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Sun, 5 Nov 2023 10:33:41 -0800 Subject: [PATCH 12/13] Regenerate UCD --- unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 840cf9d34..73311306d 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-16.0.0.txt -# Date: 2023-11-05, 18:24:36 GMT +# Date: 2023-11-05, 18:33:01 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 @@ -1752,6 +1752,7 @@ FFE3 ; ID # Sk FULLWIDTH MACRON FFE4 ; ID # So FULLWIDTH BROKEN BAR 11049..1104D ; ID # Po [5] BRAHMI PUNCTUATION DOT..BRAHMI PUNCTUATION LOTUS 11052..11065 ; ID # No [20] BRAHMI NUMBER ONE..BRAHMI NUMBER ONE THOUSAND +113D3 ; ID # Lo TULU-TIGALARI SIGN PLUTA 11F45..11F4F ; ID # Po [11] KAWI PUNCTUATION SECTION MARKER..KAWI PUNCTUATION CLOSING SPIRAL 17000..187F7 ; ID # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18AFF ; ID # Lo [768] TANGUT COMPONENT-001..TANGUT COMPONENT-768 @@ -1847,7 +1848,7 @@ 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 61865 code points not listed here. -# Total code points: 172422 +# Total code points: 172423 # ================================================ @@ -2489,7 +2490,6 @@ ABEB ; BA # Po MEETEI MAYEK CHEIKHEI 112A9 ; BA # Po MULTANI SECTION MARK 1133D ; BA # Lo GRANTHA SIGN AVAGRAHA 1135D ; BA # Lo GRANTHA SIGN PLUTA -113D3 ; BA # Lo TULU-TIGALARI SIGN PLUTA 1144B..1144E ; BA # Po [4] NEWA DANDA..NEWA GAP FILLER 1145A..1145B ; BA # Po [2] NEWA DOUBLE COMMA..NEWA PLACEHOLDER MARK 115C2..115C3 ; BA # Po [2] SIDDHAM DANDA..SIDDHAM DOUBLE DANDA @@ -2515,7 +2515,7 @@ ABEB ; BA # Po MEETEI MAYEK CHEIKHEI 1BC9F ; BA # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1DA87..1DA8A ; BA # Po [4] SIGNWRITING COMMA..SIGNWRITING COLON -# Total code points: 270 +# Total code points: 269 # ================================================ From 357ab00079e2bf2eacd20e98809daf3cb1e8eec9 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Fri, 10 Nov 2023 14:23:50 -0800 Subject: [PATCH 13/13] Revert PVA --- unicodetools/data/ucd/dev/PropertyValueAliases.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/unicodetools/data/ucd/dev/PropertyValueAliases.txt b/unicodetools/data/ucd/dev/PropertyValueAliases.txt index 5acbc6401..3d9b1a0d1 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: 2023-11-10, 22:06:34 GMT +# Date: 2023-11-10, 20:57:45 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