From d02e44eaaf3225cc824f942ef5d3e983d5590369 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 23 Apr 2024 15:30:09 +0200 Subject: [PATCH 1/9] UnicodeData.txt lines from L2/24-106 --- 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 08593a319..3693beb00 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -1,3 +1,5 @@ +0B53;ORIYA SIGN DOT ABOVE;Mn;0;NSM;;;;;N;;;;; +0B54;ORIYA SIGN DOUBLE DOT ABOVE;Mn;0;NSM;;;;;N;;;;; 0000;;Cc;0;BN;;;;;N;NULL;;;; 0001;;Cc;0;BN;;;;;N;START OF HEADING;;;; 0002;;Cc;0;BN;;;;;N;START OF TEXT;;;; From a8cc4a94aa4c76d668e569ab729527ed89fbcbf9 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 23 Apr 2024 15:32:53 +0200 Subject: [PATCH 2/9] lb=CM --- 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 1d8bd89ec..74350d4a6 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: 2024-02-02, 23:11:30 GMT +# Date: 2024-04-23, 13:31:39 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -401,6 +401,7 @@ 0B47..0B48 ; CM # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI 0B4B..0B4C ; CM # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU 0B4D ; CM # Mn ORIYA SIGN VIRAMA +0B53..0B54 ; CM # Mn [2] ORIYA SIGN DOT ABOVE..ORIYA SIGN DOUBLE DOT ABOVE 0B55..0B56 ; CM # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK 0B57 ; CM # Mc ORIYA AU LENGTH MARK 0B5C..0B5D ; AL # Lo [2] ORIYA LETTER RRA..ORIYA LETTER RHA From 32e0698c69620c28259a45497f1abc5ca49d7fd9 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 23 Apr 2024 15:33:58 +0200 Subject: [PATCH 3/9] Oriya --- unicodetools/data/ucd/dev/Scripts.txt | 1 + 1 file changed, 1 insertion(+) diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 2e0b4fd4b..55ca314e4 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,3 +1,4 @@ +0B53..0B54;Oriya # Scripts-16.0.0.txt # Date: 2024-02-02, 23:11:49 GMT # © 2024 Unicode®, Inc. From 4831633d584f6a0961cb10b7af9b6441f5bbca8f Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 23 Apr 2024 15:35:16 +0200 Subject: [PATCH 4/9] IndicMeowCategory from L2/24-106 --- unicodetools/data/ucd/dev/IndicPositionalCategory.txt | 1 + unicodetools/data/ucd/dev/IndicSyllabicCategory.txt | 2 ++ 2 files changed, 3 insertions(+) diff --git a/unicodetools/data/ucd/dev/IndicPositionalCategory.txt b/unicodetools/data/ucd/dev/IndicPositionalCategory.txt index 1ce9b4ed1..b292639c3 100644 --- a/unicodetools/data/ucd/dev/IndicPositionalCategory.txt +++ b/unicodetools/data/ucd/dev/IndicPositionalCategory.txt @@ -1,3 +1,4 @@ +0B53..0B54 ; Top # Mn [2] ORIYA SIGN DOT ABOVE..ORIYA SIGN DOUBLE DOT ABOVE # IndicPositionalCategory-16.0.0.txt # Date: 2024-02-02, 23:11:29 GMT # © 2024 Unicode®, Inc. diff --git a/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt b/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt index 9f6baafe3..871cf7f07 100644 --- a/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt +++ b/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt @@ -1,3 +1,5 @@ +0B53 ; Vowel_Dependent # Mn [1] ORIYA SIGN DOT ABOVE +0B54 ; Vowel_Dependent # Mn [1] ORIYA SIGN DOUBLE DOT ABOVE # IndicSyllabicCategory-16.0.0.txt # Date: 2024-02-02, 23:11:30 GMT # © 2024 Unicode®, Inc. From 92a2ac0e689d399c9e71a7f279b8e655d3bb1ac4 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 23 Apr 2024 15:38:36 +0200 Subject: [PATCH 5/9] Both diacritics and the double dot an extender --- unicodetools/data/ucd/dev/PropList.txt | 3 +++ 1 file changed, 3 insertions(+) diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt index 1e3e2912b..3ba136e18 100644 --- a/unicodetools/data/ucd/dev/PropList.txt +++ b/unicodetools/data/ucd/dev/PropList.txt @@ -939,6 +939,8 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM 0AFD..0AFF ; Diacritic # Mn [3] GUJARATI SIGN THREE-DOT NUKTA ABOVE..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B3C ; Diacritic # Mn ORIYA SIGN NUKTA 0B4D ; Diacritic # Mn ORIYA SIGN VIRAMA +0B53 ; Diacritic +0B54 ; Diacritic 0B55 ; Diacritic # Mn ORIYA SIGN OVERLINE 0BCD ; Diacritic # Mn TAMIL SIGN VIRAMA 0C3C ; Diacritic # Mn TELUGU SIGN NUKTA @@ -1152,6 +1154,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON 07FA ; Extender # Lm NKO LAJANYALAN 0A71 ; Extender # Mn GURMUKHI ADDAK 0AFB ; Extender # Mn GUJARATI SIGN SHADDA +0B54 ; Extender 0B55 ; Extender # Mn ORIYA SIGN OVERLINE 0E46 ; Extender # Lm THAI CHARACTER MAIYAMOK 0EC6 ; Extender # Lm LAO KO LA From 4dc7fac2c7e50ef7d5542357cebe475b8d5a93ba Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 23 Apr 2024 15:44:48 +0200 Subject: [PATCH 6/9] Regenerate UCD --- unicodetools/data/ucd/dev/DerivedAge.txt | 5 +++-- .../data/ucd/dev/DerivedCoreProperties.txt | 18 +++++++++--------- unicodetools/data/ucd/dev/EastAsianWidth.txt | 4 ++-- .../data/ucd/dev/IndicPositionalCategory.txt | 5 ++--- .../data/ucd/dev/IndicSyllabicCategory.txt | 6 ++---- unicodetools/data/ucd/dev/LineBreak.txt | 5 ++--- unicodetools/data/ucd/dev/PropList.txt | 13 +++++-------- unicodetools/data/ucd/dev/Scripts.txt | 7 +++---- unicodetools/data/ucd/dev/UnicodeData.txt | 4 ++-- .../data/ucd/dev/VerticalOrientation.txt | 4 ++-- .../dev/auxiliary/GraphemeBreakProperty.txt | 6 +++--- .../dev/auxiliary/SentenceBreakProperty.txt | 6 +++--- .../ucd/dev/auxiliary/WordBreakProperty.txt | 6 +++--- .../ucd/dev/extracted/DerivedBidiClass.txt | 10 +++++----- .../dev/extracted/DerivedCombiningClass.txt | 6 +++--- .../dev/extracted/DerivedEastAsianWidth.txt | 6 +++--- .../dev/extracted/DerivedGeneralCategory.txt | 10 +++++----- .../ucd/dev/extracted/DerivedJoiningType.txt | 6 +++--- .../ucd/dev/extracted/DerivedLineBreak.txt | 10 +++++----- .../data/ucd/dev/extracted/DerivedName.txt | 6 ++++-- 20 files changed, 69 insertions(+), 74 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index d116dccaa..b0ade2d36 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-16.0.0.txt -# Date: 2024-02-02, 23:11:18 GMT +# Date: 2024-04-23, 13:43:43 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -2010,6 +2010,7 @@ FDFE..FDFF ; 14.0 # [2] ARABIC LIGATURE SUBHAANAHU WA TAAALAA..ARABIC LIGAT # Newly assigned in Unicode 16.0.0 (September, 2024) 0897 ; 16.0 # ARABIC PEPET +0B53..0B54 ; 16.0 # [2] ORIYA SIGN DOT ABOVE..ORIYA SIGN DOUBLE DOT ABOVE 0C5C ; 16.0 # TELUGU ARCHAIC SHRII 0CDC ; 16.0 # KANNADA ARCHAIC SHRII 1B4E..1B4F ; 16.0 # [2] BALINESE INVERTED CARIK SIKI..BALINESE INVERTED CARIK PAREREN @@ -2059,6 +2060,6 @@ A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L 1FAE9 ; 16.0 # FACE WITH BAGS UNDER EYES 1FBCB..1FBEF ; 16.0 # [37] WHITE CROSS MARK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 5187 +# Total code points: 5189 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 1e054c4f2..4294e124d 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-16.0.0.txt -# Date: 2024-02-02, 23:11:24 GMT +# Date: 2024-04-23, 13:44:04 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -3103,7 +3103,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 0B3F ; Case_Ignorable # Mn ORIYA VOWEL SIGN I 0B41..0B44 ; Case_Ignorable # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR 0B4D ; Case_Ignorable # Mn ORIYA SIGN VIRAMA -0B55..0B56 ; Case_Ignorable # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B53..0B56 ; Case_Ignorable # Mn [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK 0B62..0B63 ; Case_Ignorable # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL 0B82 ; Case_Ignorable # Mn TAMIL SIGN ANUSVARA 0BC0 ; Case_Ignorable # Mn TAMIL VOWEL SIGN II @@ -3505,7 +3505,7 @@ E0001 ; Case_Ignorable # Cf LANGUAGE TAG E0020..E007F ; Case_Ignorable # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2749 +# Total code points: 2751 # ================================================ @@ -7176,7 +7176,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0B47..0B48 ; ID_Continue # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI 0B4B..0B4C ; ID_Continue # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU 0B4D ; ID_Continue # Mn ORIYA SIGN VIRAMA -0B55..0B56 ; ID_Continue # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B53..0B56 ; ID_Continue # Mn [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK 0B57 ; ID_Continue # Mc ORIYA AU LENGTH MARK 0B5C..0B5D ; ID_Continue # Lo [2] ORIYA LETTER RRA..ORIYA LETTER RHA 0B5F..0B61 ; ID_Continue # Lo [3] ORIYA LETTER YYA..ORIYA LETTER VOCALIC LL @@ -8370,7 +8370,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144543 +# Total code points: 144545 # ================================================ @@ -9358,7 +9358,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0B47..0B48 ; XID_Continue # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI 0B4B..0B4C ; XID_Continue # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU 0B4D ; XID_Continue # Mn ORIYA SIGN VIRAMA -0B55..0B56 ; XID_Continue # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B53..0B56 ; XID_Continue # Mn [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK 0B57 ; XID_Continue # Mc ORIYA AU LENGTH MARK 0B5C..0B5D ; XID_Continue # Lo [2] ORIYA LETTER RRA..ORIYA LETTER RHA 0B5F..0B61 ; XID_Continue # Lo [3] ORIYA LETTER YYA..ORIYA LETTER VOCALIC LL @@ -10557,7 +10557,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144524 +# Total code points: 144526 # ================================================ @@ -10680,7 +10680,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] ..;Cc;0;BN;;;;;N;NULL;;;; 0001;;Cc;0;BN;;;;;N;START OF HEADING;;;; 0002;;Cc;0;BN;;;;;N;START OF TEXT;;;; @@ -2688,6 +2686,8 @@ 0B4B;ORIYA VOWEL SIGN O;Mc;0;L;0B47 0B3E;;;;N;;;;; 0B4C;ORIYA VOWEL SIGN AU;Mc;0;L;0B47 0B57;;;;N;;;;; 0B4D;ORIYA SIGN VIRAMA;Mn;9;NSM;;;;;N;;;;; +0B53;ORIYA SIGN DOT ABOVE;Mn;0;NSM;;;;;N;;;;; +0B54;ORIYA SIGN DOUBLE DOT ABOVE;Mn;0;NSM;;;;;N;;;;; 0B55;ORIYA SIGN OVERLINE;Mn;0;NSM;;;;;N;;;;; 0B56;ORIYA AI LENGTH MARK;Mn;0;NSM;;;;;N;;;;; 0B57;ORIYA AU LENGTH MARK;Mc;0;L;;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index 187a0888d..ff9fe2948 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ # VerticalOrientation-16.0.0.txt -# Date: 2024-02-02, 23:11:51 GMT +# Date: 2024-04-23, 13:44:39 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -388,7 +388,7 @@ 0B47..0B48 ; R # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI 0B4B..0B4C ; R # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU 0B4D ; R # Mn ORIYA SIGN VIRAMA -0B55..0B56 ; R # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B53..0B56 ; R # Mn [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK 0B57 ; R # Mc ORIYA AU LENGTH MARK 0B5C..0B5D ; R # Lo [2] ORIYA LETTER RRA..ORIYA LETTER RHA 0B5F..0B61 ; R # Lo [3] ORIYA LETTER YYA..ORIYA LETTER VOCALIC LL diff --git a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt index 1241b2d2b..f2138289e 100644 --- a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt @@ -1,5 +1,5 @@ # GraphemeBreakProperty-16.0.0.txt -# Date: 2024-02-02, 23:11:29 GMT +# Date: 2024-04-23, 13:44:11 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -145,7 +145,7 @@ E01F0..E0FFF ; Control # Cn [3600] .. 0B3F ; Extend # Mn ORIYA VOWEL SIGN I 0B41..0B44 ; Extend # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR 0B4D ; Extend # Mn ORIYA SIGN VIRAMA -0B55..0B56 ; Extend # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B53..0B56 ; Extend # Mn [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK 0B57 ; Extend # Mc ORIYA AU LENGTH MARK 0B62..0B63 ; Extend # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL 0B82 ; Extend # Mn TAMIL SIGN ANUSVARA @@ -490,7 +490,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2190 +# Total code points: 2192 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index cec52074f..85e2c5f83 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ # SentenceBreakProperty-16.0.0.txt -# Date: 2024-02-02, 23:11:49 GMT +# Date: 2024-04-23, 13:44:36 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -111,7 +111,7 @@ 0B47..0B48 ; Extend # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI 0B4B..0B4C ; Extend # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU 0B4D ; Extend # Mn ORIYA SIGN VIRAMA -0B55..0B56 ; Extend # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B53..0B56 ; Extend # Mn [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK 0B57 ; Extend # Mc ORIYA AU LENGTH MARK 0B62..0B63 ; Extend # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL 0B82 ; Extend # Mn TAMIL SIGN ANUSVARA @@ -586,7 +586,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2601 +# Total code points: 2603 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index fd760073c..4c2c8a7a2 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-16.0.0.txt -# Date: 2024-02-22, 15:58:24 GMT +# Date: 2024-04-23, 13:44:39 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -147,7 +147,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 0B47..0B48 ; Extend # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI 0B4B..0B4C ; Extend # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU 0B4D ; Extend # Mn ORIYA SIGN VIRAMA -0B55..0B56 ; Extend # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B53..0B56 ; Extend # Mn [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK 0B57 ; Extend # Mc ORIYA AU LENGTH MARK 0B62..0B63 ; Extend # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL 0B82 ; Extend # Mn TAMIL SIGN ANUSVARA @@ -623,7 +623,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2605 +# Total code points: 2607 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index d991ed1b8..32be27ce8 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-16.0.0.txt -# Date: 2024-02-02, 23:11:23 GMT +# Date: 2024-04-23, 13:44:01 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1219,8 +1219,8 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER F0000..FFFFD ; L # Co [65534] .. 100000..10FFFD; L # Co [65534] .. -# The above property value applies to 815349 code points not listed here. -# Total code points: 1095518 +# The above property value applies to 815347 code points not listed here. +# Total code points: 1095516 # ================================================ @@ -2107,7 +2107,7 @@ FFFFE..FFFFF ; BN # Cn [2] .. 0B3F ; NSM # Mn ORIYA VOWEL SIGN I 0B41..0B44 ; NSM # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR 0B4D ; NSM # Mn ORIYA SIGN VIRAMA -0B55..0B56 ; NSM # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B53..0B56 ; NSM # Mn [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK 0B62..0B63 ; NSM # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL 0B82 ; NSM # Mn TAMIL SIGN ANUSVARA 0BC0 ; NSM # Mn TAMIL VOWEL SIGN II @@ -2408,7 +2408,7 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 1E944..1E94A ; NSM # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2028 +# Total code points: 2030 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index 639fce0ae..671e0cda0 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-16.0.0.txt -# Date: 2024-02-02, 23:11:23 GMT +# Date: 2024-04-23, 13:44:03 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -290,7 +290,7 @@ 0B41..0B44 ; 0 # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR 0B47..0B48 ; 0 # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI 0B4B..0B4C ; 0 # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU -0B55..0B56 ; 0 # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B53..0B56 ; 0 # Mn [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK 0B57 ; 0 # Mc ORIYA AU LENGTH MARK 0B5C..0B5D ; 0 # Lo [2] ORIYA LETTER RRA..ORIYA LETTER RHA 0B5F..0B61 ; 0 # Lo [3] ORIYA LETTER YYA..ORIYA LETTER VOCALIC LL @@ -2060,7 +2060,7 @@ 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 821579 code points not listed here. +# The above property value applies to 821577 code points not listed here. # Total code points: 1113178 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index 44585c48d..dff477679 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-16.0.0.txt -# Date: 2024-02-02, 23:11:25 GMT +# Date: 2024-04-23, 13:44:06 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -343,7 +343,7 @@ 0B47..0B48 ; N # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI 0B4B..0B4C ; N # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU 0B4D ; N # Mn ORIYA SIGN VIRAMA -0B55..0B56 ; N # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B53..0B56 ; N # Mn [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK 0B57 ; N # Mc ORIYA AU LENGTH MARK 0B5C..0B5D ; N # Lo [2] ORIYA LETTER RRA..ORIYA LETTER RHA 0B5F..0B61 ; N # Lo [3] ORIYA LETTER YYA..ORIYA LETTER VOCALIC LL @@ -2103,7 +2103,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 761097 code points not listed here. +# The above property value applies to 761095 code points not listed here. # Total code points: 792608 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index b9105da02..35f844ef8 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-16.0.0.txt -# Date: 2024-02-02, 23:11:25 GMT +# Date: 2024-04-23, 13:44:07 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -91,7 +91,7 @@ 0B3A..0B3B ; Cn # [2] .. 0B45..0B46 ; Cn # [2] .. 0B49..0B4A ; Cn # [2] .. -0B4E..0B54 ; Cn # [7] .. +0B4E..0B52 ; Cn # [5] .. 0B58..0B5B ; Cn # [4] .. 0B5E ; Cn # 0B64..0B65 ; Cn # [2] .. @@ -747,7 +747,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819531 +# Total code points: 819529 # ================================================ @@ -2773,7 +2773,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 0B3F ; Mn # ORIYA VOWEL SIGN I 0B41..0B44 ; Mn # [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR 0B4D ; Mn # ORIYA SIGN VIRAMA -0B55..0B56 ; Mn # [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B53..0B56 ; Mn # [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK 0B62..0B63 ; Mn # [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL 0B82 ; Mn # TAMIL SIGN ANUSVARA 0BC0 ; Mn # TAMIL VOWEL SIGN II @@ -3072,7 +3072,7 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 1E944..1E94A ; Mn # [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; Mn # [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2020 +# Total code points: 2022 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt index 6407d5c0d..906b28652 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt @@ -1,5 +1,5 @@ # DerivedJoiningType-16.0.0.txt -# Date: 2024-02-02, 23:11:26 GMT +# Date: 2024-04-23, 13:44:08 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -265,7 +265,7 @@ A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA 0B3F ; T # Mn ORIYA VOWEL SIGN I 0B41..0B44 ; T # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR 0B4D ; T # Mn ORIYA SIGN VIRAMA -0B55..0B56 ; T # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B53..0B56 ; T # Mn [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK 0B62..0B63 ; T # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL 0B82 ; T # Mn TAMIL SIGN ANUSVARA 0BC0 ; T # Mn TAMIL VOWEL SIGN II @@ -581,6 +581,6 @@ E0001 ; T # Cf LANGUAGE TAG E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2185 +# Total code points: 2187 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 3a3ecf9c1..fd9e7936e 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-16.0.0.txt -# Date: 2024-02-02, 23:11:26 GMT +# Date: 2024-04-23, 13:44:08 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -69,8 +69,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 757651 code points not listed here. -# Total code points: 895119 +# The above property value applies to 757649 code points not listed here. +# Total code points: 895117 # ================================================ @@ -1967,7 +1967,7 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 0B47..0B48 ; CM # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI 0B4B..0B4C ; CM # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU 0B4D ; CM # Mn ORIYA SIGN VIRAMA -0B55..0B56 ; CM # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B53..0B56 ; CM # Mn [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK 0B57 ; CM # Mc ORIYA AU LENGTH MARK 0B62..0B63 ; CM # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL 0B82 ; CM # Mn TAMIL SIGN ANUSVARA @@ -2382,7 +2382,7 @@ E0001 ; CM # Cf LANGUAGE TAG E0020..E007F ; CM # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; CM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2479 +# Total code points: 2481 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 4778d471e..48c730173 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-16.0.0.txt -# Date: 2024-02-02, 23:11:26 GMT +# Date: 2024-04-23, 13:44:08 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -2661,6 +2661,8 @@ 0B4B ; ORIYA VOWEL SIGN O 0B4C ; ORIYA VOWEL SIGN AU 0B4D ; ORIYA SIGN VIRAMA +0B53 ; ORIYA SIGN DOT ABOVE +0B54 ; ORIYA SIGN DOUBLE DOT ABOVE 0B55 ; ORIYA SIGN OVERLINE 0B56 ; ORIYA AI LENGTH MARK 0B57 ; ORIYA AU LENGTH MARK @@ -45369,6 +45371,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 155000 +# Total code points: 155002 # EOF From a499ac28f68317295373605860eeb1be7102d9e7 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 23 Apr 2024 17:29:52 +0200 Subject: [PATCH 7/9] more invariant exceptions --- .../resources/org/unicode/text/UCD/UnicodeInvariantTest.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt index 17d0306fe..ca5a470ad 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt @@ -574,7 +574,7 @@ Show [\u20b9] Let $nonAlphabeticBindus = [] [\p{InSc=Bindu} - \p{Alphabetic}] = $nonAlphabeticBindus -Let $nonAlphabeticDependentVowels = [\N{ORIYA SIGN OVERLINE}\N{THAI CHARACTER MAITAIKHU}\N{LIMBU SIGN KEMPHRENG}\N{SHARADA VOWEL MODIFIER MARK}\N{SHARADA EXTRA SHORT VOWEL MARK}] + [\p{Name=/^ORIYA SIGN (OVERLINE|(DOUBLE )?DOT ABOVE)$/}\N{ORIYA SIGN OVERLINE}\N{THAI CHARACTER MAITAIKHU}\N{LIMBU SIGN KEMPHRENG}\N{SHARADA VOWEL MODIFIER MARK}\N{SHARADA EXTRA SHORT VOWEL MARK}] [\p{InSC=Vowel_Dependent} - \p{Alphabetic}] = $nonAlphabeticDependentVowels # Several invariants from L2/24-009 item 2.2. From 50755dd0bcd8a0211f05bb45b4ca34506864d5a1 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 23 Apr 2024 22:10:18 +0200 Subject: [PATCH 8/9] oops --- .../resources/org/unicode/text/UCD/UnicodeInvariantTest.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt index ca5a470ad..13569afc2 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt @@ -574,7 +574,7 @@ Show [\u20b9] Let $nonAlphabeticBindus = [] [\p{InSc=Bindu} - \p{Alphabetic}] = $nonAlphabeticBindus - [\p{Name=/^ORIYA SIGN (OVERLINE|(DOUBLE )?DOT ABOVE)$/}\N{ORIYA SIGN OVERLINE}\N{THAI CHARACTER MAITAIKHU}\N{LIMBU SIGN KEMPHRENG}\N{SHARADA VOWEL MODIFIER MARK}\N{SHARADA EXTRA SHORT VOWEL MARK}] +Let $nonAlphabeticDependentVowels = [\p{Name=/^ORIYA SIGN (OVERLINE|(DOUBLE )?DOT ABOVE)$/}\N{ORIYA SIGN OVERLINE}\N{THAI CHARACTER MAITAIKHU}\N{LIMBU SIGN KEMPHRENG}\N{SHARADA VOWEL MODIFIER MARK}\N{SHARADA EXTRA SHORT VOWEL MARK}] [\p{InSC=Vowel_Dependent} - \p{Alphabetic}] = $nonAlphabeticDependentVowels # Several invariants from L2/24-009 item 2.2. From 43b85c0ed87ddfe1dd31d1262bf18baba032ef65 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 16 Oct 2024 22:33:19 +0200 Subject: [PATCH 9/9] Typo in ORIYA --- .../resources/org/unicode/text/UCD/UnicodeInvariantTest.txt | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt index 662e88c91..4e4685029 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt @@ -700,7 +700,7 @@ Let $nonAlphabeticBindus := [] Let $nonAlphabeticDependentVowels := [ \N{ORIYA SIGN OVERLINE} - \p{Name=/^ORYIA SIGN (DOUBLE )?DOT ABOVE$/} # L2/24-106R, related to the overline. + \p{Name=/^ORIYA SIGN (DOUBLE )?DOT ABOVE$/} # L2/24-106R, related to the overline. \N{THAI CHARACTER MAITAIKHU} \N{LIMBU SIGN KEMPHRENG} \N{SHARADA VOWEL MODIFIER MARK} @@ -1380,4 +1380,4 @@ Ignoring Unicode_1_Name Confusable_MA: end Ignoring; -end Ignoring; \ No newline at end of file +end Ignoring;