From ea26e61f179429c97182c2bc3ad6124e288944c7 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 3 Dec 2025 20:24:32 +0100 Subject: [PATCH 1/9] UnicodeData line according to UTC-184-C9 --- unicodetools/data/ucd/dev/UnicodeData.txt | 1 + 1 file changed, 1 insertion(+) diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 6fe88733d..fc94a7af1 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -1,3 +1,4 @@ +05C9;HEBREW POINT HEAVY DAGESH;Mn;21;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 a5d88cb3d0fdedd6383bed3b9076fc5195d8b2a8 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 3 Dec 2025 20:25:05 +0100 Subject: [PATCH 2/9] UTC-185-C33 renaming --- 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 fc94a7af1..55abbfd1b 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -1,4 +1,4 @@ -05C9;HEBREW POINT HEAVY DAGESH;Mn;21;NSM;;;;;N;;;;; +05C9;HEBREW POINT DAGESH HAZAQ MUDGASH;Mn;21;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 1eb7daa93ee3c3edf213557aed7bb883749f7210 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 3 Dec 2025 20:29:37 +0100 Subject: [PATCH 3/9] 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 a36f0e265..c98868739 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,5 @@ # LineBreak-18.0.0.txt -# Date: 2025-11-30, 20:46:34 GMT +# Date: 2025-12-03, 19:28:17 GMT # © 2025 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -201,6 +201,7 @@ 05C4..05C5 ; CM # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT 05C6 ; EX # Po HEBREW PUNCTUATION NUN HAFUKHA 05C7..05C8 ; CM # Mn [2] HEBREW POINT QAMATS QATAN..HEBREW POINT SHEVA NA MUDGASH +05C9 ; CM # Mn HEBREW POINT DAGESH HAZAQ MUDGASH 05D0..05EA ; HL # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV 05EF..05F2 ; HL # Lo [4] HEBREW YOD TRIANGLE..HEBREW LIGATURE YIDDISH DOUBLE YOD 05F3..05F4 ; AL # Po [2] HEBREW PUNCTUATION GERESH..HEBREW PUNCTUATION GERSHAYIM From ca09db7fbcb735f65202bd573eb405fb185f10a1 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 3 Dec 2025 20:30:30 +0100 Subject: [PATCH 4/9] Hebrew --- 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 0c3aeeb31..52678ab3f 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,3 +1,4 @@ +05C9; Hebrew # Scripts-18.0.0.txt # Date: 2025-11-30, 20:47:03 GMT # © 2025 Unicode®, Inc. From 74374a81af6d61f0e901a0dc33c36c180e8f7060 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 3 Dec 2025 20:35:11 +0100 Subject: [PATCH 5/9] Regenerate UCD --- unicodetools/data/ucd/dev/DerivedAge.txt | 6 ++--- .../data/ucd/dev/DerivedCoreProperties.txt | 22 +++++++++---------- unicodetools/data/ucd/dev/EastAsianWidth.txt | 4 ++-- unicodetools/data/ucd/dev/LineBreak.txt | 5 ++--- .../data/ucd/dev/NormalizationTest.txt | 4 +++- unicodetools/data/ucd/dev/Scripts.txt | 7 +++--- unicodetools/data/ucd/dev/UnicodeData.txt | 2 +- .../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 | 9 ++++---- .../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 | 5 +++-- 18 files changed, 65 insertions(+), 63 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index 9622408e9..fa2e5b39f 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-18.0.0.txt -# Date: 2025-11-30, 20:46:03 GMT +# Date: 2025-12-03, 19:31:11 GMT # © 2025 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2124,7 +2124,7 @@ FDC8..FDCE ; 17.0 # [7] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIG 0558 ; 18.0 # MODIFIER LETTER ARMENIAN SMALL EH 058B..058C ; 18.0 # [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI -05C8 ; 18.0 # HEBREW POINT SHEVA NA MUDGASH +05C8..05C9 ; 18.0 # [2] HEBREW POINT SHEVA NA MUDGASH..HEBREW POINT DAGESH HAZAQ MUDGASH 0984 ; 18.0 # BENGALI SIGN COMBINING ANUSVARA ABOVE 09FF ; 18.0 # BENGALI LETTER SANSKRIT BA 0B53..0B54 ; 18.0 # [2] ORIYA SIGN DOT ABOVE..ORIYA SIGN DOUBLE DOT ABOVE @@ -2166,6 +2166,6 @@ AB6C..AB6D ; 18.0 # [2] LATIN CAPITAL LETTER SCRIPT R..LATIN CAPITAL LETTER 2B81E ; 18.0 # CJK UNIFIED IDEOGRAPH-2B81E 3D000..3FC3F ; 18.0 # [11328] SEAL CHARACTER-3D000..SEAL CHARACTER-3FC3F -# Total code points: 12970 +# Total code points: 12971 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 3d45d9e86..5c5ba30ba 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-18.0.0.txt -# Date: 2025-11-30, 20:46:26 GMT +# Date: 2025-12-03, 19:31:35 GMT # © 2025 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -3120,7 +3120,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 05BF ; Case_Ignorable # Mn HEBREW POINT RAFE 05C1..05C2 ; Case_Ignorable # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT 05C4..05C5 ; Case_Ignorable # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT -05C7..05C8 ; Case_Ignorable # Mn [2] HEBREW POINT QAMATS QATAN..HEBREW POINT SHEVA NA MUDGASH +05C7..05C9 ; Case_Ignorable # Mn [3] HEBREW POINT QAMATS QATAN..HEBREW POINT DAGESH HAZAQ MUDGASH 05F4 ; Case_Ignorable # Po HEBREW PUNCTUATION GERSHAYIM 0600..0605 ; Case_Ignorable # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE 0610..061A ; Case_Ignorable # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA @@ -3609,7 +3609,7 @@ 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: 2875 +# Total code points: 2876 # ================================================ @@ -7256,7 +7256,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 05BF ; ID_Continue # Mn HEBREW POINT RAFE 05C1..05C2 ; ID_Continue # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT 05C4..05C5 ; ID_Continue # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT -05C7..05C8 ; ID_Continue # Mn [2] HEBREW POINT QAMATS QATAN..HEBREW POINT SHEVA NA MUDGASH +05C7..05C9 ; ID_Continue # Mn [3] HEBREW POINT QAMATS QATAN..HEBREW POINT DAGESH HAZAQ MUDGASH 05D0..05EA ; ID_Continue # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV 05EF..05F2 ; ID_Continue # Lo [4] HEBREW YOD TRIANGLE..HEBREW LIGATURE YIDDISH DOUBLE YOD 0610..061A ; ID_Continue # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA @@ -8651,7 +8651,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 3D000..3FC3F ; ID_Continue # Lo [11328] SEAL CHARACTER-3D000..SEAL CHARACTER-3FC3F E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 162118 +# Total code points: 162119 # ================================================ @@ -9512,7 +9512,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 05BF ; XID_Continue # Mn HEBREW POINT RAFE 05C1..05C2 ; XID_Continue # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT 05C4..05C5 ; XID_Continue # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT -05C7..05C8 ; XID_Continue # Mn [2] HEBREW POINT QAMATS QATAN..HEBREW POINT SHEVA NA MUDGASH +05C7..05C9 ; XID_Continue # Mn [3] HEBREW POINT QAMATS QATAN..HEBREW POINT DAGESH HAZAQ MUDGASH 05D0..05EA ; XID_Continue # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV 05EF..05F2 ; XID_Continue # Lo [4] HEBREW YOD TRIANGLE..HEBREW LIGATURE YIDDISH DOUBLE YOD 0610..061A ; XID_Continue # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA @@ -10912,7 +10912,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 3D000..3FC3F ; XID_Continue # Lo [11328] SEAL CHARACTER-3D000..SEAL CHARACTER-3FC3F E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 162099 +# Total code points: 162100 # ================================================ @@ -10979,7 +10979,7 @@ 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;;;; @@ -1468,6 +1467,7 @@ 05C6;HEBREW PUNCTUATION NUN HAFUKHA;Po;0;R;;;;;N;;;;; 05C7;HEBREW POINT QAMATS QATAN;Mn;18;NSM;;;;;N;;;;; 05C8;HEBREW POINT SHEVA NA MUDGASH;Mn;10;NSM;;;;;N;;;;; +05C9;HEBREW POINT DAGESH HAZAQ MUDGASH;Mn;21;NSM;;;;;N;;;;; 05D0;HEBREW LETTER ALEF;Lo;0;R;;;;;N;;;;; 05D1;HEBREW LETTER BET;Lo;0;R;;;;;N;;;;; 05D2;HEBREW LETTER GIMEL;Lo;0;R;;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index 928bd7e7e..a3db757d2 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ # VerticalOrientation-18.0.0.txt -# Date: 2025-11-30, 20:47:05 GMT +# Date: 2025-12-03, 19:32:19 GMT # © 2025 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -197,7 +197,7 @@ 05C3 ; R # Po HEBREW PUNCTUATION SOF PASUQ 05C4..05C5 ; R # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT 05C6 ; R # Po HEBREW PUNCTUATION NUN HAFUKHA -05C7..05C8 ; R # Mn [2] HEBREW POINT QAMATS QATAN..HEBREW POINT SHEVA NA MUDGASH +05C7..05C9 ; R # Mn [3] HEBREW POINT QAMATS QATAN..HEBREW POINT DAGESH HAZAQ MUDGASH 05D0..05EA ; R # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV 05EF..05F2 ; R # Lo [4] HEBREW YOD TRIANGLE..HEBREW LIGATURE YIDDISH DOUBLE YOD 05F3..05F4 ; R # Po [2] HEBREW PUNCTUATION GERESH..HEBREW PUNCTUATION GERSHAYIM diff --git a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt index aa89623be..5609e3b8e 100644 --- a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt @@ -1,5 +1,5 @@ # GraphemeBreakProperty-18.0.0.txt -# Date: 2025-11-30, 16:57:32 GMT +# Date: 2025-12-03, 19:31:44 GMT # © 2025 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -88,7 +88,7 @@ E01F0..E0FFF ; Control # Cn [3600] .. 05BF ; Extend # Mn HEBREW POINT RAFE 05C1..05C2 ; Extend # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT 05C4..05C5 ; Extend # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT -05C7..05C8 ; Extend # Mn [2] HEBREW POINT QAMATS QATAN..HEBREW POINT SHEVA NA MUDGASH +05C7..05C9 ; Extend # Mn [3] HEBREW POINT QAMATS QATAN..HEBREW POINT DAGESH HAZAQ MUDGASH 0610..061A ; Extend # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA 064B..065F ; Extend # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW 0670 ; Extend # Mn ARABIC LETTER SUPERSCRIPT ALEF @@ -509,7 +509,7 @@ 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: 2261 +# Total code points: 2262 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 0cd4159d7..9f7bd2efb 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ # SentenceBreakProperty-18.0.0.txt -# Date: 2025-11-30, 20:47:03 GMT +# Date: 2025-12-03, 19:32:17 GMT # © 2025 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -37,7 +37,7 @@ 05BF ; Extend # Mn HEBREW POINT RAFE 05C1..05C2 ; Extend # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT 05C4..05C5 ; Extend # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT -05C7..05C8 ; Extend # Mn [2] HEBREW POINT QAMATS QATAN..HEBREW POINT SHEVA NA MUDGASH +05C7..05C9 ; Extend # Mn [3] HEBREW POINT QAMATS QATAN..HEBREW POINT DAGESH HAZAQ MUDGASH 0610..061A ; Extend # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA 064B..065F ; Extend # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW 0670 ; Extend # Mn ARABIC LETTER SUPERSCRIPT ALEF @@ -604,7 +604,7 @@ 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: 2667 +# Total code points: 2668 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index a6b4de64b..f189f0f26 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-18.0.0.txt -# Date: 2025-11-30, 20:47:05 GMT +# Date: 2025-12-03, 19:32:19 GMT # © 2025 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -73,7 +73,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 05BF ; Extend # Mn HEBREW POINT RAFE 05C1..05C2 ; Extend # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT 05C4..05C5 ; Extend # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT -05C7..05C8 ; Extend # Mn [2] HEBREW POINT QAMATS QATAN..HEBREW POINT SHEVA NA MUDGASH +05C7..05C9 ; Extend # Mn [3] HEBREW POINT QAMATS QATAN..HEBREW POINT DAGESH HAZAQ MUDGASH 0610..061A ; Extend # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA 064B..065F ; Extend # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW 0670 ; Extend # Mn ARABIC LETTER SUPERSCRIPT ALEF @@ -641,7 +641,7 @@ 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: 2671 +# Total code points: 2672 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index f0308f81c..c326a12a9 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-18.0.0.txt -# Date: 2025-11-30, 20:46:24 GMT +# Date: 2025-12-03, 19:31:32 GMT # © 2025 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1366,8 +1366,8 @@ FB46..FB4F ; R # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE AL 1E950..1E959 ; R # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1E95E..1E95F ; R # Po [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK -# The above property value applies to 2060 code points not listed here. -# Total code points: 3630 +# The above property value applies to 2059 code points not listed here. +# Total code points: 3629 # ================================================ @@ -2106,7 +2106,7 @@ FFFFE..FFFFF ; BN # Cn [2] .. 05BF ; NSM # Mn HEBREW POINT RAFE 05C1..05C2 ; NSM # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT 05C4..05C5 ; NSM # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT -05C7..05C8 ; NSM # Mn [2] HEBREW POINT QAMATS QATAN..HEBREW POINT SHEVA NA MUDGASH +05C7..05C9 ; NSM # Mn [3] HEBREW POINT QAMATS QATAN..HEBREW POINT DAGESH HAZAQ MUDGASH 0610..061A ; NSM # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA 064B..065F ; NSM # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW 0670 ; NSM # Mn ARABIC LETTER SUPERSCRIPT ALEF @@ -2472,7 +2472,7 @@ 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: 2085 +# Total code points: 2086 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index 401964918..e7b81e852 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-18.0.0.txt -# Date: 2025-11-30, 20:46:25 GMT +# Date: 2025-12-03, 19:31:34 GMT # © 2025 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2110,8 +2110,8 @@ 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 803808 code points not listed here. -# Total code points: 1113124 +# The above property value applies to 803807 code points not listed here. +# Total code points: 1113123 # ================================================ @@ -2348,8 +2348,9 @@ ABED ; 9 # Mn MEETEI MAYEK APUN IYEK # Canonical_Combining_Class=CCC21 05BC ; 21 # Mn HEBREW POINT DAGESH OR MAPIQ +05C9 ; 21 # Mn HEBREW POINT DAGESH HAZAQ MUDGASH -# Total code points: 1 +# Total code points: 2 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index 45b05b453..f62bb5c1e 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-18.0.0.txt -# Date: 2025-11-30, 20:46:28 GMT +# Date: 2025-12-03, 19:31:37 GMT # © 2025 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -155,7 +155,7 @@ 05C3 ; N # Po HEBREW PUNCTUATION SOF PASUQ 05C4..05C5 ; N # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT 05C6 ; N # Po HEBREW PUNCTUATION NUN HAFUKHA -05C7..05C8 ; N # Mn [2] HEBREW POINT QAMATS QATAN..HEBREW POINT SHEVA NA MUDGASH +05C7..05C9 ; N # Mn [3] HEBREW POINT QAMATS QATAN..HEBREW POINT DAGESH HAZAQ MUDGASH 05D0..05EA ; N # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV 05EF..05F2 ; N # Lo [4] HEBREW YOD TRIANGLE..HEBREW LIGATURE YIDDISH DOUBLE YOD 05F3..05F4 ; N # Po [2] HEBREW PUNCTUATION GERESH..HEBREW PUNCTUATION GERSHAYIM @@ -2162,7 +2162,7 @@ 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 758971 code points not listed here. +# The above property value applies to 758970 code points not listed here. # Total code points: 791282 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index aa796a02d..a25591905 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-18.0.0.txt -# Date: 2025-11-30, 20:46:28 GMT +# Date: 2025-12-03, 19:31:37 GMT # © 2025 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -23,7 +23,7 @@ 0530 ; Cn # 0557 ; Cn # 0590 ; Cn # -05C9..05CF ; Cn # [7] .. +05CA..05CF ; Cn # [6] .. 05EB..05EE ; Cn # [4] .. 05F5..05FF ; Cn # [11] .. 070E ; Cn # @@ -749,7 +749,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 801760 +# Total code points: 801759 # ================================================ @@ -2785,7 +2785,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 05BF ; Mn # HEBREW POINT RAFE 05C1..05C2 ; Mn # [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT 05C4..05C5 ; Mn # [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT -05C7..05C8 ; Mn # [2] HEBREW POINT QAMATS QATAN..HEBREW POINT SHEVA NA MUDGASH +05C7..05C9 ; Mn # [3] HEBREW POINT QAMATS QATAN..HEBREW POINT DAGESH HAZAQ MUDGASH 0610..061A ; Mn # [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA 064B..065F ; Mn # [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW 0670 ; Mn # ARABIC LETTER SUPERSCRIPT ALEF @@ -3149,7 +3149,7 @@ 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: 2077 +# Total code points: 2078 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt index 1d726a2db..693d9c739 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt @@ -1,5 +1,5 @@ # DerivedJoiningType-18.0.0.txt -# Date: 2025-11-30, 16:57:27 GMT +# Date: 2025-12-03, 19:31:38 GMT # © 2025 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -213,7 +213,7 @@ A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA 05BF ; T # Mn HEBREW POINT RAFE 05C1..05C2 ; T # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT 05C4..05C5 ; T # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT -05C7..05C8 ; T # Mn [2] HEBREW POINT QAMATS QATAN..HEBREW POINT SHEVA NA MUDGASH +05C7..05C9 ; T # Mn [3] HEBREW POINT QAMATS QATAN..HEBREW POINT DAGESH HAZAQ MUDGASH 0610..061A ; T # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA 061C ; T # Cf ARABIC LETTER MARK 064B..065F ; T # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW @@ -596,6 +596,6 @@ 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: 2242 +# Total code points: 2243 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index f0eb74f36..238486b03 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-18.0.0.txt -# Date: 2025-11-30, 20:46:29 GMT +# Date: 2025-12-03, 19:31:39 GMT # © 2025 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -71,8 +71,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 755561 code points not listed here. -# Total code points: 893029 +# The above property value applies to 755560 code points not listed here. +# Total code points: 893028 # ================================================ @@ -1939,7 +1939,7 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 05BF ; CM # Mn HEBREW POINT RAFE 05C1..05C2 ; CM # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT 05C4..05C5 ; CM # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT -05C7..05C8 ; CM # Mn [2] HEBREW POINT QAMATS QATAN..HEBREW POINT SHEVA NA MUDGASH +05C7..05C9 ; CM # Mn [3] HEBREW POINT QAMATS QATAN..HEBREW POINT DAGESH HAZAQ MUDGASH 0610..061A ; CM # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA 061C ; CM # Cf ARABIC LETTER MARK 064B..065F ; CM # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW @@ -2454,7 +2454,7 @@ 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: 2536 +# Total code points: 2537 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 65f945aed..61e91e669 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-18.0.0.txt -# Date: 2025-11-30, 20:46:30 GMT +# Date: 2025-12-03, 19:31:39 GMT # © 2025 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1442,6 +1442,7 @@ 05C6 ; HEBREW PUNCTUATION NUN HAFUKHA 05C7 ; HEBREW POINT QAMATS QATAN 05C8 ; HEBREW POINT SHEVA NA MUDGASH +05C9 ; HEBREW POINT DAGESH HAZAQ MUDGASH 05D0 ; HEBREW LETTER ALEF 05D1 ; HEBREW LETTER BET 05D2 ; HEBREW LETTER GIMEL @@ -46545,6 +46546,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 172771 +# Total code points: 172772 # EOF From 5c8a83ae8eb245d491b9bac09c7ce765e6ef357a Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 3 Dec 2025 20:46:52 +0100 Subject: [PATCH 6/9] A test --- .../text/UCD/AdditionComparisons/248.txt | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100644 unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/248.txt diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/248.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/248.txt new file mode 100644 index 000000000..e3b66472c --- /dev/null +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/248.txt @@ -0,0 +1,18 @@ +# Hebrew: DAGESH HAZAQ MUDGASH (05C9) +# https://github.com/unicode-org/utc-release-management/issues/248 + +# Names always differ. +# Age always differs since these tests are comparing additions to pre-existing characters. +Ignoring Name Age: + +# Ignore the security and IDNA properties, as these are not yet included until β. +Ignoring Confusable_MA Identifier_Status Identifier_Type Idn_Status Idn_Mapping Idn_2008 IDNA2008_Category: + +Propertywise [ + \x{05BC}\N{HEBREW POINT DAGESH OR MAPIQ} + \x{05C9}\N{HEBREW POINT DAGESH HAZAQ MUDGASH} +] AreAlike + +end Ignoring; + +end Ignoring; \ No newline at end of file From db5d4b1bdd90afb5fa87bcae54c24d7b4b800cb0 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 3 Dec 2025 21:02:11 +0100 Subject: [PATCH 7/9] Alphabetic Diacritic --- unicodetools/data/ucd/dev/DerivedCoreProperties.txt | 6 +++--- unicodetools/data/ucd/dev/PropList.txt | 10 +++++----- 2 files changed, 8 insertions(+), 8 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 5c5ba30ba..6e22c0bc0 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-18.0.0.txt -# Date: 2025-12-03, 19:31:35 GMT +# Date: 2025-12-03, 19:51:00 GMT # © 2025 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -305,7 +305,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 05BF ; Alphabetic # Mn HEBREW POINT RAFE 05C1..05C2 ; Alphabetic # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT 05C4..05C5 ; Alphabetic # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT -05C7..05C8 ; Alphabetic # Mn [2] HEBREW POINT QAMATS QATAN..HEBREW POINT SHEVA NA MUDGASH +05C7..05C9 ; Alphabetic # Mn [3] HEBREW POINT QAMATS QATAN..HEBREW POINT DAGESH HAZAQ MUDGASH 05D0..05EA ; Alphabetic # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV 05EF..05F2 ; Alphabetic # Lo [4] HEBREW YOD TRIANGLE..HEBREW LIGATURE YIDDISH DOUBLE YOD 0610..061A ; Alphabetic # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA @@ -1482,7 +1482,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 31350..33479 ; Alphabetic # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479 3D000..3FC3F ; Alphabetic # Lo [11328] SEAL CHARACTER-3D000..SEAL CHARACTER-3FC3F -# Total code points: 160268 +# Total code points: 160269 # ================================================ diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt index 29522195b..c40e1cacb 100644 --- a/unicodetools/data/ucd/dev/PropList.txt +++ b/unicodetools/data/ucd/dev/PropList.txt @@ -1,5 +1,5 @@ # PropList-18.0.0.txt -# Date: 2025-11-30, 16:57:44 GMT +# Date: 2025-12-03, 19:51:20 GMT # © 2025 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -445,7 +445,7 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 05BF ; Other_Alphabetic # Mn HEBREW POINT RAFE 05C1..05C2 ; Other_Alphabetic # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT 05C4..05C5 ; Other_Alphabetic # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT -05C7..05C8 ; Other_Alphabetic # Mn [2] HEBREW POINT QAMATS QATAN..HEBREW POINT SHEVA NA MUDGASH +05C7..05C9 ; Other_Alphabetic # Mn [3] HEBREW POINT QAMATS QATAN..HEBREW POINT DAGESH HAZAQ MUDGASH 0610..061A ; Other_Alphabetic # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA 064B..0657 ; Other_Alphabetic # Mn [13] ARABIC FATHATAN..ARABIC INVERTED DAMMA 0659..065F ; Other_Alphabetic # Mn [7] ARABIC ZWARAKAY..ARABIC WAVY HAMZA BELOW @@ -871,7 +871,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 1F150..1F169 ; Other_Alphabetic # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Other_Alphabetic # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 1513 +# Total code points: 1514 # ================================================ @@ -937,7 +937,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM 05BF ; Diacritic # Mn HEBREW POINT RAFE 05C1..05C2 ; Diacritic # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT 05C4..05C5 ; Diacritic # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT -05C7..05C8 ; Diacritic # Mn [2] HEBREW POINT QAMATS QATAN..HEBREW POINT SHEVA NA MUDGASH +05C7..05C9 ; Diacritic # Mn [3] HEBREW POINT QAMATS QATAN..HEBREW POINT DAGESH HAZAQ MUDGASH 064B..0652 ; Diacritic # Mn [8] ARABIC FATHATAN..ARABIC SUKUN 0657..0658 ; Diacritic # Mn [2] ARABIC INVERTED DAMMA..ARABIC MARK NOON GHUNNA 06DF..06E0 ; Diacritic # Mn [2] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH UPRIGHT RECTANGULAR ZERO @@ -1179,7 +1179,7 @@ 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: 1317 +# Total code points: 1318 # ================================================ From 6bcd69238feb3afa04c2f04a1cb1890e7f2dc38a Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 3 Dec 2025 21:05:51 +0100 Subject: [PATCH 8/9] Ignore Unicode_1_Name --- .../resources/org/unicode/text/UCD/AdditionComparisons/248.txt | 2 ++ 1 file changed, 2 insertions(+) diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/248.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/248.txt index e3b66472c..c6d61b73a 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/248.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/248.txt @@ -8,10 +8,12 @@ Ignoring Name Age: # Ignore the security and IDNA properties, as these are not yet included until β. Ignoring Confusable_MA Identifier_Status Identifier_Type Idn_Status Idn_Mapping Idn_2008 IDNA2008_Category: +Ignoring Unicode_1_Name # U+05BC was called HEBREW POINT DAGESH. Propertywise [ \x{05BC}\N{HEBREW POINT DAGESH OR MAPIQ} \x{05C9}\N{HEBREW POINT DAGESH HAZAQ MUDGASH} ] AreAlike +end Ignoring; end Ignoring; From 1e65c5624a129e87f35bd68ffb43deb6c656fd17 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 3 Dec 2025 21:23:16 +0100 Subject: [PATCH 9/9] syntax error --- .../resources/org/unicode/text/UCD/AdditionComparisons/248.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/248.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/248.txt index c6d61b73a..6733660a2 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/248.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/248.txt @@ -8,7 +8,7 @@ Ignoring Name Age: # Ignore the security and IDNA properties, as these are not yet included until β. Ignoring Confusable_MA Identifier_Status Identifier_Type Idn_Status Idn_Mapping Idn_2008 IDNA2008_Category: -Ignoring Unicode_1_Name # U+05BC was called HEBREW POINT DAGESH. +Ignoring Unicode_1_Name: # U+05BC was called HEBREW POINT DAGESH. Propertywise [ \x{05BC}\N{HEBREW POINT DAGESH OR MAPIQ} \x{05C9}\N{HEBREW POINT DAGESH HAZAQ MUDGASH}