From 5a4f2af1ea308090b86d9ac5db10c477da48328a Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 23 Apr 2024 14:41:15 +0200 Subject: [PATCH 1/6] UnicodeData.txt lines from L2/24-107 --- unicodetools/data/ucd/dev/UnicodeData.txt | 3 +++ 1 file changed, 3 insertions(+) diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 08593a319..80aecd85a 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -1,3 +1,6 @@ +0558;MODIFIER LETTER ARMENIAN SMALL EH;Lm;0;L; 0567;;;;N;;;;; +055B;MODIFIER LETTER ARMENIAN SMALL INI;Lm;0;L; 056B;;;;N;;;;; +055C;MODIFIER LETTER ARMENIAN SMALL YI;Lm;0;L; 0575;;;;N;;;;; 0000;;Cc;0;BN;;;;;N;NULL;;;; 0001;;Cc;0;BN;;;;;N;START OF HEADING;;;; 0002;;Cc;0;BN;;;;;N;START OF TEXT;;;; From d55d3a691ed60ebcf7065610b2945497e7883db0 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 23 Apr 2024 14:30:45 +0200 Subject: [PATCH 2/6] lb=AL per L2/24-107 --- unicodetools/data/ucd/dev/LineBreak.txt | 3 +++ 1 file changed, 3 insertions(+) diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 1d8bd89ec..9d8c3f753 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,3 +1,6 @@ +0558;AL +055B;AL +055C;AL # LineBreak-16.0.0.txt # Date: 2024-02-02, 23:11:30 GMT # © 2024 Unicode®, Inc. From 9ac1030f8eaad90db9569064781be1538cd4a9c7 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 23 Apr 2024 14:31:55 +0200 Subject: [PATCH 3/6] Armenian --- unicodetools/data/ucd/dev/Scripts.txt | 3 +++ 1 file changed, 3 insertions(+) diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 2e0b4fd4b..9d278cb8c 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,3 +1,6 @@ +0558;Armenian +055B;Armenian +055C;Armenian # Scripts-16.0.0.txt # Date: 2024-02-02, 23:11:49 GMT # © 2024 Unicode®, Inc. From 2ef4430e8525928b074239501a03aecac22c2cff Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 23 Apr 2024 14:33:55 +0200 Subject: [PATCH 4/6] Other_Lowercase Diacritic --- unicodetools/data/ucd/dev/PropList.txt | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt index 1e3e2912b..a70d2537a 100644 --- a/unicodetools/data/ucd/dev/PropList.txt +++ b/unicodetools/data/ucd/dev/PropList.txt @@ -880,7 +880,9 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM # Total code points: 106477 # ================================================ - +0558;Diacritic +055B;Diacritic +055C;Diacritic 005E ; Diacritic # Sk CIRCUMFLEX ACCENT 0060 ; Diacritic # Sk GRAVE ACCENT 00A8 ; Diacritic # Sk DIAERESIS @@ -1192,7 +1194,9 @@ FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND # Total code points: 59 # ================================================ - +0558;Other_Lowercase +055B;Other_Lowercase +055C;Other_Lowercase 00AA ; Other_Lowercase # Lo FEMININE ORDINAL INDICATOR 00BA ; Other_Lowercase # Lo MASCULINE ORDINAL INDICATOR 02B0..02B8 ; Other_Lowercase # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y From c44977e3771e9884f68f2d01467078d4b0f7c1aa Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 23 Apr 2024 14:48:40 +0200 Subject: [PATCH 5/6] Wrong code points in the UnicodeData.txt lines from L2/24-107 --- unicodetools/data/ucd/dev/LineBreak.txt | 4 ++-- unicodetools/data/ucd/dev/PropList.txt | 8 ++++---- unicodetools/data/ucd/dev/Scripts.txt | 4 ++-- unicodetools/data/ucd/dev/UnicodeData.txt | 4 ++-- 4 files changed, 10 insertions(+), 10 deletions(-) diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 9d8c3f753..14e3788bf 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,6 +1,6 @@ 0558;AL -055B;AL -055C;AL +058B;AL +058C;AL # LineBreak-16.0.0.txt # Date: 2024-02-02, 23:11:30 GMT # © 2024 Unicode®, Inc. diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt index a70d2537a..21f26c3bf 100644 --- a/unicodetools/data/ucd/dev/PropList.txt +++ b/unicodetools/data/ucd/dev/PropList.txt @@ -881,8 +881,8 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM # ================================================ 0558;Diacritic -055B;Diacritic -055C;Diacritic +058B;Diacritic +058C;Diacritic 005E ; Diacritic # Sk CIRCUMFLEX ACCENT 0060 ; Diacritic # Sk GRAVE ACCENT 00A8 ; Diacritic # Sk DIAERESIS @@ -1195,8 +1195,8 @@ FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND # ================================================ 0558;Other_Lowercase -055B;Other_Lowercase -055C;Other_Lowercase +058B;Other_Lowercase +058C;Other_Lowercase 00AA ; Other_Lowercase # Lo FEMININE ORDINAL INDICATOR 00BA ; Other_Lowercase # Lo MASCULINE ORDINAL INDICATOR 02B0..02B8 ; Other_Lowercase # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 9d278cb8c..bcc966421 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,6 +1,6 @@ 0558;Armenian -055B;Armenian -055C;Armenian +058B;Armenian +058C;Armenian # Scripts-16.0.0.txt # Date: 2024-02-02, 23:11:49 GMT # © 2024 Unicode®, Inc. diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 80aecd85a..89cfd5428 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -1,6 +1,6 @@ 0558;MODIFIER LETTER ARMENIAN SMALL EH;Lm;0;L; 0567;;;;N;;;;; -055B;MODIFIER LETTER ARMENIAN SMALL INI;Lm;0;L; 056B;;;;N;;;;; -055C;MODIFIER LETTER ARMENIAN SMALL YI;Lm;0;L; 0575;;;;N;;;;; +058B;MODIFIER LETTER ARMENIAN SMALL INI;Lm;0;L; 056B;;;;N;;;;; +058C;MODIFIER LETTER ARMENIAN SMALL YI;Lm;0;L; 0575;;;;N;;;;; 0000;;Cc;0;BN;;;;;N;NULL;;;; 0001;;Cc;0;BN;;;;;N;START OF HEADING;;;; 0002;;Cc;0;BN;;;;;N;START OF TEXT;;;; From afb5a6c854892e0442651fe7f80a16588c7ed985 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 23 Apr 2024 14:51:26 +0200 Subject: [PATCH 6/6] Regenerate UCD --- unicodetools/data/ucd/dev/DerivedAge.txt | 6 ++- .../data/ucd/dev/DerivedCoreProperties.txt | 45 ++++++++++++------- .../ucd/dev/DerivedNormalizationProps.txt | 24 +++++++--- unicodetools/data/ucd/dev/EastAsianWidth.txt | 5 ++- unicodetools/data/ucd/dev/LineBreak.txt | 8 ++-- .../data/ucd/dev/NormalizationTest.txt | 5 ++- unicodetools/data/ucd/dev/PropList.txt | 19 ++++---- unicodetools/data/ucd/dev/Scripts.txt | 10 ++--- unicodetools/data/ucd/dev/UnicodeData.txt | 6 +-- .../data/ucd/dev/VerticalOrientation.txt | 5 ++- .../dev/auxiliary/SentenceBreakProperty.txt | 6 ++- .../ucd/dev/auxiliary/WordBreakProperty.txt | 7 +-- .../ucd/dev/extracted/DerivedBidiClass.txt | 7 +-- .../dev/extracted/DerivedCombiningClass.txt | 7 +-- .../extracted/DerivedDecompositionType.txt | 6 ++- .../dev/extracted/DerivedEastAsianWidth.txt | 7 +-- .../dev/extracted/DerivedGeneralCategory.txt | 12 ++--- .../ucd/dev/extracted/DerivedLineBreak.txt | 11 ++--- .../data/ucd/dev/extracted/DerivedName.txt | 7 ++- 19 files changed, 120 insertions(+), 83 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index d116dccaa..3e4b706f5 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, 12:50:09 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 @@ -2009,6 +2009,8 @@ FDFE..FDFF ; 14.0 # [2] ARABIC LIGATURE SUBHAANAHU WA TAAALAA..ARABIC LIGAT # Newly assigned in Unicode 16.0.0 (September, 2024) +0558 ; 16.0 # MODIFIER LETTER ARMENIAN SMALL EH +058B..058C ; 16.0 # [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 0897 ; 16.0 # ARABIC PEPET 0C5C ; 16.0 # TELUGU ARCHAIC SHRII 0CDC ; 16.0 # KANNADA ARCHAIC SHRII @@ -2059,6 +2061,6 @@ 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: 5190 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 1e054c4f2..6e6e28e67 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, 12:50:29 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 @@ -296,8 +296,9 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 03F7..0481 ; Alphabetic # L& [139] GREEK CAPITAL LETTER SHO..CYRILLIC SMALL LETTER KOPPA 048A..052F ; Alphabetic # L& [166] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EL WITH DESCENDER 0531..0556 ; Alphabetic # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH -0559 ; Alphabetic # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING +0558..0559 ; Alphabetic # Lm [2] MODIFIER LETTER ARMENIAN SMALL EH..ARMENIAN MODIFIER LETTER LEFT HALF RING 0560..0588 ; Alphabetic # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE +058B..058C ; Alphabetic # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 05B0..05BD ; Alphabetic # Mn [14] HEBREW POINT SHEVA..HEBREW POINT METEG 05BF ; Alphabetic # Mn HEBREW POINT RAFE 05C1..05C2 ; Alphabetic # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT @@ -1441,7 +1442,7 @@ 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: 142761 +# Total code points: 142764 # ================================================ @@ -1724,7 +1725,9 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 052B ; Lowercase # L& CYRILLIC SMALL LETTER DZZHE 052D ; Lowercase # L& CYRILLIC SMALL LETTER DCHE 052F ; Lowercase # L& CYRILLIC SMALL LETTER EL WITH DESCENDER +0558 ; Lowercase # Lm MODIFIER LETTER ARMENIAN SMALL EH 0560..0588 ; Lowercase # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE +058B..058C ; Lowercase # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 10D0..10FA ; Lowercase # L& [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN 10FC ; Lowercase # Lm MODIFIER LETTER GEORGIAN NAR 10FD..10FF ; Lowercase # L& [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN @@ -2139,7 +2142,7 @@ FF41..FF5A ; Lowercase # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 1E030..1E06D ; Lowercase # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E922..1E943 ; Lowercase # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2569 +# Total code points: 2572 # ================================================ @@ -2839,7 +2842,9 @@ FF21..FF3A ; Uppercase # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH 03F7..0481 ; Cased # L& [139] GREEK CAPITAL LETTER SHO..CYRILLIC SMALL LETTER KOPPA 048A..052F ; Cased # L& [166] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EL WITH DESCENDER 0531..0556 ; Cased # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH +0558 ; Cased # Lm MODIFIER LETTER ARMENIAN SMALL EH 0560..0588 ; Cased # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE +058B..058C ; Cased # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 10A0..10C5 ; Cased # L& [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE 10C7 ; Cased # L& GEORGIAN CAPITAL LETTER YN 10CD ; Cased # L& GEORGIAN CAPITAL LETTER AEN @@ -2988,7 +2993,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1F150..1F169 ; Cased # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Cased # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 4578 +# Total code points: 4581 # ================================================ @@ -3027,8 +3032,9 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 0387 ; Case_Ignorable # Po GREEK ANO TELEIA 0483..0487 ; Case_Ignorable # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE 0488..0489 ; Case_Ignorable # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN -0559 ; Case_Ignorable # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING +0558..0559 ; Case_Ignorable # Lm [2] MODIFIER LETTER ARMENIAN SMALL EH..ARMENIAN MODIFIER LETTER LEFT HALF RING 055F ; Case_Ignorable # Po ARMENIAN ABBREVIATION MARK +058B..058C ; Case_Ignorable # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 0591..05BD ; Case_Ignorable # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG 05BF ; Case_Ignorable # Mn HEBREW POINT RAFE 05C1..05C2 ; Case_Ignorable # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT @@ -3505,7 +3511,7 @@ 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: 2752 # ================================================ @@ -6231,8 +6237,9 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 03F7..0481 ; ID_Start # L& [139] GREEK CAPITAL LETTER SHO..CYRILLIC SMALL LETTER KOPPA 048A..052F ; ID_Start # L& [166] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EL WITH DESCENDER 0531..0556 ; ID_Start # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH -0559 ; ID_Start # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING +0558..0559 ; ID_Start # Lm [2] MODIFIER LETTER ARMENIAN SMALL EH..ARMENIAN MODIFIER LETTER LEFT HALF RING 0560..0588 ; ID_Start # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE +058B..058C ; ID_Start # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 05D0..05EA ; ID_Start # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV 05EF..05F2 ; ID_Start # Lo [4] HEBREW YOD TRIANGLE..HEBREW LIGATURE YIDDISH DOUBLE YOD 0620..063F ; ID_Start # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE @@ -6962,7 +6969,7 @@ 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: 141271 +# Total code points: 141274 # ================================================ @@ -7015,8 +7022,9 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0483..0487 ; ID_Continue # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE 048A..052F ; ID_Continue # L& [166] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EL WITH DESCENDER 0531..0556 ; ID_Continue # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH -0559 ; ID_Continue # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING +0558..0559 ; ID_Continue # Lm [2] MODIFIER LETTER ARMENIAN SMALL EH..ARMENIAN MODIFIER LETTER LEFT HALF RING 0560..0588 ; ID_Continue # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE +058B..058C ; ID_Continue # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 0591..05BD ; ID_Continue # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG 05BF ; ID_Continue # Mn HEBREW POINT RAFE 05C1..05C2 ; ID_Continue # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT @@ -8370,7 +8378,7 @@ 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: 144546 # ================================================ @@ -8413,8 +8421,9 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 03F7..0481 ; XID_Start # L& [139] GREEK CAPITAL LETTER SHO..CYRILLIC SMALL LETTER KOPPA 048A..052F ; XID_Start # L& [166] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EL WITH DESCENDER 0531..0556 ; XID_Start # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH -0559 ; XID_Start # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING +0558..0559 ; XID_Start # Lm [2] MODIFIER LETTER ARMENIAN SMALL EH..ARMENIAN MODIFIER LETTER LEFT HALF RING 0560..0588 ; XID_Start # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE +058B..058C ; XID_Start # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 05D0..05EA ; XID_Start # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV 05EF..05F2 ; XID_Start # Lo [4] HEBREW YOD TRIANGLE..HEBREW LIGATURE YIDDISH DOUBLE YOD 0620..063F ; XID_Start # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE @@ -9148,7 +9157,7 @@ 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: 141248 +# Total code points: 141251 # ================================================ @@ -9197,8 +9206,9 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0483..0487 ; XID_Continue # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE 048A..052F ; XID_Continue # L& [166] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EL WITH DESCENDER 0531..0556 ; XID_Continue # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH -0559 ; XID_Continue # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING +0558..0559 ; XID_Continue # Lm [2] MODIFIER LETTER ARMENIAN SMALL EH..ARMENIAN MODIFIER LETTER LEFT HALF RING 0560..0588 ; XID_Continue # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE +058B..058C ; XID_Continue # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 0591..05BD ; XID_Continue # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG 05BF ; XID_Continue # Mn HEBREW POINT RAFE 05C1..05C2 ; XID_Continue # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT @@ -10557,7 +10567,7 @@ 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: 144527 # ================================================ @@ -11125,11 +11135,12 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 0482 ; Grapheme_Base # So CYRILLIC THOUSANDS SIGN 048A..052F ; Grapheme_Base # L& [166] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EL WITH DESCENDER 0531..0556 ; Grapheme_Base # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH -0559 ; Grapheme_Base # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING +0558..0559 ; Grapheme_Base # Lm [2] MODIFIER LETTER ARMENIAN SMALL EH..ARMENIAN MODIFIER LETTER LEFT HALF RING 055A..055F ; Grapheme_Base # Po [6] ARMENIAN APOSTROPHE..ARMENIAN ABBREVIATION MARK 0560..0588 ; Grapheme_Base # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE 0589 ; Grapheme_Base # Po ARMENIAN FULL STOP 058A ; Grapheme_Base # Pd ARMENIAN HYPHEN +058B..058C ; Grapheme_Base # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 058D..058E ; Grapheme_Base # So [2] RIGHT-FACING ARMENIAN ETERNITY SIGN..LEFT-FACING ARMENIAN ETERNITY SIGN 058F ; Grapheme_Base # Sc ARMENIAN DRAM SIGN 05BE ; Grapheme_Base # Pd HEBREW PUNCTUATION MAQAF @@ -12811,7 +12822,7 @@ 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: 152740 +# Total code points: 152743 # ================================================ diff --git a/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt b/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt index b526bd1d0..96f8704b4 100644 --- a/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt +++ b/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt @@ -1,5 +1,5 @@ # DerivedNormalizationProps-16.0.0.txt -# Date: 2024-02-02, 23:11:27 GMT +# Date: 2024-04-23, 12:50:32 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 @@ -1266,7 +1266,9 @@ FB46..FB4E ; NFC_QC; N # Lo [9] HEBREW LETTER TSADI WITH DAGESH..HEBREW LET 04E2..04E7 ; NFKD_QC; N # L& [6] CYRILLIC CAPITAL LETTER I WITH MACRON..CYRILLIC SMALL LETTER O WITH DIAERESIS 04EA..04F5 ; NFKD_QC; N # L& [12] CYRILLIC CAPITAL LETTER BARRED O WITH DIAERESIS..CYRILLIC SMALL LETTER CHE WITH DIAERESIS 04F8..04F9 ; NFKD_QC; N # L& [2] CYRILLIC CAPITAL LETTER YERU WITH DIAERESIS..CYRILLIC SMALL LETTER YERU WITH DIAERESIS +0558 ; NFKD_QC; N # Lm MODIFIER LETTER ARMENIAN SMALL EH 0587 ; NFKD_QC; N # L& ARMENIAN SMALL LIGATURE ECH YIWN +058B..058C ; NFKD_QC; N # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 0622..0626 ; NFKD_QC; N # Lo [5] ARABIC LETTER ALEF WITH MADDA ABOVE..ARABIC LETTER YEH WITH HAMZA ABOVE 0675..0678 ; NFKD_QC; N # Lo [4] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER HIGH HAMZA YEH 06C0 ; NFKD_QC; N # Lo ARABIC LETTER HEH WITH YEH ABOVE @@ -1753,7 +1755,7 @@ FFED..FFEE ; NFKD_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 1FBF0..1FBF9 ; NFKD_QC; N # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE 2F800..2FA1D ; NFKD_QC; N # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 17085 +# Total code points: 17088 # ================================================ @@ -1799,7 +1801,9 @@ FFED..FFEE ; NFKD_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 03F0..03F2 ; NFKC_QC; N # L& [3] GREEK KAPPA SYMBOL..GREEK LUNATE SIGMA SYMBOL 03F4..03F5 ; NFKC_QC; N # L& [2] GREEK CAPITAL THETA SYMBOL..GREEK LUNATE EPSILON SYMBOL 03F9 ; NFKC_QC; N # L& GREEK CAPITAL LUNATE SIGMA SYMBOL +0558 ; NFKC_QC; N # Lm MODIFIER LETTER ARMENIAN SMALL EH 0587 ; NFKC_QC; N # L& ARMENIAN SMALL LIGATURE ECH YIWN +058B..058C ; NFKC_QC; N # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 0675..0678 ; NFKC_QC; N # Lo [4] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER HIGH HAMZA YEH 0958..095F ; NFKC_QC; N # Lo [8] DEVANAGARI LETTER QA..DEVANAGARI LETTER YYA 09DC..09DD ; NFKC_QC; N # Lo [2] BENGALI LETTER RRA..BENGALI LETTER RHA @@ -2164,7 +2168,7 @@ FFED..FFEE ; NFKC_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 1FBF0..1FBF9 ; NFKC_QC; N # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE 2F800..2FA1D ; NFKC_QC; N # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 4964 +# Total code points: 4967 # ================================================ @@ -3520,7 +3524,10 @@ FFE3 ; Expands_On_NFKC # Sk FULLWIDTH MACRON 0554 ; NFKC_CF; 0584 # L& ARMENIAN CAPITAL LETTER KEH 0555 ; NFKC_CF; 0585 # L& ARMENIAN CAPITAL LETTER OH 0556 ; NFKC_CF; 0586 # L& ARMENIAN CAPITAL LETTER FEH +0558 ; NFKC_CF; 0567 # Lm MODIFIER LETTER ARMENIAN SMALL EH 0587 ; NFKC_CF; 0565 0582 # L& ARMENIAN SMALL LIGATURE ECH YIWN +058B ; NFKC_CF; 056B # Lm MODIFIER LETTER ARMENIAN SMALL INI +058C ; NFKC_CF; 0575 # Lm MODIFIER LETTER ARMENIAN SMALL YI 061C ; NFKC_CF; # Cf ARABIC LETTER MARK 0675 ; NFKC_CF; 0627 0674 # Lo ARABIC LETTER HIGH HAMZA ALEF 0676 ; NFKC_CF; 0648 0674 # Lo ARABIC LETTER HIGH HAMZA WAW @@ -9148,7 +9155,7 @@ E0080..E00FF ; NFKC_CF; # Cn [128] .... -# Total code points: 10554 +# Total code points: 10557 # ================================================ @@ -9690,7 +9697,10 @@ E01F0..E0FFF ; NFKC_CF; # Cn [3600] ...... -# Total code points: 10516 +# Total code points: 10519 # ================================================ @@ -15581,7 +15591,9 @@ E01F0..E0FFF ; NFKC_SCF; # Cn [3600] ...... -# Total code points: 10554 +# Total code points: 10557 # EOF diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index dccf9c5a7..51e9f5fe0 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: 2024-02-02, 23:11:29 GMT +# Date: 2024-04-23, 12:50:34 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 @@ -244,11 +244,12 @@ 048A..04FF ; N # L& [118] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER HA WITH STROKE 0500..052F ; N # L& [48] CYRILLIC CAPITAL LETTER KOMI DE..CYRILLIC SMALL LETTER EL WITH DESCENDER 0531..0556 ; N # Lu [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH -0559 ; N # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING +0558..0559 ; N # Lm [2] MODIFIER LETTER ARMENIAN SMALL EH..ARMENIAN MODIFIER LETTER LEFT HALF RING 055A..055F ; N # Po [6] ARMENIAN APOSTROPHE..ARMENIAN ABBREVIATION MARK 0560..0588 ; N # Ll [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE 0589 ; N # Po ARMENIAN FULL STOP 058A ; N # Pd ARMENIAN HYPHEN +058B..058C ; N # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 058D..058E ; N # So [2] RIGHT-FACING ARMENIAN ETERNITY SIGN..LEFT-FACING ARMENIAN ETERNITY SIGN 058F ; N # Sc ARMENIAN DRAM SIGN 0591..05BD ; N # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 14e3788bf..bf22e3b41 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,8 +1,5 @@ -0558;AL -058B;AL -058C;AL # LineBreak-16.0.0.txt -# Date: 2024-02-02, 23:11:30 GMT +# Date: 2024-04-23, 12:50:35 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 @@ -189,11 +186,12 @@ 048A..04FF ; AL # L& [118] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER HA WITH STROKE 0500..052F ; AL # L& [48] CYRILLIC CAPITAL LETTER KOMI DE..CYRILLIC SMALL LETTER EL WITH DESCENDER 0531..0556 ; AL # Lu [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH -0559 ; AL # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING +0558..0559 ; AL # Lm [2] MODIFIER LETTER ARMENIAN SMALL EH..ARMENIAN MODIFIER LETTER LEFT HALF RING 055A..055F ; AL # Po [6] ARMENIAN APOSTROPHE..ARMENIAN ABBREVIATION MARK 0560..0588 ; AL # Ll [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE 0589 ; IS # Po ARMENIAN FULL STOP 058A ; BA # Pd ARMENIAN HYPHEN +058B..058C ; AL # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 058D..058E ; AL # So [2] RIGHT-FACING ARMENIAN ETERNITY SIGN..LEFT-FACING ARMENIAN ETERNITY SIGN 058F ; PR # Sc ARMENIAN DRAM SIGN 0591..05BD ; CM # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG diff --git a/unicodetools/data/ucd/dev/NormalizationTest.txt b/unicodetools/data/ucd/dev/NormalizationTest.txt index 1e88cecdf..4f458b71a 100644 --- a/unicodetools/data/ucd/dev/NormalizationTest.txt +++ b/unicodetools/data/ucd/dev/NormalizationTest.txt @@ -1,5 +1,5 @@ # NormalizationTest-16.0.0.txt -# Date: 2024-02-02, 23:11:32 GMT +# Date: 2024-04-23, 12:50:38 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 @@ -489,7 +489,10 @@ FEFA 0334;FEFA 0334;FEFA 0334;0644 0625 0334;0644 0627 0334 0655; # (ﻺ◌̴; 04F5;04F5;0447 0308;04F5;0447 0308; # (ӵ; ӵ; ч◌̈; ӵ; ч◌̈; ) CYRILLIC SMALL LETTER CHE WITH DIAERESIS 04F8;04F8;042B 0308;04F8;042B 0308; # (Ӹ; Ӹ; Ы◌̈; Ӹ; Ы◌̈; ) CYRILLIC CAPITAL LETTER YERU WITH DIAERESIS 04F9;04F9;044B 0308;04F9;044B 0308; # (ӹ; ӹ; ы◌̈; ӹ; ы◌̈; ) CYRILLIC SMALL LETTER YERU WITH DIAERESIS +0558;0558;0558;0567;0567; # (՘; ՘; ՘; է; է; ) MODIFIER LETTER ARMENIAN SMALL EH 0587;0587;0587;0565 0582;0565 0582; # (և; և; և; եւ; եւ; ) ARMENIAN SMALL LIGATURE ECH YIWN +058B;058B;058B;056B;056B; # (֋; ֋; ֋; ի; ի; ) MODIFIER LETTER ARMENIAN SMALL INI +058C;058C;058C;0575;0575; # (֌; ֌; ֌; յ; յ; ) MODIFIER LETTER ARMENIAN SMALL YI 0622;0622;0627 0653;0622;0627 0653; # (آ; آ; ا◌ٓ; آ; ا◌ٓ; ) ARABIC LETTER ALEF WITH MADDA ABOVE 0623;0623;0627 0654;0623;0627 0654; # (أ; أ; ا◌ٔ; أ; ا◌ٔ; ) ARABIC LETTER ALEF WITH HAMZA ABOVE 0624;0624;0648 0654;0624;0648 0654; # (ؤ; ؤ; و◌ٔ; ؤ; و◌ٔ; ) ARABIC LETTER WAW WITH HAMZA ABOVE diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt index 21f26c3bf..f9d711042 100644 --- a/unicodetools/data/ucd/dev/PropList.txt +++ b/unicodetools/data/ucd/dev/PropList.txt @@ -1,5 +1,5 @@ # PropList-16.0.0.txt -# Date: 2024-03-12, 13:28:44 GMT +# Date: 2024-04-23, 12:50:45 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 @@ -880,9 +880,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM # Total code points: 106477 # ================================================ -0558;Diacritic -058B;Diacritic -058C;Diacritic + 005E ; Diacritic # Sk CIRCUMFLEX ACCENT 0060 ; Diacritic # Sk GRAVE ACCENT 00A8 ; Diacritic # Sk DIAERESIS @@ -908,7 +906,8 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM 037A ; Diacritic # Lm GREEK YPOGEGRAMMENI 0384..0385 ; Diacritic # Sk [2] GREEK TONOS..GREEK DIALYTIKA TONOS 0483..0487 ; Diacritic # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE -0559 ; Diacritic # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING +0558..0559 ; Diacritic # Lm [2] MODIFIER LETTER ARMENIAN SMALL EH..ARMENIAN MODIFIER LETTER LEFT HALF RING +058B..058C ; Diacritic # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 0591..05A1 ; Diacritic # Mn [17] HEBREW ACCENT ETNAHTA..HEBREW ACCENT PAZER 05A3..05BD ; Diacritic # Mn [27] HEBREW ACCENT MUNAH..HEBREW POINT METEG 05BF ; Diacritic # Mn HEBREW POINT RAFE @@ -1144,7 +1143,7 @@ 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: 1178 +# Total code points: 1181 # ================================================ @@ -1194,9 +1193,7 @@ FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND # Total code points: 59 # ================================================ -0558;Other_Lowercase -058B;Other_Lowercase -058C;Other_Lowercase + 00AA ; Other_Lowercase # Lo FEMININE ORDINAL INDICATOR 00BA ; Other_Lowercase # Lo MASCULINE ORDINAL INDICATOR 02B0..02B8 ; Other_Lowercase # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y @@ -1204,6 +1201,8 @@ FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND 02E0..02E4 ; Other_Lowercase # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP 0345 ; Other_Lowercase # Mn COMBINING GREEK YPOGEGRAMMENI 037A ; Other_Lowercase # Lm GREEK YPOGEGRAMMENI +0558 ; Other_Lowercase # Lm MODIFIER LETTER ARMENIAN SMALL EH +058B..058C ; Other_Lowercase # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 10FC ; Other_Lowercase # Lm MODIFIER LETTER GEORGIAN NAR 1D2C..1D6A ; Other_Lowercase # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI 1D78 ; Other_Lowercase # Lm MODIFIER LETTER CYRILLIC EN @@ -1226,7 +1225,7 @@ AB69 ; Other_Lowercase # Lm MODIFIER LETTER SMALL TURNED W 107B2..107BA ; Other_Lowercase # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 1E030..1E06D ; Other_Lowercase # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE -# Total code points: 311 +# Total code points: 314 # ================================================ diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index bcc966421..feb7110c0 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,8 +1,5 @@ -0558;Armenian -058B;Armenian -058C;Armenian # Scripts-16.0.0.txt -# Date: 2024-02-02, 23:11:49 GMT +# Date: 2024-04-23, 12:51:08 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 @@ -799,16 +796,17 @@ FE2E..FE2F ; Cyrillic # Mn [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBININ # ================================================ 0531..0556 ; Armenian # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH -0559 ; Armenian # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING +0558..0559 ; Armenian # Lm [2] MODIFIER LETTER ARMENIAN SMALL EH..ARMENIAN MODIFIER LETTER LEFT HALF RING 055A..055F ; Armenian # Po [6] ARMENIAN APOSTROPHE..ARMENIAN ABBREVIATION MARK 0560..0588 ; Armenian # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE 0589 ; Armenian # Po ARMENIAN FULL STOP 058A ; Armenian # Pd ARMENIAN HYPHEN +058B..058C ; Armenian # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 058D..058E ; Armenian # So [2] RIGHT-FACING ARMENIAN ETERNITY SIGN..LEFT-FACING ARMENIAN ETERNITY SIGN 058F ; Armenian # Sc ARMENIAN DRAM SIGN FB13..FB17 ; Armenian # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH -# Total code points: 96 +# Total code points: 99 # ================================================ diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 89cfd5428..274a43c83 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -1,6 +1,3 @@ -0558;MODIFIER LETTER ARMENIAN SMALL EH;Lm;0;L; 0567;;;;N;;;;; -058B;MODIFIER LETTER ARMENIAN SMALL INI;Lm;0;L; 056B;;;;N;;;;; -058C;MODIFIER LETTER ARMENIAN SMALL YI;Lm;0;L; 0575;;;;N;;;;; 0000;;Cc;0;BN;;;;;N;NULL;;;; 0001;;Cc;0;BN;;;;;N;START OF HEADING;;;; 0002;;Cc;0;BN;;;;;N;START OF TEXT;;;; @@ -1358,6 +1355,7 @@ 0554;ARMENIAN CAPITAL LETTER KEH;Lu;0;L;;;;;N;;;;0584; 0555;ARMENIAN CAPITAL LETTER OH;Lu;0;L;;;;;N;;;;0585; 0556;ARMENIAN CAPITAL LETTER FEH;Lu;0;L;;;;;N;;;;0586; +0558;MODIFIER LETTER ARMENIAN SMALL EH;Lm;0;L; 0567;;;;N;;;;; 0559;ARMENIAN MODIFIER LETTER LEFT HALF RING;Lm;0;L;;;;;N;;;;; 055A;ARMENIAN APOSTROPHE;Po;0;L;;;;;N;ARMENIAN MODIFIER LETTER RIGHT HALF RING;;;; 055B;ARMENIAN EMPHASIS MARK;Po;0;L;;;;;N;;;;; @@ -1408,6 +1406,8 @@ 0588;ARMENIAN SMALL LETTER YI WITH STROKE;Ll;0;L;;;;;N;;;;; 0589;ARMENIAN FULL STOP;Po;0;L;;;;;N;ARMENIAN PERIOD;;;; 058A;ARMENIAN HYPHEN;Pd;0;ON;;;;;N;;;;; +058B;MODIFIER LETTER ARMENIAN SMALL INI;Lm;0;L; 056B;;;;N;;;;; +058C;MODIFIER LETTER ARMENIAN SMALL YI;Lm;0;L; 0575;;;;N;;;;; 058D;RIGHT-FACING ARMENIAN ETERNITY SIGN;So;0;ON;;;;;N;;;;; 058E;LEFT-FACING ARMENIAN ETERNITY SIGN;So;0;ON;;;;;N;;;;; 058F;ARMENIAN DRAM SIGN;Sc;0;ET;;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index 187a0888d..d90e26b16 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, 12:51:12 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 @@ -178,11 +178,12 @@ 048A..04FF ; R # L& [118] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER HA WITH STROKE 0500..052F ; R # L& [48] CYRILLIC CAPITAL LETTER KOMI DE..CYRILLIC SMALL LETTER EL WITH DESCENDER 0531..0556 ; R # Lu [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH -0559 ; R # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING +0558..0559 ; R # Lm [2] MODIFIER LETTER ARMENIAN SMALL EH..ARMENIAN MODIFIER LETTER LEFT HALF RING 055A..055F ; R # Po [6] ARMENIAN APOSTROPHE..ARMENIAN ABBREVIATION MARK 0560..0588 ; R # Ll [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE 0589 ; R # Po ARMENIAN FULL STOP 058A ; R # Pd ARMENIAN HYPHEN +058B..058C ; R # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 058D..058E ; R # So [2] RIGHT-FACING ARMENIAN ETERNITY SIGN..LEFT-FACING ARMENIAN ETERNITY SIGN 058F ; R # Sc ARMENIAN DRAM SIGN 0591..05BD ; R # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index cec52074f..928d268d6 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, 12:51:09 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 @@ -907,7 +907,9 @@ E0001 ; Format # Cf LANGUAGE TAG 052B ; Lower # L& CYRILLIC SMALL LETTER DZZHE 052D ; Lower # L& CYRILLIC SMALL LETTER DCHE 052F ; Lower # L& CYRILLIC SMALL LETTER EL WITH DESCENDER +0558 ; Lower # Lm MODIFIER LETTER ARMENIAN SMALL EH 0560..0588 ; Lower # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE +058B..058C ; Lower # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 10FC ; Lower # Lm MODIFIER LETTER GEORGIAN NAR 13F8..13FD ; Lower # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV 1C80..1C88 ; Lower # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK @@ -1320,7 +1322,7 @@ FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1E030..1E06D ; Lower # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E922..1E943 ; Lower # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2522 +# Total code points: 2525 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index fd760073c..1a35d8e57 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, 12:51:13 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 @@ -714,11 +714,12 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 03F7..0481 ; ALetter # L& [139] GREEK CAPITAL LETTER SHO..CYRILLIC SMALL LETTER KOPPA 048A..052F ; ALetter # L& [166] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EL WITH DESCENDER 0531..0556 ; ALetter # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH -0559 ; ALetter # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING +0558..0559 ; ALetter # Lm [2] MODIFIER LETTER ARMENIAN SMALL EH..ARMENIAN MODIFIER LETTER LEFT HALF RING 055A..055C ; ALetter # Po [3] ARMENIAN APOSTROPHE..ARMENIAN EXCLAMATION MARK 055E ; ALetter # Po ARMENIAN QUESTION MARK 0560..0588 ; ALetter # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE 058A ; ALetter # Pd ARMENIAN HYPHEN +058B..058C ; ALetter # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 05F3 ; ALetter # Po HEBREW PUNCTUATION GERESH 0620..063F ; ALetter # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE 0640 ; ALetter # Lm ARABIC TATWEEL @@ -1355,7 +1356,7 @@ 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: 33793 +# Total code points: 33796 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index d991ed1b8..7a0407a90 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, 12:50:27 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 @@ -159,10 +159,11 @@ 0482 ; L # So CYRILLIC THOUSANDS SIGN 048A..052F ; L # L& [166] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EL WITH DESCENDER 0531..0556 ; L # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH -0559 ; L # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING +0558..0559 ; L # Lm [2] MODIFIER LETTER ARMENIAN SMALL EH..ARMENIAN MODIFIER LETTER LEFT HALF RING 055A..055F ; L # Po [6] ARMENIAN APOSTROPHE..ARMENIAN ABBREVIATION MARK 0560..0588 ; L # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE 0589 ; L # Po ARMENIAN FULL STOP +058B..058C ; L # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 0903 ; L # Mc DEVANAGARI SIGN VISARGA 0904..0939 ; L # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA 093B ; L # Mc DEVANAGARI VOWEL SIGN OOE @@ -1219,7 +1220,7 @@ 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. +# The above property value applies to 815346 code points not listed here. # Total code points: 1095518 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index 639fce0ae..36967f78c 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, 12:50:29 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 @@ -117,11 +117,12 @@ 0488..0489 ; 0 # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN 048A..052F ; 0 # L& [166] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EL WITH DESCENDER 0531..0556 ; 0 # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH -0559 ; 0 # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING +0558..0559 ; 0 # Lm [2] MODIFIER LETTER ARMENIAN SMALL EH..ARMENIAN MODIFIER LETTER LEFT HALF RING 055A..055F ; 0 # Po [6] ARMENIAN APOSTROPHE..ARMENIAN ABBREVIATION MARK 0560..0588 ; 0 # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE 0589 ; 0 # Po ARMENIAN FULL STOP 058A ; 0 # Pd ARMENIAN HYPHEN +058B..058C ; 0 # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 058D..058E ; 0 # So [2] RIGHT-FACING ARMENIAN ETERNITY SIGN..LEFT-FACING ARMENIAN ETERNITY SIGN 058F ; 0 # Sc ARMENIAN DRAM SIGN 05BE ; 0 # Pd HEBREW PUNCTUATION MAQAF @@ -2060,7 +2061,7 @@ 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 821576 code points not listed here. # Total code points: 1113178 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedDecompositionType.txt b/unicodetools/data/ucd/dev/extracted/DerivedDecompositionType.txt index a49462856..544159680 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedDecompositionType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedDecompositionType.txt @@ -1,5 +1,5 @@ # DerivedDecompositionType-16.0.0.txt -# Date: 2024-02-02, 23:11:25 GMT +# Date: 2024-04-23, 12:50:30 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 @@ -851,6 +851,8 @@ FEFB ; Isolated # Lo ARABIC LIGATURE LAM WITH ALEF ISOLATED FORM 00BA ; Super # Lo MASCULINE ORDINAL INDICATOR 02B0..02B8 ; Super # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y 02E0..02E4 ; Super # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP +0558 ; Super # Lm MODIFIER LETTER ARMENIAN SMALL EH +058B..058C ; Super # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 10FC ; Super # Lm MODIFIER LETTER GEORGIAN NAR 1D2C..1D2E ; Super # Lm [3] MODIFIER LETTER CAPITAL A..MODIFIER LETTER CAPITAL B 1D30..1D3A ; Super # Lm [11] MODIFIER LETTER CAPITAL D..MODIFIER LETTER CAPITAL N @@ -884,7 +886,7 @@ AB69 ; Super # Lm MODIFIER LETTER SMALL TURNED W 1E06B..1E06D ; Super # Lm [3] MODIFIER LETTER CYRILLIC SMALL ES WITH DESCENDER..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1F16A..1F16C ; Super # So [3] RAISED MC SIGN..RAISED MR SIGN -# Total code points: 249 +# Total code points: 252 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index 44585c48d..6bc1cea7c 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, 12:50:30 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 @@ -137,11 +137,12 @@ 0488..0489 ; N # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN 048A..052F ; N # L& [166] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EL WITH DESCENDER 0531..0556 ; N # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH -0559 ; N # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING +0558..0559 ; N # Lm [2] MODIFIER LETTER ARMENIAN SMALL EH..ARMENIAN MODIFIER LETTER LEFT HALF RING 055A..055F ; N # Po [6] ARMENIAN APOSTROPHE..ARMENIAN ABBREVIATION MARK 0560..0588 ; N # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE 0589 ; N # Po ARMENIAN FULL STOP 058A ; N # Pd ARMENIAN HYPHEN +058B..058C ; N # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 058D..058E ; N # So [2] RIGHT-FACING ARMENIAN ETERNITY SIGN..LEFT-FACING ARMENIAN ETERNITY SIGN 058F ; N # Sc ARMENIAN DRAM SIGN 0591..05BD ; N # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG @@ -2103,7 +2104,7 @@ 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 761094 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..608321ff3 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, 12:50:31 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 @@ -21,8 +21,7 @@ 038D ; Cn # 03A2 ; Cn # 0530 ; Cn # -0557..0558 ; Cn # [2] .. -058B..058C ; Cn # [2] .. +0557 ; Cn # 0590 ; Cn # 05C8..05CF ; Cn # [8] .. 05EB..05EE ; Cn # [4] .. @@ -747,7 +746,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819531 +# Total code points: 819528 # ================================================ @@ -2104,7 +2103,8 @@ FF41..FF5A ; Ll # [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL 02EE ; Lm # MODIFIER LETTER DOUBLE APOSTROPHE 0374 ; Lm # GREEK NUMERAL SIGN 037A ; Lm # GREEK YPOGEGRAMMENI -0559 ; Lm # ARMENIAN MODIFIER LETTER LEFT HALF RING +0558..0559 ; Lm # [2] MODIFIER LETTER ARMENIAN SMALL EH..ARMENIAN MODIFIER LETTER LEFT HALF RING +058B..058C ; Lm # [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 0640 ; Lm # ARABIC TATWEEL 06E5..06E6 ; Lm # [2] ARABIC SMALL WAW..ARABIC SMALL YEH 07F4..07F5 ; Lm # [2] NKO HIGH TONE APOSTROPHE..NKO LOW TONE APOSTROPHE @@ -2173,7 +2173,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 1E4EB ; Lm # NAG MUNDARI SIGN OJOD 1E94B ; Lm # ADLAM NASALIZATION MARK -# Total code points: 404 +# Total code points: 407 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 3a3ecf9c1..d2e6bab68 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, 12:50:32 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 757648 code points not listed here. +# Total code points: 895116 # ================================================ @@ -618,9 +618,10 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 0482 ; AL # So CYRILLIC THOUSANDS SIGN 048A..052F ; AL # L& [166] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EL WITH DESCENDER 0531..0556 ; AL # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH -0559 ; AL # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING +0558..0559 ; AL # Lm [2] MODIFIER LETTER ARMENIAN SMALL EH..ARMENIAN MODIFIER LETTER LEFT HALF RING 055A..055F ; AL # Po [6] ARMENIAN APOSTROPHE..ARMENIAN ABBREVIATION MARK 0560..0588 ; AL # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE +058B..058C ; AL # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 058D..058E ; AL # So [2] RIGHT-FACING ARMENIAN ETERNITY SIGN..LEFT-FACING ARMENIAN ETERNITY SIGN 05C0 ; AL # Po HEBREW PUNCTUATION PASEQ 05C3 ; AL # Po HEBREW PUNCTUATION SOF PASUQ @@ -1611,7 +1612,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1FB00..1FB92 ; AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBEF ; AL # So [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 26685 +# Total code points: 26688 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 4778d471e..66f6a8586 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, 12:50:32 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 @@ -1330,6 +1330,7 @@ 0554 ; ARMENIAN CAPITAL LETTER KEH 0555 ; ARMENIAN CAPITAL LETTER OH 0556 ; ARMENIAN CAPITAL LETTER FEH +0558 ; MODIFIER LETTER ARMENIAN SMALL EH 0559 ; ARMENIAN MODIFIER LETTER LEFT HALF RING 055A ; ARMENIAN APOSTROPHE 055B ; ARMENIAN EMPHASIS MARK @@ -1380,6 +1381,8 @@ 0588 ; ARMENIAN SMALL LETTER YI WITH STROKE 0589 ; ARMENIAN FULL STOP 058A ; ARMENIAN HYPHEN +058B ; MODIFIER LETTER ARMENIAN SMALL INI +058C ; MODIFIER LETTER ARMENIAN SMALL YI 058D ; RIGHT-FACING ARMENIAN ETERNITY SIGN 058E ; LEFT-FACING ARMENIAN ETERNITY SIGN 058F ; ARMENIAN DRAM SIGN @@ -45369,6 +45372,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 155000 +# Total code points: 155003 # EOF