From 6da68627c20dafcdc3e16c2f67196fa45d4cf83d Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Thu, 14 Nov 2024 19:31:45 +0100 Subject: [PATCH] Arabic double vertical bar below (#592) * UnicodeData.txt from L2/23-248 * LB=CM * Scripts.txt * Alphabetic diacritic like kasratan? * Regenerate UCD --- unicodetools/data/ucd/dev/DerivedAge.txt | 6 ++--- .../data/ucd/dev/DerivedCoreProperties.txt | 26 +++++++++---------- unicodetools/data/ucd/dev/EastAsianWidth.txt | 4 +-- unicodetools/data/ucd/dev/LineBreak.txt | 4 +-- .../data/ucd/dev/NormalizationTest.txt | 4 ++- unicodetools/data/ucd/dev/PropList.txt | 9 ++++--- unicodetools/data/ucd/dev/Scripts.txt | 6 ++--- unicodetools/data/ucd/dev/UnicodeData.txt | 1 + .../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 | 10 +++---- .../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 ++-- 19 files changed, 72 insertions(+), 67 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index 426462abd..7978c07c3 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-17.0.0.txt -# Date: 2024-11-14, 15:54:07 GMT +# Date: 2024-11-14, 16:07:50 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 and license, see https://www.unicode.org/terms_of_use.html @@ -2083,8 +2083,8 @@ FDC8..FDCE ; 17.0 # [7] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIG 10940..1095C ; 17.0 # [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10EC5..10EC7 ; 17.0 # [3] ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10ED0..10ED8 ; 17.0 # [9] ARABIC BIBLICAL END OF VERSE..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH -10EFB ; 17.0 # ARABIC SMALL LOW NOON +10EFA..10EFB ; 17.0 # [2] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW NOON -# Total code points: 106 +# Total code points: 107 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 629eaad62..0fee5fc29 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-17.0.0.txt -# Date: 2024-11-14, 15:54:32 GMT +# Date: 2024-11-14, 16:08:15 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 and license, see https://www.unicode.org/terms_of_use.html @@ -1054,7 +1054,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 10EC2..10EC4 ; Alphabetic # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; Alphabetic # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW 10EC6..10EC7 ; Alphabetic # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW -10EFB..10EFC ; Alphabetic # Mn [2] ARABIC SMALL LOW NOON..ARABIC COMBINING ALEF OVERLAY +10EFA..10EFC ; Alphabetic # Mn [3] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC COMBINING ALEF OVERLAY 10F00..10F1C ; Alphabetic # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; Alphabetic # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; Alphabetic # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -1442,7 +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: 142801 +# Total code points: 142802 # ================================================ @@ -3354,7 +3354,7 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 10D6F ; Case_Ignorable # Lm GARAY REDUPLICATION MARK 10EAB..10EAC ; Case_Ignorable # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EC5 ; Case_Ignorable # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW -10EFB..10EFF ; Case_Ignorable # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA +10EFA..10EFF ; Case_Ignorable # Mn [6] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Case_Ignorable # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; Case_Ignorable # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; Case_Ignorable # Mn BRAHMI SIGN ANUSVARA @@ -3509,7 +3509,7 @@ 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: 2781 +# Total code points: 2782 # ================================================ @@ -7912,7 +7912,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 10EC2..10EC4 ; ID_Continue # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; ID_Continue # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW 10EC6..10EC7 ; ID_Continue # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW -10EFB..10EFF ; ID_Continue # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA +10EFA..10EFF ; ID_Continue # Mn [6] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; ID_Continue # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; ID_Continue # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; ID_Continue # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -8387,7 +8387,7 @@ 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: 144612 +# Total code points: 144613 # ================================================ @@ -10102,7 +10102,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 10EC2..10EC4 ; XID_Continue # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; XID_Continue # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW 10EC6..10EC7 ; XID_Continue # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW -10EFB..10EFF ; XID_Continue # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA +10EFA..10EFF ; XID_Continue # Mn [6] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; XID_Continue # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; XID_Continue # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; XID_Continue # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -10577,7 +10577,7 @@ 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: 144593 +# Total code points: 144594 # ================================================ @@ -10895,7 +10895,7 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 10D24..10D27 ; Grapheme_Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D69..10D6D ; Grapheme_Extend # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; Grapheme_Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK -10EFB..10EFF ; Grapheme_Extend # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA +10EFA..10EFF ; Grapheme_Extend # Mn [6] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Grapheme_Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; Grapheme_Extend # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; Grapheme_Extend # Mn BRAHMI SIGN ANUSVARA @@ -11050,7 +11050,7 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. E0020..E007F ; Grapheme_Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2223 +# Total code points: 2224 # ================================================ @@ -13228,7 +13228,7 @@ FF9E..FF9F ; InCB; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HA 10D24..10D27 ; InCB; Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D69..10D6D ; InCB; Extend # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; InCB; Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK -10EFB..10EFF ; InCB; Extend # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA +10EFA..10EFF ; InCB; Extend # Mn [6] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; InCB; Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; InCB; Extend # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; InCB; Extend # Mn BRAHMI SIGN ANUSVARA @@ -13384,6 +13384,6 @@ FF9E..FF9F ; InCB; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HA E0020..E007F ; InCB; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; InCB; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2222 +# Total code points: 2223 # EOF diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index 3a0583121..abf5bdbf8 100644 --- a/unicodetools/data/ucd/dev/EastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/EastAsianWidth.txt @@ -1,5 +1,5 @@ # EastAsianWidth-17.0.0.txt -# Date: 2024-11-14, 15:54:39 GMT +# Date: 2024-11-14, 16:08:21 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 and license, see https://www.unicode.org/terms_of_use.html @@ -1969,7 +1969,7 @@ FFFD ; A # So REPLACEMENT CHARACTER 10EC6..10EC7 ; N # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10ED0 ; N # Po ARABIC BIBLICAL END OF VERSE 10ED1..10ED8 ; N # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH -10EFB..10EFF ; N # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA +10EFA..10EFF ; N # Mn [6] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; N # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; N # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF 10F27 ; N # Lo OLD SOGDIAN LIGATURE AYIN-DALETH diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 430014be1..e1f790790 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,5 @@ # LineBreak-17.0.0.txt -# Date: 2024-11-14, 15:54:40 GMT +# Date: 2024-11-14, 16:08:22 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 and license, see https://www.unicode.org/terms_of_use.html @@ -2826,7 +2826,7 @@ FFFD ; AI # So REPLACEMENT CHARACTER 10EC6..10EC7 ; AL # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10ED0 ; BA # Po ARABIC BIBLICAL END OF VERSE 10ED1..10ED8 ; AL # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH -10EFB..10EFF ; CM # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA +10EFA..10EFF ; CM # Mn [6] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; AL # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; AL # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF 10F27 ; AL # Lo OLD SOGDIAN LIGATURE AYIN-DALETH diff --git a/unicodetools/data/ucd/dev/NormalizationTest.txt b/unicodetools/data/ucd/dev/NormalizationTest.txt index d47e846f2..c5e7583c7 100644 --- a/unicodetools/data/ucd/dev/NormalizationTest.txt +++ b/unicodetools/data/ucd/dev/NormalizationTest.txt @@ -1,5 +1,5 @@ # NormalizationTest-17.0.0.txt -# Date: 2024-11-14, 14:55:28 GMT +# Date: 2024-11-14, 16:08:28 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 and license, see https://www.unicode.org/terms_of_use.html @@ -18701,6 +18701,8 @@ FFEE;FFEE;FFEE;25CB;25CB; # (￮; ￮; ￮; ○; ○; ) HALFWIDTH WHITE CIRCLE 0061 10EAB 0315 0300 05AE 0062;0061 05AE 10EAB 0300 0315 0062;0061 05AE 10EAB 0300 0315 0062;0061 05AE 10EAB 0300 0315 0062;0061 05AE 10EAB 0300 0315 0062; # (a◌𐺫◌̕◌̀◌֮b; a◌֮◌𐺫◌̀◌̕b; a◌֮◌𐺫◌̀◌̕b; a◌֮◌𐺫◌̀◌̕b; a◌֮◌𐺫◌̀◌̕b; ) LATIN SMALL LETTER A, YEZIDI COMBINING HAMZA MARK, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B 0061 0315 0300 05AE 10EAC 0062;00E0 05AE 10EAC 0315 0062;0061 05AE 0300 10EAC 0315 0062;00E0 05AE 10EAC 0315 0062;0061 05AE 0300 10EAC 0315 0062; # (a◌̕◌̀◌֮◌𐺬b; à◌֮◌𐺬◌̕b; a◌֮◌̀◌𐺬◌̕b; à◌֮◌𐺬◌̕b; a◌֮◌̀◌𐺬◌̕b; ) LATIN SMALL LETTER A, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, YEZIDI COMBINING MADDA MARK, LATIN SMALL LETTER B 0061 10EAC 0315 0300 05AE 0062;0061 05AE 10EAC 0300 0315 0062;0061 05AE 10EAC 0300 0315 0062;0061 05AE 10EAC 0300 0315 0062;0061 05AE 10EAC 0300 0315 0062; # (a◌𐺬◌̕◌̀◌֮b; a◌֮◌𐺬◌̀◌̕b; a◌֮◌𐺬◌̀◌̕b; a◌֮◌𐺬◌̀◌̕b; a◌֮◌𐺬◌̀◌̕b; ) LATIN SMALL LETTER A, YEZIDI COMBINING MADDA MARK, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B +0061 059A 0316 1DFA 10EFA 0062;0061 1DFA 0316 10EFA 059A 0062;0061 1DFA 0316 10EFA 059A 0062;0061 1DFA 0316 10EFA 059A 0062;0061 1DFA 0316 10EFA 059A 0062; # (a◌֚◌̖◌᷺◌𐻺b; a◌᷺◌̖◌𐻺◌֚b; a◌᷺◌̖◌𐻺◌֚b; a◌᷺◌̖◌𐻺◌֚b; a◌᷺◌̖◌𐻺◌֚b; ) LATIN SMALL LETTER A, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, ARABIC DOUBLE VERTICAL BAR BELOW, LATIN SMALL LETTER B +0061 10EFA 059A 0316 1DFA 0062;0061 1DFA 10EFA 0316 059A 0062;0061 1DFA 10EFA 0316 059A 0062;0061 1DFA 10EFA 0316 059A 0062;0061 1DFA 10EFA 0316 059A 0062; # (a◌𐻺◌֚◌̖◌᷺b; a◌᷺◌𐻺◌̖◌֚b; a◌᷺◌𐻺◌̖◌֚b; a◌᷺◌𐻺◌̖◌֚b; a◌᷺◌𐻺◌̖◌֚b; ) LATIN SMALL LETTER A, ARABIC DOUBLE VERTICAL BAR BELOW, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, LATIN SMALL LETTER B 0061 059A 0316 1DFA 10EFB 0062;0061 1DFA 0316 10EFB 059A 0062;0061 1DFA 0316 10EFB 059A 0062;0061 1DFA 0316 10EFB 059A 0062;0061 1DFA 0316 10EFB 059A 0062; # (a◌֚◌̖◌᷺◌𐻻b; a◌᷺◌̖◌𐻻◌֚b; a◌᷺◌̖◌𐻻◌֚b; a◌᷺◌̖◌𐻻◌֚b; a◌᷺◌̖◌𐻻◌֚b; ) LATIN SMALL LETTER A, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, ARABIC SMALL LOW NOON, LATIN SMALL LETTER B 0061 10EFB 059A 0316 1DFA 0062;0061 1DFA 10EFB 0316 059A 0062;0061 1DFA 10EFB 0316 059A 0062;0061 1DFA 10EFB 0316 059A 0062;0061 1DFA 10EFB 0316 059A 0062; # (a◌𐻻◌֚◌̖◌᷺b; a◌᷺◌𐻻◌̖◌֚b; a◌᷺◌𐻻◌̖◌֚b; a◌᷺◌𐻻◌̖◌֚b; a◌᷺◌𐻻◌̖◌֚b; ) LATIN SMALL LETTER A, ARABIC SMALL LOW NOON, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, LATIN SMALL LETTER B 0061 059A 0316 1DFA 10EFD 0062;0061 1DFA 0316 10EFD 059A 0062;0061 1DFA 0316 10EFD 059A 0062;0061 1DFA 0316 10EFD 059A 0062;0061 1DFA 0316 10EFD 059A 0062; # (a◌֚◌̖◌᷺◌𐻽b; a◌᷺◌̖◌𐻽◌֚b; a◌᷺◌̖◌𐻽◌֚b; a◌᷺◌̖◌𐻽◌֚b; a◌᷺◌̖◌𐻽◌֚b; ) LATIN SMALL LETTER A, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, ARABIC SMALL LOW WORD SAKTA, LATIN SMALL LETTER B diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt index 48dea2722..545d02c88 100644 --- a/unicodetools/data/ucd/dev/PropList.txt +++ b/unicodetools/data/ucd/dev/PropList.txt @@ -1,5 +1,5 @@ # PropList-17.0.0.txt -# Date: 2024-11-14, 14:55:37 GMT +# Date: 2024-11-14, 16:08:35 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 and license, see https://www.unicode.org/terms_of_use.html @@ -702,7 +702,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 10D24..10D27 ; Other_Alphabetic # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D69 ; Other_Alphabetic # Mn GARAY VOWEL SIGN E 10EAB..10EAC ; Other_Alphabetic # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK -10EFB..10EFC ; Other_Alphabetic # Mn [2] ARABIC SMALL LOW NOON..ARABIC COMBINING ALEF OVERLAY +10EFA..10EFC ; Other_Alphabetic # Mn [3] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC COMBINING ALEF OVERLAY 11000 ; Other_Alphabetic # Mc BRAHMI SIGN CANDRABINDU 11001 ; Other_Alphabetic # Mn BRAHMI SIGN ANUSVARA 11002 ; Other_Alphabetic # Mc BRAHMI SIGN VISARGA @@ -858,7 +858,7 @@ 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: 1496 +# Total code points: 1497 # ================================================ @@ -1080,6 +1080,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON 10D24..10D27 ; Diacritic # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D4E ; Diacritic # Lm GARAY VOWEL LENGTH MARK 10D69..10D6D ; Diacritic # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK +10EFA ; Diacritic # Mn ARABIC DOUBLE VERTICAL BAR BELOW 10EFD..10EFF ; Diacritic # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Diacritic # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; Diacritic # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW @@ -1153,7 +1154,7 @@ 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: 1208 +# Total code points: 1209 # ================================================ diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index c611447bd..e71bbcbdd 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,5 +1,5 @@ # Scripts-17.0.0.txt -# Date: 2024-11-14, 15:55:12 GMT +# Date: 2024-11-14, 16:08:54 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 and license, see https://www.unicode.org/terms_of_use.html @@ -892,7 +892,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA 10EC6..10EC7 ; Arabic # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10ED0 ; Arabic # Po ARABIC BIBLICAL END OF VERSE 10ED1..10ED8 ; Arabic # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH -10EFB..10EFF ; Arabic # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA +10EFA..10EFF ; Arabic # Mn [6] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW WORD MADDA 1EE00..1EE03 ; Arabic # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL 1EE05..1EE1F ; Arabic # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF 1EE21..1EE22 ; Arabic # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM @@ -928,7 +928,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA 1EEAB..1EEBB ; Arabic # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1EEF0..1EEF1 ; Arabic # Sm [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL -# Total code points: 1412 +# Total code points: 1413 # ================================================ diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index ce600d4b7..ab7fed94b 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -19646,6 +19646,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 10ED6;ARABIC LIGATURE QUDDISA SIRRAHUMAA;So;0;ON;;;;;N;;;;; 10ED7;ARABIC LIGATURE QUDDISAT ASRAARUHUM;So;0;ON;;;;;N;;;;; 10ED8;ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH;So;0;ON;;;;;N;;;;; +10EFA;ARABIC DOUBLE VERTICAL BAR BELOW;Mn;220;NSM;;;;;N;;;;; 10EFB;ARABIC SMALL LOW NOON;Mn;220;NSM;;;;;N;;;;; 10EFC;ARABIC COMBINING ALEF OVERLAY;Mn;0;NSM;;;;;N;;;;; 10EFD;ARABIC SMALL LOW WORD SAKTA;Mn;220;NSM;;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index d2a4df22d..923ed7072 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ # VerticalOrientation-17.0.0.txt -# Date: 2024-11-14, 15:55:15 GMT +# Date: 2024-11-14, 16:08:57 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 and license, see https://www.unicode.org/terms_of_use.html @@ -1790,7 +1790,7 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 10EC6..10EC7 ; R # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10ED0 ; R # Po ARABIC BIBLICAL END OF VERSE 10ED1..10ED8 ; R # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH -10EFB..10EFF ; R # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA +10EFA..10EFF ; R # Mn [6] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; R # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; R # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF 10F27 ; R # Lo OLD SOGDIAN LIGATURE AYIN-DALETH diff --git a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt index 97b805ce1..790beba09 100644 --- a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt @@ -1,5 +1,5 @@ # GraphemeBreakProperty-17.0.0.txt -# Date: 2024-11-14, 14:55:18 GMT +# Date: 2024-11-14, 16:08:22 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 and license, see https://www.unicode.org/terms_of_use.html @@ -340,7 +340,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 10D24..10D27 ; Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D69..10D6D ; Extend # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK -10EFB..10EFF ; Extend # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA +10EFA..10EFF ; Extend # Mn [6] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; Extend # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; Extend # Mn BRAHMI SIGN ANUSVARA @@ -496,7 +496,7 @@ 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: 2228 +# Total code points: 2229 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 625ffe50f..4f2e7dbd9 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ # SentenceBreakProperty-17.0.0.txt -# Date: 2024-11-14, 15:28:07 GMT +# Date: 2024-11-14, 16:08:55 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 and license, see https://www.unicode.org/terms_of_use.html @@ -374,7 +374,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 10D24..10D27 ; Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D69..10D6D ; Extend # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK -10EFB..10EFF ; Extend # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA +10EFA..10EFF ; Extend # Mn [6] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; Extend # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11000 ; Extend # Mc BRAHMI SIGN CANDRABINDU @@ -587,7 +587,7 @@ 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: 2631 +# Total code points: 2632 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index c9ed2146c..b97cc34ed 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-17.0.0.txt -# Date: 2024-11-14, 15:28:10 GMT +# Date: 2024-11-14, 16:08:58 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 and license, see https://www.unicode.org/terms_of_use.html @@ -410,7 +410,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 10D24..10D27 ; Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D69..10D6D ; Extend # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK -10EFB..10EFF ; Extend # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA +10EFA..10EFF ; Extend # Mn [6] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; Extend # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11000 ; Extend # Mc BRAHMI SIGN CANDRABINDU @@ -624,7 +624,7 @@ 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: 2635 +# Total code points: 2636 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 0bf1157fa..a3f88f639 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-17.0.0.txt -# Date: 2024-11-14, 15:54:29 GMT +# Date: 2024-11-14, 16:08:12 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 and license, see https://www.unicode.org/terms_of_use.html @@ -2278,7 +2278,7 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 10D24..10D27 ; NSM # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D69..10D6D ; NSM # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; NSM # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK -10EFB..10EFF ; NSM # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA +10EFA..10EFF ; NSM # Mn [6] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; NSM # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; NSM # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; NSM # Mn BRAHMI SIGN ANUSVARA @@ -2412,7 +2412,7 @@ 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: 2058 +# Total code points: 2059 # ================================================ @@ -2507,8 +2507,8 @@ FE76..FEFC ; AL # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WI 1EEA5..1EEA9 ; AL # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; AL # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN -# The above property value applies to 254 code points not listed here. -# Total code points: 1732 +# The above property value applies to 253 code points not listed here. +# Total code points: 1731 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index ad658a165..4ded0a6d3 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-17.0.0.txt -# Date: 2024-11-14, 15:54:31 GMT +# Date: 2024-11-14, 16:08:14 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 and license, see https://www.unicode.org/terms_of_use.html @@ -2064,8 +2064,8 @@ 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 821475 code points not listed here. -# Total code points: 1113150 +# The above property value applies to 821474 code points not listed here. +# Total code points: 1113149 # ================================================ @@ -2621,7 +2621,7 @@ FE27..FE2D ; 220 # Mn [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CON 10A0D ; 220 # Mn KHAROSHTHI SIGN DOUBLE RING BELOW 10A3A ; 220 # Mn KHAROSHTHI SIGN DOT BELOW 10AE6 ; 220 # Mn MANICHAEAN ABBREVIATION MARK BELOW -10EFB ; 220 # Mn ARABIC SMALL LOW NOON +10EFA..10EFB ; 220 # Mn [2] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW NOON 10EFD..10EFF ; 220 # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA 10F46..10F47 ; 220 # Mn [2] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING TWO DOTS BELOW 10F4B ; 220 # Mn SOGDIAN COMBINING CURVE BELOW @@ -2634,7 +2634,7 @@ FE27..FE2D ; 220 # Mn [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CON 1E5EF ; 220 # Mn OL ONAL SIGN IKIR 1E8D0..1E8D6 ; 220 # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS -# Total code points: 185 +# Total code points: 186 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index 43bd0d94d..0296ddd35 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-17.0.0.txt -# Date: 2024-11-14, 15:54:34 GMT +# Date: 2024-11-14, 16:08:16 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 and license, see https://www.unicode.org/terms_of_use.html @@ -1491,7 +1491,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 10EC6..10EC7 ; N # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10ED0 ; N # Po ARABIC BIBLICAL END OF VERSE 10ED1..10ED8 ; N # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH -10EFB..10EFF ; N # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA +10EFA..10EFF ; N # Mn [6] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; N # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; N # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF 10F27 ; N # Lo OLD SOGDIAN LIGATURE AYIN-DALETH @@ -2108,7 +2108,7 @@ 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 760993 code points not listed here. +# The above property value applies to 760992 code points not listed here. # Total code points: 792420 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index 5ffd7454b..2afe33131 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-17.0.0.txt -# Date: 2024-11-14, 15:54:35 GMT +# Date: 2024-11-14, 16:08:17 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 and license, see https://www.unicode.org/terms_of_use.html @@ -433,7 +433,7 @@ FFFE..FFFF ; Cn # [2] .. 10EAE..10EAF ; Cn # [2] .. 10EB2..10EC1 ; Cn # [16] .. 10EC8..10ECF ; Cn # [8] .. -10ED9..10EFA ; Cn # [34] .. +10ED9..10EF9 ; Cn # [33] .. 10F28..10F2F ; Cn # [8] .. 10F5A..10F6F ; Cn # [22] .. 10F8A..10FAF ; Cn # [38] .. @@ -741,7 +741,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819427 +# Total code points: 819426 # ================================================ @@ -2941,7 +2941,7 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 10D24..10D27 ; Mn # [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D69..10D6D ; Mn # [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; Mn # [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK -10EFB..10EFF ; Mn # [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA +10EFA..10EFF ; Mn # [6] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Mn # [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; Mn # [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; Mn # BRAHMI SIGN ANUSVARA @@ -3075,7 +3075,7 @@ 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: 2050 +# Total code points: 2051 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt index fc0d6d2cb..34f4d6bbb 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt @@ -1,5 +1,5 @@ # DerivedJoiningType-17.0.0.txt -# Date: 2024-11-14, 15:27:18 GMT +# Date: 2024-11-14, 16:08:18 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 and license, see https://www.unicode.org/terms_of_use.html @@ -444,7 +444,7 @@ FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATI 10D24..10D27 ; T # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D69..10D6D ; T # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; T # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK -10EFB..10EFF ; T # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA +10EFA..10EFF ; T # Mn [6] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; T # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; T # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; T # Mn BRAHMI SIGN ANUSVARA @@ -584,6 +584,6 @@ 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: 2215 +# Total code points: 2216 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 60ff34b61..c330cbf10 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-17.0.0.txt -# Date: 2024-11-14, 15:54:36 GMT +# Date: 2024-11-14, 16:08:18 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 and license, 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 757547 code points not listed here. -# Total code points: 895015 +# The above property value applies to 757546 code points not listed here. +# Total code points: 895014 # ================================================ @@ -2187,7 +2187,7 @@ FFF9..FFFB ; CM # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTAT 10D24..10D27 ; CM # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D69..10D6D ; CM # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; CM # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK -10EFB..10EFF ; CM # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA +10EFA..10EFF ; CM # Mn [6] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; CM # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; CM # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11000 ; CM # Mc BRAHMI SIGN CANDRABINDU @@ -2392,7 +2392,7 @@ 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: 2499 +# Total code points: 2500 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 2c3d04d62..a2098a1a7 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-17.0.0.txt -# Date: 2024-11-14, 15:54:36 GMT +# Date: 2024-11-14, 16:08:19 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 and license, see https://www.unicode.org/terms_of_use.html @@ -30311,6 +30311,7 @@ FFFD ; REPLACEMENT CHARACTER 10ED6 ; ARABIC LIGATURE QUDDISA SIRRAHUMAA 10ED7 ; ARABIC LIGATURE QUDDISAT ASRAARUHUM 10ED8 ; ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH +10EFA ; ARABIC DOUBLE VERTICAL BAR BELOW 10EFB ; ARABIC SMALL LOW NOON 10EFC ; ARABIC COMBINING ALEF OVERLAY 10EFD ; ARABIC SMALL LOW WORD SAKTA @@ -45473,6 +45474,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 155104 +# Total code points: 155105 # EOF