diff --git a/unicodetools/data/ucd/dev/Blocks.txt b/unicodetools/data/ucd/dev/Blocks.txt index 15fbbd0a3..1b8059751 100644 --- a/unicodetools/data/ucd/dev/Blocks.txt +++ b/unicodetools/data/ucd/dev/Blocks.txt @@ -217,6 +217,7 @@ FFF0..FFFF; Specials 10500..1052F; Elbasan 10530..1056F; Caucasian Albanian 10570..105BF; Vithkuqi +105C0..105FF; Todhri 10600..1077F; Linear A 10780..107BF; Latin Extended-F 10800..1083F; Cypriot Syllabary diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index eedf1bc69..d61ad0073 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-16.0.0.txt -# Date: 2023-10-13, 15:52:11 GMT +# Date: 2023-10-16, 14:22:03 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -2013,11 +2013,12 @@ FDFE..FDFF ; 14.0 # [2] ARABIC LIGATURE SUBHAANAHU WA TAAALAA..ARABIC LIGAT 0C5C ; 16.0 # TELUGU ARCHAIC SHRII 0CDC ; 16.0 # KANNADA ARCHAIC SHRII 1C89..1C8A ; 16.0 # [2] CYRILLIC CAPITAL LETTER TJE..CYRILLIC SMALL LETTER TJE +105C0..105F3 ; 16.0 # [52] TODHRI LETTER A..TODHRI LETTER OO 10EC2..10EC4 ; 16.0 # [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EFC ; 16.0 # ARABIC COMBINING ALEF OVERLAY 11BC0..11BE1 ; 16.0 # [34] SUNUWAR LETTER DEVI..SUNUWAR SIGN PVO 11BF0..11BF9 ; 16.0 # [10] SUNUWAR DIGIT ZERO..SUNUWAR DIGIT NINE -# Total code points: 53 +# Total code points: 105 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 132266cb1..00c82e85b 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-16.0.0.txt -# Date: 2023-10-13, 15:52:30 GMT +# Date: 2023-10-16, 14:22:22 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -999,6 +999,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 105A3..105B1 ; Alphabetic # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE 105B3..105B9 ; Alphabetic # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE 105BB..105BC ; Alphabetic # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE +105C0..105F3 ; Alphabetic # Lo [52] TODHRI LETTER A..TODHRI LETTER OO 10600..10736 ; Alphabetic # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; Alphabetic # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; Alphabetic # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 @@ -1406,7 +1407,7 @@ 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: 138429 +# Total code points: 138481 # ================================================ @@ -6612,6 +6613,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 105A3..105B1 ; ID_Start # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE 105B3..105B9 ; ID_Start # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE 105BB..105BC ; ID_Start # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE +105C0..105F3 ; ID_Start # Lo [52] TODHRI LETTER A..TODHRI LETTER OO 10600..10736 ; ID_Start # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; ID_Start # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; ID_Start # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 @@ -6870,7 +6872,7 @@ 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: 137007 +# Total code points: 137059 # ================================================ @@ -7746,6 +7748,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 105A3..105B1 ; ID_Continue # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE 105B3..105B9 ; ID_Continue # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE 105BB..105BC ; ID_Continue # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE +105C0..105F3 ; ID_Continue # Lo [52] TODHRI LETTER A..TODHRI LETTER OO 10600..10736 ; ID_Continue # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; ID_Continue # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; ID_Continue # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 @@ -8232,7 +8235,7 @@ 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: 140160 +# Total code points: 140212 # ================================================ @@ -8731,6 +8734,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 105A3..105B1 ; XID_Start # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE 105B3..105B9 ; XID_Start # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE 105BB..105BC ; XID_Start # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE +105C0..105F3 ; XID_Start # Lo [52] TODHRI LETTER A..TODHRI LETTER OO 10600..10736 ; XID_Start # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; XID_Start # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; XID_Start # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 @@ -8989,7 +8993,7 @@ 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: 136984 +# Total code points: 137036 # ================================================ @@ -9866,6 +9870,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 105A3..105B1 ; XID_Continue # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE 105B3..105B9 ; XID_Continue # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE 105BB..105BC ; XID_Continue # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE +105C0..105F3 ; XID_Continue # Lo [52] TODHRI LETTER A..TODHRI LETTER OO 10600..10736 ; XID_Continue # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; XID_Continue # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; XID_Continue # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 @@ -10352,7 +10357,7 @@ 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: 140141 +# Total code points: 140193 # ================================================ @@ -12019,6 +12024,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 105A3..105B1 ; Grapheme_Base # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE 105B3..105B9 ; Grapheme_Base # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE 105BB..105BC ; Grapheme_Base # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE +105C0..105F3 ; Grapheme_Base # Lo [52] TODHRI LETTER A..TODHRI LETTER OO 10600..10736 ; Grapheme_Base # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; Grapheme_Base # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; Grapheme_Base # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 @@ -12546,7 +12552,7 @@ 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: 147664 +# Total code points: 147716 # ================================================ diff --git a/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt b/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt index 7d9e18c0a..102600acc 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: 2023-10-12, 21:06:48 GMT +# Date: 2023-10-16, 14:22:26 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -981,6 +981,8 @@ FB3E ; NFD_QC; N # Lo HEBREW LETTER MEM WITH DAGESH FB40..FB41 ; NFD_QC; N # Lo [2] HEBREW LETTER NUN WITH DAGESH..HEBREW LETTER SAMEKH WITH DAGESH FB43..FB44 ; NFD_QC; N # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETTER PE WITH DAGESH FB46..FB4E ; NFD_QC; N # Lo [9] HEBREW LETTER TSADI WITH DAGESH..HEBREW LETTER PE WITH RAFE +105C9 ; NFD_QC; N # Lo TODHRI LETTER EI +105E4 ; NFD_QC; N # Lo TODHRI LETTER U 1109A ; NFD_QC; N # Lo KAITHI LETTER DDDHA 1109C ; NFD_QC; N # Lo KAITHI LETTER RHA 110AB ; NFD_QC; N # Lo KAITHI LETTER VA @@ -994,7 +996,7 @@ FB46..FB4E ; NFD_QC; N # Lo [9] HEBREW LETTER TSADI WITH DAGESH..HEBREW LET 1D1BB..1D1C0 ; NFD_QC; N # So [6] MUSICAL SYMBOL MINIMA..MUSICAL SYMBOL FUSA BLACK 2F800..2FA1D ; NFD_QC; N # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 13233 +# Total code points: 13235 # ================================================ @@ -1597,6 +1599,8 @@ FFE5..FFE6 ; NFKD_QC; N # Sc [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN FFE8 ; NFKD_QC; N # So HALFWIDTH FORMS LIGHT VERTICAL FFE9..FFEC ; NFKD_QC; N # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS ARROW FFED..FFEE ; NFKD_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE +105C9 ; NFKD_QC; N # Lo TODHRI LETTER EI +105E4 ; NFKD_QC; N # Lo TODHRI LETTER U 10781..10785 ; NFKD_QC; N # Lm [5] MODIFIER LETTER SUPERSCRIPT TRIANGULAR COLON..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; NFKD_QC; N # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK 107B2..107BA ; NFKD_QC; N # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL @@ -1698,7 +1702,7 @@ 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: 17029 +# Total code points: 17031 # ================================================ @@ -2379,6 +2383,8 @@ FB3E ; Expands_On_NFD # Lo HEBREW LETTER MEM WITH DAGESH FB40..FB41 ; Expands_On_NFD # Lo [2] HEBREW LETTER NUN WITH DAGESH..HEBREW LETTER SAMEKH WITH DAGESH FB43..FB44 ; Expands_On_NFD # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETTER PE WITH DAGESH FB46..FB4E ; Expands_On_NFD # Lo [9] HEBREW LETTER TSADI WITH DAGESH..HEBREW LETTER PE WITH RAFE +105C9 ; Expands_On_NFD # Lo TODHRI LETTER EI +105E4 ; Expands_On_NFD # Lo TODHRI LETTER U 1109A ; Expands_On_NFD # Lo KAITHI LETTER DDDHA 1109C ; Expands_On_NFD # Lo KAITHI LETTER RHA 110AB ; Expands_On_NFD # Lo KAITHI LETTER VA @@ -2391,7 +2397,7 @@ FB46..FB4E ; Expands_On_NFD # Lo [9] HEBREW LETTER TSADI WITH DAGESH..HEBRE 1D15E..1D164 ; Expands_On_NFD # So [7] MUSICAL SYMBOL HALF NOTE..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE 1D1BB..1D1C0 ; Expands_On_NFD # So [6] MUSICAL SYMBOL MINIMA..MUSICAL SYMBOL FUSA BLACK -# Total code points: 12216 +# Total code points: 12218 # ================================================ @@ -2733,6 +2739,8 @@ FE76..FE7F ; Expands_On_NFKD # Lo [10] ARABIC FATHA ISOLATED FORM..ARABIC SU FE81..FE8C ; Expands_On_NFKD # Lo [12] ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM..ARABIC LETTER YEH WITH HAMZA ABOVE MEDIAL FORM FEF5..FEFC ; Expands_On_NFKD # Lo [8] ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE ISOLATED FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM FFE3 ; Expands_On_NFKD # Sk FULLWIDTH MACRON +105C9 ; Expands_On_NFKD # Lo TODHRI LETTER EI +105E4 ; Expands_On_NFKD # Lo TODHRI LETTER U 1109A ; Expands_On_NFKD # Lo KAITHI LETTER DDDHA 1109C ; Expands_On_NFKD # Lo KAITHI LETTER RHA 110AB ; Expands_On_NFKD # Lo KAITHI LETTER VA @@ -2754,7 +2762,7 @@ FFE3 ; Expands_On_NFKD # Sk FULLWIDTH MACRON 1F213 ; Expands_On_NFKD # So SQUARED KATAKANA DE 1F240..1F248 ; Expands_On_NFKD # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 -# Total code points: 13390 +# Total code points: 13392 # ================================================ diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index 171c4350c..4f2c164bb 100644 --- a/unicodetools/data/ucd/dev/EastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/EastAsianWidth.txt @@ -1,5 +1,5 @@ # EastAsianWidth-16.0.0.txt -# Date: 2023-10-13, 15:52:36 GMT +# Date: 2023-10-16, 14:22:27 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1870,6 +1870,7 @@ FFFD ; A # So REPLACEMENT CHARACTER 105A3..105B1 ; N # Ll [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE 105B3..105B9 ; N # Ll [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE 105BB..105BC ; N # Ll [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE +105C0..105F3 ; N # Lo [52] TODHRI LETTER A..TODHRI LETTER OO 10600..10736 ; N # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; N # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; N # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 65cac516f..2a584fb00 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,5 @@ # LineBreak-16.0.0.txt -# Date: 2023-10-13, 11:29:24 GMT +# Date: 2023-10-16, 14:22:28 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -2721,6 +2721,7 @@ FFFD ; AI # So REPLACEMENT CHARACTER 105A3..105B1 ; AL # Ll [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE 105B3..105B9 ; AL # Ll [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE 105BB..105BC ; AL # Ll [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE +105C0..105F3 ; AL # Lo [52] TODHRI LETTER A..TODHRI LETTER OO 10600..10736 ; AL # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; AL # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; AL # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 diff --git a/unicodetools/data/ucd/dev/NormalizationTest.txt b/unicodetools/data/ucd/dev/NormalizationTest.txt index 757d8f5de..5a4e3fc79 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: 2023-10-02, 12:41:11 GMT +# Date: 2023-10-09, 15:12:35 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -15130,6 +15130,8 @@ FFEB;FFEB;FFEB;2192;2192; # (￫; ￫; ￫; →; →; ) HALFWIDTH RIGHTWARDS ARR FFEC;FFEC;FFEC;2193;2193; # (￬; ￬; ￬; ↓; ↓; ) HALFWIDTH DOWNWARDS ARROW FFED;FFED;FFED;25A0;25A0; # (￭; ￭; ￭; ■; ■; ) HALFWIDTH BLACK SQUARE FFEE;FFEE;FFEE;25CB;25CB; # (￮; ￮; ￮; ○; ○; ) HALFWIDTH WHITE CIRCLE +105C9;105C9;105D2 0307;105C9;105D2 0307; # (𐗉; 𐗉; 𐗒◌̇; 𐗉; 𐗒◌̇; ) TODHRI LETTER EI +105E4;105E4;105DA 0307;105E4;105DA 0307; # (𐗤; 𐗤; 𐗚◌̇; 𐗤; 𐗚◌̇; ) TODHRI LETTER U 10781;10781;10781;02D0;02D0; # (𐞁; 𐞁; 𐞁; ː; ː; ) MODIFIER LETTER SUPERSCRIPT TRIANGULAR COLON 10782;10782;10782;02D1;02D1; # (𐞂; 𐞂; 𐞂; ˑ; ˑ; ) MODIFIER LETTER SUPERSCRIPT HALF TRIANGULAR COLON 10783;10783;10783;00E6;00E6; # (𐞃; 𐞃; 𐞃; æ; æ; ) MODIFIER LETTER SMALL AE diff --git a/unicodetools/data/ucd/dev/PropertyValueAliases.txt b/unicodetools/data/ucd/dev/PropertyValueAliases.txt index 7dc6c1457..bdfc60aee 100644 --- a/unicodetools/data/ucd/dev/PropertyValueAliases.txt +++ b/unicodetools/data/ucd/dev/PropertyValueAliases.txt @@ -1,5 +1,5 @@ # PropertyValueAliases-16.0.0.txt -# Date: 2023-10-11, 21:16:05 GMT +# Date: 2023-10-16, 14:22:33 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -462,6 +462,7 @@ blk; Thai ; Thai blk; Tibetan ; Tibetan blk; Tifinagh ; Tifinagh blk; Tirhuta ; Tirhuta +blk; Todhri ; Todhri blk; Toto ; Toto blk; Transport_And_Map ; Transport_And_Map_Symbols blk; UCAS ; Unified_Canadian_Aboriginal_Syllabics; Canadian_Syllabics @@ -1443,6 +1444,7 @@ sc ; Thai ; Thai sc ; Tibt ; Tibetan sc ; Tirh ; Tirhuta sc ; Tnsa ; Tangsa +sc ; Todr ; Todhri sc ; Toto ; Toto sc ; Ugar ; Ugaritic sc ; Vaii ; Vai diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 1d914b667..5943454c8 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,5 +1,5 @@ # Scripts-16.0.0.txt -# Date: 2023-10-13, 15:52:54 GMT +# Date: 2023-10-16, 14:22:46 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -3039,4 +3039,10 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI # Total code points: 44 +# ================================================ + +105C0..105F3 ; Todhri # Lo [52] TODHRI LETTER A..TODHRI LETTER OO + +# Total code points: 52 + # EOF diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index c13107f25..87a38d76d 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -18006,6 +18006,58 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 105B9;VITHKUQI SMALL LETTER XE;Ll;0;L;;;;;N;;;10592;;10592 105BB;VITHKUQI SMALL LETTER Y;Ll;0;L;;;;;N;;;10594;;10594 105BC;VITHKUQI SMALL LETTER ZE;Ll;0;L;;;;;N;;;10595;;10595 +105C0;TODHRI LETTER A;Lo;0;L;;;;;N;;;;; +105C1;TODHRI LETTER AS;Lo;0;L;;;;;N;;;;; +105C2;TODHRI LETTER BA;Lo;0;L;;;;;N;;;;; +105C3;TODHRI LETTER MBA;Lo;0;L;;;;;N;;;;; +105C4;TODHRI LETTER CA;Lo;0;L;;;;;N;;;;; +105C5;TODHRI LETTER CHA;Lo;0;L;;;;;N;;;;; +105C6;TODHRI LETTER DA;Lo;0;L;;;;;N;;;;; +105C7;TODHRI LETTER NDA;Lo;0;L;;;;;N;;;;; +105C8;TODHRI LETTER DHA;Lo;0;L;;;;;N;;;;; +105C9;TODHRI LETTER EI;Lo;0;L;105D2 0307;;;;N;;;;; +105CA;TODHRI LETTER E;Lo;0;L;;;;;N;;;;; +105CB;TODHRI LETTER FA;Lo;0;L;;;;;N;;;;; +105CC;TODHRI LETTER GA;Lo;0;L;;;;;N;;;;; +105CD;TODHRI LETTER NGA;Lo;0;L;;;;;N;;;;; +105CE;TODHRI LETTER GJA;Lo;0;L;;;;;N;;;;; +105CF;TODHRI LETTER NGJA;Lo;0;L;;;;;N;;;;; +105D0;TODHRI LETTER HA;Lo;0;L;;;;;N;;;;; +105D1;TODHRI LETTER HJA;Lo;0;L;;;;;N;;;;; +105D2;TODHRI LETTER I;Lo;0;L;;;;;N;;;;; +105D3;TODHRI LETTER JA;Lo;0;L;;;;;N;;;;; +105D4;TODHRI LETTER KA;Lo;0;L;;;;;N;;;;; +105D5;TODHRI LETTER LA;Lo;0;L;;;;;N;;;;; +105D6;TODHRI LETTER LLA;Lo;0;L;;;;;N;;;;; +105D7;TODHRI LETTER MA;Lo;0;L;;;;;N;;;;; +105D8;TODHRI LETTER NA;Lo;0;L;;;;;N;;;;; +105D9;TODHRI LETTER NJAN;Lo;0;L;;;;;N;;;;; +105DA;TODHRI LETTER O;Lo;0;L;;;;;N;;;;; +105DB;TODHRI LETTER PA;Lo;0;L;;;;;N;;;;; +105DC;TODHRI LETTER QA;Lo;0;L;;;;;N;;;;; +105DD;TODHRI LETTER RA;Lo;0;L;;;;;N;;;;; +105DE;TODHRI LETTER RRA;Lo;0;L;;;;;N;;;;; +105DF;TODHRI LETTER SA;Lo;0;L;;;;;N;;;;; +105E0;TODHRI LETTER SHA;Lo;0;L;;;;;N;;;;; +105E1;TODHRI LETTER SHTA;Lo;0;L;;;;;N;;;;; +105E2;TODHRI LETTER TA;Lo;0;L;;;;;N;;;;; +105E3;TODHRI LETTER THA;Lo;0;L;;;;;N;;;;; +105E4;TODHRI LETTER U;Lo;0;L;105DA 0307;;;;N;;;;; +105E5;TODHRI LETTER VA;Lo;0;L;;;;;N;;;;; +105E6;TODHRI LETTER XA;Lo;0;L;;;;;N;;;;; +105E7;TODHRI LETTER NXA;Lo;0;L;;;;;N;;;;; +105E8;TODHRI LETTER XHA;Lo;0;L;;;;;N;;;;; +105E9;TODHRI LETTER NXHA;Lo;0;L;;;;;N;;;;; +105EA;TODHRI LETTER Y;Lo;0;L;;;;;N;;;;; +105EB;TODHRI LETTER JY;Lo;0;L;;;;;N;;;;; +105EC;TODHRI LETTER ZA;Lo;0;L;;;;;N;;;;; +105ED;TODHRI LETTER ZHA;Lo;0;L;;;;;N;;;;; +105EE;TODHRI LETTER GHA;Lo;0;L;;;;;N;;;;; +105EF;TODHRI LETTER STA;Lo;0;L;;;;;N;;;;; +105F0;TODHRI LETTER SKAN;Lo;0;L;;;;;N;;;;; +105F1;TODHRI LETTER KHA;Lo;0;L;;;;;N;;;;; +105F2;TODHRI LETTER PSA;Lo;0;L;;;;;N;;;;; +105F3;TODHRI LETTER OO;Lo;0;L;;;;;N;;;;; 10600;LINEAR A SIGN AB001;Lo;0;L;;;;;N;;;;; 10601;LINEAR A SIGN AB002;Lo;0;L;;;;;N;;;;; 10602;LINEAR A SIGN AB003;Lo;0;L;;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index 541f1428a..67987a270 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ # VerticalOrientation-16.0.0.txt -# Date: 2023-10-13, 15:52:57 GMT +# Date: 2023-10-16, 14:22:48 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1694,6 +1694,7 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 105A3..105B1 ; R # Ll [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE 105B3..105B9 ; R # Ll [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE 105BB..105BC ; R # Ll [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE +105C0..105F3 ; R # Lo [52] TODHRI LETTER A..TODHRI LETTER OO 10600..10736 ; R # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; R # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; R # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 03b5da341..a7fc826ab 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ # SentenceBreakProperty-16.0.0.txt -# Date: 2023-10-13, 15:52:55 GMT +# Date: 2023-10-16, 14:22:46 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -2323,6 +2323,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10450..1049D ; OLetter # Lo [78] SHAVIAN LETTER PEEP..OSMANYA LETTER OO 10500..10527 ; OLetter # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; OLetter # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW +105C0..105F3 ; OLetter # Lo [52] TODHRI LETTER A..TODHRI LETTER OO 10600..10736 ; OLetter # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; OLetter # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; OLetter # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 @@ -2540,7 +2541,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; OLetter # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; OLetter # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 132696 +# Total code points: 132748 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index d24f06dc8..a44fa5d44 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-16.0.0.txt -# Date: 2023-10-13, 15:52:57 GMT +# Date: 2023-10-16, 14:22:48 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1077,6 +1077,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 105A3..105B1 ; ALetter # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE 105B3..105B9 ; ALetter # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE 105BB..105BC ; ALetter # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE +105C0..105F3 ; ALetter # Lo [52] TODHRI LETTER A..TODHRI LETTER OO 10600..10736 ; ALetter # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; ALetter # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; ALetter # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 @@ -1315,7 +1316,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1F150..1F169 ; ALetter # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; ALetter # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 29530 +# Total code points: 29582 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 0d6c4ac6f..99cacf205 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-16.0.0.txt -# Date: 2023-10-13, 15:52:28 GMT +# Date: 2023-10-16, 14:22:20 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -821,6 +821,7 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 105A3..105B1 ; L # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE 105B3..105B9 ; L # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE 105BB..105BC ; L # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE +105C0..105F3 ; L # Lo [52] TODHRI LETTER A..TODHRI LETTER OO 10600..10736 ; L # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; L # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; L # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 @@ -1185,7 +1186,7 @@ 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 820414 code points not listed here. +# The above property value applies to 820362 code points not listed here. # Total code points: 1096267 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index 23929b30f..63e2db1b7 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-16.0.0.txt -# Date: 2023-10-13, 15:52:30 GMT +# Date: 2023-10-16, 14:22:22 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1392,6 +1392,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 105A3..105B1 ; 0 # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE 105B3..105B9 ; 0 # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE 105BB..105BC ; 0 # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE +105C0..105F3 ; 0 # Lo [52] TODHRI LETTER A..TODHRI LETTER OO 10600..10736 ; 0 # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; 0 # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; 0 # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 @@ -2010,7 +2011,7 @@ 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 826713 code points not listed here. +# The above property value applies to 826661 code points not listed here. # Total code points: 1113189 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedDecompositionType.txt b/unicodetools/data/ucd/dev/extracted/DerivedDecompositionType.txt index 6bd9e8ee6..b1789d11f 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedDecompositionType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedDecompositionType.txt @@ -1,5 +1,5 @@ -# DerivedDecompositionType-15.1.0.txt -# Date: 2023-01-05, 20:34:36 GMT +# DerivedDecompositionType-16.0.0.txt +# Date: 2023-10-16, 14:22:23 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -249,6 +249,8 @@ FB3E ; Canonical # Lo HEBREW LETTER MEM WITH DAGESH FB40..FB41 ; Canonical # Lo [2] HEBREW LETTER NUN WITH DAGESH..HEBREW LETTER SAMEKH WITH DAGESH FB43..FB44 ; Canonical # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETTER PE WITH DAGESH FB46..FB4E ; Canonical # Lo [9] HEBREW LETTER TSADI WITH DAGESH..HEBREW LETTER PE WITH RAFE +105C9 ; Canonical # Lo TODHRI LETTER EI +105E4 ; Canonical # Lo TODHRI LETTER U 1109A ; Canonical # Lo KAITHI LETTER DDDHA 1109C ; Canonical # Lo KAITHI LETTER RHA 110AB ; Canonical # Lo KAITHI LETTER VA @@ -262,7 +264,7 @@ FB46..FB4E ; Canonical # Lo [9] HEBREW LETTER TSADI WITH DAGESH..HEBREW LET 1D1BB..1D1C0 ; Canonical # So [6] MUSICAL SYMBOL MINIMA..MUSICAL SYMBOL FUSA BLACK 2F800..2FA1D ; Canonical # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 13233 +# Total code points: 13235 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index c82890ade..07a6926ae 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-16.0.0.txt -# Date: 2023-10-13, 15:52:32 GMT +# Date: 2023-10-16, 14:22:24 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1397,6 +1397,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 105A3..105B1 ; N # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE 105B3..105B9 ; N # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE 105BB..105BC ; N # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE +105C0..105F3 ; N # Lo [52] TODHRI LETTER A..TODHRI LETTER OO 10600..10736 ; N # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; N # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; N # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 @@ -2047,7 +2048,7 @@ 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 766231 code points not listed here. +# The above property value applies to 766179 code points not listed here. # Total code points: 792618 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index e2a1f7ee6..cf69b275f 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-16.0.0.txt -# Date: 2023-10-13, 15:52:32 GMT +# Date: 2023-10-16, 14:22:24 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -388,7 +388,8 @@ FFFE..FFFF ; Cn # [2] .. 105A2 ; Cn # 105B2 ; Cn # 105BA ; Cn # -105BD..105FF ; Cn # [67] .. +105BD..105BF ; Cn # [3] .. +105F4..105FF ; Cn # [12] .. 10737..1073F ; Cn # [9] .. 10756..1075F ; Cn # [10] .. 10768..1077F ; Cn # [24] .. @@ -726,7 +727,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 824665 +# Total code points: 824613 # ================================================ @@ -2456,6 +2457,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 10450..1049D ; Lo # [78] SHAVIAN LETTER PEEP..OSMANYA LETTER OO 10500..10527 ; Lo # [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; Lo # [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW +105C0..105F3 ; Lo # [52] TODHRI LETTER A..TODHRI LETTER OO 10600..10736 ; Lo # [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; Lo # [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; Lo # [8] LINEAR A SIGN A800..LINEAR A SIGN A807 @@ -2661,7 +2663,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 30000..3134A ; Lo # [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Lo # [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 132272 +# Total code points: 132324 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index fab5c30c2..7f80e04e5 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-16.0.0.txt -# Date: 2023-10-13, 15:52:33 GMT +# Date: 2023-10-16, 14:22:25 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -68,8 +68,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 762672 code points not listed here. -# Total code points: 900140 +# The above property value applies to 762620 code points not listed here. +# Total code points: 900088 # ================================================ @@ -1239,6 +1239,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 105A3..105B1 ; AL # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE 105B3..105B9 ; AL # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE 105BB..105BC ; AL # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE +105C0..105F3 ; AL # Lo [52] TODHRI LETTER A..TODHRI LETTER OO 10600..10736 ; AL # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; AL # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; AL # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 @@ -1584,7 +1585,7 @@ 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..1FBCA ; AL # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON -# Total code points: 21770 +# Total code points: 21822 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 1c7f11fd5..4ebbab9f7 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-16.0.0.txt -# Date: 2023-10-13, 15:52:34 GMT +# Date: 2023-10-16, 14:22:25 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -28671,6 +28671,58 @@ FFFD ; REPLACEMENT CHARACTER 105B9 ; VITHKUQI SMALL LETTER XE 105BB ; VITHKUQI SMALL LETTER Y 105BC ; VITHKUQI SMALL LETTER ZE +105C0 ; TODHRI LETTER A +105C1 ; TODHRI LETTER AS +105C2 ; TODHRI LETTER BA +105C3 ; TODHRI LETTER MBA +105C4 ; TODHRI LETTER CA +105C5 ; TODHRI LETTER CHA +105C6 ; TODHRI LETTER DA +105C7 ; TODHRI LETTER NDA +105C8 ; TODHRI LETTER DHA +105C9 ; TODHRI LETTER EI +105CA ; TODHRI LETTER E +105CB ; TODHRI LETTER FA +105CC ; TODHRI LETTER GA +105CD ; TODHRI LETTER NGA +105CE ; TODHRI LETTER GJA +105CF ; TODHRI LETTER NGJA +105D0 ; TODHRI LETTER HA +105D1 ; TODHRI LETTER HJA +105D2 ; TODHRI LETTER I +105D3 ; TODHRI LETTER JA +105D4 ; TODHRI LETTER KA +105D5 ; TODHRI LETTER LA +105D6 ; TODHRI LETTER LLA +105D7 ; TODHRI LETTER MA +105D8 ; TODHRI LETTER NA +105D9 ; TODHRI LETTER NJAN +105DA ; TODHRI LETTER O +105DB ; TODHRI LETTER PA +105DC ; TODHRI LETTER QA +105DD ; TODHRI LETTER RA +105DE ; TODHRI LETTER RRA +105DF ; TODHRI LETTER SA +105E0 ; TODHRI LETTER SHA +105E1 ; TODHRI LETTER SHTA +105E2 ; TODHRI LETTER TA +105E3 ; TODHRI LETTER THA +105E4 ; TODHRI LETTER U +105E5 ; TODHRI LETTER VA +105E6 ; TODHRI LETTER XA +105E7 ; TODHRI LETTER NXA +105E8 ; TODHRI LETTER XHA +105E9 ; TODHRI LETTER NXHA +105EA ; TODHRI LETTER Y +105EB ; TODHRI LETTER JY +105EC ; TODHRI LETTER ZA +105ED ; TODHRI LETTER ZHA +105EE ; TODHRI LETTER GHA +105EF ; TODHRI LETTER STA +105F0 ; TODHRI LETTER SKAN +105F1 ; TODHRI LETTER KHA +105F2 ; TODHRI LETTER PSA +105F3 ; TODHRI LETTER OO 10600 ; LINEAR A SIGN AB001 10601 ; LINEAR A SIGN AB002 10602 ; LINEAR A SIGN AB003 @@ -44229,6 +44281,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 149866 +# Total code points: 149918 # EOF diff --git a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java index a9ca850c6..6ca4f7d99 100644 --- a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java +++ b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java @@ -487,6 +487,7 @@ public enum Block_Values implements Named { Tibetan("Tibetan"), Tifinagh("Tifinagh"), Tirhuta("Tirhuta"), + Todhri("Todhri"), Toto("Toto"), Transport_And_Map_Symbols("Transport_And_Map"), Unified_Canadian_Aboriginal_Syllabics("UCAS", "Canadian_Syllabics"), @@ -1852,6 +1853,7 @@ public enum Script_Values implements Named { Tibetan("Tibt"), Tirhuta("Tirh"), Tangsa("Tnsa"), + Todhri("Todr"), Toto("Toto"), Ugaritic("Ugar"), Vai("Vaii"), diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt index 3fc09e21a..34cdb0cf3 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt @@ -308,6 +308,7 @@ Thai ; Thai Tibetan ; Tibetan Tifinagh ; Tifinagh Tirhuta ; Tirhuta +Todhri ; Todhri Toto ; Toto Transport_And_Map ; Transport_And_Map_Symbols Ugaritic ; Ugaritic