diff --git a/unicodetools/data/ucd/dev/Blocks.txt b/unicodetools/data/ucd/dev/Blocks.txt index 1517dde0c..be3e10ce3 100644 --- a/unicodetools/data/ucd/dev/Blocks.txt +++ b/unicodetools/data/ucd/dev/Blocks.txt @@ -228,6 +228,7 @@ FFF0..FFFF; Specials 108E0..108FF; Hatran 10900..1091F; Phoenician 10920..1093F; Lydian +10940..1095C; Sidetic 10980..1099F; Meroitic Hieroglyphs 109A0..109FF; Meroitic Cursive 10A00..10A5F; Kharoshthi diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index b69576b8f..bd835436c 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, 12:16:05 GMT +# Date: 2024-11-14, 14:37:04 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2080,8 +2080,9 @@ A7F1 ; 17.0 # MODIFIER LETTER CAPITAL S FBC3..FBD2 ; 17.0 # [16] ARABIC LIGATURE JALLA WA-ALAA..ARABIC LIGATURE ALAYHI AR-RAHMAH FD90..FD91 ; 17.0 # [2] ARABIC LIGATURE RAHMATU ALLAAHI ALAYH..ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FDC8..FDCE ; 17.0 # [7] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIGATURE KARRAMA ALLAAHU WAJHAH +10940..1095C ; 17.0 # [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10ED1..10ED8 ; 17.0 # [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH -# Total code points: 72 +# Total code points: 101 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index ddd0bed1b..a301fb3bd 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, 12:16:23 GMT +# Date: 2024-11-14, 14:37:21 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 @@ -1018,6 +1018,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 108F4..108F5 ; Alphabetic # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW 10900..10915 ; Alphabetic # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU 10920..10939 ; Alphabetic # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C +10940..1095C ; Alphabetic # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; Alphabetic # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BE..109BF ; Alphabetic # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN 10A00 ; Alphabetic # Lo KHAROSHTHI LETTER A @@ -1439,7 +1440,7 @@ 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: 142768 +# Total code points: 142797 # ================================================ @@ -6710,6 +6711,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 108F4..108F5 ; ID_Start # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW 10900..10915 ; ID_Start # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU 10920..10939 ; ID_Start # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C +10940..1095C ; ID_Start # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; ID_Start # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BE..109BF ; ID_Start # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN 10A00 ; ID_Start # Lo KHAROSHTHI LETTER A @@ -6970,7 +6972,7 @@ 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: 141278 +# Total code points: 141307 # ================================================ @@ -7864,6 +7866,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 108F4..108F5 ; ID_Continue # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW 10900..10915 ; ID_Continue # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU 10920..10939 ; ID_Continue # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C +10940..1095C ; ID_Continue # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; ID_Continue # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BE..109BF ; ID_Continue # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN 10A00 ; ID_Continue # Lo KHAROSHTHI LETTER A @@ -8377,7 +8380,7 @@ 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: 144579 +# Total code points: 144608 # ================================================ @@ -8893,6 +8896,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 108F4..108F5 ; XID_Start # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW 10900..10915 ; XID_Start # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU 10920..10939 ; XID_Start # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C +10940..1095C ; XID_Start # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; XID_Start # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BE..109BF ; XID_Start # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN 10A00 ; XID_Start # Lo KHAROSHTHI LETTER A @@ -9153,7 +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: 141255 +# Total code points: 141284 # ================================================ @@ -10048,6 +10052,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 108F4..108F5 ; XID_Continue # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW 10900..10915 ; XID_Continue # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU 10920..10939 ; XID_Continue # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C +10940..1095C ; XID_Continue # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; XID_Continue # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BE..109BF ; XID_Continue # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN 10A00 ; XID_Continue # Lo KHAROSHTHI LETTER A @@ -10561,7 +10566,7 @@ 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: 144560 +# Total code points: 144589 # ================================================ @@ -12284,6 +12289,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1091F ; Grapheme_Base # Po PHOENICIAN WORD SEPARATOR 10920..10939 ; Grapheme_Base # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C 1093F ; Grapheme_Base # Po LYDIAN TRIANGULAR MARK +10940..1095C ; Grapheme_Base # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; Grapheme_Base # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BC..109BD ; Grapheme_Base # No [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF 109BE..109BF ; Grapheme_Base # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN @@ -12817,7 +12823,7 @@ 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: 152773 +# Total code points: 152802 # ================================================ diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index 962986fa9..1775ad934 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, 12:16:27 GMT +# Date: 2024-11-14, 14:37:25 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 @@ -1904,6 +1904,7 @@ FFFD ; A # So REPLACEMENT CHARACTER 1091F ; N # Po PHOENICIAN WORD SEPARATOR 10920..10939 ; N # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C 1093F ; N # Po LYDIAN TRIANGULAR MARK +10940..1095C ; N # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..1099F ; N # Lo [32] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC HIEROGLYPHIC SYMBOL VIDJ-2 109A0..109B7 ; N # Lo [24] MEROITIC CURSIVE LETTER A..MEROITIC CURSIVE LETTER DA 109BC..109BD ; N # No [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 4f0edadf4..eef5add38 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, 12:16:28 GMT +# Date: 2024-11-14, 14:37:26 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 @@ -2759,6 +2759,7 @@ FFFD ; AI # So REPLACEMENT CHARACTER 1091F ; BA # Po PHOENICIAN WORD SEPARATOR 10920..10939 ; AL # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C 1093F ; AL # Po LYDIAN TRIANGULAR MARK +10940..1095C ; AL # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..1099F ; AL # Lo [32] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC HIEROGLYPHIC SYMBOL VIDJ-2 109A0..109B7 ; AL # Lo [24] MEROITIC CURSIVE LETTER A..MEROITIC CURSIVE LETTER DA 109BC..109BD ; AL # No [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF diff --git a/unicodetools/data/ucd/dev/PropertyValueAliases.txt b/unicodetools/data/ucd/dev/PropertyValueAliases.txt index 4358a787e..7b9734001 100644 --- a/unicodetools/data/ucd/dev/PropertyValueAliases.txt +++ b/unicodetools/data/ucd/dev/PropertyValueAliases.txt @@ -1,5 +1,5 @@ # PropertyValueAliases-17.0.0.txt -# Date: 2024-09-11, 23:38:17 GMT +# Date: 2024-10-16, 17:27:56 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 @@ -423,6 +423,7 @@ blk; Sharada ; Sharada blk; Shavian ; Shavian blk; Shorthand_Format_Controls ; Shorthand_Format_Controls blk; Siddham ; Siddham +blk; Sidetic ; Sidetic blk; Sinhala ; Sinhala blk; Sinhala_Archaic_Numbers ; Sinhala_Archaic_Numbers blk; Small_Forms ; Small_Form_Variants @@ -1439,6 +1440,7 @@ sc ; Sgnw ; SignWriting sc ; Shaw ; Shavian sc ; Shrd ; Sharada sc ; Sidd ; Siddham +sc ; Sidt ; Sidetic sc ; Sind ; Khudawadi sc ; Sinh ; Sinhala sc ; Sogd ; Sogdian diff --git a/unicodetools/data/ucd/dev/ScriptExtensions.txt b/unicodetools/data/ucd/dev/ScriptExtensions.txt index 140901a87..27e16cbe4 100644 --- a/unicodetools/data/ucd/dev/ScriptExtensions.txt +++ b/unicodetools/data/ucd/dev/ScriptExtensions.txt @@ -1,5 +1,5 @@ -# ScriptExtensions-16.0.0.txt -# Date: 2024-07-30, 19:38:00 GMT +# ScriptExtensions-17.0.0.txt +# Date: 2024-10-16, 17:28:17 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 diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index d7cf7e07c..da4dc7bdf 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, 12:16:50 GMT +# Date: 2024-11-14, 14:37:44 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 @@ -3126,4 +3126,10 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI # Total code points: 80 +# ================================================ + +10940..1095C ; Sidetic # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 + +# Total code points: 29 + # EOF diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index ec9c0e0f3..d61a3c99d 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -18772,6 +18772,35 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 10938;LYDIAN LETTER NN;Lo;0;R;;;;;N;;;;; 10939;LYDIAN LETTER C;Lo;0;R;;;;;N;;;;; 1093F;LYDIAN TRIANGULAR MARK;Po;0;R;;;;;N;;;;; +10940;SIDETIC LETTER N01;Lo;0;R;;;;;N;;;;; +10941;SIDETIC LETTER N02;Lo;0;R;;;;;N;;;;; +10942;SIDETIC LETTER N03;Lo;0;R;;;;;N;;;;; +10943;SIDETIC LETTER N04;Lo;0;R;;;;;N;;;;; +10944;SIDETIC LETTER N05;Lo;0;R;;;;;N;;;;; +10945;SIDETIC LETTER N06;Lo;0;R;;;;;N;;;;; +10946;SIDETIC LETTER N07;Lo;0;R;;;;;N;;;;; +10947;SIDETIC LETTER N08;Lo;0;R;;;;;N;;;;; +10948;SIDETIC LETTER N09;Lo;0;R;;;;;N;;;;; +10949;SIDETIC LETTER N10;Lo;0;R;;;;;N;;;;; +1094A;SIDETIC LETTER N11;Lo;0;R;;;;;N;;;;; +1094B;SIDETIC LETTER N12;Lo;0;R;;;;;N;;;;; +1094C;SIDETIC LETTER N13;Lo;0;R;;;;;N;;;;; +1094D;SIDETIC LETTER N14;Lo;0;R;;;;;N;;;;; +1094E;SIDETIC LETTER N15;Lo;0;R;;;;;N;;;;; +1094F;SIDETIC LETTER N16;Lo;0;R;;;;;N;;;;; +10950;SIDETIC LETTER N17;Lo;0;R;;;;;N;;;;; +10951;SIDETIC LETTER N18;Lo;0;R;;;;;N;;;;; +10952;SIDETIC LETTER N19;Lo;0;R;;;;;N;;;;; +10953;SIDETIC LETTER N20;Lo;0;R;;;;;N;;;;; +10954;SIDETIC LETTER N21;Lo;0;R;;;;;N;;;;; +10955;SIDETIC LETTER N22;Lo;0;R;;;;;N;;;;; +10956;SIDETIC LETTER N23;Lo;0;R;;;;;N;;;;; +10957;SIDETIC LETTER N24;Lo;0;R;;;;;N;;;;; +10958;SIDETIC LETTER N25;Lo;0;R;;;;;N;;;;; +10959;SIDETIC LETTER N26;Lo;0;R;;;;;N;;;;; +1095A;SIDETIC LETTER N27;Lo;0;R;;;;;N;;;;; +1095B;SIDETIC LETTER N28;Lo;0;R;;;;;N;;;;; +1095C;SIDETIC LETTER N29;Lo;0;R;;;;;N;;;;; 10980;MEROITIC HIEROGLYPHIC LETTER A;Lo;0;R;;;;;N;;;;; 10981;MEROITIC HIEROGLYPHIC LETTER E;Lo;0;R;;;;;N;;;;; 10982;MEROITIC HIEROGLYPHIC LETTER I;Lo;0;R;;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index b4dc08030..05cd2171f 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, 12:16:52 GMT +# Date: 2024-11-14, 14:37:46 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 @@ -1725,6 +1725,7 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 1091F ; R # Po PHOENICIAN WORD SEPARATOR 10920..10939 ; R # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C 1093F ; R # Po LYDIAN TRIANGULAR MARK +10940..1095C ; R # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..1099F ; U # Lo [32] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC HIEROGLYPHIC SYMBOL VIDJ-2 109A0..109B7 ; R # Lo [24] MEROITIC CURSIVE LETTER A..MEROITIC CURSIVE LETTER DA 109BC..109BD ; R # No [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 44f556893..5e1badd5b 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: 2024-11-13, 22:19:10 GMT +# Date: 2024-11-14, 14:37:45 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 and license, see https://www.unicode.org/terms_of_use.html @@ -2372,6 +2372,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 108F4..108F5 ; OLetter # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW 10900..10915 ; OLetter # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU 10920..10939 ; OLetter # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C +10940..1095C ; OLetter # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; OLetter # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BE..109BF ; OLetter # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN 10A00 ; OLetter # Lo KHAROSHTHI LETTER A @@ -2591,7 +2592,7 @@ 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: 136913 +# Total code points: 136942 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index 6ddc428da..25d826481 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: 2024-11-13, 22:19:12 GMT +# Date: 2024-11-14, 14:37:47 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 @@ -1114,6 +1114,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 108F4..108F5 ; ALetter # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW 10900..10915 ; ALetter # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU 10920..10939 ; ALetter # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C +10940..1095C ; ALetter # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; ALetter # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BE..109BF ; ALetter # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN 10A00 ; ALetter # Lo KHAROSHTHI LETTER A @@ -1354,7 +1355,7 @@ 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: 33800 +# Total code points: 33829 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 1a3186df2..c87254b23 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, 12:16:21 GMT +# Date: 2024-11-14, 14:37:19 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 @@ -67,6 +67,7 @@ # 108E0..108FF Hatran # 10900..1091F Phoenician # 10920..1093F Lydian +# 10940..1095C Sidetic # 10980..1099F Meroitic_Hieroglyphs # 109A0..109FF Meroitic_Cursive # 10A00..10A5F Kharoshthi @@ -1267,6 +1268,7 @@ FB46..FB4F ; R # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE AL 10916..1091B ; R # No [6] PHOENICIAN NUMBER ONE..PHOENICIAN NUMBER THREE 10920..10939 ; R # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C 1093F ; R # Po LYDIAN TRIANGULAR MARK +10940..1095C ; R # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; R # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BC..109BD ; R # No [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF 109BE..109BF ; R # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN @@ -1325,7 +1327,7 @@ FB46..FB4F ; R # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE AL 1E950..1E959 ; R # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1E95E..1E95F ; R # Po [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK -# The above property value applies to 2087 code points not listed here. +# The above property value applies to 2058 code points not listed here. # Total code points: 3631 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index b03e18c1c..158023481 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, 12:16:23 GMT +# Date: 2024-11-14, 14:37:21 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 @@ -1420,6 +1420,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1091F ; 0 # Po PHOENICIAN WORD SEPARATOR 10920..10939 ; 0 # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C 1093F ; 0 # Po LYDIAN TRIANGULAR MARK +10940..1095C ; 0 # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; 0 # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BC..109BD ; 0 # No [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF 109BE..109BF ; 0 # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN @@ -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 821509 code points not listed here. +# The above property value applies to 821480 code points not listed here. # Total code points: 1113151 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index e8d16e4a9..60379f00a 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, 12:16:24 GMT +# Date: 2024-11-14, 14:37:22 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 @@ -1427,6 +1427,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 1091F ; N # Po PHOENICIAN WORD SEPARATOR 10920..10939 ; N # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C 1093F ; N # Po LYDIAN TRIANGULAR MARK +10940..1095C ; N # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; N # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BC..109BD ; N # No [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF 109BE..109BF ; N # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN @@ -2104,7 +2105,7 @@ 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 761027 code points not listed here. +# The above property value applies to 760998 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 44b621cbf..7bc6babc2 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, 12:16:25 GMT +# Date: 2024-11-14, 14:37:23 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 @@ -400,7 +400,7 @@ FFFE..FFFF ; Cn # [2] .. 108F6..108FA ; Cn # [5] .. 1091C..1091E ; Cn # [3] .. 1093A..1093E ; Cn # [5] .. -10940..1097F ; Cn # [64] .. +1095D..1097F ; Cn # [35] .. 109B8..109BB ; Cn # [4] .. 109D0..109D1 ; Cn # [2] .. 10A04 ; Cn # @@ -741,7 +741,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819461 +# Total code points: 819432 # ================================================ @@ -2503,6 +2503,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 108F4..108F5 ; Lo # [2] HATRAN LETTER SHIN..HATRAN LETTER TAW 10900..10915 ; Lo # [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU 10920..10939 ; Lo # [26] LYDIAN LETTER A..LYDIAN LETTER C +10940..1095C ; Lo # [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; Lo # [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BE..109BF ; Lo # [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN 10A00 ; Lo # KHAROSHTHI LETTER A @@ -2707,7 +2708,7 @@ 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: 136482 +# Total code points: 136511 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 26e8f2b03..f6600add6 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, 12:16:26 GMT +# Date: 2024-11-14, 14:37:24 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 757581 code points not listed here. -# Total code points: 895049 +# The above property value applies to 757552 code points not listed here. +# Total code points: 895020 # ================================================ @@ -1271,6 +1271,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 10916..1091B ; AL # No [6] PHOENICIAN NUMBER ONE..PHOENICIAN NUMBER THREE 10920..10939 ; AL # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C 1093F ; AL # Po LYDIAN TRIANGULAR MARK +10940..1095C ; AL # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; AL # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BC..109BD ; AL # No [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF 109BE..109BF ; AL # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN @@ -1614,7 +1615,7 @@ 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: 26722 +# Total code points: 26751 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 8cafde19a..85af14a48 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, 12:16:26 GMT +# Date: 2024-11-14, 14:37:24 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 @@ -29437,6 +29437,35 @@ FFFD ; REPLACEMENT CHARACTER 10938 ; LYDIAN LETTER NN 10939 ; LYDIAN LETTER C 1093F ; LYDIAN TRIANGULAR MARK +10940 ; SIDETIC LETTER N01 +10941 ; SIDETIC LETTER N02 +10942 ; SIDETIC LETTER N03 +10943 ; SIDETIC LETTER N04 +10944 ; SIDETIC LETTER N05 +10945 ; SIDETIC LETTER N06 +10946 ; SIDETIC LETTER N07 +10947 ; SIDETIC LETTER N08 +10948 ; SIDETIC LETTER N09 +10949 ; SIDETIC LETTER N10 +1094A ; SIDETIC LETTER N11 +1094B ; SIDETIC LETTER N12 +1094C ; SIDETIC LETTER N13 +1094D ; SIDETIC LETTER N14 +1094E ; SIDETIC LETTER N15 +1094F ; SIDETIC LETTER N16 +10950 ; SIDETIC LETTER N17 +10951 ; SIDETIC LETTER N18 +10952 ; SIDETIC LETTER N19 +10953 ; SIDETIC LETTER N20 +10954 ; SIDETIC LETTER N21 +10955 ; SIDETIC LETTER N22 +10956 ; SIDETIC LETTER N23 +10957 ; SIDETIC LETTER N24 +10958 ; SIDETIC LETTER N25 +10959 ; SIDETIC LETTER N26 +1095A ; SIDETIC LETTER N27 +1095B ; SIDETIC LETTER N28 +1095C ; SIDETIC LETTER N29 10980 ; MEROITIC HIEROGLYPHIC LETTER A 10981 ; MEROITIC HIEROGLYPHIC LETTER E 10982 ; MEROITIC HIEROGLYPHIC LETTER I @@ -45439,6 +45468,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 155070 +# Total code points: 155099 # EOF diff --git a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java index 55107dc2a..ff767d030 100644 --- a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java +++ b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java @@ -448,6 +448,7 @@ public enum Block_Values implements Named { Shavian("Shavian"), Shorthand_Format_Controls("Shorthand_Format_Controls"), Siddham("Siddham"), + Sidetic("Sidetic"), Sinhala("Sinhala"), Sinhala_Archaic_Numbers("Sinhala_Archaic_Numbers"), Small_Form_Variants("Small_Forms"), @@ -1969,6 +1970,7 @@ public enum Script_Values implements Named { Shavian("Shaw"), Sharada("Shrd"), Siddham("Sidd"), + Sidetic("Sidt"), Khudawadi("Sind"), Sinhala("Sinh"), Sogdian("Sogd"), 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 eaa03a0f7..c1800d243 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt @@ -267,6 +267,7 @@ Sharada ; Sharada Shavian ; Shavian Shorthand_Format_Controls ; Shorthand_Format_Controls Siddham ; Siddham +Sidetic ; Sidetic Sinhala ; Sinhala Sinhala_Archaic_Numbers ; Sinhala_Archaic_Numbers Small_Forms ; Small_Form_Variants