diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index b4dcd2e48..7318a484b 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ -# DerivedAge-16.0.0.txt -# Date: 2024-04-30, 21:48:12 GMT +# DerivedAge-17.0.0.txt +# Date: 2024-10-16, 15:41:44 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 @@ -2059,4 +2059,14 @@ A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L # Total code points: 5185 +# ================================================ + +# Age=V17_0 + +# Newly assigned in Unicode 17.0.0 (September, 2025) + +107BB..107BF ; 17.0 # [5] MODIFIER LETTER SMALL TURNED T..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR + +# Total code points: 5 + # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 1075638f1..f935d258a 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ -# DerivedCoreProperties-16.0.0.txt -# Date: 2024-05-31, 18:09:32 GMT +# DerivedCoreProperties-17.0.0.txt +# Date: 2024-10-16, 15:42:38 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1007,7 +1007,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 10760..10767 ; Alphabetic # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 10780..10785 ; Alphabetic # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; Alphabetic # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK -107B2..107BA ; Alphabetic # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +107B2..107BF ; Alphabetic # Lm [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 10800..10805 ; Alphabetic # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; Alphabetic # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; Alphabetic # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -1441,7 +1441,7 @@ 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: 142759 +# Total code points: 142764 # ================================================ @@ -2100,7 +2100,7 @@ FF41..FF5A ; Lowercase # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 10780 ; Lowercase # Lm MODIFIER LETTER SMALL CAPITAL AA 10783..10785 ; Lowercase # Lm [3] MODIFIER LETTER SMALL AE..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; Lowercase # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK -107B2..107BA ; Lowercase # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +107B2..107BF ; Lowercase # Lm [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 10CC0..10CF2 ; Lowercase # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 10D70..10D85 ; Lowercase # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA 118C0..118DF ; Lowercase # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO @@ -2139,7 +2139,7 @@ FF41..FF5A ; Lowercase # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 1E030..1E06D ; Lowercase # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E922..1E943 ; Lowercase # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2569 +# Total code points: 2574 # ================================================ @@ -2942,7 +2942,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 10780 ; Cased # Lm MODIFIER LETTER SMALL CAPITAL AA 10783..10785 ; Cased # Lm [3] MODIFIER LETTER SMALL AE..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; Cased # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK -107B2..107BA ; Cased # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +107B2..107BF ; Cased # Lm [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 10C80..10CB2 ; Cased # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 10CC0..10CF2 ; Cased # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 10D50..10D65 ; Cased # L& [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA @@ -2988,7 +2988,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1F150..1F169 ; Cased # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Cased # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 4578 +# Total code points: 4583 # ================================================ @@ -3338,7 +3338,7 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 10376..1037A ; Case_Ignorable # Mn [5] COMBINING OLD PERMIC LETTER AN..COMBINING OLD PERMIC LETTER SII 10780..10785 ; Case_Ignorable # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; Case_Ignorable # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK -107B2..107BA ; Case_Ignorable # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +107B2..107BF ; Case_Ignorable # Lm [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 10A01..10A03 ; Case_Ignorable # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R 10A05..10A06 ; Case_Ignorable # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O 10A0C..10A0F ; Case_Ignorable # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA @@ -3505,7 +3505,7 @@ E0001 ; Case_Ignorable # Cf LANGUAGE TAG E0020..E007F ; Case_Ignorable # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2749 +# Total code points: 2754 # ================================================ @@ -6689,7 +6689,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10760..10767 ; ID_Start # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 10780..10785 ; ID_Start # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; ID_Start # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK -107B2..107BA ; ID_Start # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +107B2..107BF ; ID_Start # Lm [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 10800..10805 ; ID_Start # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; ID_Start # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; ID_Start # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -6962,7 +6962,7 @@ 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: 141269 +# Total code points: 141274 # ================================================ @@ -7844,7 +7844,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 10760..10767 ; ID_Continue # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 10780..10785 ; ID_Continue # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; ID_Continue # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK -107B2..107BA ; ID_Continue # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +107B2..107BF ; ID_Continue # Lm [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 10800..10805 ; ID_Continue # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; ID_Continue # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; ID_Continue # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -8370,7 +8370,7 @@ 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: 144541 +# Total code points: 144546 # ================================================ @@ -8875,7 +8875,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 10760..10767 ; XID_Start # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 10780..10785 ; XID_Start # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; XID_Start # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK -107B2..107BA ; XID_Start # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +107B2..107BF ; XID_Start # Lm [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 10800..10805 ; XID_Start # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; XID_Start # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; XID_Start # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -9148,7 +9148,7 @@ 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: 141246 +# Total code points: 141251 # ================================================ @@ -10031,7 +10031,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 10760..10767 ; XID_Continue # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 10780..10785 ; XID_Continue # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; XID_Continue # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK -107B2..107BA ; XID_Continue # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +107B2..107BF ; XID_Continue # Lm [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 10800..10805 ; XID_Continue # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; XID_Continue # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; XID_Continue # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -10557,7 +10557,7 @@ 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: 144522 +# Total code points: 144527 # ================================================ @@ -12258,7 +12258,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 10760..10767 ; Grapheme_Base # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 10780..10785 ; Grapheme_Base # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; Grapheme_Base # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK -107B2..107BA ; Grapheme_Base # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +107B2..107BF ; Grapheme_Base # Lm [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 10800..10805 ; Grapheme_Base # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; Grapheme_Base # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; Grapheme_Base # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -12812,7 +12812,7 @@ 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: 152730 +# Total code points: 152735 # ================================================ diff --git a/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt b/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt index ce636abb5..f54223fff 100644 --- a/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt +++ b/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt @@ -1,5 +1,5 @@ -# DerivedNormalizationProps-16.0.0.txt -# Date: 2024-04-30, 21:48:18 GMT +# DerivedNormalizationProps-17.0.0.txt +# Date: 2024-10-16, 15:42:48 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 @@ -1644,7 +1644,7 @@ FFED..FFEE ; NFKD_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 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 +107B2..107BF ; NFKD_QC; N # Lm [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 1109A ; NFKD_QC; N # Lo KAITHI LETTER DDDHA 1109C ; NFKD_QC; N # Lo KAITHI LETTER RHA 110AB ; NFKD_QC; N # Lo KAITHI LETTER VA @@ -1753,7 +1753,7 @@ FFED..FFEE ; NFKD_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 1FBF0..1FBF9 ; NFKD_QC; N # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE 2F800..2FA1D ; NFKD_QC; N # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 17085 +# Total code points: 17090 # ================================================ @@ -2072,7 +2072,7 @@ FFE9..FFEC ; NFKC_QC; N # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNW FFED..FFEE ; NFKC_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 10781..10785 ; NFKC_QC; N # Lm [5] MODIFIER LETTER SUPERSCRIPT TRIANGULAR COLON..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; NFKC_QC; N # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK -107B2..107BA ; NFKC_QC; N # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +107B2..107BF ; NFKC_QC; N # Lm [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 1CCD6..1CCEF ; NFKC_QC; N # So [26] OUTLINED LATIN CAPITAL LETTER A..OUTLINED LATIN CAPITAL LETTER Z 1CCF0..1CCF9 ; NFKC_QC; N # Nd [10] OUTLINED DIGIT ZERO..OUTLINED DIGIT NINE 1D15E..1D164 ; NFKC_QC; N # So [7] MUSICAL SYMBOL HALF NOTE..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE @@ -2164,7 +2164,7 @@ FFED..FFEE ; NFKC_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 1FBF0..1FBF9 ; NFKC_QC; N # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE 2F800..2FA1D ; NFKC_QC; N # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 4964 +# Total code points: 4969 # ================================================ @@ -7047,6 +7047,11 @@ FFF0..FFF8 ; NFKC_CF; # Cn [9] ...... -# Total code points: 10554 +# Total code points: 10559 # ================================================ @@ -13181,6 +13186,11 @@ FFF0..FFF8 ; NFKC_SCF; # Cn [9] ...... -# Total code points: 10516 +# Total code points: 10521 # ================================================ @@ -16194,7 +16204,7 @@ FFF0..FFF8 ; Changes_When_NFKC_Casefolded # Cn [9] ...... -# Total code points: 10554 +# Total code points: 10559 # EOF diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index 99f7a31ea..1c8e6b84f 100644 --- a/unicodetools/data/ucd/dev/EastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/EastAsianWidth.txt @@ -1,5 +1,5 @@ # EastAsianWidth-16.0.0.txt -# Date: 2024-04-30, 21:48:20 GMT +# Date: 2024-07-25, 16:10:25 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 @@ -1881,7 +1881,7 @@ FFFD ; A # So REPLACEMENT CHARACTER 10760..10767 ; N # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 10780..10785 ; N # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; N # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK -107B2..107BA ; N # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +107B2..107BF ; N # Lm [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 10800..10805 ; N # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; N # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; N # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 3ce258217..65c1b5a33 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: 2024-07-29, 16:26:55 GMT +# LineBreak-17.0.0.txt +# Date: 2024-10-16, 15:42:55 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 @@ -2735,7 +2735,7 @@ FFFD ; AI # So REPLACEMENT CHARACTER 10760..10767 ; AL # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 10780..10785 ; AL # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; AL # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK -107B2..107BA ; AL # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +107B2..107BF ; AL # Lm [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 10800..10805 ; AL # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; AL # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; AL # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO diff --git a/unicodetools/data/ucd/dev/NormalizationTest.txt b/unicodetools/data/ucd/dev/NormalizationTest.txt index 3aae8f72e..9a0d9265d 100644 --- a/unicodetools/data/ucd/dev/NormalizationTest.txt +++ b/unicodetools/data/ucd/dev/NormalizationTest.txt @@ -1,5 +1,5 @@ # NormalizationTest-16.0.0.txt -# Date: 2024-04-30, 21:48:23 GMT +# Date: 2024-07-25, 16:10:37 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 @@ -15208,6 +15208,11 @@ FFEE;FFEE;FFEE;25CB;25CB; # (￮; ￮; ￮; ○; ○; ) HALFWIDTH WHITE CIRCLE 107B8;107B8;107B8;01C2;01C2; # (𐞸; 𐞸; 𐞸; ǂ; ǂ; ) MODIFIER LETTER ALVEOLAR CLICK 107B9;107B9;107B9;1DF0A;1DF0A; # (𐞹; 𐞹; 𐞹; 𝼊; 𝼊; ) MODIFIER LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 107BA;107BA;107BA;1DF1E;1DF1E; # (𐞺; 𐞺; 𐞺; 𝼞; 𝼞; ) MODIFIER LETTER SMALL S WITH CURL +107BB;107BB;107BB;0287;0287; # (𐞻; 𐞻; 𐞻; ʇ; ʇ; ) MODIFIER LETTER SMALL TURNED T +107BC;107BC;107BC;0296;0296; # (𐞼; 𐞼; 𐞼; ʖ; ʖ; ) MODIFIER LETTER INVERTED GLOTTAL STOP +107BD;107BD;107BD;0297;0297; # (𐞽; 𐞽; 𐞽; ʗ; ʗ; ) MODIFIER LETTER STRETCHED C +107BE;107BE;107BE;029E;029E; # (𐞾; 𐞾; 𐞾; ʞ; ʞ; ) MODIFIER LETTER SMALL TURNED K +107BF;107BF;107BF;1DF0B;1DF0B; # (𐞿; 𐞿; 𐞿; 𝼋; 𝼋; ) MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 1109A;1109A;11099 110BA;1109A;11099 110BA; # (𑂚; 𑂚; 𑂙◌𑂺; 𑂚; 𑂙◌𑂺; ) KAITHI LETTER DDDHA 1109C;1109C;1109B 110BA;1109C;1109B 110BA; # (𑂜; 𑂜; 𑂛◌𑂺; 𑂜; 𑂛◌𑂺; ) KAITHI LETTER RHA 110AB;110AB;110A5 110BA;110AB;110A5 110BA; # (𑂫; 𑂫; 𑂥◌𑂺; 𑂫; 𑂥◌𑂺; ) KAITHI LETTER VA diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt index fae2831e7..c96057088 100644 --- a/unicodetools/data/ucd/dev/PropList.txt +++ b/unicodetools/data/ucd/dev/PropList.txt @@ -1,5 +1,5 @@ # PropList-16.0.0.txt -# Date: 2024-05-31, 18:09:48 GMT +# Date: 2024-07-25, 16:16:59 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 @@ -1227,10 +1227,10 @@ AB69 ; Other_Lowercase # Lm MODIFIER LETTER SMALL TURNED W 10780 ; Other_Lowercase # Lm MODIFIER LETTER SMALL CAPITAL AA 10783..10785 ; Other_Lowercase # Lm [3] MODIFIER LETTER SMALL AE..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; Other_Lowercase # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK -107B2..107BA ; Other_Lowercase # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +107B2..107BF ; Other_Lowercase # Lm [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 1E030..1E06D ; Other_Lowercase # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE -# Total code points: 311 +# Total code points: 316 # ================================================ diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 443a6d2dd..bf54f2236 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: 2024-04-30, 21:48:40 GMT +# Date: 2024-07-25, 16:11:18 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 @@ -696,13 +696,13 @@ FF21..FF3A ; Latin # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT FF41..FF5A ; Latin # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z 10780..10785 ; Latin # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; Latin # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK -107B2..107BA ; Latin # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +107B2..107BF ; Latin # Lm [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 1DF00..1DF09 ; Latin # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0A ; Latin # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF1E ; Latin # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1DF25..1DF2A ; Latin # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK -# Total code points: 1487 +# Total code points: 1492 # ================================================ diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 64258a373..e6ddd45bc 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -18468,6 +18468,11 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 107B8;MODIFIER LETTER ALVEOLAR CLICK;Lm;0;L; 01C2;;;;N;;;;; 107B9;MODIFIER LETTER RETROFLEX CLICK WITH RETROFLEX HOOK;Lm;0;L; 1DF0A;;;;N;;;;; 107BA;MODIFIER LETTER SMALL S WITH CURL;Lm;0;L; 1DF1E;;;;N;;;;; +107BB;MODIFIER LETTER SMALL TURNED T;Lm;0;L; 0287;;;;N;;;;; +107BC;MODIFIER LETTER INVERTED GLOTTAL STOP;Lm;0;L; 0296;;;;N;;;;; +107BD;MODIFIER LETTER STRETCHED C;Lm;0;L; 0297;;;;N;;;;; +107BE;MODIFIER LETTER SMALL TURNED K;Lm;0;L; 029E;;;;N;;;;; +107BF;MODIFIER LETTER SMALL ESH WITH DOUBLE BAR;Lm;0;L; 1DF0B;;;;N;;;;; 10800;CYPRIOT SYLLABLE A;Lo;0;R;;;;;N;;;;; 10801;CYPRIOT SYLLABLE E;Lo;0;R;;;;;N;;;;; 10802;CYPRIOT SYLLABLE I;Lo;0;R;;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index 1ebcd7228..bba502c16 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ # VerticalOrientation-16.0.0.txt -# Date: 2024-04-30, 21:48:42 GMT +# Date: 2024-07-25, 16:11:23 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 @@ -1701,7 +1701,7 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 10760..10767 ; R # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 10780..10785 ; R # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; R # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK -107B2..107BA ; R # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +107B2..107BF ; R # Lm [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 10800..10805 ; R # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; R # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; R # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index ca3689e6b..25a7a54ac 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ -# SentenceBreakProperty-16.0.0.txt -# Date: 2024-07-29, 16:27:32 GMT +# SentenceBreakProperty-17.0.0.txt +# Date: 2024-10-16, 15:44:11 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 @@ -1281,7 +1281,7 @@ FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 10780 ; Lower # Lm MODIFIER LETTER SMALL CAPITAL AA 10783..10785 ; Lower # Lm [3] MODIFIER LETTER SMALL AE..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; Lower # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK -107B2..107BA ; Lower # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +107B2..107BF ; Lower # Lm [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 10CC0..10CF2 ; Lower # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 10D70..10D85 ; Lower # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA 118C0..118DF ; Lower # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO @@ -1320,7 +1320,7 @@ FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1E030..1E06D ; Lower # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E922..1E943 ; Lower # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2522 +# Total code points: 2527 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index e557c3d0d..7a8a2d746 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ -# WordBreakProperty-16.0.0.txt -# Date: 2024-07-29, 16:27:36 GMT +# WordBreakProperty-17.0.0.txt +# Date: 2024-10-16, 15:44:17 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 @@ -1102,7 +1102,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10760..10767 ; ALetter # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 10780..10785 ; ALetter # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; ALetter # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK -107B2..107BA ; ALetter # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +107B2..107BF ; ALetter # Lm [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 10800..10805 ; ALetter # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; ALetter # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; ALetter # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -1355,7 +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: 33791 +# Total code points: 33796 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 2aceac0aa..77164728d 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ -# DerivedBidiClass-16.0.0.txt -# Date: 2024-04-30, 21:48:13 GMT +# DerivedBidiClass-17.0.0.txt +# Date: 2024-10-16, 15:42:32 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -829,7 +829,7 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 10760..10767 ; L # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 10780..10785 ; L # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; L # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK -107B2..107BA ; L # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +107B2..107BF ; L # Lm [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 11000 ; L # Mc BRAHMI SIGN CANDRABINDU 11002 ; L # Mc BRAHMI SIGN VISARGA 11003..11037 ; L # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA @@ -1214,7 +1214,7 @@ 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 815351 code points not listed here. +# The above property value applies to 815346 code points not listed here. # Total code points: 1095513 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index a5d57af96..9678b0c66 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ -# DerivedCombiningClass-16.0.0.txt -# Date: 2024-04-30, 21:48:15 GMT +# DerivedCombiningClass-17.0.0.txt +# Date: 2024-10-16, 15:42:36 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 @@ -1399,7 +1399,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 10760..10767 ; 0 # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 10780..10785 ; 0 # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; 0 # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK -107B2..107BA ; 0 # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +107B2..107BF ; 0 # Lm [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 10800..10805 ; 0 # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; 0 # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; 0 # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -2060,7 +2060,7 @@ 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 821581 code points not listed here. +# The above property value applies to 821576 code points not listed here. # Total code points: 1113178 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedDecompositionType.txt b/unicodetools/data/ucd/dev/extracted/DerivedDecompositionType.txt index a825479ac..30732e33e 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedDecompositionType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedDecompositionType.txt @@ -1,5 +1,5 @@ -# DerivedDecompositionType-16.0.0.txt -# Date: 2024-04-30, 21:48:17 GMT +# DerivedDecompositionType-17.0.0.txt +# Date: 2024-10-16, 15:42:42 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 @@ -879,12 +879,12 @@ AB5C..AB5F ; Super # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMA AB69 ; Super # Lm MODIFIER LETTER SMALL TURNED W 10781..10785 ; Super # Lm [5] MODIFIER LETTER SUPERSCRIPT TRIANGULAR COLON..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; Super # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK -107B2..107BA ; Super # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +107B2..107BF ; Super # Lm [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 1E030..1E050 ; Super # Lm [33] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL PALOCHKA 1E06B..1E06D ; Super # Lm [3] MODIFIER LETTER CYRILLIC SMALL ES WITH DESCENDER..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1F16A..1F16C ; Super # So [3] RAISED MC SIGN..RAISED MR SIGN -# Total code points: 249 +# Total code points: 254 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index cc1d91aaa..0e3686718 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ -# DerivedEastAsianWidth-16.0.0.txt -# Date: 2024-04-30, 21:48:17 GMT +# DerivedEastAsianWidth-17.0.0.txt +# Date: 2024-10-16, 15:42:42 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 @@ -1405,7 +1405,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 10760..10767 ; N # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 10780..10785 ; N # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; N # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK -107B2..107BA ; N # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +107B2..107BF ; N # Lm [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 10800..10805 ; N # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; N # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; N # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -2103,7 +2103,7 @@ 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 761099 code points not listed here. +# The above property value applies to 761094 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 07bf7bca9..10b46c999 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ -# DerivedGeneralCategory-16.0.0.txt -# Date: 2024-04-30, 21:48:17 GMT +# DerivedGeneralCategory-17.0.0.txt +# Date: 2024-10-16, 15:42:43 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 @@ -394,7 +394,7 @@ FFFE..FFFF ; Cn # [2] .. 10768..1077F ; Cn # [24] .. 10786 ; Cn # 107B1 ; Cn # -107BB..107FF ; Cn # [69] .. +107C0..107FF ; Cn # [64] .. 10806..10807 ; Cn # [2] .. 10809 ; Cn # 10836 ; Cn # @@ -747,7 +747,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819533 +# Total code points: 819528 # ================================================ @@ -2156,7 +2156,7 @@ FF70 ; Lm # HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK 10780..10785 ; Lm # [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; Lm # [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK -107B2..107BA ; Lm # [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +107B2..107BF ; Lm # [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 10D4E ; Lm # GARAY VOWEL LENGTH MARK 10D6F ; Lm # GARAY REDUPLICATION MARK 16B40..16B43 ; Lm # [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM @@ -2173,7 +2173,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 1E4EB ; Lm # NAG MUNDARI SIGN OJOD 1E94B ; Lm # ADLAM NASALIZATION MARK -# Total code points: 404 +# Total code points: 409 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 31d143e92..d979ed7cd 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ -# DerivedLineBreak-16.0.0.txt -# Date: 2024-07-29, 16:26:50 GMT +# DerivedLineBreak-17.0.0.txt +# Date: 2024-10-16, 15:42:47 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 @@ -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 757653 code points not listed here. -# Total code points: 895121 +# The above property value applies to 757648 code points not listed here. +# Total code points: 895116 # ================================================ @@ -1251,7 +1251,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 10760..10767 ; AL # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 10780..10785 ; AL # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; AL # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK -107B2..107BA ; AL # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +107B2..107BF ; AL # Lm [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 10800..10805 ; AL # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; AL # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; AL # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -1613,7 +1613,7 @@ 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: 26679 +# Total code points: 26684 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 07b0176b5..34886a06a 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ -# DerivedName-16.0.0.txt -# Date: 2024-04-30, 21:48:18 GMT +# DerivedName-17.0.0.txt +# Date: 2024-10-16, 15:42:47 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 @@ -29133,6 +29133,11 @@ FFFD ; REPLACEMENT CHARACTER 107B8 ; MODIFIER LETTER ALVEOLAR CLICK 107B9 ; MODIFIER LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 107BA ; MODIFIER LETTER SMALL S WITH CURL +107BB ; MODIFIER LETTER SMALL TURNED T +107BC ; MODIFIER LETTER INVERTED GLOTTAL STOP +107BD ; MODIFIER LETTER STRETCHED C +107BE ; MODIFIER LETTER SMALL TURNED K +107BF ; MODIFIER LETTER SMALL ESH WITH DOUBLE BAR 10800 ; CYPRIOT SYLLABLE A 10801 ; CYPRIOT SYLLABLE E 10802 ; CYPRIOT SYLLABLE I @@ -45367,6 +45372,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 154998 +# Total code points: 155003 # EOF diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt index 570de2e90..4b35efd6d 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt @@ -733,7 +733,7 @@ Let $nonLowercaseSmallModifierLetters := [ \p{gc=Lm} & \p{name=/^ARABIC SMALL/} ## Consistency of Lowercase with decompositions. # Note that the same is not true of Uppercase. # A non-lowercase character has non-lowercase characters in its decomposition, -# or its decomposition is (㋍ etc.). +# or it its decomposition is (㋍ etc.). In [\P{Lowercase} - \p{dt=square}], \p{Lowercase} * toNFKD ≠ toNFKD ## Joining_Type and Joining_Group