diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index 18d53a3f0..4c2d61fc0 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: 2025-01-27, 18:09:08 GMT +# Date: 2025-01-30, 20:54:04 GMT # © 2025 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 @@ -2095,6 +2095,7 @@ FDC8..FDCE ; 17.0 # [7] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIG 187F8..187FF ; 17.0 # [8] TANGUT IDEOGRAPH-187F8..TANGUT IDEOGRAPH-187FF 18D09..18D1E ; 17.0 # [22] TANGUT IDEOGRAPH-18D09..TANGUT IDEOGRAPH-18D1E 18D80..18DF2 ; 17.0 # [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883 +1B126 ; 17.0 # KATAKANA DIGRAPH YORI 1CCFA..1CCFC ; 17.0 # [3] SNAKE SYMBOL..NOSE SYMBOL 1CEBA..1CED0 ; 17.0 # [23] FRAGILE SYMBOL..LEUKOTHEA 1CEE0..1CEF0 ; 17.0 # [17] GEOMANTIC FIGURE POPULUS..MEDIUM SMALL WHITE CIRCLE WITH HORIZONTAL BAR @@ -2116,6 +2117,6 @@ FDC8..FDCE ; 17.0 # [7] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIG 2B73A..2B73E ; 17.0 # [5] CJK UNIFIED IDEOGRAPH-2B73A..CJK UNIFIED IDEOGRAPH-2B73E 323B0..33479 ; 17.0 # [4298] CJK UNIFIED IDEOGRAPH-323B0..CJK UNIFIED IDEOGRAPH-33479 -# Total code points: 4836 +# Total code points: 4837 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 44b253f44..a58c77b10 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: 2025-01-27, 18:09:11 GMT +# Date: 2025-01-30, 20:54:25 GMT # © 2025 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 @@ -1346,6 +1346,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 1AFF5..1AFFB ; Alphabetic # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 1AFFD..1AFFE ; Alphabetic # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1B000..1B122 ; Alphabetic # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU +1B126 ; Alphabetic # Lo KATAKANA DIGRAPH YORI 1B132 ; Alphabetic # Lo HIRAGANA LETTER SMALL KO 1B150..1B152 ; Alphabetic # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B155 ; Alphabetic # Lo KATAKANA LETTER SMALL KO @@ -1471,7 +1472,7 @@ 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..33479 ; Alphabetic # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479 -# Total code points: 147441 +# Total code points: 147442 # ================================================ @@ -6934,6 +6935,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1AFF5..1AFFB ; ID_Start # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 1AFFD..1AFFE ; ID_Start # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1B000..1B122 ; ID_Start # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU +1B126 ; ID_Start # Lo KATAKANA DIGRAPH YORI 1B132 ; ID_Start # Lo HIRAGANA LETTER SMALL KO 1B150..1B152 ; ID_Start # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B155 ; ID_Start # Lo KATAKANA LETTER SMALL KO @@ -7044,7 +7046,7 @@ 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..33479 ; ID_Start # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479 -# Total code points: 145935 +# Total code points: 145936 # ================================================ @@ -8332,6 +8334,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 1AFF5..1AFFB ; ID_Continue # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 1AFFD..1AFFE ; ID_Continue # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1B000..1B122 ; ID_Continue # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU +1B126 ; ID_Continue # Lo KATAKANA DIGRAPH YORI 1B132 ; ID_Continue # Lo HIRAGANA LETTER SMALL KO 1B150..1B152 ; ID_Continue # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B155 ; ID_Continue # Lo KATAKANA LETTER SMALL KO @@ -8484,7 +8487,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 31350..33479 ; ID_Continue # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479 E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 149273 +# Total code points: 149274 # ================================================ @@ -9169,6 +9172,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1AFF5..1AFFB ; XID_Start # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 1AFFD..1AFFE ; XID_Start # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1B000..1B122 ; XID_Start # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU +1B126 ; XID_Start # Lo KATAKANA DIGRAPH YORI 1B132 ; XID_Start # Lo HIRAGANA LETTER SMALL KO 1B150..1B152 ; XID_Start # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B155 ; XID_Start # Lo KATAKANA LETTER SMALL KO @@ -9279,7 +9283,7 @@ 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..33479 ; XID_Start # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479 -# Total code points: 145912 +# Total code points: 145913 # ================================================ @@ -10568,6 +10572,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 1AFF5..1AFFB ; XID_Continue # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 1AFFD..1AFFE ; XID_Continue # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1B000..1B122 ; XID_Continue # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU +1B126 ; XID_Continue # Lo KATAKANA DIGRAPH YORI 1B132 ; XID_Continue # Lo HIRAGANA LETTER SMALL KO 1B150..1B152 ; XID_Continue # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B155 ; XID_Continue # Lo KATAKANA LETTER SMALL KO @@ -10720,7 +10725,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 31350..33479 ; XID_Continue # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479 E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 149254 +# Total code points: 149255 # ================================================ @@ -12805,6 +12810,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1AFF5..1AFFB ; Grapheme_Base # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 1AFFD..1AFFE ; Grapheme_Base # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1B000..1B122 ; Grapheme_Base # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU +1B126 ; Grapheme_Base # Lo KATAKANA DIGRAPH YORI 1B132 ; Grapheme_Base # Lo HIRAGANA LETTER SMALL KO 1B150..1B152 ; Grapheme_Base # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B155 ; Grapheme_Base # Lo KATAKANA LETTER SMALL KO @@ -13016,7 +13022,7 @@ 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..33479 ; Grapheme_Base # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479 -# Total code points: 157523 +# Total code points: 157524 # ================================================ diff --git a/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt b/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt index 448ba69d6..3007d98d6 100644 --- a/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt +++ b/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt @@ -1,5 +1,5 @@ # DerivedNormalizationProps-17.0.0.txt -# Date: 2025-01-27, 18:09:14 GMT +# Date: 2025-01-30, 20:54:29 GMT # © 2025 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 @@ -1663,6 +1663,7 @@ FFED..FFEE ; NFKD_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 11938 ; NFKD_QC; N # Mc DIVES AKURU VOWEL SIGN O 16121..16128 ; NFKD_QC; N # Mn [8] GURUNG KHEMA VOWEL SIGN U..GURUNG KHEMA VOWEL SIGN AU 16D68..16D6A ; NFKD_QC; N # Lo [3] KIRAT RAI VOWEL SIGN AI..KIRAT RAI VOWEL SIGN AU +1B126 ; NFKD_QC; N # Lo KATAKANA DIGRAPH YORI 1CCD6..1CCEF ; NFKD_QC; N # So [26] OUTLINED LATIN CAPITAL LETTER A..OUTLINED LATIN CAPITAL LETTER Z 1CCF0..1CCF9 ; NFKD_QC; N # Nd [10] OUTLINED DIGIT ZERO..OUTLINED DIGIT NINE 1D15E..1D164 ; NFKD_QC; N # So [7] MUSICAL SYMBOL HALF NOTE..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE @@ -1754,7 +1755,7 @@ FFED..FFEE ; NFKD_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 1FBF0..1FBF9 ; NFKD_QC; N # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE 2F800..2FA1D ; NFKD_QC; N # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 17086 +# Total code points: 17087 # ================================================ @@ -2074,6 +2075,7 @@ FFED..FFEE ; NFKC_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 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 +1B126 ; NFKC_QC; N # Lo KATAKANA DIGRAPH YORI 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 @@ -2165,7 +2167,7 @@ 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: 4965 +# Total code points: 4966 # ================================================ @@ -2827,6 +2829,7 @@ FFE3 ; Expands_On_NFKD # Sk FULLWIDTH MACRON 11938 ; Expands_On_NFKD # Mc DIVES AKURU VOWEL SIGN O 16121..16128 ; Expands_On_NFKD # Mn [8] GURUNG KHEMA VOWEL SIGN U..GURUNG KHEMA VOWEL SIGN AU 16D68..16D6A ; Expands_On_NFKD # Lo [3] KIRAT RAI VOWEL SIGN AI..KIRAT RAI VOWEL SIGN AU +1B126 ; Expands_On_NFKD # Lo KATAKANA DIGRAPH YORI 1D15E..1D164 ; Expands_On_NFKD # So [7] MUSICAL SYMBOL HALF NOTE..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE 1D1BB..1D1C0 ; Expands_On_NFKD # So [6] MUSICAL SYMBOL MINIMA..MUSICAL SYMBOL FUSA BLACK 1F100..1F10A ; Expands_On_NFKD # No [11] DIGIT ZERO FULL STOP..DIGIT NINE COMMA @@ -2839,7 +2842,7 @@ 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: 13410 +# Total code points: 13411 # ================================================ @@ -2966,6 +2969,7 @@ FE74 ; Expands_On_NFKC # Lo ARABIC KASRATAN ISOLATED FORM FE76..FE7F ; Expands_On_NFKC # Lo [10] ARABIC FATHA ISOLATED FORM..ARABIC SUKUN MEDIAL FORM FEF5..FEFC ; Expands_On_NFKC # Lo [8] ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE ISOLATED FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM FFE3 ; Expands_On_NFKC # Sk FULLWIDTH MACRON +1B126 ; Expands_On_NFKC # Lo KATAKANA DIGRAPH YORI 1D15E..1D164 ; Expands_On_NFKC # So [7] MUSICAL SYMBOL HALF NOTE..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE 1D1BB..1D1C0 ; Expands_On_NFKC # So [6] MUSICAL SYMBOL MINIMA..MUSICAL SYMBOL FUSA BLACK 1F100..1F10A ; Expands_On_NFKC # No [11] DIGIT ZERO FULL STOP..DIGIT NINE COMMA @@ -2977,7 +2981,7 @@ FFE3 ; Expands_On_NFKC # Sk FULLWIDTH MACRON 1F200..1F201 ; Expands_On_NFKC # So [2] SQUARE HIRAGANA HOKA..SQUARED KATAKANA KOKO 1F240..1F248 ; Expands_On_NFKC # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 -# Total code points: 1237 +# Total code points: 1238 # ================================================ @@ -7214,6 +7218,7 @@ FFF0..FFF8 ; NFKC_CF; # Cn [9] ...... -# Total code points: 10583 +# Total code points: 10584 # ================================================ @@ -13377,6 +13382,7 @@ FFF0..FFF8 ; NFKC_SCF; # Cn [9] ...... -# Total code points: 10545 +# Total code points: 10546 # ================================================ @@ -16262,6 +16268,7 @@ FFF0..FFF8 ; Changes_When_NFKC_Casefolded # Cn [9] ...... -# Total code points: 10583 +# Total code points: 10584 # EOF diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index a5c270b19..7c1cf4107 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: 2025-01-27, 18:09:15 GMT +# Date: 2025-01-30, 20:54:30 GMT # © 2025 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 @@ -2395,6 +2395,7 @@ FFFD ; A # So REPLACEMENT CHARACTER 1AFFD..1AFFE ; W # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1B000..1B0FF ; W # Lo [256] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER RE-2 1B100..1B122 ; W # Lo [35] HENTAIGANA LETTER RE-3..KATAKANA LETTER ARCHAIC WU +1B126 ; W # Lo KATAKANA DIGRAPH YORI 1B132 ; W # Lo HIRAGANA LETTER SMALL KO 1B150..1B152 ; W # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B155 ; W # Lo KATAKANA LETTER SMALL KO diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index e122f19e6..a1864074d 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: 2025-01-27, 18:09:16 GMT +# Date: 2025-01-30, 20:54:33 GMT # © 2025 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 @@ -3306,6 +3306,7 @@ FFFD ; AI # So REPLACEMENT CHARACTER 1AFFD..1AFFE ; AL # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1B000..1B0FF ; ID # Lo [256] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER RE-2 1B100..1B122 ; ID # Lo [35] HENTAIGANA LETTER RE-3..KATAKANA LETTER ARCHAIC WU +1B126 ; ID # Lo KATAKANA DIGRAPH YORI 1B132 ; CJ # Lo HIRAGANA LETTER SMALL KO 1B150..1B152 ; CJ # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B155 ; CJ # Lo KATAKANA LETTER SMALL KO diff --git a/unicodetools/data/ucd/dev/NormalizationTest.txt b/unicodetools/data/ucd/dev/NormalizationTest.txt index 9eee32616..94c61ea26 100644 --- a/unicodetools/data/ucd/dev/NormalizationTest.txt +++ b/unicodetools/data/ucd/dev/NormalizationTest.txt @@ -1,5 +1,5 @@ # NormalizationTest-17.0.0.txt -# Date: 2025-01-27, 18:09:23 GMT +# Date: 2025-01-30, 20:54:40 GMT # © 2025 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 @@ -15240,6 +15240,7 @@ FFEE;FFEE;FFEE;25CB;25CB; # (￮; ￮; ￮; ○; ○; ) HALFWIDTH WHITE CIRCLE 16D68;16D68;16D67 16D67;16D68;16D67 16D67; # (𖵨; 𖵨; 𖵨; 𖵨; 𖵨; ) KIRAT RAI VOWEL SIGN AI 16D69;16D69;16D63 16D67;16D69;16D63 16D67; # (𖵩; 𖵩; 𖵩; 𖵩; 𖵩; ) KIRAT RAI VOWEL SIGN O 16D6A;16D6A;16D63 16D67 16D67;16D6A;16D63 16D67 16D67; # (𖵪; 𖵪; 𖵪; 𖵪; 𖵪; ) KIRAT RAI VOWEL SIGN AU +1B126;1B126;1B126;30E8 30EA;30E8 30EA; # (𛄦; 𛄦; 𛄦; ヨリ; ヨリ; ) KATAKANA DIGRAPH YORI 1CCD6;1CCD6;1CCD6;0041;0041; # (𜳖; 𜳖; 𜳖; A; A; ) OUTLINED LATIN CAPITAL LETTER A 1CCD7;1CCD7;1CCD7;0042;0042; # (𜳗; 𜳗; 𜳗; B; B; ) OUTLINED LATIN CAPITAL LETTER B 1CCD8;1CCD8;1CCD8;0043;0043; # (𜳘; 𜳘; 𜳘; C; C; ) OUTLINED LATIN CAPITAL LETTER C diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 139c00537..f8e2fce09 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: 2025-01-27, 18:09:39 GMT +# Date: 2025-01-30, 20:55:01 GMT # © 2025 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 @@ -1573,10 +1573,11 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 1AFFD..1AFFE ; Katakana # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1B000 ; Katakana # Lo KATAKANA LETTER ARCHAIC E 1B120..1B122 ; Katakana # Lo [3] KATAKANA LETTER ARCHAIC YI..KATAKANA LETTER ARCHAIC WU +1B126 ; Katakana # Lo KATAKANA DIGRAPH YORI 1B155 ; Katakana # Lo KATAKANA LETTER SMALL KO 1B164..1B167 ; Katakana # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N -# Total code points: 321 +# Total code points: 322 # ================================================ diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 908382199..b37e4d5b9 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -32206,6 +32206,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1B120;KATAKANA LETTER ARCHAIC YI;Lo;0;L;;;;;N;;;;; 1B121;KATAKANA LETTER ARCHAIC YE;Lo;0;L;;;;;N;;;;; 1B122;KATAKANA LETTER ARCHAIC WU;Lo;0;L;;;;;N;;;;; +1B126;KATAKANA DIGRAPH YORI;Lo;0;L; 30E8 30EA;;;;N;;;;; 1B132;HIRAGANA LETTER SMALL KO;Lo;0;L;;;;;N;;;;; 1B150;HIRAGANA LETTER SMALL WI;Lo;0;L;;;;;N;;;;; 1B151;HIRAGANA LETTER SMALL WE;Lo;0;L;;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index 71770a13d..c934d6603 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: 2025-01-29 +# Date: 2025-01-30, 20:55:03 GMT # © 2025 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 @@ -2238,7 +2238,9 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 1AFFF ; U # Cn 1B000..1B0FF ; U # Lo [256] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER RE-2 1B100..1B122 ; U # Lo [35] HENTAIGANA LETTER RE-3..KATAKANA LETTER ARCHAIC WU -1B123..1B12F ; U # Cn [13] .. +1B123..1B125 ; U # Cn [3] .. +1B126 ; U # Lo KATAKANA DIGRAPH YORI +1B127..1B12F ; U # Cn [9] .. 1B130..1B131 ; U # Cn [2] .. 1B132 ; Tu # Lo HIRAGANA LETTER SMALL KO 1B133..1B14F ; U # Cn [29] .. diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 0e5dc2e11..0749a6cb3 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: 2025-01-27, 18:09:39 GMT +# Date: 2025-01-30, 20:55:02 GMT # © 2025 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 @@ -2547,6 +2547,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1AFF5..1AFFB ; OLetter # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 1AFFD..1AFFE ; OLetter # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1B000..1B122 ; OLetter # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU +1B126 ; OLetter # Lo KATAKANA DIGRAPH YORI 1B132 ; OLetter # Lo HIRAGANA LETTER SMALL KO 1B150..1B152 ; OLetter # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B155 ; OLetter # Lo KATAKANA LETTER SMALL KO @@ -2622,7 +2623,7 @@ 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..33479 ; OLetter # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479 -# Total code points: 141520 +# Total code points: 141521 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index e5a5b9937..0fdad1385 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: 2025-01-27, 18:09:43 GMT +# Date: 2025-01-30, 20:55:04 GMT # © 2025 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 @@ -681,10 +681,11 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 1AFFD..1AFFE ; Katakana # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1B000 ; Katakana # Lo KATAKANA LETTER ARCHAIC E 1B120..1B122 ; Katakana # Lo [3] KATAKANA LETTER ARCHAIC YI..KATAKANA LETTER ARCHAIC WU +1B126 ; Katakana # Lo KATAKANA DIGRAPH YORI 1B155 ; Katakana # Lo KATAKANA LETTER SMALL KO 1B164..1B167 ; Katakana # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N -# Total code points: 331 +# Total code points: 332 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index a4dc4250a..3dda5f293 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: 2025-01-27, 18:09:10 GMT +# Date: 2025-01-30, 20:54:23 GMT # © 2025 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 @@ -1123,6 +1123,7 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 1AFF5..1AFFB ; L # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 1AFFD..1AFFE ; L # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1B000..1B122 ; L # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU +1B126 ; L # Lo KATAKANA DIGRAPH YORI 1B132 ; L # Lo HIRAGANA LETTER SMALL KO 1B150..1B152 ; L # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B155 ; L # Lo KATAKANA LETTER SMALL KO @@ -1234,7 +1235,7 @@ 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 810584 code points not listed here. +# The above property value applies to 810583 code points not listed here. # Total code points: 1095402 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index 3a10fc1e4..18bcadaa6 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: 2025-01-27, 18:09:10 GMT +# Date: 2025-01-30, 20:54:24 GMT # © 2025 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 @@ -1868,6 +1868,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1AFF5..1AFFB ; 0 # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 1AFFD..1AFFE ; 0 # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1B000..1B122 ; 0 # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU +1B126 ; 0 # Lo KATAKANA DIGRAPH YORI 1B132 ; 0 # Lo HIRAGANA LETTER SMALL KO 1B150..1B152 ; 0 # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B155 ; 0 # Lo KATAKANA LETTER SMALL KO @@ -2095,7 +2096,7 @@ 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 816745 code points not listed here. +# The above property value applies to 816744 code points not listed here. # Total code points: 1113143 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedDecompositionType.txt b/unicodetools/data/ucd/dev/extracted/DerivedDecompositionType.txt index 37fc20842..dfc190a49 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedDecompositionType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedDecompositionType.txt @@ -1,5 +1,5 @@ # DerivedDecompositionType-17.0.0.txt -# Date: 2025-01-27, 18:09:12 GMT +# Date: 2025-01-30, 20:54:26 GMT # © 2025 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 @@ -928,8 +928,9 @@ FE43 ; Vertical # Ps PRESENTATION FORM FOR VERTICAL LEFT WHITE CO FE44 ; Vertical # Pe PRESENTATION FORM FOR VERTICAL RIGHT WHITE CORNER BRACKET FE47 ; Vertical # Ps PRESENTATION FORM FOR VERTICAL LEFT SQUARE BRACKET FE48 ; Vertical # Pe PRESENTATION FORM FOR VERTICAL RIGHT SQUARE BRACKET +1B126 ; Vertical # Lo KATAKANA DIGRAPH YORI -# Total code points: 35 +# Total code points: 36 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index c3d0bb02a..b5416a58f 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: 2025-01-27, 18:09:12 GMT +# Date: 2025-01-31, 16:44:07 GMT # © 2025 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 @@ -2144,8 +2144,8 @@ 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 760566 code points not listed here. -# Total code points: 792267 +# The above property value applies to 760565 code points not listed here. +# Total code points: 792266 # ================================================ @@ -2556,6 +2556,7 @@ FE6A..FE6B ; W # Po [2] SMALL PERCENT SIGN..SMALL COMMERCIAL AT 1AFF5..1AFFB ; W # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 1AFFD..1AFFE ; W # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1B000..1B122 ; W # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU +1B126 ; W # Lo KATAKANA DIGRAPH YORI 1B132 ; W # Lo HIRAGANA LETTER SMALL KO 1B150..1B152 ; W # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B155 ; W # Lo KATAKANA LETTER SMALL KO @@ -2622,7 +2623,7 @@ FE6A..FE6B ; W # Po [2] SMALL PERCENT SIGN..SMALL COMMERCIAL AT 31350..33479 ; W # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479 # The above property value applies to 56179 code points not listed here. -# Total code points: 182768 +# Total code points: 182769 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index 22b9a85f6..3c5eeabcd 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: 2025-01-27, 18:09:13 GMT +# Date: 2025-01-30, 20:54:27 GMT # © 2025 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 @@ -586,7 +586,8 @@ FFFE..FFFF ; Cn # [2] .. 1AFF4 ; Cn # 1AFFC ; Cn # 1AFFF ; Cn # -1B123..1B131 ; Cn # [15] .. +1B123..1B125 ; Cn # [3] .. +1B127..1B131 ; Cn # [11] .. 1B133..1B14F ; Cn # [29] .. 1B153..1B154 ; Cn # [2] .. 1B156..1B163 ; Cn # [14] .. @@ -754,7 +755,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 814697 +# Total code points: 814696 # ================================================ @@ -2667,6 +2668,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 18CFF..18D1E ; Lo # [32] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1E 18D80..18DF2 ; Lo # [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883 1B000..1B122 ; Lo # [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU +1B126 ; Lo # KATAKANA DIGRAPH YORI 1B132 ; Lo # HIRAGANA LETTER SMALL KO 1B150..1B152 ; Lo # [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B155 ; Lo # KATAKANA LETTER SMALL KO @@ -2738,7 +2740,7 @@ 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..33479 ; Lo # [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479 -# Total code points: 141081 +# Total code points: 141082 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 03b4c0a9b..93400e63d 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: 2025-01-27, 18:09:13 GMT +# Date: 2025-01-30, 20:54:28 GMT # © 2025 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 @@ -70,8 +70,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 757136 code points not listed here. -# Total code points: 894604 +# The above property value applies to 757135 code points not listed here. +# Total code points: 894603 # ================================================ @@ -1796,6 +1796,7 @@ FFE4 ; ID # So FULLWIDTH BROKEN BAR 18D00..18D1E ; ID # Lo [31] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D1E 18D80..18DF2 ; ID # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883 1B000..1B122 ; ID # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU +1B126 ; ID # Lo KATAKANA DIGRAPH YORI 1B170..1B2FB ; ID # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1F000..1F02B ; ID # So [44] MAHJONG TILE EAST WIND..MAHJONG TILE BACK 1F030..1F093 ; ID # So [100] DOMINO TILE HORIZONTAL BACK..DOMINO TILE VERTICAL-06-06 @@ -1885,7 +1886,7 @@ FFE4 ; ID # So FULLWIDTH BROKEN BAR 31350..33479 ; ID # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479 # The above property value applies to 57546 code points not listed here. -# Total code points: 172561 +# Total code points: 172562 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 5876213a1..93f7d6b94 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: 2025-01-27, 18:09:14 GMT +# Date: 2025-01-30, 20:54:28 GMT # © 2025 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 @@ -38406,6 +38406,7 @@ FFFD ; REPLACEMENT CHARACTER 1B120 ; KATAKANA LETTER ARCHAIC YI 1B121 ; KATAKANA LETTER ARCHAIC YE 1B122 ; KATAKANA LETTER ARCHAIC WU +1B126 ; KATAKANA DIGRAPH YORI 1B132 ; HIRAGANA LETTER SMALL KO 1B150 ; HIRAGANA LETTER SMALL WI 1B151 ; HIRAGANA LETTER SMALL WE @@ -45870,6 +45871,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 159834 +# Total code points: 159835 # EOF diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/190.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/190.txt new file mode 100644 index 000000000..b3344fdb7 --- /dev/null +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/190.txt @@ -0,0 +1,20 @@ +# Katakana digraph (1B126) +# https://github.com/unicode-org/utc-release-management/issues/190 + +# Names always differ. +# Age always differs since these tests are comparing additions to pre-existing characters. +Ignoring Name Age: + +# Ignore the security and IDNA properties, as these are not yet included for provisionally assigned characters. +Ignoring Confusable_MA Identifier_Status Identifier_Type Idn_Status Idn_Mapping Idn_2008: + +Ignoring Block: +Propertywise [ \N{KATAKANA DIGRAPH YORI}] + ⧴ [{ヨリ} {\N{KATAKANA LETTER YO}\N{KATAKANA LETTER RI}}] +CorrespondTo [ヿ\N{KATAKANA DIGRAPH KOTO}] + ⧴ [{コト} {\N{KATAKANA LETTER KO}\N{KATAKANA LETTER TO}}] +end Ignoring; + +end Ignoring; + +end Ignoring; \ No newline at end of file