diff --git a/.github/workflows/pythonpackage.yml b/.github/workflows/pythonpackage.yml index 8317ccb34..22c9beb61 100644 --- a/.github/workflows/pythonpackage.yml +++ b/.github/workflows/pythonpackage.yml @@ -15,7 +15,7 @@ jobs: runs-on: ubuntu-latest strategy: matrix: - python-version: [3.8] + python-version: [3.12] steps: - uses: actions/checkout@v3 diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index c246223aa..96ea95bdc 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: 2024-10-15, 01:32:01 GMT +# Date: 2024-10-15, 01:37:57 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2067,7 +2067,9 @@ A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L 1DF1F..1DF24 ; 17.0 # [6] LATIN SMALL LETTER D-ETH DIGRAPH..LATIN SMALL LETTER T-THETA DIGRAPH 1DF2B..1DF2C ; 17.0 # [2] LATIN SMALL LETTER DEZH DIGRAPH WITH CURL..LATIN SMALL LETTER TESH DIGRAPH WITH CURL +1DF3E..1DF3F ; 17.0 # [2] LATIN SMALL LETTER BARRED TURNED H..LATIN SMALL LETTER BARRED W +1DFD8..1DFE8 ; 17.0 # [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D -# Total code points: 8 +# Total code points: 27 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index b3eb25d51..727d403e0 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: 2024-10-15, 01:32:34 GMT +# Date: 2024-10-15, 01:38:32 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 @@ -1370,6 +1370,8 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 1DF00..1DF09 ; Alphabetic # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0A ; Alphabetic # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF2C ; Alphabetic # L& [34] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER TESH DIGRAPH WITH CURL +1DF3E..1DF3F ; Alphabetic # L& [2] LATIN SMALL LETTER BARRED TURNED H..LATIN SMALL LETTER BARRED W +1DFD8..1DFE8 ; Alphabetic # Lm [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D 1E000..1E006 ; Alphabetic # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E008..1E018 ; Alphabetic # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU 1E01B..1E021 ; Alphabetic # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI @@ -1440,7 +1442,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 30000..3134A ; Alphabetic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Alphabetic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 142767 +# Total code points: 142786 # ================================================ @@ -2134,10 +2136,12 @@ FF41..FF5A ; Lowercase # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 1D7CB ; Lowercase # L& MATHEMATICAL BOLD SMALL DIGAMMA 1DF00..1DF09 ; Lowercase # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0B..1DF2C ; Lowercase # L& [34] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER TESH DIGRAPH WITH CURL +1DF3E..1DF3F ; Lowercase # L& [2] LATIN SMALL LETTER BARRED TURNED H..LATIN SMALL LETTER BARRED W +1DFD8..1DFE8 ; Lowercase # Lm [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D 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: 2577 +# Total code points: 2596 # ================================================ @@ -2979,13 +2983,15 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1D7C4..1D7CB ; Cased # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA 1DF00..1DF09 ; Cased # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0B..1DF2C ; Cased # L& [34] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER TESH DIGRAPH WITH CURL +1DF3E..1DF3F ; Cased # L& [2] LATIN SMALL LETTER BARRED TURNED H..LATIN SMALL LETTER BARRED W +1DFD8..1DFE8 ; Cased # Lm [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D 1E030..1E06D ; Cased # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E900..1E943 ; Cased # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA 1F130..1F149 ; Cased # So [26] SQUARED LATIN CAPITAL LETTER A..SQUARED LATIN CAPITAL LETTER Z 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: 4586 +# Total code points: 4605 # ================================================ @@ -3480,6 +3486,7 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 1DA84 ; Case_Ignorable # Mn SIGNWRITING LOCATION HEAD NECK 1DA9B..1DA9F ; Case_Ignorable # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA1..1DAAF ; Case_Ignorable # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1DFD8..1DFE8 ; Case_Ignorable # Lm [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D 1E000..1E006 ; Case_Ignorable # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E008..1E018 ; Case_Ignorable # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU 1E01B..1E021 ; Case_Ignorable # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI @@ -3502,7 +3509,7 @@ E0001 ; Case_Ignorable # Cf LANGUAGE TAG E0020..E007F ; Case_Ignorable # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2749 +# Total code points: 2766 # ================================================ @@ -6898,6 +6905,8 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1DF00..1DF09 ; ID_Start # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0A ; ID_Start # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF2C ; ID_Start # L& [34] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER TESH DIGRAPH WITH CURL +1DF3E..1DF3F ; ID_Start # L& [2] LATIN SMALL LETTER BARRED TURNED H..LATIN SMALL LETTER BARRED W +1DFD8..1DFE8 ; ID_Start # Lm [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D 1E030..1E06D ; ID_Start # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E100..1E12C ; ID_Start # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; ID_Start # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER @@ -6958,7 +6967,7 @@ 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: 141277 +# Total code points: 141296 # ================================================ @@ -8285,6 +8294,8 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 1DF00..1DF09 ; ID_Continue # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0A ; ID_Continue # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF2C ; ID_Continue # L& [34] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER TESH DIGRAPH WITH CURL +1DF3E..1DF3F ; ID_Continue # L& [2] LATIN SMALL LETTER BARRED TURNED H..LATIN SMALL LETTER BARRED W +1DFD8..1DFE8 ; ID_Continue # Lm [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D 1E000..1E006 ; ID_Continue # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E008..1E018 ; ID_Continue # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU 1E01B..1E021 ; ID_Continue # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI @@ -8365,7 +8376,7 @@ 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: 144549 +# Total code points: 144568 # ================================================ @@ -9082,6 +9093,8 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1DF00..1DF09 ; XID_Start # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0A ; XID_Start # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF2C ; XID_Start # L& [34] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER TESH DIGRAPH WITH CURL +1DF3E..1DF3F ; XID_Start # L& [2] LATIN SMALL LETTER BARRED TURNED H..LATIN SMALL LETTER BARRED W +1DFD8..1DFE8 ; XID_Start # Lm [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D 1E030..1E06D ; XID_Start # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E100..1E12C ; XID_Start # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; XID_Start # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER @@ -9142,7 +9155,7 @@ 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: 141254 +# Total code points: 141273 # ================================================ @@ -10470,6 +10483,8 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 1DF00..1DF09 ; XID_Continue # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0A ; XID_Continue # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF2C ; XID_Continue # L& [34] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER TESH DIGRAPH WITH CURL +1DF3E..1DF3F ; XID_Continue # L& [2] LATIN SMALL LETTER BARRED TURNED H..LATIN SMALL LETTER BARRED W +1DFD8..1DFE8 ; XID_Continue # Lm [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D 1E000..1E006 ; XID_Continue # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E008..1E018 ; XID_Continue # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU 1E01B..1E021 ; XID_Continue # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI @@ -10550,7 +10565,7 @@ 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: 144530 +# Total code points: 144549 # ================================================ @@ -12685,6 +12700,8 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1DF00..1DF09 ; Grapheme_Base # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0A ; Grapheme_Base # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF2C ; Grapheme_Base # L& [34] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER TESH DIGRAPH WITH CURL +1DF3E..1DF3F ; Grapheme_Base # L& [2] LATIN SMALL LETTER BARRED TURNED H..LATIN SMALL LETTER BARRED W +1DFD8..1DFE8 ; Grapheme_Base # Lm [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D 1E030..1E06D ; Grapheme_Base # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E100..1E12C ; Grapheme_Base # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; Grapheme_Base # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER @@ -12804,7 +12821,7 @@ 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: 152738 +# Total code points: 152757 # ================================================ diff --git a/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt b/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt index ce636abb5..7ebe9a350 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: 2024-10-15, 01:38:38 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 @@ -1707,6 +1707,7 @@ FFED..FFEE ; NFKD_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 1D7C3 ; NFKD_QC; N # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL 1D7C4..1D7CB ; NFKD_QC; N # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA 1D7CE..1D7FF ; NFKD_QC; N # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE +1DFD8..1DFE8 ; NFKD_QC; N # Lm [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D 1E030..1E06D ; NFKD_QC; N # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1EE00..1EE03 ; NFKD_QC; N # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL 1EE05..1EE1F ; NFKD_QC; N # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF @@ -1753,7 +1754,7 @@ 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: 17102 # ================================================ @@ -2118,6 +2119,7 @@ FFED..FFEE ; NFKC_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 1D7C3 ; NFKC_QC; N # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL 1D7C4..1D7CB ; NFKC_QC; N # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA 1D7CE..1D7FF ; NFKC_QC; N # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE +1DFD8..1DFE8 ; NFKC_QC; N # Lm [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D 1E030..1E06D ; NFKC_QC; N # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1EE00..1EE03 ; NFKC_QC; N # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL 1EE05..1EE1F ; NFKC_QC; N # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF @@ -2164,7 +2166,7 @@ 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: 4981 # ================================================ @@ -8225,6 +8227,23 @@ FFF0..FFF8 ; NFKC_CF; # Cn [9] ...... -# Total code points: 10554 +# Total code points: 10571 # ================================================ @@ -14359,6 +14378,23 @@ FFF0..FFF8 ; NFKC_SCF; # Cn [9] ...... -# Total code points: 10516 +# Total code points: 10533 # ================================================ @@ -16246,6 +16282,7 @@ FFF0..FFF8 ; Changes_When_NFKC_Casefolded # Cn [9] ...... -# Total code points: 10554 +# Total code points: 10571 # EOF diff --git a/unicodetools/data/ucd/dev/DoNotEmit.txt b/unicodetools/data/ucd/dev/DoNotEmit.txt index e0033cec3..e8183cab4 100644 --- a/unicodetools/data/ucd/dev/DoNotEmit.txt +++ b/unicodetools/data/ucd/dev/DoNotEmit.txt @@ -418,14 +418,18 @@ 02E1 0322; 1DA9; Precomposed_Form # MODIFIER LETTER SMALL L, COMBINING RETROFLEX HOOK BELOW; MODIFIER LETTER SMALL L WITH RETROFLEX HOOK 1D48 0322; 1078B; Precomposed_Form # MODIFIER LETTER SMALL D, COMBINING RETROFLEX HOOK BELOW; MODIFIER LETTER SMALL D WITH TAIL 1D57 0322; 107AF; Precomposed_Form # MODIFIER LETTER SMALL T, COMBINING RETROFLEX HOOK BELOW; MODIFIER LETTER SMALL T WITH RETROFLEX HOOK +1DB4 0322; 1DFE3; Precomposed_Form # MODIFIER LETTER SMALL ESH, COMBINING RETROFLEX HOOK BELOW; MODIFIER LETTER SMALL ESH WITH RETROFLEX HOOK 1DBB 0322; 1DBC; Precomposed_Form # MODIFIER LETTER SMALL Z, COMBINING RETROFLEX HOOK BELOW; MODIFIER LETTER SMALL Z WITH RETROFLEX HOOK +1DBE 0322; 1DFE7; Precomposed_Form # MODIFIER LETTER SMALL EZH, COMBINING RETROFLEX HOOK BELOW; MODIFIER LETTER SMALL EZH WITH RETROFLEX HOOK 207F 0322; 1DAF; Precomposed_Form # SUPERSCRIPT LATIN SMALL LETTER N, COMBINING RETROFLEX HOOK BELOW; MODIFIER LETTER SMALL N WITH RETROFLEX HOOK 10787 0322; 10788; Precomposed_Form # MODIFIER LETTER SMALL DZ DIGRAPH, COMBINING RETROFLEX HOOK BELOW; MODIFIER LETTER SMALL DZ DIGRAPH WITH RETROFLEX HOOK +1078A 0322; 1DFE1; Precomposed_Form # MODIFIER LETTER SMALL DEZH DIGRAPH, COMBINING RETROFLEX HOOK BELOW; MODIFIER LETTER SMALL DEZH DIGRAPH WITH RETROFLEX HOOK 1078C 0322; 1078D; Precomposed_Form # MODIFIER LETTER SMALL D WITH HOOK, COMBINING RETROFLEX HOOK BELOW; MODIFIER LETTER SMALL D WITH HOOK AND TAIL 1079B 0322; 1079D; Precomposed_Form # MODIFIER LETTER SMALL L WITH BELT, COMBINING RETROFLEX HOOK BELOW; MODIFIER LETTER SMALL L WITH RETROFLEX HOOK AND BELT 1079E 0322; 1079F; Precomposed_Form # MODIFIER LETTER SMALL LEZH, COMBINING RETROFLEX HOOK BELOW; MODIFIER LETTER SMALL LEZH WITH RETROFLEX HOOK 107A6 0322; 107A7; Precomposed_Form # MODIFIER LETTER SMALL TURNED R WITH LONG LEG, COMBINING RETROFLEX HOOK BELOW; MODIFIER LETTER SMALL TURNED R WITH LONG LEG AND RETROFLEX HOOK 107AC 0322; 107AD; Precomposed_Form # MODIFIER LETTER SMALL TS DIGRAPH, COMBINING RETROFLEX HOOK BELOW; MODIFIER LETTER SMALL TS DIGRAPH WITH RETROFLEX HOOK +107AE 0322; 1DFE5; Precomposed_Form # MODIFIER LETTER SMALL TESH DIGRAPH, COMBINING RETROFLEX HOOK BELOW; MODIFIER LETTER SMALL TESH DIGRAPH WITH RETROFLEX HOOK 1DF20 0322; 1DF21; Precomposed_Form # LATIN SMALL LETTER D-LEZH DIGRAPH, COMBINING RETROFLEX HOOK BELOW; LATIN SMALL LETTER D-LEZH DIGRAPH WITH RETROFLEX HOOK 1DF22 0322; 1DF23; Precomposed_Form # LATIN SMALL LETTER TL DIGRAPH WITH BELT, COMBINING RETROFLEX HOOK BELOW; LATIN SMALL LETTER TL DIGRAPH WITH RETROFLEX HOOK AND BELT diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index 9cccdf5e8..bc0aa2c28 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: 2024-06-04, 23:16:59 GMT +# Date: 2024-07-25, 16:24:46 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 @@ -2467,6 +2467,8 @@ FFFD ; A # So REPLACEMENT CHARACTER 1DF00..1DF09 ; N # Ll [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0A ; N # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF2C ; N # Ll [34] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER TESH DIGRAPH WITH CURL +1DF3E..1DF3F ; N # Ll [2] LATIN SMALL LETTER BARRED TURNED H..LATIN SMALL LETTER BARRED W +1DFD8..1DFE8 ; N # Lm [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D 1E000..1E006 ; N # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E008..1E018 ; N # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU 1E01B..1E021 ; N # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 7eacbc10d..afb929073 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: 2024-08-15, 13:17:38 GMT +# Date: 2024-08-15, 13:22:48 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 @@ -3377,6 +3377,8 @@ FFFD ; AI # So REPLACEMENT CHARACTER 1DF00..1DF09 ; AL # Ll [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0A ; AL # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF2C ; AL # Ll [34] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER TESH DIGRAPH WITH CURL +1DF3E..1DF3F ; AL # Ll [2] LATIN SMALL LETTER BARRED TURNED H..LATIN SMALL LETTER BARRED W +1DFD8..1DFE8 ; AL # Lm [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D 1E000..1E006 ; CM # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E008..1E018 ; CM # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU 1E01B..1E021 ; CM # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI diff --git a/unicodetools/data/ucd/dev/NormalizationTest.txt b/unicodetools/data/ucd/dev/NormalizationTest.txt index 3aae8f72e..142cd4f6f 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, 16:25:01 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 @@ -16284,6 +16284,23 @@ FFEE;FFEE;FFEE;25CB;25CB; # (￮; ￮; ￮; ○; ○; ) HALFWIDTH WHITE CIRCLE 1D7FD;1D7FD;1D7FD;0037;0037; # (𝟽; 𝟽; 𝟽; 7; 7; ) MATHEMATICAL MONOSPACE DIGIT SEVEN 1D7FE;1D7FE;1D7FE;0038;0038; # (𝟾; 𝟾; 𝟾; 8; 8; ) MATHEMATICAL MONOSPACE DIGIT EIGHT 1D7FF;1D7FF;1D7FF;0039;0039; # (𝟿; 𝟿; 𝟿; 9; 9; ) MATHEMATICAL MONOSPACE DIGIT NINE +1DFD8;1DFD8;1DFD8;1DF3E;1DF3E; # (𝿘; 𝿘; 𝿘; 𝼾; 𝼾; ) MODIFIER LETTER SMALL BARRED TURNED H +1DFD9;1DFD9;1DFD9;0249;0249; # (𝿙; 𝿙; 𝿙; ɉ; ɉ; ) MODIFIER LETTER SMALL J WITH STROKE +1DFDA;1DFDA;1DFDA;1D7F;1D7F; # (𝿚; 𝿚; 𝿚; ᵿ; ᵿ; ) MODIFIER LETTER SMALL UPSILON WITH STROKE +1DFDB;1DFDB;1DFDB;1DF3F;1DF3F; # (𝿛; 𝿛; 𝿛; 𝼿; 𝼿; ) MODIFIER LETTER SMALL BARRED W +1DFDC;1DFDC;1DFDC;019E;019E; # (𝿜; 𝿜; 𝿜; ƞ; ƞ; ) MODIFIER LETTER SMALL N WITH LONG RIGHT LEG +1DFDD;1DFDD;1DFDD;027C;027C; # (𝿝; 𝿝; 𝿝; ɼ; ɼ; ) MODIFIER LETTER SMALL R WITH LONG LEG +1DFDE;1DFDE;1DFDE;0238;0238; # (𝿞; 𝿞; 𝿞; ȸ; ȸ; ) MODIFIER LETTER SMALL DB DIGRAPH +1DFDF;1DFDF;1DFDF;0239;0239; # (𝿟; 𝿟; 𝿟; ȹ; ȹ; ) MODIFIER LETTER SMALL QP DIGRAPH +1DFE0;1DFE0;1DFE0;1DF2B;1DF2B; # (𝿠; 𝿠; 𝿠; 𝼫; 𝼫; ) MODIFIER LETTER SMALL DEZH DIGRAPH WITH CURL +1DFE1;1DFE1;1DFE1;1DF19;1DF19; # (𝿡; 𝿡; 𝿡; 𝼙; 𝼙; ) MODIFIER LETTER SMALL DEZH DIGRAPH WITH RETROFLEX HOOK +1DFE2;1DFE2;1DFE2;0286;0286; # (𝿢; 𝿢; 𝿢; ʆ; ʆ; ) MODIFIER LETTER SMALL ESH WITH CURL +1DFE3;1DFE3;1DFE3;1D98;1D98; # (𝿣; 𝿣; 𝿣; ᶘ; ᶘ; ) MODIFIER LETTER SMALL ESH WITH RETROFLEX HOOK +1DFE4;1DFE4;1DFE4;1DF2C;1DF2C; # (𝿤; 𝿤; 𝿤; 𝼬; 𝼬; ) MODIFIER LETTER SMALL TESH DIGRAPH WITH CURL +1DFE5;1DFE5;1DFE5;1DF1C;1DF1C; # (𝿥; 𝿥; 𝿥; 𝼜; 𝼜; ) MODIFIER LETTER SMALL TESH DIGRAPH WITH RETROFLEX HOOK +1DFE6;1DFE6;1DFE6;0293;0293; # (𝿦; 𝿦; 𝿦; ʓ; ʓ; ) MODIFIER LETTER SMALL EZH WITH CURL +1DFE7;1DFE7;1DFE7;1D9A;1D9A; # (𝿧; 𝿧; 𝿧; ᶚ; ᶚ; ) MODIFIER LETTER SMALL EZH WITH RETROFLEX HOOK +1DFE8;1DFE8;1DFE8;1D05;1D05; # (𝿨; 𝿨; 𝿨; ᴅ; ᴅ; ) MODIFIER LETTER SMALL CAPITAL D 1E030;1E030;1E030;0430;0430; # (𞀰; 𞀰; 𞀰; а; а; ) MODIFIER LETTER CYRILLIC SMALL A 1E031;1E031;1E031;0431;0431; # (𞀱; 𞀱; 𞀱; б; б; ) MODIFIER LETTER CYRILLIC SMALL BE 1E032;1E032;1E032;0432;0432; # (𞀲; 𞀲; 𞀲; в; в; ) MODIFIER LETTER CYRILLIC SMALL VE diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt index fae2831e7..502aafcbb 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: 2024-08-15, 15:57:58 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1141,6 +1141,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON 1D17B..1D182 ; Diacritic # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE 1D185..1D18B ; Diacritic # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE 1D1AA..1D1AD ; Diacritic # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1DFD8..1DFE8 ; Diacritic # Lm [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D 1E030..1E06D ; Diacritic # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E130..1E136 ; Diacritic # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D 1E2AE ; Diacritic # Mn TOTO SIGN RISING TONE @@ -1150,7 +1151,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON 1E944..1E946 ; Diacritic # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK 1E948..1E94A ; Diacritic # Mn [3] ADLAM CONSONANT MODIFIER..ADLAM NUKTA -# Total code points: 1178 +# Total code points: 1195 # ================================================ @@ -1228,9 +1229,10 @@ AB69 ; Other_Lowercase # Lm MODIFIER LETTER SMALL TURNED W 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 +1DFD8..1DFE8 ; Other_Lowercase # Lm [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D 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: 328 # ================================================ @@ -1433,10 +1435,11 @@ E0001 ; Deprecated # Cf LANGUAGE TAG 1D65E..1D65F ; Soft_Dotted # L& [2] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL I..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL J 1D692..1D693 ; Soft_Dotted # L& [2] MATHEMATICAL MONOSPACE SMALL I..MATHEMATICAL MONOSPACE SMALL J 1DF1A ; Soft_Dotted # L& LATIN SMALL LETTER I WITH STROKE AND RETROFLEX HOOK +1DFD9 ; Soft_Dotted # Lm MODIFIER LETTER SMALL J WITH STROKE 1E04C..1E04D ; Soft_Dotted # Lm [2] MODIFIER LETTER CYRILLIC SMALL BYELORUSSIAN-UKRAINIAN I..MODIFIER LETTER CYRILLIC SMALL JE 1E068 ; Soft_Dotted # Lm CYRILLIC SUBSCRIPT SMALL LETTER BYELORUSSIAN-UKRAINIAN I -# Total code points: 50 +# Total code points: 51 # ================================================ diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index ca5678177..50b37d1f0 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: 2024-06-04, 23:17:24 GMT +# Date: 2024-07-25, 16:25:40 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 @@ -700,8 +700,10 @@ FF41..FF5A ; Latin # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 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..1DF2C ; Latin # L& [34] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER TESH DIGRAPH WITH CURL +1DF3E..1DF3F ; Latin # L& [2] LATIN SMALL LETTER BARRED TURNED H..LATIN SMALL LETTER BARRED W +1DFD8..1DFE8 ; Latin # Lm [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D -# Total code points: 1495 +# Total code points: 1514 # ================================================ diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 03e3d4e3f..f4d592f0c 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -35664,6 +35664,25 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1DF2A;LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK;Ll;0;L;;;;;N;;;;; 1DF2B;LATIN SMALL LETTER DEZH DIGRAPH WITH CURL;Ll;0;L;;;;;N;;;;; 1DF2C;LATIN SMALL LETTER TESH DIGRAPH WITH CURL;Ll;0;L;;;;;N;;;;; +1DF3E;LATIN SMALL LETTER BARRED TURNED H;Ll;0;L;;;;;N;;;;; +1DF3F;LATIN SMALL LETTER BARRED W;Ll;0;L;;;;;N;;;;; +1DFD8;MODIFIER LETTER SMALL BARRED TURNED H;Lm;0;L; 1DF3E;;;;N;;;;; +1DFD9;MODIFIER LETTER SMALL J WITH STROKE;Lm;0;L; 0249;;;;N;;;;; +1DFDA;MODIFIER LETTER SMALL UPSILON WITH STROKE;Lm;0;L; 1D7F;;;;N;;;;; +1DFDB;MODIFIER LETTER SMALL BARRED W;Lm;0;L; 1DF3F;;;;N;;;;; +1DFDC;MODIFIER LETTER SMALL N WITH LONG RIGHT LEG;Lm;0;L; 019E;;;;N;;;;; +1DFDD;MODIFIER LETTER SMALL R WITH LONG LEG;Lm;0;L; 027C;;;;N;;;;; +1DFDE;MODIFIER LETTER SMALL DB DIGRAPH;Lm;0;L; 0238;;;;N;;;;; +1DFDF;MODIFIER LETTER SMALL QP DIGRAPH;Lm;0;L; 0239;;;;N;;;;; +1DFE0;MODIFIER LETTER SMALL DEZH DIGRAPH WITH CURL;Lm;0;L; 1DF2B;;;;N;;;;; +1DFE1;MODIFIER LETTER SMALL DEZH DIGRAPH WITH RETROFLEX HOOK;Lm;0;L; 1DF19;;;;N;;;;; +1DFE2;MODIFIER LETTER SMALL ESH WITH CURL;Lm;0;L; 0286;;;;N;;;;; +1DFE3;MODIFIER LETTER SMALL ESH WITH RETROFLEX HOOK;Lm;0;L; 1D98;;;;N;;;;; +1DFE4;MODIFIER LETTER SMALL TESH DIGRAPH WITH CURL;Lm;0;L; 1DF2C;;;;N;;;;; +1DFE5;MODIFIER LETTER SMALL TESH DIGRAPH WITH RETROFLEX HOOK;Lm;0;L; 1DF1C;;;;N;;;;; +1DFE6;MODIFIER LETTER SMALL EZH WITH CURL;Lm;0;L; 0293;;;;N;;;;; +1DFE7;MODIFIER LETTER SMALL EZH WITH RETROFLEX HOOK;Lm;0;L; 1D9A;;;;N;;;;; +1DFE8;MODIFIER LETTER SMALL CAPITAL D;Lm;0;L; 1D05;;;;N;;;;; 1E000;COMBINING GLAGOLITIC LETTER AZU;Mn;230;NSM;;;;;N;;;;; 1E001;COMBINING GLAGOLITIC LETTER BUKY;Mn;230;NSM;;;;;N;;;;; 1E002;COMBINING GLAGOLITIC LETTER VEDE;Mn;230;NSM;;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index b7b034580..971280109 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: 2024-06-04, 23:17:26 GMT +# Date: 2024-07-25, 16:25:45 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 @@ -2319,6 +2319,8 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 1DF00..1DF09 ; R # Ll [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0A ; R # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF2C ; R # Ll [34] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER TESH DIGRAPH WITH CURL +1DF3E..1DF3F ; R # Ll [2] LATIN SMALL LETTER BARRED TURNED H..LATIN SMALL LETTER BARRED W +1DFD8..1DFE8 ; R # Lm [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D 1E000..1E006 ; R # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E008..1E018 ; R # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU 1E01B..1E021 ; R # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 249c0b7ac..7e90edbe4 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: 2024-10-15, 01:33:26 GMT +# Date: 2024-10-15, 01:39:25 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 @@ -1316,10 +1316,12 @@ FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1D7CB ; Lower # L& MATHEMATICAL BOLD SMALL DIGAMMA 1DF00..1DF09 ; Lower # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0B..1DF2C ; Lower # L& [34] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER TESH DIGRAPH WITH CURL +1DF3E..1DF3F ; Lower # L& [2] LATIN SMALL LETTER BARRED TURNED H..LATIN SMALL LETTER BARRED W +1DFD8..1DFE8 ; Lower # Lm [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D 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: 2530 +# Total code points: 2549 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index c64ecf81e..19adddaaa 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: 2024-10-15, 01:33:30 GMT +# Date: 2024-10-15, 01:39:28 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1300,6 +1300,8 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1DF00..1DF09 ; ALetter # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0A ; ALetter # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF2C ; ALetter # L& [34] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER TESH DIGRAPH WITH CURL +1DF3E..1DF3F ; ALetter # L& [2] LATIN SMALL LETTER BARRED TURNED H..LATIN SMALL LETTER BARRED W +1DFD8..1DFE8 ; ALetter # Lm [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D 1E030..1E06D ; ALetter # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E100..1E12C ; ALetter # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; ALetter # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER @@ -1354,7 +1356,7 @@ 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: 33799 +# Total code points: 33818 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 0623a28f0..b6285362f 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: 2024-10-15, 01:32:31 GMT +# Date: 2024-10-15, 01:38:28 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1174,6 +1174,8 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 1DF00..1DF09 ; L # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0A ; L # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF2C ; L # L& [34] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER TESH DIGRAPH WITH CURL +1DF3E..1DF3F ; L # L& [2] LATIN SMALL LETTER BARRED TURNED H..LATIN SMALL LETTER BARRED W +1DFD8..1DFE8 ; L # Lm [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D 1E030..1E06D ; L # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E100..1E12C ; L # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; L # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER @@ -1213,7 +1215,7 @@ 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 815343 code points not listed here. +# The above property value applies to 815324 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 3892f09ef..2cf3b98e6 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: 2024-10-15, 01:32:34 GMT +# Date: 2024-10-15, 01:38:31 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 @@ -1935,6 +1935,8 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1DF00..1DF09 ; 0 # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0A ; 0 # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF2C ; 0 # L& [34] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER TESH DIGRAPH WITH CURL +1DF3E..1DF3F ; 0 # L& [2] LATIN SMALL LETTER BARRED TURNED H..LATIN SMALL LETTER BARRED W +1DFD8..1DFE8 ; 0 # Lm [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D 1E030..1E06D ; 0 # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E100..1E12C ; 0 # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; 0 # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER @@ -2059,7 +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 821573 code points not listed here. +# The above property value applies to 821554 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..94d38f8f8 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: 2024-10-15, 01:38:34 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 @@ -880,11 +880,12 @@ 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 +1DFD8..1DFE8 ; Super # Lm [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D 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: 266 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index cd61212e0..e286819d5 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: 2024-10-15, 01:32:37 GMT +# Date: 2024-10-15, 01:38:34 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 @@ -1964,6 +1964,8 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 1DF00..1DF09 ; N # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0A ; N # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF2C ; N # L& [34] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER TESH DIGRAPH WITH CURL +1DF3E..1DF3F ; N # L& [2] LATIN SMALL LETTER BARRED TURNED H..LATIN SMALL LETTER BARRED W +1DFD8..1DFE8 ; N # Lm [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D 1E000..1E006 ; N # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E008..1E018 ; N # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU 1E01B..1E021 ; N # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI @@ -2102,7 +2104,7 @@ 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 761091 code points not listed here. +# The above property value applies to 761072 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 0af3e0d45..8246bb234 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: 2024-10-15, 01:32:38 GMT +# Date: 2024-10-15, 01:38:35 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -632,7 +632,9 @@ FFFE..FFFF ; Cn # [2] .. 1DA8C..1DA9A ; Cn # [15] .. 1DAA0 ; Cn # 1DAB0..1DEFF ; Cn # [1104] .. -1DF2D..1DFFF ; Cn # [211] .. +1DF2D..1DF3D ; Cn # [17] .. +1DF40..1DFD7 ; Cn # [152] .. +1DFE9..1DFFF ; Cn # [23] .. 1E007 ; Cn # 1E019..1E01A ; Cn # [2] .. 1E022 ; Cn # @@ -746,7 +748,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819525 +# Total code points: 819506 # ================================================ @@ -2070,9 +2072,10 @@ FF41..FF5A ; Ll # [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL 1D7CB ; Ll # MATHEMATICAL BOLD SMALL DIGAMMA 1DF00..1DF09 ; Ll # [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0B..1DF2C ; Ll # [34] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER TESH DIGRAPH WITH CURL +1DF3E..1DF3F ; Ll # [2] LATIN SMALL LETTER BARRED TURNED H..LATIN SMALL LETTER BARRED W 1E922..1E943 ; Ll # [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2266 +# Total code points: 2268 # ================================================ @@ -2166,12 +2169,13 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 1AFF0..1AFF3 ; Lm # [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 1AFF5..1AFFB ; Lm # [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 1AFFD..1AFFE ; Lm # [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1DFD8..1DFE8 ; Lm # [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D 1E030..1E06D ; Lm # [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E137..1E13D ; Lm # [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E4EB ; Lm # NAG MUNDARI SIGN OJOD 1E94B ; Lm # ADLAM NASALIZATION MARK -# Total code points: 404 +# Total code points: 421 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 5b232161e..a8ca58bb3 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: 2024-10-15, 01:32:40 GMT +# Date: 2024-10-15, 01:38:37 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 @@ -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 757645 code points not listed here. -# Total code points: 895113 +# The above property value applies to 757626 code points not listed here. +# Total code points: 895094 # ================================================ @@ -1519,6 +1519,8 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1DF00..1DF09 ; AL # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0A ; AL # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF2C ; AL # L& [34] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER TESH DIGRAPH WITH CURL +1DF3E..1DF3F ; AL # L& [2] LATIN SMALL LETTER BARRED TURNED H..LATIN SMALL LETTER BARRED W +1DFD8..1DFE8 ; AL # Lm [17] MODIFIER LETTER SMALL BARRED TURNED H..MODIFIER LETTER SMALL CAPITAL D 1E030..1E06D ; AL # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E100..1E12C ; AL # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; AL # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER @@ -1612,7 +1614,7 @@ 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: 26687 +# Total code points: 26706 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 630c38b79..603e858ac 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: 2024-10-15, 01:32:40 GMT +# Date: 2024-10-15, 01:38:37 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 @@ -41469,6 +41469,25 @@ FFFD ; REPLACEMENT CHARACTER 1DF2A ; LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK 1DF2B ; LATIN SMALL LETTER DEZH DIGRAPH WITH CURL 1DF2C ; LATIN SMALL LETTER TESH DIGRAPH WITH CURL +1DF3E ; LATIN SMALL LETTER BARRED TURNED H +1DF3F ; LATIN SMALL LETTER BARRED W +1DFD8 ; MODIFIER LETTER SMALL BARRED TURNED H +1DFD9 ; MODIFIER LETTER SMALL J WITH STROKE +1DFDA ; MODIFIER LETTER SMALL UPSILON WITH STROKE +1DFDB ; MODIFIER LETTER SMALL BARRED W +1DFDC ; MODIFIER LETTER SMALL N WITH LONG RIGHT LEG +1DFDD ; MODIFIER LETTER SMALL R WITH LONG LEG +1DFDE ; MODIFIER LETTER SMALL DB DIGRAPH +1DFDF ; MODIFIER LETTER SMALL QP DIGRAPH +1DFE0 ; MODIFIER LETTER SMALL DEZH DIGRAPH WITH CURL +1DFE1 ; MODIFIER LETTER SMALL DEZH DIGRAPH WITH RETROFLEX HOOK +1DFE2 ; MODIFIER LETTER SMALL ESH WITH CURL +1DFE3 ; MODIFIER LETTER SMALL ESH WITH RETROFLEX HOOK +1DFE4 ; MODIFIER LETTER SMALL TESH DIGRAPH WITH CURL +1DFE5 ; MODIFIER LETTER SMALL TESH DIGRAPH WITH RETROFLEX HOOK +1DFE6 ; MODIFIER LETTER SMALL EZH WITH CURL +1DFE7 ; MODIFIER LETTER SMALL EZH WITH RETROFLEX HOOK +1DFE8 ; MODIFIER LETTER SMALL CAPITAL D 1E000 ; COMBINING GLAGOLITIC LETTER AZU 1E001 ; COMBINING GLAGOLITIC LETTER BUKY 1E002 ; COMBINING GLAGOLITIC LETTER VEDE @@ -45375,6 +45394,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 155006 +# Total code points: 155025 # EOF diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/129.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/129.txt new file mode 100644 index 000000000..620ddd8c7 --- /dev/null +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/129.txt @@ -0,0 +1,86 @@ +# IPA: Misc historical and para-IPA modifier letters +# https://github.com/unicode-org/utc-release-management/issues/129 + +# 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{LATIN SMALL LETTER BARRED TURNED H} + \N{LATIN SMALL LETTER BARRED W} + ꬳ\N{LATIN SMALL LETTER BARRED E}] AreAlike +Ignoring Unicode_1_Name: # ʱ and ɦ have Unicode_1_Names. +Propertywise [ \N{MODIFIER LETTER SMALL N WITH LONG RIGHT LEG}] + : [ƞ\N{LATIN SMALL LETTER N WITH LONG RIGHT LEG}] + : [Ƞ\N{LATIN CAPITAL LETTER N WITH LONG RIGHT LEG}] +CorrespondTo [ʱ\N{MODIFIER LETTER SMALL H WITH HOOK}] + : [ɦ\N{LATIN SMALL LETTER H WITH HOOK}] + : [Ɦ\N{LATIN CAPITAL LETTER H WITH HOOK}] +end Ignoring; +Propertywise [ \N{MODIFIER LETTER SMALL DB DIGRAPH} + \N{MODIFIER LETTER SMALL QP DIGRAPH}] + : [ȸ\N{LATIN SMALL LETTER DB DIGRAPH} + ȹ\N{LATIN SMALL LETTER QP DIGRAPH}] +CorrespondTo [ʶ\N{MODIFIER LETTER SMALL CAPITAL INVERTED R}] + : [ʁ\N{LATIN LETTER SMALL CAPITAL INVERTED R}] +Ignoring Unicode_1_Name: # ʝ has a Unicode_1_Name. +# ᶨ is not Diacritic, but this seems to be an oversight. +# See https://github.com/unicode-org/properties/issues/315. +# TODO(egg): Remove the Ignoring clause if that gets accepted. +Ignoring Diacritic: +Propertywise [ \N{MODIFIER LETTER SMALL J WITH STROKE}] + : [ɉ\N{LATIN SMALL LETTER J WITH STROKE}] + : [Ɉ\N{LATIN CAPITAL LETTER J WITH STROKE}] +CorrespondTo [ᶨ\N{MODIFIER LETTER SMALL J WITH CROSSED-TAIL}] + : [ʝ\N{LATIN SMALL LETTER J WITH CROSSED-TAIL}] + : [Ʝ\N{LATIN CAPITAL LETTER J WITH CROSSED-TAIL}] +end Ignoring; +end Ignoring; +Ignoring Unicode_1_Name: # ʆ and ʓ have Unicode_1_Names. +Propertywise [ \N{MODIFIER LETTER SMALL R WITH LONG LEG} + \N{MODIFIER LETTER SMALL ESH WITH CURL} + \N{MODIFIER LETTER SMALL EZH WITH CURL} + \N{MODIFIER LETTER SMALL CAPITAL D}] + : [ɼ\N{LATIN SMALL LETTER R WITH LONG LEG} + ʆ\N{LATIN SMALL LETTER ESH WITH CURL} + ʓ\N{LATIN SMALL LETTER EZH WITH CURL} + ᴅ\N{LATIN LETTER SMALL CAPITAL D}] +CorrespondTo [ʶ\N{MODIFIER LETTER SMALL CAPITAL INVERTED R}] + : [ʁ\N{LATIN LETTER SMALL CAPITAL INVERTED R}] +end Ignoring; +Propertywise [ \N{MODIFIER LETTER SMALL UPSILON WITH STROKE} + \N{MODIFIER LETTER SMALL ESH WITH RETROFLEX HOOK} + \N{MODIFIER LETTER SMALL EZH WITH RETROFLEX HOOK}] + : [ᵿ\N{LATIN SMALL LETTER UPSILON WITH STROKE} + ᶘ\N{LATIN SMALL LETTER ESH WITH RETROFLEX HOOK} + ᶚ\N{LATIN SMALL LETTER EZH WITH RETROFLEX HOOK}] +CorrespondTo [ʶ\N{MODIFIER LETTER SMALL CAPITAL INVERTED R}] + : [ʁ\N{LATIN LETTER SMALL CAPITAL INVERTED R}] +Propertywise [ \N{MODIFIER LETTER SMALL DEZH DIGRAPH WITH RETROFLEX HOOK} + \N{MODIFIER LETTER SMALL TESH DIGRAPH WITH RETROFLEX HOOK}] + : [𝼙\N{LATIN SMALL LETTER DEZH DIGRAPH WITH RETROFLEX HOOK} + 𝼜\N{LATIN SMALL LETTER TESH DIGRAPH WITH RETROFLEX HOOK}] +CorrespondTo [ʶ\N{MODIFIER LETTER SMALL CAPITAL INVERTED R}] + : [ʁ\N{LATIN LETTER SMALL CAPITAL INVERTED R}] +Propertywise [ \N{MODIFIER LETTER SMALL DEZH DIGRAPH WITH CURL} + \N{MODIFIER LETTER SMALL TESH DIGRAPH WITH CURL}] + : # From L2/24-051: + [ \N{LATIN SMALL LETTER DEZH DIGRAPH WITH CURL} + \N{LATIN SMALL LETTER TESH DIGRAPH WITH CURL}] +CorrespondTo [ʶ\N{MODIFIER LETTER SMALL CAPITAL INVERTED R}] + : [ʁ\N{LATIN LETTER SMALL CAPITAL INVERTED R}] +Propertywise [ \N{MODIFIER LETTER SMALL BARRED TURNED H} + \N{MODIFIER LETTER SMALL BARRED W}] + : # From the same proposal: + [ \N{LATIN SMALL LETTER BARRED TURNED H} + \N{LATIN SMALL LETTER BARRED W}] +CorrespondTo [ʶ\N{MODIFIER LETTER SMALL CAPITAL INVERTED R}] + : [ʁ\N{LATIN LETTER SMALL CAPITAL INVERTED R}] +end Ignoring; + +end Ignoring; + +end Ignoring; \ No newline at end of file