From 0d9f7490b09a29d9e9226c36bf663a24b2f82250 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 5 Jun 2024 00:38:37 +0200 Subject: [PATCH 1/8] UnicodeData.txt lines from Kirk --- unicodetools/data/ucd/dev/UnicodeData.txt | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 64258a373..8565a6c36 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -1,3 +1,13 @@ +1DFE9;MODIFIER LETTER SMALL CAPITAL A;Lm;0;L; 1D00;;;;N;;;;; +1DFEA;MODIFIER LETTER SMALL CAPITAL E;Lm;0;L; 1D07;;;;N;;;;; +1DFEB;MODIFIER LETTER SMALL REVERSED R WITH FISHHOOK;Lm;0;L; 027F;;;;N;;;;; +1DFEC;MODIFIER LETTER SMALL SQUAT REVERSED ESH;Lm;0;L; 0285;;;;N;;;;; +1DFED;MODIFIER LETTER SMALL TURNED H WITH FISHHOOK;Lm;0;L; 02AE;;;;N;;;;; +1DFEE;MODIFIER LETTER SMALL TURNED H WITH FISHHOOK AND TAIL;Lm;0;L; 02AF;;;;N;;;;; +1DFEF;MODIFIER LETTER SMALL D WITH CURL;Lm;0;L; 0221;;;;N;;;;; +1DFF0;MODIFIER LETTER SMALL L WITH CURL;Lm;0;L; 0234;;;;N;;;;; +1DFF1;MODIFIER LETTER SMALL N WITH CURL;Lm;0;L; 0235;;;;N;;;;; +1DFF2;MODIFIER LETTER SMALL T WITH CURL;Lm;0;L; 0236;;;;N;;;;; 0000;;Cc;0;BN;;;;;N;NULL;;;; 0001;;Cc;0;BN;;;;;N;START OF HEADING;;;; 0002;;Cc;0;BN;;;;;N;START OF TEXT;;;; From 043a321e0dfc8f5c4cc665169e7f39de5e443669 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 5 Jun 2024 00:42:08 +0200 Subject: [PATCH 2/8] lb=AL --- unicodetools/data/ucd/dev/LineBreak.txt | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 9dc61d95d..f20354f4c 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: 2024-05-11, 16:57:19 GMT +# Date: 2024-06-04, 22:39:51 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 @@ -3383,6 +3383,7 @@ FFFD ; AI # So REPLACEMENT CHARACTER 1DF0A ; AL # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF1E ; AL # Ll [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1DF25..1DF2A ; AL # Ll [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1DFE9..1DFF2 ; AL # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 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 From 7e334d412199fdaf9abbe162c540e99acdaf6e1c Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 5 Jun 2024 00:42:42 +0200 Subject: [PATCH 3/8] Latin --- unicodetools/data/ucd/dev/Scripts.txt | 1 + 1 file changed, 1 insertion(+) diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 443a6d2dd..a10f953ce 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,3 +1,4 @@ +1DFE9..1DFF2; Latin # Scripts-16.0.0.txt # Date: 2024-04-30, 21:48:40 GMT # © 2024 Unicode®, Inc. From f93e30a6e8180056b38824d7a6351224bc32a0ba Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 5 Jun 2024 00:43:31 +0200 Subject: [PATCH 4/8] Diacritic --- unicodetools/data/ucd/dev/PropList.txt | 1 + 1 file changed, 1 insertion(+) diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt index 395aa448d..587284b99 100644 --- a/unicodetools/data/ucd/dev/PropList.txt +++ b/unicodetools/data/ucd/dev/PropList.txt @@ -1,3 +1,4 @@ +1DFE9..1DFF2; Diacritic # PropList-16.0.0.txt # Date: 2024-05-08, 03:40:06 GMT # © 2024 Unicode®, Inc. From 0339bcaf4d538f206f14fd6f681372f1e8f50b5b Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 5 Jun 2024 00:48:41 +0200 Subject: [PATCH 5/8] Regenerate UCD --- unicodetools/data/ucd/dev/DerivedAge.txt | 5 +-- .../data/ucd/dev/DerivedCoreProperties.txt | 23 +++++++----- .../ucd/dev/DerivedNormalizationProps.txt | 35 +++++++++++++++---- unicodetools/data/ucd/dev/EastAsianWidth.txt | 3 +- .../data/ucd/dev/NormalizationTest.txt | 12 ++++++- unicodetools/data/ucd/dev/PropList.txt | 6 ++-- unicodetools/data/ucd/dev/Scripts.txt | 6 ++-- unicodetools/data/ucd/dev/UnicodeData.txt | 20 +++++------ .../data/ucd/dev/VerticalOrientation.txt | 3 +- .../dev/auxiliary/SentenceBreakProperty.txt | 5 +-- .../ucd/dev/auxiliary/WordBreakProperty.txt | 5 +-- .../ucd/dev/extracted/DerivedBidiClass.txt | 5 +-- .../dev/extracted/DerivedCombiningClass.txt | 5 +-- .../extracted/DerivedDecompositionType.txt | 5 +-- .../dev/extracted/DerivedEastAsianWidth.txt | 5 +-- .../dev/extracted/DerivedGeneralCategory.txt | 10 +++--- .../ucd/dev/extracted/DerivedLineBreak.txt | 9 ++--- .../data/ucd/dev/extracted/DerivedName.txt | 14 ++++++-- 18 files changed, 119 insertions(+), 57 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index b4dcd2e48..babfa4b71 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 +# Date: 2024-06-04, 22:44:04 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2044,6 +2044,7 @@ A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L 18CFF ; 16.0 # KHITAN SMALL SCRIPT CHARACTER-18CFF 1CC00..1CCF9 ; 16.0 # [250] UP-POINTING GO-KART..OUTLINED DIGIT NINE 1CD00..1CEB3 ; 16.0 # [436] BLOCK OCTANT-3..BLACK RIGHT TRIANGLE CARET +1DFE9..1DFF2 ; 16.0 # [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 1E5D0..1E5FA ; 16.0 # [43] OL ONAL LETTER O..OL ONAL DIGIT NINE 1E5FF ; 16.0 # OL ONAL ABBREVIATION SIGN 1F8B2..1F8BB ; 16.0 # [10] RIGHTWARDS ARROW WITH LOWER HOOK..SOUTH WEST ARROW FROM BAR @@ -2057,6 +2058,6 @@ A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L 1FAE9 ; 16.0 # FACE WITH BAGS UNDER EYES 1FBCB..1FBEF ; 16.0 # [37] WHITE CROSS MARK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 5185 +# Total code points: 5195 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 88df29b3b..cb0f4a4cc 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: 2024-05-02, 15:02:37 GMT +# Date: 2024-06-04, 22:44:24 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1371,6 +1371,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 1DF0A ; Alphabetic # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF1E ; Alphabetic # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1DF25..1DF2A ; Alphabetic # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1DFE9..1DFF2 ; Alphabetic # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 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 @@ -1441,7 +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: 142759 +# Total code points: 142769 # ================================================ @@ -3483,6 +3484,7 @@ 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 +1DFE9..1DFF2 ; Case_Ignorable # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 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 @@ -3505,7 +3507,7 @@ 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: 2759 # ================================================ @@ -6902,6 +6904,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1DF0A ; ID_Start # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF1E ; ID_Start # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1DF25..1DF2A ; ID_Start # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1DFE9..1DFF2 ; ID_Start # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 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 @@ -6962,7 +6965,7 @@ 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: 141279 # ================================================ @@ -8290,6 +8293,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 1DF0A ; ID_Continue # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF1E ; ID_Continue # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1DF25..1DF2A ; ID_Continue # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1DFE9..1DFF2 ; ID_Continue # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 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 @@ -8370,7 +8374,7 @@ 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: 144551 # ================================================ @@ -9088,6 +9092,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1DF0A ; XID_Start # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF1E ; XID_Start # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1DF25..1DF2A ; XID_Start # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1DFE9..1DFF2 ; XID_Start # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 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 @@ -9148,7 +9153,7 @@ 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: 141256 # ================================================ @@ -10477,6 +10482,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 1DF0A ; XID_Continue # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF1E ; XID_Continue # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1DF25..1DF2A ; XID_Continue # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1DFE9..1DFF2 ; XID_Continue # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 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 @@ -10557,7 +10563,7 @@ 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: 144532 # ================================================ @@ -12692,6 +12698,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1DF0A ; Grapheme_Base # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF1E ; Grapheme_Base # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1DF25..1DF2A ; Grapheme_Base # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1DFE9..1DFF2 ; Grapheme_Base # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 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 @@ -12811,7 +12818,7 @@ 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: 152748 # ================================================ diff --git a/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt b/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt index ce636abb5..943cbae5e 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 +# Date: 2024-06-04, 22:44:27 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 +1DFE9..1DFF2 ; NFKD_QC; N # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 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: 17095 # ================================================ @@ -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 +1DFE9..1DFF2 ; NFKC_QC; N # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 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: 4974 # ================================================ @@ -8225,6 +8227,16 @@ FFF0..FFF8 ; NFKC_CF; # Cn [9] ...... -# Total code points: 10554 +# Total code points: 10564 # ================================================ @@ -14359,6 +14371,16 @@ FFF0..FFF8 ; NFKC_SCF; # Cn [9] ...... -# Total code points: 10516 +# Total code points: 10526 # ================================================ @@ -16246,6 +16268,7 @@ FFF0..FFF8 ; Changes_When_NFKC_Casefolded # Cn [9] ...... -# Total code points: 10554 +# Total code points: 10564 # EOF diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index 99f7a31ea..27c5f22cb 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: 2024-06-04, 22:44:29 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 @@ -2468,6 +2468,7 @@ FFFD ; A # So REPLACEMENT CHARACTER 1DF0A ; N # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF1E ; N # Ll [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1DF25..1DF2A ; N # Ll [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1DFE9..1DFF2 ; N # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 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/NormalizationTest.txt b/unicodetools/data/ucd/dev/NormalizationTest.txt index 3aae8f72e..68c9d12c7 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: 2024-06-04, 22:44:35 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 @@ -16284,6 +16284,16 @@ 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 +1DFE9;1DFE9;1DFE9;1D00;1D00; # (𝿩; 𝿩; 𝿩; ᴀ; ᴀ; ) MODIFIER LETTER SMALL CAPITAL A +1DFEA;1DFEA;1DFEA;1D07;1D07; # (𝿪; 𝿪; 𝿪; ᴇ; ᴇ; ) MODIFIER LETTER SMALL CAPITAL E +1DFEB;1DFEB;1DFEB;027F;027F; # (𝿫; 𝿫; 𝿫; ɿ; ɿ; ) MODIFIER LETTER SMALL REVERSED R WITH FISHHOOK +1DFEC;1DFEC;1DFEC;0285;0285; # (𝿬; 𝿬; 𝿬; ʅ; ʅ; ) MODIFIER LETTER SMALL SQUAT REVERSED ESH +1DFED;1DFED;1DFED;02AE;02AE; # (𝿭; 𝿭; 𝿭; ʮ; ʮ; ) MODIFIER LETTER SMALL TURNED H WITH FISHHOOK +1DFEE;1DFEE;1DFEE;02AF;02AF; # (𝿮; 𝿮; 𝿮; ʯ; ʯ; ) MODIFIER LETTER SMALL TURNED H WITH FISHHOOK AND TAIL +1DFEF;1DFEF;1DFEF;0221;0221; # (𝿯; 𝿯; 𝿯; ȡ; ȡ; ) MODIFIER LETTER SMALL D WITH CURL +1DFF0;1DFF0;1DFF0;0234;0234; # (𝿰; 𝿰; 𝿰; ȴ; ȴ; ) MODIFIER LETTER SMALL L WITH CURL +1DFF1;1DFF1;1DFF1;0235;0235; # (𝿱; 𝿱; 𝿱; ȵ; ȵ; ) MODIFIER LETTER SMALL N WITH CURL +1DFF2;1DFF2;1DFF2;0236;0236; # (𝿲; 𝿲; 𝿲; ȶ; ȶ; ) MODIFIER LETTER SMALL T WITH CURL 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 587284b99..1de909a90 100644 --- a/unicodetools/data/ucd/dev/PropList.txt +++ b/unicodetools/data/ucd/dev/PropList.txt @@ -1,6 +1,5 @@ -1DFE9..1DFF2; Diacritic # PropList-16.0.0.txt -# Date: 2024-05-08, 03:40:06 GMT +# Date: 2024-06-04, 22:44:39 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 @@ -1142,6 +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 +1DFE9..1DFF2 ; Diacritic # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 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 @@ -1151,7 +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: 1188 # ================================================ diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index a10f953ce..0f26e9c0b 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,6 +1,5 @@ -1DFE9..1DFF2; Latin # Scripts-16.0.0.txt -# Date: 2024-04-30, 21:48:40 GMT +# Date: 2024-06-04, 22:44:55 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 @@ -702,8 +701,9 @@ FF41..FF5A ; Latin # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 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 +1DFE9..1DFF2 ; Latin # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL -# Total code points: 1487 +# Total code points: 1497 # ================================================ diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 8565a6c36..9941ac6a3 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -1,13 +1,3 @@ -1DFE9;MODIFIER LETTER SMALL CAPITAL A;Lm;0;L; 1D00;;;;N;;;;; -1DFEA;MODIFIER LETTER SMALL CAPITAL E;Lm;0;L; 1D07;;;;N;;;;; -1DFEB;MODIFIER LETTER SMALL REVERSED R WITH FISHHOOK;Lm;0;L; 027F;;;;N;;;;; -1DFEC;MODIFIER LETTER SMALL SQUAT REVERSED ESH;Lm;0;L; 0285;;;;N;;;;; -1DFED;MODIFIER LETTER SMALL TURNED H WITH FISHHOOK;Lm;0;L; 02AE;;;;N;;;;; -1DFEE;MODIFIER LETTER SMALL TURNED H WITH FISHHOOK AND TAIL;Lm;0;L; 02AF;;;;N;;;;; -1DFEF;MODIFIER LETTER SMALL D WITH CURL;Lm;0;L; 0221;;;;N;;;;; -1DFF0;MODIFIER LETTER SMALL L WITH CURL;Lm;0;L; 0234;;;;N;;;;; -1DFF1;MODIFIER LETTER SMALL N WITH CURL;Lm;0;L; 0235;;;;N;;;;; -1DFF2;MODIFIER LETTER SMALL T WITH CURL;Lm;0;L; 0236;;;;N;;;;; 0000;;Cc;0;BN;;;;;N;NULL;;;; 0001;;Cc;0;BN;;;;;N;START OF HEADING;;;; 0002;;Cc;0;BN;;;;;N;START OF TEXT;;;; @@ -35666,6 +35656,16 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1DF28;LATIN SMALL LETTER R WITH MID-HEIGHT LEFT HOOK;Ll;0;L;;;;;N;;;;; 1DF29;LATIN SMALL LETTER S WITH MID-HEIGHT LEFT HOOK;Ll;0;L;;;;;N;;;;; 1DF2A;LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK;Ll;0;L;;;;;N;;;;; +1DFE9;MODIFIER LETTER SMALL CAPITAL A;Lm;0;L; 1D00;;;;N;;;;; +1DFEA;MODIFIER LETTER SMALL CAPITAL E;Lm;0;L; 1D07;;;;N;;;;; +1DFEB;MODIFIER LETTER SMALL REVERSED R WITH FISHHOOK;Lm;0;L; 027F;;;;N;;;;; +1DFEC;MODIFIER LETTER SMALL SQUAT REVERSED ESH;Lm;0;L; 0285;;;;N;;;;; +1DFED;MODIFIER LETTER SMALL TURNED H WITH FISHHOOK;Lm;0;L; 02AE;;;;N;;;;; +1DFEE;MODIFIER LETTER SMALL TURNED H WITH FISHHOOK AND TAIL;Lm;0;L; 02AF;;;;N;;;;; +1DFEF;MODIFIER LETTER SMALL D WITH CURL;Lm;0;L; 0221;;;;N;;;;; +1DFF0;MODIFIER LETTER SMALL L WITH CURL;Lm;0;L; 0234;;;;N;;;;; +1DFF1;MODIFIER LETTER SMALL N WITH CURL;Lm;0;L; 0235;;;;N;;;;; +1DFF2;MODIFIER LETTER SMALL T WITH CURL;Lm;0;L; 0236;;;;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 1ebcd7228..33b323051 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: 2024-06-04, 22:44:57 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 @@ -2320,6 +2320,7 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 1DF0A ; R # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF1E ; R # Ll [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1DF25..1DF2A ; R # Ll [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1DFE9..1DFF2 ; R # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 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 39fdb57c0..8d0c2355b 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: 2024-05-13, 20:53:44 GMT +# Date: 2024-06-04, 22:44:55 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 @@ -2527,6 +2527,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1BC80..1BC88 ; OLetter # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL 1BC90..1BC99 ; OLetter # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW 1DF0A ; OLetter # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DFE9..1DFF2 ; OLetter # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 1E100..1E12C ; OLetter # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; OLetter # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E14E ; OLetter # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ @@ -2585,7 +2586,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; OLetter # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; OLetter # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 136908 +# Total code points: 136918 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index 925ea3c48..6e6538219 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: 2024-04-30, 21:48:43 GMT +# Date: 2024-06-04, 22:44:57 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 @@ -1301,6 +1301,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1DF0A ; ALetter # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF1E ; ALetter # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1DF25..1DF2A ; ALetter # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1DFE9..1DFF2 ; ALetter # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 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 @@ -1355,7 +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: 33791 +# Total code points: 33801 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 2aceac0aa..3c0823afd 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 +# Date: 2024-06-04, 22:44:21 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1175,6 +1175,7 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 1DF0A ; L # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF1E ; L # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1DF25..1DF2A ; L # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1DFE9..1DFF2 ; L # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 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 @@ -1214,7 +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 815351 code points not listed here. +# The above property value applies to 815341 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..ed621e59b 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 +# Date: 2024-06-04, 22:44:23 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 @@ -1936,6 +1936,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1DF0A ; 0 # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF1E ; 0 # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1DF25..1DF2A ; 0 # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1DFE9..1DFF2 ; 0 # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 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 @@ -2060,7 +2061,7 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] .. 100000..10FFFD; 0 # Co [65534] .. -# The above property value applies to 821581 code points not listed here. +# The above property value applies to 821571 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..591e996aa 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 +# Date: 2024-06-04, 22:44:25 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 @@ -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 +1DFE9..1DFF2 ; Super # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 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: 259 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index cc1d91aaa..3543cadcd 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 +# Date: 2024-06-04, 22:44:25 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 @@ -1965,6 +1965,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 1DF0A ; N # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF1E ; N # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1DF25..1DF2A ; N # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1DFE9..1DFF2 ; N # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 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 @@ -2103,7 +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 761099 code points not listed here. +# The above property value applies to 761089 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..15d55e968 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 +# Date: 2024-06-04, 22:44:26 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -633,7 +633,8 @@ FFFE..FFFF ; Cn # [2] .. 1DAA0 ; Cn # 1DAB0..1DEFF ; Cn # [1104] .. 1DF1F..1DF24 ; Cn # [6] .. -1DF2B..1DFFF ; Cn # [213] .. +1DF2B..1DFE8 ; Cn # [190] .. +1DFF3..1DFFF ; Cn # [13] .. 1E007 ; Cn # 1E019..1E01A ; Cn # [2] .. 1E022 ; Cn # @@ -747,7 +748,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819533 +# Total code points: 819523 # ================================================ @@ -2168,12 +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 +1DFE9..1DFF2 ; Lm # [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 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: 414 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 866536783..c5198d40c 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: 2024-05-11, 16:57:14 GMT +# Date: 2024-06-04, 22:44:27 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 757643 code points not listed here. +# Total code points: 895111 # ================================================ @@ -1522,6 +1522,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1DF0A ; AL # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1DF0B..1DF1E ; AL # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1DF25..1DF2A ; AL # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1DFE9..1DFF2 ; AL # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 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 @@ -1615,7 +1616,7 @@ 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: 26690 +# Total code points: 26700 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 07b0176b5..10b73aff6 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 +# Date: 2024-06-04, 22:44:27 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 @@ -41461,6 +41461,16 @@ FFFD ; REPLACEMENT CHARACTER 1DF28 ; LATIN SMALL LETTER R WITH MID-HEIGHT LEFT HOOK 1DF29 ; LATIN SMALL LETTER S WITH MID-HEIGHT LEFT HOOK 1DF2A ; LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1DFE9 ; MODIFIER LETTER SMALL CAPITAL A +1DFEA ; MODIFIER LETTER SMALL CAPITAL E +1DFEB ; MODIFIER LETTER SMALL REVERSED R WITH FISHHOOK +1DFEC ; MODIFIER LETTER SMALL SQUAT REVERSED ESH +1DFED ; MODIFIER LETTER SMALL TURNED H WITH FISHHOOK +1DFEE ; MODIFIER LETTER SMALL TURNED H WITH FISHHOOK AND TAIL +1DFEF ; MODIFIER LETTER SMALL D WITH CURL +1DFF0 ; MODIFIER LETTER SMALL L WITH CURL +1DFF1 ; MODIFIER LETTER SMALL N WITH CURL +1DFF2 ; MODIFIER LETTER SMALL T WITH CURL 1E000 ; COMBINING GLAGOLITIC LETTER AZU 1E001 ; COMBINING GLAGOLITIC LETTER BUKY 1E002 ; COMBINING GLAGOLITIC LETTER VEDE @@ -45367,6 +45377,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 154998 +# Total code points: 155008 # EOF From 939c605c213c2e99362bd8425f0d4e93a25f9b21 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 5 Jun 2024 06:39:10 +0200 Subject: [PATCH 6/8] Other_Lowercase --- unicodetools/data/ucd/dev/PropList.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt index 1de909a90..c472b3aa3 100644 --- a/unicodetools/data/ucd/dev/PropList.txt +++ b/unicodetools/data/ucd/dev/PropList.txt @@ -1201,7 +1201,7 @@ FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND # Total code points: 59 # ================================================ - +1DFE9..1DFF2; Other_Lowercase 00AA ; Other_Lowercase # Lo FEMININE ORDINAL INDICATOR 00BA ; Other_Lowercase # Lo MASCULINE ORDINAL INDICATOR 02B0..02B8 ; Other_Lowercase # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y From 1b4f055015fafe4c40edf5ca78621c3a982ae419 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 5 Jun 2024 06:44:14 +0200 Subject: [PATCH 7/8] Regenerate UCD --- unicodetools/data/ucd/dev/DerivedCoreProperties.txt | 8 +++++--- unicodetools/data/ucd/dev/PropList.txt | 7 ++++--- .../data/ucd/dev/auxiliary/SentenceBreakProperty.txt | 8 ++++---- 3 files changed, 13 insertions(+), 10 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index cb0f4a4cc..f3e0a0ec8 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: 2024-06-04, 22:44:24 GMT +# Date: 2024-06-05, 04:40:40 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 @@ -2137,10 +2137,11 @@ FF41..FF5A ; Lowercase # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 1DF00..1DF09 ; Lowercase # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0B..1DF1E ; Lowercase # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1DF25..1DF2A ; Lowercase # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1DFE9..1DFF2 ; Lowercase # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 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: 2579 # ================================================ @@ -2983,13 +2984,14 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1DF00..1DF09 ; Cased # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0B..1DF1E ; Cased # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1DF25..1DF2A ; Cased # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1DFE9..1DFF2 ; Cased # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 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: 4578 +# Total code points: 4588 # ================================================ diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt index c472b3aa3..25e250cbc 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: 2024-06-04, 22:44:39 GMT +# Date: 2024-06-05, 04:41:06 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 @@ -1201,7 +1201,7 @@ FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND # Total code points: 59 # ================================================ -1DFE9..1DFF2; Other_Lowercase + 00AA ; Other_Lowercase # Lo FEMININE ORDINAL INDICATOR 00BA ; Other_Lowercase # Lo MASCULINE ORDINAL INDICATOR 02B0..02B8 ; Other_Lowercase # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y @@ -1229,9 +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 +1DFE9..1DFF2 ; Other_Lowercase # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 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: 321 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 8d0c2355b..cc2e54922 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: 2024-06-04, 22:44:55 GMT +# Date: 2024-06-05, 04:41:36 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 @@ -1317,10 +1317,11 @@ FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1DF00..1DF09 ; Lower # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK 1DF0B..1DF1E ; Lower # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1DF25..1DF2A ; Lower # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1DFE9..1DFF2 ; Lower # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 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: 2532 # ================================================ @@ -2527,7 +2528,6 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1BC80..1BC88 ; OLetter # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL 1BC90..1BC99 ; OLetter # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW 1DF0A ; OLetter # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK -1DFE9..1DFF2 ; OLetter # Lm [10] MODIFIER LETTER SMALL CAPITAL A..MODIFIER LETTER SMALL T WITH CURL 1E100..1E12C ; OLetter # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; OLetter # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E14E ; OLetter # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ @@ -2586,7 +2586,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; OLetter # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; OLetter # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 136918 +# Total code points: 136908 # ================================================ From 4e62a4be6eb6750f45de9f8d1dd7c96f7d466055 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Thu, 15 Aug 2024 14:53:51 +0200 Subject: [PATCH 8/8] a test. --- .../unicode/text/UCD/AdditionComparisons.txt | 38 ++++++++++++++++++- 1 file changed, 37 insertions(+), 1 deletion(-) diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons.txt index 9db1fdf1d..035eda975 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons.txt @@ -35,7 +35,43 @@ CorrespondTo [\N{OLD HUNGARIAN SMALL LETTER A}] ## Provisionally assigned. [placeholder for draft PRs] # 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: +Ignoring Confusable_MA Identifier_Status Identifier_Type Idn_Status Idn_Mapping: + +Ignoring Block: +# The range \N{MODIFIER LETTER SMALL CAPITAL A}-\N{MODIFIER LETTER SMALL T WITH CURL} is split in +# three tests because the modifiers are encoded in the order (small capitals, fishhooks, curls), but +# the non-modifiers are in code point order (curls, fishhooks, small capitals). +Propertywise [ \N{MODIFIER LETTER SMALL CAPITAL A} + \N{MODIFIER LETTER SMALL CAPITAL E}] + : [ᴀ\N{LATIN LETTER SMALL CAPITAL A} + ᴇ\N{LATIN LETTER SMALL CAPITAL E}] +CorrespondTo [ʶ\N{MODIFIER LETTER SMALL CAPITAL INVERTED R}] + : [ʁ\N{LATIN LETTER SMALL CAPITAL INVERTED R}] + +Ignoring Unicode_1_Name: # ɿ has a Unicode_1_Name (FISHHOOK R instead of R WITH FISHHOOK). +Propertywise [ \N{MODIFIER LETTER SMALL REVERSED R WITH FISHHOOK} + \N{MODIFIER LETTER SMALL SQUAT REVERSED ESH} + \N{MODIFIER LETTER SMALL TURNED H WITH FISHHOOK} + \N{MODIFIER LETTER SMALL TURNED H WITH FISHHOOK AND TAIL}] + : [ɿ\N{LATIN SMALL LETTER REVERSED R WITH FISHHOOK} + ʅ\N{LATIN SMALL LETTER SQUAT REVERSED ESH} + ʮ\N{LATIN SMALL LETTER TURNED H WITH FISHHOOK} + ʯ\N{LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL}] +CorrespondTo [ʶ\N{MODIFIER LETTER SMALL CAPITAL INVERTED R}] + : [ʁ\N{LATIN LETTER SMALL CAPITAL INVERTED R}] +end Ignoring; + +Propertywise [ \N{MODIFIER LETTER SMALL D WITH CURL} + \N{MODIFIER LETTER SMALL L WITH CURL} + \N{MODIFIER LETTER SMALL N WITH CURL} + \N{MODIFIER LETTER SMALL T WITH CURL}] + : [ȡ\N{LATIN SMALL LETTER D WITH CURL} + ȴ\N{LATIN SMALL LETTER L WITH CURL} + ȵ\N{LATIN SMALL LETTER N WITH CURL} + ȶ\N{LATIN SMALL LETTER T WITH CURL}] +CorrespondTo [ʶ\N{MODIFIER LETTER SMALL CAPITAL INVERTED R}] + : [ʁ\N{LATIN LETTER SMALL CAPITAL INVERTED R}] +end Ignoring; end Ignoring;