From 6e19f271d9ac8450f72b4efcf9e89b618b247dfd Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 3 Oct 2023 21:46:41 +0200 Subject: [PATCH 01/10] Four Arabic Pegon Characters (#435) --- unicodetools/data/ucd/dev/ArabicShaping.txt | 5 +++ unicodetools/data/ucd/dev/DerivedAge.txt | 15 +++++++- .../data/ucd/dev/DerivedCoreProperties.txt | 38 +++++++++++-------- unicodetools/data/ucd/dev/EastAsianWidth.txt | 7 ++-- unicodetools/data/ucd/dev/LineBreak.txt | 7 ++-- .../data/ucd/dev/NormalizationTest.txt | 6 ++- unicodetools/data/ucd/dev/Scripts.txt | 9 +++-- unicodetools/data/ucd/dev/UnicodeData.txt | 4 ++ .../data/ucd/dev/VerticalOrientation.txt | 7 ++-- .../dev/auxiliary/GraphemeBreakProperty.txt | 8 ++-- .../dev/auxiliary/SentenceBreakProperty.txt | 11 +++--- .../ucd/dev/auxiliary/WordBreakProperty.txt | 11 +++--- .../ucd/dev/extracted/DerivedBidiClass.txt | 13 ++++--- .../dev/extracted/DerivedCombiningClass.txt | 13 ++++--- .../dev/extracted/DerivedEastAsianWidth.txt | 9 +++-- .../dev/extracted/DerivedGeneralCategory.txt | 18 +++++---- .../ucd/dev/extracted/DerivedJoiningGroup.txt | 13 ++++--- .../ucd/dev/extracted/DerivedJoiningType.txt | 14 ++++--- .../ucd/dev/extracted/DerivedLineBreak.txt | 15 ++++---- .../data/ucd/dev/extracted/DerivedName.txt | 10 +++-- 20 files changed, 141 insertions(+), 92 deletions(-) diff --git a/unicodetools/data/ucd/dev/ArabicShaping.txt b/unicodetools/data/ucd/dev/ArabicShaping.txt index dd8cb333e..0def17a03 100644 --- a/unicodetools/data/ucd/dev/ArabicShaping.txt +++ b/unicodetools/data/ucd/dev/ArabicShaping.txt @@ -828,6 +828,11 @@ A873; PHAGS-PA CANDRABINDU; U; No_Joining_Group 10D22; HANIFI ROHINGYA SAKIN; R; No_Joining_Group 10D23; HANIFI ROHINGYA DOTLESS KINNA YA WITH DOT ABOVE; D; HANIFI ROHINGYA KINNA YA +# Arabic Extended-D Characters +10EC2; DAL WITH VERTICAL 2 DOTS BELOW; R; DAL +10EC3; TAH WITH VERTICAL 2 DOTS BELOW; D; TAH +10EC4; KAF WITH VERTICAL 2 DOTS BELOW; D; KAF + # Sogdian Characters 10F30; SOGDIAN ALEPH; D; No_Joining_Group diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index 4cfdd54de..0572b7be6 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ -# DerivedAge-15.1.0.txt -# Date: 2023-07-28, 23:33:51 GMT +# DerivedAge-16.0.0.txt +# Date: 2023-10-02, 12:16:00 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -2003,4 +2003,15 @@ FDFE..FDFF ; 14.0 # [2] ARABIC LIGATURE SUBHAANAHU WA TAAALAA..ARABIC LIGAT # Total code points: 627 +# ================================================ + +# Age=V16_0 + +# Newly assigned in Unicode 16.0.0 (September, 2024) + +0897 ; 16.0 # ARABIC PEPET +10EC2..10EC4 ; 16.0 # [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW + +# Total code points: 4 + # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 220c55685..21cf3645d 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ -# DerivedCoreProperties-15.1.0.txt -# Date: 2023-08-07, 15:21:24 GMT +# DerivedCoreProperties-16.0.0.txt +# Date: 2023-10-02, 12:41:01 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1041,6 +1041,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 10E80..10EA9 ; Alphabetic # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EAB..10EAC ; Alphabetic # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EB0..10EB1 ; Alphabetic # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE +10EC2..10EC4 ; Alphabetic # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10F00..10F1C ; Alphabetic # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; Alphabetic # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; Alphabetic # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -1402,7 +1403,7 @@ 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: 138387 +# Total code points: 138390 # ================================================ @@ -3015,7 +3016,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 0859..085B ; Case_Ignorable # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK 0888 ; Case_Ignorable # Sk ARABIC RAISED ROUND DOT 0890..0891 ; Case_Ignorable # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE -0898..089F ; Case_Ignorable # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +0897..089F ; Case_Ignorable # Mn [9] ARABIC PEPET..ARABIC HALF MADDA OVER MADDA 08C9 ; Case_Ignorable # Lm ARABIC SMALL FARSI YEH 08CA..08E1 ; Case_Ignorable # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E2 ; Case_Ignorable # Cf ARABIC DISPUTED END OF AYAH @@ -3440,7 +3441,7 @@ 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: 2707 +# Total code points: 2708 # ================================================ @@ -6641,6 +6642,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10D00..10D23 ; ID_Start # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA 10E80..10EA9 ; ID_Start # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EB0..10EB1 ; ID_Start # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE +10EC2..10EC4 ; ID_Start # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10F00..10F1C ; ID_Start # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; ID_Start # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; ID_Start # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -6859,7 +6861,7 @@ 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: 136967 +# Total code points: 136970 # ================================================ @@ -6966,7 +6968,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0860..086A ; ID_Continue # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 0870..0887 ; ID_Continue # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT 0889..088E ; ID_Continue # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL -0898..089F ; ID_Continue # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +0897..089F ; ID_Continue # Mn [9] ARABIC PEPET..ARABIC HALF MADDA OVER MADDA 08A0..08C8 ; ID_Continue # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF 08C9 ; ID_Continue # Lm ARABIC SMALL FARSI YEH 08CA..08E1 ; ID_Continue # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA @@ -7782,6 +7784,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 10E80..10EA9 ; ID_Continue # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EAB..10EAC ; ID_Continue # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EB0..10EB1 ; ID_Continue # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE +10EC2..10EC4 ; ID_Continue # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EFD..10EFF ; ID_Continue # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; ID_Continue # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; ID_Continue # Lo OLD SOGDIAN LIGATURE AYIN-DALETH @@ -8218,7 +8221,7 @@ 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: 140108 +# Total code points: 140112 # ================================================ @@ -8755,6 +8758,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 10D00..10D23 ; XID_Start # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA 10E80..10EA9 ; XID_Start # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EB0..10EB1 ; XID_Start # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE +10EC2..10EC4 ; XID_Start # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10F00..10F1C ; XID_Start # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; XID_Start # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; XID_Start # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -8973,7 +8977,7 @@ 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: 136944 +# Total code points: 136947 # ================================================ @@ -9076,7 +9080,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0860..086A ; XID_Continue # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 0870..0887 ; XID_Continue # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT 0889..088E ; XID_Continue # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL -0898..089F ; XID_Continue # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +0897..089F ; XID_Continue # Mn [9] ARABIC PEPET..ARABIC HALF MADDA OVER MADDA 08A0..08C8 ; XID_Continue # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF 08C9 ; XID_Continue # Lm ARABIC SMALL FARSI YEH 08CA..08E1 ; XID_Continue # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA @@ -9897,6 +9901,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 10E80..10EA9 ; XID_Continue # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EAB..10EAC ; XID_Continue # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EB0..10EB1 ; XID_Continue # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE +10EC2..10EC4 ; XID_Continue # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EFD..10EFF ; XID_Continue # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; XID_Continue # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; XID_Continue # Lo OLD SOGDIAN LIGATURE AYIN-DALETH @@ -10333,7 +10338,7 @@ 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: 140089 +# Total code points: 140093 # ================================================ @@ -10418,7 +10423,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] .... 0825..0827 ; Extend # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; Extend # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; Extend # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK -0898..089F ; Extend # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +0897..089F ; Extend # Mn [9] ARABIC PEPET..ARABIC HALF MADDA OVER MADDA 08CA..08E1 ; Extend # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; Extend # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 093A ; Extend # Mn DEVANAGARI VOWEL SIGN OE @@ -459,7 +459,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2130 +# Total code points: 2131 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index f848af1d1..04638c600 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ -# SentenceBreakProperty-15.1.0.txt -# Date: 2023-07-28, 23:34:37 GMT +# SentenceBreakProperty-16.0.0.txt +# Date: 2023-10-02, 12:17:03 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -55,7 +55,7 @@ 0825..0827 ; Extend # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; Extend # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; Extend # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK -0898..089F ; Extend # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +0897..089F ; Extend # Mn [9] ARABIC PEPET..ARABIC HALF MADDA OVER MADDA 08CA..08E1 ; Extend # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; Extend # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 0903 ; Extend # Mc DEVANAGARI SIGN VISARGA @@ -567,7 +567,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2550 +# Total code points: 2551 # ================================================ @@ -2355,6 +2355,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10D00..10D23 ; OLetter # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA 10E80..10EA9 ; OLetter # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EB0..10EB1 ; OLetter # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE +10EC2..10EC4 ; OLetter # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10F00..10F1C ; OLetter # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; OLetter # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; OLetter # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -2536,7 +2537,7 @@ 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: 132658 +# Total code points: 132661 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index 302a2769b..870eb1937 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ -# WordBreakProperty-15.1.0.txt -# Date: 2023-03-31, 03:19:05 GMT +# WordBreakProperty-16.0.0.txt +# Date: 2023-10-02, 12:17:10 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -91,7 +91,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 0825..0827 ; Extend # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; Extend # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; Extend # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK -0898..089F ; Extend # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +0897..089F ; Extend # Mn [9] ARABIC PEPET..ARABIC HALF MADDA OVER MADDA 08CA..08E1 ; Extend # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; Extend # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 0903 ; Extend # Mc DEVANAGARI SIGN VISARGA @@ -604,7 +604,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2554 +# Total code points: 2555 # ================================================ @@ -1115,6 +1115,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10D00..10D23 ; ALetter # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA 10E80..10EA9 ; ALetter # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EB0..10EB1 ; ALetter # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE +10EC2..10EC4 ; ALetter # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10F00..10F1C ; ALetter # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; ALetter # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; ALetter # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -1313,7 +1314,7 @@ 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: 29490 +# Total code points: 29493 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index e81a64410..425000246 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ -# DerivedBidiClass-15.1.0.txt -# Date: 2023-07-28, 23:33:54 GMT +# DerivedBidiClass-16.0.0.txt +# Date: 2023-10-02, 12:16:21 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -2023,7 +2023,7 @@ FFFFE..FFFFF ; BN # Cn [2] .. 0825..0827 ; NSM # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; NSM # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; NSM # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK -0898..089F ; NSM # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +0897..089F ; NSM # Mn [9] ARABIC PEPET..ARABIC HALF MADDA OVER MADDA 08CA..08E1 ; NSM # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; NSM # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 093A ; NSM # Mn DEVANAGARI VOWEL SIGN OE @@ -2348,7 +2348,7 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 1E944..1E94A ; NSM # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1993 +# Total code points: 1994 # ================================================ @@ -2395,6 +2395,7 @@ FDFC ; AL # Sc RIAL SIGN FE70..FE74 ; AL # Lo [5] ARABIC FATHATAN ISOLATED FORM..ARABIC KASRATAN ISOLATED FORM FE76..FEFC ; AL # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM 10D00..10D23 ; AL # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA +10EC2..10EC4 ; AL # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10F30..10F45 ; AL # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN 10F51..10F54 ; AL # No [4] SOGDIAN NUMBER ONE..SOGDIAN NUMBER ONE HUNDRED 10F55..10F59 ; AL # Po [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT @@ -2440,8 +2441,8 @@ FE76..FEFC ; AL # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WI 1EEA5..1EEA9 ; AL # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; AL # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN -# The above property value applies to 298 code points not listed here. -# Total code points: 1769 +# The above property value applies to 294 code points not listed here. +# Total code points: 1768 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index 88acc6f4b..d2888c80d 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ -# DerivedCombiningClass-15.1.0.txt -# Date: 2023-07-28, 23:33:58 GMT +# DerivedCombiningClass-16.0.0.txt +# Date: 2023-10-02, 12:41:00 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1463,6 +1463,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 10E80..10EA9 ; 0 # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EAD ; 0 # Pd YEZIDI HYPHENATION MARK 10EB0..10EB1 ; 0 # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE +10EC2..10EC4 ; 0 # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10F00..10F1C ; 0 # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; 0 # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF 10F27 ; 0 # Lo OLD SOGDIAN LIGATURE AYIN-DALETH @@ -2005,8 +2006,8 @@ 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 826766 code points not listed here. -# Total code points: 1113190 +# The above property value applies to 826762 code points not listed here. +# Total code points: 1113189 # ================================================ @@ -2652,7 +2653,7 @@ FE27..FE2D ; 220 # Mn [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CON 081B..0823 ; 230 # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A 0825..0827 ; 230 # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; 230 # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA -0898 ; 230 # Mn ARABIC SMALL HIGH WORD AL-JUZ +0897..0898 ; 230 # Mn [2] ARABIC PEPET..ARABIC SMALL HIGH WORD AL-JUZ 089C..089F ; 230 # Mn [4] ARABIC MADDA WAAJIB..ARABIC HALF MADDA OVER MADDA 08CA..08CE ; 230 # Mn [5] ARABIC SMALL HIGH FARSI YEH..ARABIC LARGE ROUND DOT ABOVE 08D4..08E1 ; 230 # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA @@ -2741,7 +2742,7 @@ FE2E..FE2F ; 230 # Mn [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBINING CYR 1E4EF ; 230 # Mn NAG MUNDARI SIGN SUTUH 1E944..1E949 ; 230 # Mn [6] ADLAM ALIF LENGTHENER..ADLAM GEMINATE CONSONANT MODIFIER -# Total code points: 510 +# Total code points: 511 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index e2bac0bd5..6776cd4c8 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ -# DerivedEastAsianWidth-15.1.0.txt -# Date: 2023-07-28, 23:34:01 GMT +# DerivedEastAsianWidth-16.0.0.txt +# Date: 2023-10-02, 12:16:27 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -225,7 +225,7 @@ 0888 ; N # Sk ARABIC RAISED ROUND DOT 0889..088E ; N # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL 0890..0891 ; N # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE -0898..089F ; N # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +0897..089F ; N # Mn [9] ARABIC PEPET..ARABIC HALF MADDA OVER MADDA 08A0..08C8 ; N # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF 08C9 ; N # Lm ARABIC SMALL FARSI YEH 08CA..08E1 ; N # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA @@ -1472,6 +1472,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 10EAB..10EAC ; N # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EAD ; N # Pd YEZIDI HYPHENATION MARK 10EB0..10EB1 ; N # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE +10EC2..10EC4 ; N # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EFD..10EFF ; N # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; N # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; N # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF @@ -2043,7 +2044,7 @@ 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 766284 code points not listed here. +# The above property value applies to 766280 code points not listed here. # Total code points: 792618 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index 285ffa8fb..b75457c76 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ -# DerivedGeneralCategory-15.1.0.txt -# Date: 2023-07-28, 23:34:02 GMT +# DerivedGeneralCategory-16.0.0.txt +# Date: 2023-10-02, 12:16:28 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -37,7 +37,7 @@ 085F ; Cn # 086B..086F ; Cn # [5] .. 088F ; Cn # -0892..0897 ; Cn # [6] .. +0892..0896 ; Cn # [5] .. 0984 ; Cn # 098D..098E ; Cn # [2] .. 0991..0992 ; Cn # [2] .. @@ -435,7 +435,8 @@ FFFE..FFFF ; Cn # [2] .. 10E7F ; Cn # 10EAA ; Cn # 10EAE..10EAF ; Cn # [2] .. -10EB2..10EFC ; Cn # [75] .. +10EB2..10EC1 ; Cn # [16] .. +10EC5..10EFC ; Cn # [56] .. 10F28..10F2F ; Cn # [8] .. 10F5A..10F6F ; Cn # [22] .. 10F8A..10FAF ; Cn # [38] .. @@ -723,7 +724,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 824718 +# Total code points: 824714 # ================================================ @@ -2484,6 +2485,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 10D00..10D23 ; Lo # [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA 10E80..10EA9 ; Lo # [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EB0..10EB1 ; Lo # [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE +10EC2..10EC4 ; Lo # [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10F00..10F1C ; Lo # [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; Lo # OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; Lo # [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -2654,7 +2656,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 30000..3134A ; Lo # [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Lo # [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 132234 +# Total code points: 132237 # ================================================ @@ -2684,7 +2686,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 0825..0827 ; Mn # [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; Mn # [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; Mn # [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK -0898..089F ; Mn # [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +0897..089F ; Mn # [9] ARABIC PEPET..ARABIC HALF MADDA OVER MADDA 08CA..08E1 ; Mn # [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; Mn # [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 093A ; Mn # DEVANAGARI VOWEL SIGN OE @@ -3007,7 +3009,7 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 1E944..1E94A ; Mn # [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; Mn # [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1985 +# Total code points: 1986 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedJoiningGroup.txt b/unicodetools/data/ucd/dev/extracted/DerivedJoiningGroup.txt index 364847b91..2589107eb 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedJoiningGroup.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedJoiningGroup.txt @@ -1,5 +1,5 @@ -# DerivedJoiningGroup-15.1.0.txt -# Date: 2023-01-05, 20:34:37 GMT +# DerivedJoiningGroup-16.0.0.txt +# Date: 2023-10-02, 12:16:28 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -72,8 +72,9 @@ 06EE ; Dal # Lo ARABIC LETTER DAL WITH INVERTED V 0759..075A ; Dal # Lo [2] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER DAL WITH INVERTED SMALL V BELOW 08AE ; Dal # Lo ARABIC LETTER DAL WITH THREE DOTS BELOW +10EC2 ; Dal # Lo ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW -# Total code points: 15 +# Total code points: 16 # ================================================ @@ -177,8 +178,9 @@ 06AC..06AE ; Kaf # Lo [3] ARABIC LETTER KAF WITH DOT ABOVE..ARABIC LETTER KAF WITH THREE DOTS BELOW 077F ; Kaf # Lo ARABIC LETTER KAF WITH TWO DOTS ABOVE 08B4 ; Kaf # Lo ARABIC LETTER KAF WITH DOT BELOW +10EC4 ; Kaf # Lo ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW -# Total code points: 6 +# Total code points: 7 # ================================================ @@ -331,8 +333,9 @@ 069F ; Tah # Lo ARABIC LETTER TAH WITH THREE DOTS ABOVE 088B..088C ; Tah # Lo [2] ARABIC LETTER TAH WITH DOT BELOW..ARABIC LETTER TAH WITH THREE DOTS BELOW 08A3 ; Tah # Lo ARABIC LETTER TAH WITH TWO DOTS ABOVE +10EC3 ; Tah # Lo ARABIC LETTER TAH WITH TWO DOTS VERTICALLY BELOW -# Total code points: 6 +# Total code points: 7 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt index a4e01e7d3..082e7a262 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt @@ -1,5 +1,5 @@ -# DerivedJoiningType-15.1.0.txt -# Date: 2023-01-05, 20:34:38 GMT +# DerivedJoiningType-16.0.0.txt +# Date: 2023-10-02, 12:16:29 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -95,6 +95,7 @@ A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA 10BAD..10BAE ; D # No [2] PSALTER PAHLAVI NUMBER TEN..PSALTER PAHLAVI NUMBER TWENTY 10D01..10D21 ; D # Lo [33] HANIFI ROHINGYA LETTER BA..HANIFI ROHINGYA VOWEL O 10D23 ; D # Lo HANIFI ROHINGYA MARK NA KHONNA +10EC3..10EC4 ; D # Lo [2] ARABIC LETTER TAH WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10F30..10F32 ; D # Lo [3] SOGDIAN LETTER ALEPH..SOGDIAN LETTER GIMEL 10F34..10F44 ; D # Lo [17] SOGDIAN LETTER WAW..SOGDIAN LETTER LESH 10F51..10F53 ; D # No [3] SOGDIAN NUMBER ONE..SOGDIAN NUMBER TWENTY @@ -110,7 +111,7 @@ A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA 10FCA ; D # No CHORASMIAN NUMBER TWENTY 1E900..1E943 ; D # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 610 +# Total code points: 612 # ================================================ @@ -173,6 +174,7 @@ A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA 10B91 ; R # Lo PSALTER PAHLAVI LETTER TAW 10BA9..10BAC ; R # No [4] PSALTER PAHLAVI NUMBER ONE..PSALTER PAHLAVI NUMBER FOUR 10D22 ; R # Lo HANIFI ROHINGYA MARK SAKIN +10EC2 ; R # Lo ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW 10F33 ; R # Lo SOGDIAN LETTER HE 10F54 ; R # No SOGDIAN NUMBER ONE HUNDRED 10F74..10F75 ; R # Lo [2] OLD UYGHUR LETTER ZAYIN..OLD UYGHUR LETTER FINAL HETH @@ -182,7 +184,7 @@ A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA 10FC2..10FC3 ; R # Lo [2] CHORASMIAN LETTER RESH..CHORASMIAN LETTER SHIN 10FC9 ; R # No CHORASMIAN NUMBER TEN -# Total code points: 152 +# Total code points: 153 # ================================================ @@ -228,7 +230,7 @@ A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA 0825..0827 ; T # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; T # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; T # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK -0898..089F ; T # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +0897..089F ; T # Mn [9] ARABIC PEPET..ARABIC HALF MADDA OVER MADDA 08CA..08E1 ; T # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; T # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 093A ; T # Mn DEVANAGARI VOWEL SIGN OE @@ -568,6 +570,6 @@ E0001 ; T # Cf LANGUAGE TAG E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2150 +# Total code points: 2151 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index a0c7ab142..c2f084c5f 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ -# DerivedLineBreak-15.1.0.txt -# Date: 2023-07-28, 23:34:03 GMT +# DerivedLineBreak-16.0.0.txt +# Date: 2023-10-02, 12:16:29 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -68,8 +68,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 762725 code points not listed here. -# Total code points: 900193 +# The above property value applies to 762721 code points not listed here. +# Total code points: 900189 # ================================================ @@ -1299,6 +1299,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 10E60..10E7E ; AL # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS 10E80..10EA9 ; AL # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EB0..10EB1 ; AL # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE +10EC2..10EC4 ; AL # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10F00..10F1C ; AL # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; AL # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF 10F27 ; AL # Lo OLD SOGDIAN LIGATURE AYIN-DALETH @@ -1580,7 +1581,7 @@ 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..1FBCA ; AL # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON -# Total code points: 21729 +# Total code points: 21732 # ================================================ @@ -1881,7 +1882,7 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 0825..0827 ; CM # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; CM # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; CM # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK -0898..089F ; CM # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +0897..089F ; CM # Mn [9] ARABIC PEPET..ARABIC HALF MADDA OVER MADDA 08CA..08E1 ; CM # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; CM # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 0903 ; CM # Mc DEVANAGARI SIGN VISARGA @@ -2336,7 +2337,7 @@ E0001 ; CM # Cf LANGUAGE TAG E0020..E007F ; CM # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; CM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2429 +# Total code points: 2430 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index d67c48e05..080ce3711 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ -# DerivedName-15.1.0.txt -# Date: 2023-07-28, 23:34:03 GMT +# DerivedName-16.0.0.txt +# Date: 2023-10-02, 12:16:30 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -2098,6 +2098,7 @@ 088E ; ARABIC VERTICAL TAIL 0890 ; ARABIC POUND MARK ABOVE 0891 ; ARABIC PIASTRE MARK ABOVE +0897 ; ARABIC PEPET 0898 ; ARABIC SMALL HIGH WORD AL-JUZ 0899 ; ARABIC SMALL LOW WORD ISHMAAM 089A ; ARABIC SMALL LOW WORD IMAALA @@ -30065,6 +30066,9 @@ FFFD ; REPLACEMENT CHARACTER 10EAD ; YEZIDI HYPHENATION MARK 10EB0 ; YEZIDI LETTER LAM WITH DOT ABOVE 10EB1 ; YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE +10EC2 ; ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW +10EC3 ; ARABIC LETTER TAH WITH TWO DOTS VERTICALLY BELOW +10EC4 ; ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EFD ; ARABIC SMALL LOW WORD SAKTA 10EFE ; ARABIC SMALL LOW WORD QASR 10EFF ; ARABIC SMALL LOW WORD MADDA @@ -44176,6 +44180,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 149813 +# Total code points: 149817 # EOF From c0353fe929e382b6ce85de413c5cc469bc47047a Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 3 Oct 2023 23:51:48 +0200 Subject: [PATCH 02/10] Script codes from the future (#546) --- .../java/org/unicode/text/UCD/UCD_Names.java | 38 +++++++++---------- .../java/org/unicode/text/UCD/UCD_Types.java | 24 ++++++------ 2 files changed, 31 insertions(+), 31 deletions(-) diff --git a/unicodetools/src/main/java/org/unicode/text/UCD/UCD_Names.java b/unicodetools/src/main/java/org/unicode/text/UCD/UCD_Names.java index c48269675..0f12b0ffc 100644 --- a/unicodetools/src/main/java/org/unicode/text/UCD/UCD_Names.java +++ b/unicodetools/src/main/java/org/unicode/text/UCD/UCD_Names.java @@ -414,19 +414,19 @@ public final class UCD_Names implements UCD_Types { // Unicode 15 "Kawi", "Nag_Mundari", - // A future version of Unicode - "Sunuwar", - "Tulu_Tigalari", - "Kirat_Rai", - "Todhri", + // Unicode 16 "Garay", "Gurung_Khema", + "Kirat_Rai", "Ol_Onal", + "Sunuwar", + "Todhri", + "Tulu_Tigalari", // Provisionally assigned - "Sidetic", "Chisoi", - "Tolong_Siki", + "Sidetic", "Tai_Yo", + "Tolong_Siki", }; public static final Relation EXTRA_SCRIPT = @@ -611,19 +611,19 @@ public final class UCD_Names implements UCD_Types { // Unicode 15 "Kawi", "Nagm", - // A future version of Unicode - "Qaba", - "Qabb", - "Qabc", - "Qabd", - "Qabe", - "Qabf", - "Qabg", + // Unicode 16 + "Gara", + "Gukh", + "Krai", + "Onao", + "Sunu", + "Todr", + "Tutg", // Provisionally assigned - "Qabh", - "Qabi", - "Qabj", - "Qabk", + "Chis", + "Sidt", + "Tayo", + "Tols", }; static final String[] SHORT_AGE = { diff --git a/unicodetools/src/main/java/org/unicode/text/UCD/UCD_Types.java b/unicodetools/src/main/java/org/unicode/text/UCD/UCD_Types.java index 6f5a76340..972753c37 100644 --- a/unicodetools/src/main/java/org/unicode/text/UCD/UCD_Types.java +++ b/unicodetools/src/main/java/org/unicode/text/UCD/UCD_Types.java @@ -599,20 +599,20 @@ public interface UCD_Types { // Unicode 15 Kawi = 164, Nag_Mundari = 165, - // A future version of Unicode - Sunuwar = 166, - Tulu_Tigalari = 167, + // Unicode 16 + Garay = 166, + Gurung_Khema = 167, Kirat_Rai = 168, - Todhri = 169, - Garay = 170, - Gurung_Khema = 171, - Ol_Onal = 172, + Ol_Onal = 169, + Sunuwar = 170, + Todhri = 171, + Tulu_Tigalari = 172, // Provisionally assigned - Sidetic = 173, - Chisoi = 174, - Tolong_Siki = 175, - Tai_Yo = 176, - LIMIT_SCRIPT = Tai_Yo + 1; + Chisoi = 173, + Sidetic = 174, + Tai_Yo = 175, + Tolong_Siki = 176, + LIMIT_SCRIPT = Tolong_Siki + 1; // Bidi_Paired_Bracket_Type public static final byte BPT_N = 0, BPT_O = 1, BPT_C = 2, LIMIT_BPT = 3; From 7908510529a608c31a974dfd357dcf209979bf07 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Tue, 3 Oct 2023 16:51:58 -0500 Subject: [PATCH 03/10] Bump guava from 29.0-jre to 32.0.0-jre in /UnicodeJsps (#501) Bumps [guava](https://github.com/google/guava) from 29.0-jre to 32.0.0-jre. - [Release notes](https://github.com/google/guava/releases) - [Commits](https://github.com/google/guava/commits) --- updated-dependencies: - dependency-name: com.google.guava:guava dependency-type: direct:production ... Signed-off-by: dependabot[bot] Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> --- UnicodeJsps/pom.xml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/UnicodeJsps/pom.xml b/UnicodeJsps/pom.xml index 98f0e75b2..83d01106f 100644 --- a/UnicodeJsps/pom.xml +++ b/UnicodeJsps/pom.xml @@ -65,7 +65,7 @@ com.google.guava guava - 29.0-jre + 32.0.0-jre From 5386812ccfb39edd3268c53a9237cca2a20f53e4 Mon Sep 17 00:00:00 2001 From: "Steven R. Loomis" Date: Tue, 3 Oct 2023 19:32:17 -0500 Subject: [PATCH 04/10] docs(jsp): document how to build and run with Docker (#559) --- docs/unicodejsps/index.md | 27 ++++++++++++++++++++------- 1 file changed, 20 insertions(+), 7 deletions(-) diff --git a/docs/unicodejsps/index.md b/docs/unicodejsps/index.md index 477f20d08..c3d97f27c 100644 --- a/docs/unicodejsps/index.md +++ b/docs/unicodejsps/index.md @@ -1,11 +1,5 @@ # Building UnicodeJsp -- Note: you can run the latest UnicodeJsp locally with docker using: - -``` -docker run --rm -p 8080:8080 unicode/unicode-jsp -``` - - Note 2: there are some notes on updated processes for using GCP at [gcp-run.md](./gcp-run.md) - at present, automated deployment is TODO. ## Compiling @@ -113,7 +107,26 @@ Look at , and make sure that there aren't any Z-Other props at the bottom (you'll need to update via Adding New Properties if there are). -(:construction: **TODO**: explain how to do a Docker-based build here.) +### Running a Docker-based build + +compile java stuff + +- `mvn -B package -am -pl UnicodeJsps -DskipTests=true` + +”backup” copy of CLDR and UnicodeTools. (`~/src/cldr` is an optional existing CLDR dir to save a few packets) + +- `git clone --reference-if-able ~/src/cldr https://github.com/unicode-org/cldr.git || (cd cldr && git pull)` +- `mkdir -p UnicodeJsps/target && tar -cpz --exclude=.git --exclude=unicodetools/target/ -f UnicodeJsps/target/cldr-unicodetools.tgz ./cldr/ ./unicodetools/` + +Now, finally build. + +- `docker build -t unicode/unicode-jsp:latest UnicodeJsps/` + +… And run. Control-C to cancel it, otherwise visit + +``` +docker run --rm -p 8080:8080 unicode/unicode-jsp:latest +``` ## Commit/PR From 625b35c27458b112f70ca75099dc4c177738792d Mon Sep 17 00:00:00 2001 From: "Steven R. Loomis" Date: Tue, 3 Oct 2023 19:32:31 -0500 Subject: [PATCH 05/10] feat(jsp): robots.txt for JSP utilities (#558) Fixes: #529 --- UnicodeJsps/jetty.d/ROOT/robots.txt | 2 ++ 1 file changed, 2 insertions(+) create mode 100644 UnicodeJsps/jetty.d/ROOT/robots.txt diff --git a/UnicodeJsps/jetty.d/ROOT/robots.txt b/UnicodeJsps/jetty.d/ROOT/robots.txt new file mode 100644 index 000000000..a40ff93be --- /dev/null +++ b/UnicodeJsps/jetty.d/ROOT/robots.txt @@ -0,0 +1,2 @@ +User-agent: * +Disallow: /UnicodeJsps From 9e3e3870fc1ba6c34c417d59ece9dc87e207194e Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 4 Oct 2023 23:16:36 +0200 Subject: [PATCH 06/10] Make MakeUnicodeFiles regenerate IndicMeowCategory.txt (#547) --- .../data/ucd/dev/IndicPositionalCategory.txt | 8 +- .../data/ucd/dev/IndicSyllabicCategory.txt | 10 +- .../unicode/text/UCD/MakeUnicodeFiles.java | 70 +++- .../org/unicode/text/UCD/MakeUnicodeFiles.txt | 370 ++++++++++++++++++ 4 files changed, 443 insertions(+), 15 deletions(-) diff --git a/unicodetools/data/ucd/dev/IndicPositionalCategory.txt b/unicodetools/data/ucd/dev/IndicPositionalCategory.txt index a7c5aef60..9b5aabfa0 100644 --- a/unicodetools/data/ucd/dev/IndicPositionalCategory.txt +++ b/unicodetools/data/ucd/dev/IndicPositionalCategory.txt @@ -1,11 +1,11 @@ -# IndicPositionalCategory-15.1.0.txt -# Date: 2023-01-05 +# IndicPositionalCategory-16.0.0.txt +# Date: 2023-10-02, 22:58:33 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html # -# For documentation, see UAX #44: Unicode Character Database, -# at https://www.unicode.org/reports/tr44/ +# Unicode Character Database +# For documentation, see https://www.unicode.org/reports/tr44/ # # This file defines the following property: # diff --git a/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt b/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt index f2623b471..5de0d7554 100644 --- a/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt +++ b/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt @@ -1,11 +1,11 @@ -# IndicSyllabicCategory-15.1.0.txt -# Date: 2023-01-05 +# IndicSyllabicCategory-16.0.0.txt +# Date: 2023-10-02, 22:58:33 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html # -# For documentation, see UAX #44: Unicode Character Database, -# at https://www.unicode.org/reports/tr44/ +# Unicode Character Database +# For documentation, see https://www.unicode.org/reports/tr44/ # # This file defines the following property: # @@ -1335,7 +1335,7 @@ ABF0..ABF9 ; Number # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NI # script, e.g. in Brahmi) # # Note: These are different from Numbers, in the way that there is no known -# evidence of Brahmi Joining Numbers taking vowels or subjoined consonants. +# evidence of Brahmi Joining Numbers taking vowels or subjoined consonants. # Until such evidence is found, implementations may assume that Brahmi # Joining Numbers only participate in shaping with other Brahmi Joining # Numbers. diff --git a/unicodetools/src/main/java/org/unicode/text/UCD/MakeUnicodeFiles.java b/unicodetools/src/main/java/org/unicode/text/UCD/MakeUnicodeFiles.java index e1ff508ad..759361106 100644 --- a/unicodetools/src/main/java/org/unicode/text/UCD/MakeUnicodeFiles.java +++ b/unicodetools/src/main/java/org/unicode/text/UCD/MakeUnicodeFiles.java @@ -67,6 +67,7 @@ static class Format { Map> fileToPropertySet = new TreeMap>(); Map fileToComments = new TreeMap(); Map fileToDirectory = new TreeMap(); + Map> propertyToOrderedValues = new TreeMap>(); Map> propertyToValueToComments = new TreeMap>(); Map hackMap = new HashMap(); @@ -110,6 +111,12 @@ public static class PrintStyle { // Unicode 15.1 and later LineBreak.txt and EastAsianWidth.txt, which are all generated // in that format by some other tool. boolean kenFile = false; + // Whether the file should be produced in the style of IndicPositionalCategory.txt and + // IndicSyllabicCategory.txt, which are both generated in that format by some other + // tool. + boolean roozbehFile = false; + // Whether to separate values of enumerated properties using a line of equal signs. + boolean separateValues = true; boolean hackValues = false; boolean mergeRanges = true; String nameStyle = "none"; @@ -138,6 +145,10 @@ String parse(String options) { interleaveValues = true; } else if (piece.equals("kenFile")) { kenFile = true; + } else if (piece.equals("roozbehFile")) { + roozbehFile = true; + } else if (piece.startsWith("separateValues=")) { + separateValues = afterEqualsBoolean(piece); } else if (piece.equals("hackValues")) { hackValues = true; } else if (piece.equals("sortNumeric")) { @@ -301,6 +312,10 @@ private void build() { } line = line.trim(); if (line.length() == 0) { + if (comments.length() != 0) { + // Preserve blank lines between comments. + comments += "\n"; + } continue; } if (DEBUG) { @@ -321,6 +336,7 @@ private void build() { comments += line; } else { // end of comments, roll up + comments = comments.trim(); if (comments.length() != 0) { if (property != null) { addValueComments(property, value, comments); @@ -350,6 +366,10 @@ private void build() { value = ""; } else if (line.startsWith("Value:")) { value = lineValue; + final var values = + propertyToOrderedValues.computeIfAbsent( + property, k -> new ArrayList()); + values.add(value); } else if (line.startsWith("HackName:")) { final String regularItem = Utility.getUnskeleton(lineValue, true); hackMap.put(regularItem, lineValue); @@ -1152,6 +1172,9 @@ public static void generatePropertyFile(String filename) throws IOException { filename, Format.theFormat.getPrintStyle(name)); if (!ps.kenFile) { pwProp.println(); + if (!ps.separateValues) { + pwProp.println(); + } pwProp.println(SEPARATOR); } final String propComment = Format.theFormat.getValueComments(name, ""); @@ -1161,7 +1184,11 @@ public static void generatePropertyFile(String filename) throws IOException { pwProp.println(propComment); } else if (!prop.isType(UnicodeProperty.BINARY_MASK)) { pwProp.println(); - pwProp.println("# Property:\t" + name); + if (ps.roozbehFile) { + pwProp.println("# Property: " + name); + } else { + pwProp.println("# Property:\t" + name); + } } } @@ -1182,9 +1209,12 @@ public static void generatePropertyFile(String filename) throws IOException { v = v + " (" + v2 + ")"; } } - pwProp.println(); + pwProp.println(ps.roozbehFile ? "#" : ""); pwProp.println("# All code points not explicitly listed for " + prop.getName()); - pwProp.println("# have the value " + v + "."); + pwProp.println( + "# have the value " + + v + + (ps.roozbehFile && v.equals("NA") ? " (not applicable)." : ".")); } if (!ps.interleaveValues && prop.isType(UnicodeProperty.BINARY_MASK)) { @@ -1254,6 +1284,21 @@ private static void writeEnumeratedValues( temp2.addAll(aliases); aliases = temp2; } + if (ps.roozbehFile) { + aliases.removeIf(alias -> UnicodeProperty.compareNames(alias, ps.skipValue) == 0); + if (!Format.theFormat + .propertyToOrderedValues + .get(prop.getName()) + .containsAll(aliases)) { + final TreeSet missingAliases = new TreeSet(aliases); + missingAliases.removeAll( + Format.theFormat.propertyToOrderedValues.get(prop.getName())); + throw new IllegalArgumentException( + "All values must be listed when using roozbehFile; missing " + + missingAliases); + } + aliases = Format.theFormat.propertyToOrderedValues.get(prop.getName()); + } if (ps.sortNumeric) { if (DEBUG) { System.out.println("Reordering"); @@ -1284,7 +1329,7 @@ private static void writeEnumeratedValues( final String missing = ps.skipUnassigned != null ? ps.skipUnassigned : ps.skipValue; if (missing != null && !missing.equals(UCD_Names.NO)) { - pw.println(); + pw.println(ps.roozbehFile ? "#" : ""); final String propName = bf.getPropName(); // if (propName == null) propName = ""; // else if (propName.length() != 0) propName = propName + "; "; @@ -1302,6 +1347,10 @@ private static void writeEnumeratedValues( writeEnumeratedMissingValues(pw, overallDefault, defaultLbValues); } } + if (!ps.separateValues) { + pw.println(); + pw.println(SEPARATOR.replace('=', '-')); + } for (final Iterator it = aliases.iterator(); it.hasNext(); ) { final String value = it.next(); if (DEBUG) { @@ -1416,9 +1465,13 @@ private static void writeEnumeratedValues( if (!prop.isType(UnicodeProperty.BINARY_MASK)) { pw.println(); - pw.println(SEPARATOR); + if (ps.separateValues) { + pw.println(SEPARATOR); + } if (nonLongValue) { - pw.println(); + if (ps.separateValues) { + pw.println(); + } pw.println("# " + prop.getName() + "=" + value); } } @@ -1442,6 +1495,11 @@ private static void writeEnumeratedValues( pw.println(); // if (s.size() != 0) bf.setMergeRanges(ps.mergeRanges); + bf.setShowTotal(!ps.roozbehFile); + if (ps.roozbehFile) { + bf.setRangeBreakSource( + ToolUnicodePropertySource.make(Default.ucdVersion()).getProperty("Block")); + } bf.showSetNames(pw, s); if (DEBUG) { System.out.println(bf.showSetNames(s)); diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/MakeUnicodeFiles.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/MakeUnicodeFiles.txt index 702c46ca5..db8ebd7b8 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/MakeUnicodeFiles.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/MakeUnicodeFiles.txt @@ -908,6 +908,376 @@ Format: kenFile skipValue=Rotated # Property: VerticalOrientation +File: IndicPositionalCategory +# +# This file defines the following property: +# +# Indic_Positional_Category enumerated property +# +# Scope: This property is aimed at the problem of +# the specification of syllabic structure for Indic scripts. +# Because dependent vowels (matras), visible viramas, and other +# characters are placed in notional slots around the consonant (or +# consonant cluster) core of an Indic syllable, there may be +# cooccurrence constraints or other interactions. Also, it may be +# desirable, in cases where more than one such character may occur in +# sequence, as for example, in a top slot and a bottom slot, to +# specify preferred orders for spelling. As such, this property +# is designed primarily to supplement the Indic_Syllabic_Category +# property. +# +# In addition to combining marks associated with Indic scripts, the +# Indic_Positional_Category has non-trivial values for special signs +# associated with Indic_Syllabic_Category=Consonant_Prefixed +# or Indic_Syllabic_Category=Consonant_Preceding_Repha. Those signs +# have General_Category=Lo, rather than being combining marks. +# They occur in initial position in syllabic structure. However, when +# rendered, they appear as marks positioned with respect to another +# base letter (usually above it). Hence, having an explicit value for +# Indic_Positional_Category for those signs can be helpful. +# +# Note that this property is *not* intended as +# a prescriptive property regarding display or font design, +# for a number of reasons. Good font design requires information +# that is outside the context of a character encoding standard, +# and is best handled in other venues. For Indic dependent +# vowels and similar characters, in particular: +# +# 1. Matra placement may vary somewhat based on typeface design. +# 2. Matra placement, even within a single script, may vary +# somewhat according to historic period or local conventions. +# 3. Matra placement may be changed by explicit orthographic reform +# decisions. +# 4. Matras may ligate in various ways with a consonant (or even +# other elements of a syllable) instead of occurring in a +# discrete location. +# 5. Matra display may be contextually determined. This is +# notable, for example, in the Tamil script, where the shape +# and placement of -u and -uu vowels depends strongly on +# which consonant they adjoin. +# +# Format: +# Field 0 Unicode code point value or range of code point values +# Field 1 Indic_Positional_Category property value +# +# Field 1 is followed by a comment field, starting with the number sign '#', +# which shows the General_Category property value, the Unicode character name +# or names, and, in lines with ranges of code points, the code point count in +# square brackets. +# +# The scripts assessed as containing dependent vowels or similar characters +# in the structural sense used for the Indic_Positional_Category are the +# following: +# +# Ahom, Balinese, Batak, Bengali, Bhaiksuki, Brahmi, Buginese, Buhid, +# Chakma, Cham, Devanagari, Dives Akuru, Dogra, Grantha, Gujarati, +# Gunjala Gondi, Gurmukhi, Hanunoo, Javanese, Kaithi, Kannada, Kawi, +# Kayah Li, Kharoshthi, Khmer, Khojki, Khudawadi, Lao, Lepcha, Limbu, +# Makasar, Malayalam, Marchen, Masaram Gondi, Meetei Mayek, Modi, +# Myanmar, Nandinagari, Newa, New Tai Lue, Oriya, Rejang, Saurashtra, +# Sharada, Siddham, Sinhala, Soyombo, Sundanese, Syloti Nagri, +# Tagalog, Tagbanwa, Tai Tham, Tai Viet, Takri, Tamil, Telugu, Thai, +# Tibetan, Tirhuta, and Zanabazar Square. +# +# All characters for all other scripts not in that list +# take the default value for this property. +# +# See IndicSyllabicCategory.txt for a slightly more extended +# list of Indic scripts, including those which do not have +# positional characters. Currently, those additional +# Indic scripts without positional characters are +# Multani, Phags-pa, and Tai Le. +# +# Notes: +# +# 1. The following characters are all assigned the positional category Right, +# but may have different positions in some cases: +# * U+0BC1 TAMIL VOWEL SIGN U and U+0BC2 TAMIL VOWEL SIGN UU have +# contextually variable placement in Tamil. +# * U+0D41 MALAYALAM VOWEL SIGN U and U+0D42 MALAYALAM VOWEL SIGN UU form +# complex ligatures with consonants in older Malayalam orthography. +# * U+11341 GRANTHA VOWEL SIGN U and U+11342 GRANTHA VOWEL SIGN UU have +# contextually variable placement in Grantha. +# * U+11440 NEWA VOWEL SIGN O and U+11441 NEWA VOWEL SIGN AU have contextually +# variable placement in Newa. +# +# 2. The following characters are all assigned the positional category Top, +# but may have different positions in some cases: +# * U+1143E NEWA VOWEL SIGN E and U+1143F NEWA VOWEL SIGN AI have contextually +# variable placement in Newa. +# +# 3. The following characters are all assigned the positional category Bottom, +# but may have different positions in some cases: +# * U+102F MYANMAR VOWEL SIGN U and U+1030 MYANMAR VOWEL SIGN UU have +# contextually variable placement in Myanmar. +# * U+1A69 TAI THAM VOWEL SIGN U and U+1A6A TAI THAM VOWEL SIGN UU have +# contextually variable placement in Tai Tham. +# +# 4. The following character is assigned the positional category Left, but +# may have different positions in different styles: +# * U+119D2 NANDINAGARI VOWEL SIGN I has stylistically variable placement +# in Nandinagari. +Property: Indic_Positional_Category +Format: roozbehFile separateValues=false valueStyle=short skipValue=NA +Value: Right +Value: Left +Value: Visual_Order_Left + +# These are dependent vowels that occur to the left of the consonant +# letter in a syllable, but which occur in scripts using the visual order +# model, instead of the logical order model. Because of the different +# model, these left-side vowels occur first in the backing store (before +# the consonant letter) and are not reordered during text rendering. +# +# [Derivation: Logical_Order_Exception=Yes] +Value: Left_And_Right +Value: Top +Value: Bottom +Value: Top_And_Bottom +Value: Top_And_Right +Value: Top_And_Left +Value: Top_And_Left_And_Right +Value: Bottom_And_Right +Value: Bottom_And_Left +Value: Top_And_Bottom_And_Right +Value: Top_And_Bottom_And_Left +Value: Overstruck + +File: IndicSyllabicCategory +# +# This file defines the following property: +# +# Indic_Syllabic_Category enumerated property +# +# Scope: This property is aimed at two general problem +# areas involving the analysis and processing of Indic scripts: +# +# 1. Specification of syllabic structure. +# 2. Specification of segmentation rules. +# +# Both of these problem areas may benefit from having defined subtypes +# of Indic script characters which are relevant to how Indic +# syllables (or aksaras) are constructed. Note that rules for +# syllabic structure in Indic scripts may differ significantly +# from how phonological syllables are defined. +# +# Format: +# Field 0 Unicode code point value or range of code point values +# Field 1 Indic_Syllabic_Category property value +# +# Field 1 is followed by a comment field, starting with the number sign '#', +# which shows the General_Category property value, the Unicode character name +# or names, and, in lines with ranges of code points, the code point count in +# square brackets. +# +# The scripts assessed as Indic in the structural sense used for the +# Indic_Syllabic_Category are the following: +# +# Ahom, Balinese, Batak, Bengali, Bhaiksuki, Brahmi, Buginese, Buhid, +# Chakma, Cham, Devanagari, Dives Akuru, Dogra, Grantha, Gujarati, +# Gunjala Gondi, Gurmukhi, Hanunoo, Javanese, Kaithi, Kannada, Kawi, +# Kayah Li, Kharoshthi, Khmer, Khojki, Khudawadi, Lao, Lepcha, Limbu, +# Mahajani, Makasar, Malayalam, Marchen, Masaram Gondi, Meetei Mayek, +# Modi, Multani, Myanmar, Nandinagari, Newa, New Tai Lue, Oriya, +# Phags-pa, Rejang, Saurashtra, Sharada, Siddham, Sinhala, Soyombo, +# Sundanese, Syloti Nagri, Tagalog, Tagbanwa, Tai Le, Tai Tham, +# Tai Viet, Takri, Tamil, Telugu, Thai, Tibetan, Tirhuta, and +# Zanabazar Square. +# +# All characters for all other scripts not in that list +# take the default value for this property, unless they +# are individually listed in this data file. +# +Property: Indic_Syllabic_Category +Format: roozbehFile valueStyle=short skipValue=Other +Value: Bindu +# Bindu/Anusvara (nasalization or -n) + +# [Not derivable] +Value: Visarga +# Visarga (-h) +# Excludes letters for jihvamuliya and upadhmaniya, which are +# related, but structured somewhat differently. + +# [Not derivable] +Value: Avagraha +# Avagraha (elision of initial a- in sandhi) + +# [Not derivable] +Value: Nukta +# Nukta (diacritic for borrowed consonants or other consonant +# modifications). Note that while the resulting sound is typically a +# consonant, the base letter a nukta follows may be an independent +# vowel. For example, is used to transcribe ARABIC LETTER +# AIN. + +# [Not derivable] +Value: Virama +# Virama (killing of inherent vowel in consonant sequence +# or consonant stacker) +# Only includes characters that can act both as visible killer viramas +# and consonant stackers. Separate property values exist for characters +# that can only act as pure killers or only as consonant stackers. + +# [Derivation: (ccc=9) - (InSC=Pure_Killer) - (InSC=Invisible_Stacker) +# - (InSC=Number_Joiner) - 2D7F] +Value: Pure_Killer +# Pure killer (killing of inherent vowel in consonant sequence, +# with no consonant stacking behavior) + +# [Not derivable] +Value: Invisible_Stacker +# Invisible stacker (invisible consonant stacker virama). +# +# Note that in some scripts, such as Kharoshthi and Masaram Gondi, an invisible +# stacker may have a second function, changing the shape and/or location of the +# consonant preceding it, even when there is no consonant following the +# invisible stacker. + +# [Not derivable] +Value: Vowel_Independent +# Independent Vowels (contrasted with matras) + +# [Not derivable] +Value: Vowel_Dependent +# Dependent Vowels (contrasted with independent vowels and/or with +# complex placement). Known as matras in Indic scripts. Also +# includes vowel modifiers that follow dependent (and sometimes +# independent) vowels. + +# [Not derivable] +Value: Vowel +# (Other) Vowels (reanalyzed as ordinary alphabetic letters or marks) + +# [Not derivable] +Value: Consonant_Placeholder +# Consonant Placeholder +# This includes generic placeholders used for +# Indic script layout (NBSP and dotted circle), as well as a few script- +# specific vowel-holder characters which are not technically +# consonants, but serve instead as bases for placement of vowel marks. + +# [Not derivable] +Value: Consonant +# Consonant (ordinary abugida consonants, with inherent vowels) + +# [Not derivable] +Value: Consonant_Dead +# Dead Consonant (special consonant with killed vowel) + +# [Not derivable] +Value: Consonant_With_Stacker +# Consonants that may make stacked ligatures with the next consonant +# without the use of a virama + +# [Not derivable] +Value: Consonant_Prefixed +# Cluster-initial consonants + +# [Not derivable] +Value: Consonant_Preceding_Repha +# Repha Form of RA (reanalyzed in some scripts), when preceding the main +# consonant. + +# [Not derivable] +Value: Consonant_Initial_Postfixed +# Consonants that succeed the main consonant in character sequences, but are +# pronounced before it. + +# [Not derivable] +Value: Consonant_Succeeding_Repha +# Repha Form of RA (reanalyzed in some scripts), when succeeding the main +# consonant. + +# [Not derivable] +Value: Consonant_Subjoined +# Subjoined Consonant (C2 form subtending a base consonant in Tibetan, etc.) + +# [Not derivable] +Value: Consonant_Medial +# Medial Consonant (medial liquid, occurring in clusters) + +# [Not derivable] +Value: Consonant_Final +# Final Consonant (special final forms which do not take vowels) + +# [Not derivable] +Value: Consonant_Head_Letter +# Head Letter (Tibetan) + +# [Not derivable] +Value: Modifying_Letter +# Reanalyzed letters not participating in the abugida structure, but +# serving to modify the sound of an adjacent vowel or consonant. +# Note that this is not the same as General_Category=Modifier_Letter. + +# [Not derivable] +Value: Tone_Letter +# Tone Letter (spacing lexical tone mark with status as a letter) + +# [Not derivable] +Value: Tone_Mark +# Tone Mark (nonspacing or spacing lexical tone mark) + +# [Not derivable] +Value: Gemination_Mark +# Gemination Mark (doubling of the preceding or following consonant) +# +# U+0A71 GURMUKHI ADDAK precedes the consonant it geminates, while the +# others follow the consonant they geminate. + +# [Not derivable] +Value: Cantillation_Mark +# Cantillation Mark (recitation marks, such as svara markers for the Samaveda) + +# [Not derivable] +Value: Register_Shifter +# Register Shifter (shifts register for consonants, akin to a tone mark) + +# [Not derivable] +Value: Syllable_Modifier +# Syllable Modifier (miscellaneous combining characters that modify +# something in the orthographic syllable they succeed or appear in) + +# [Not derivable] +Value: Consonant_Killer +# Consonant Killer (signifies that the previous consonant or consonants are +# not pronounced) + +# [Not derivable] +Value: Non_Joiner +# Non_Joiner (Zero Width Non-Joiner) + +# [Not derivable] +Value: Joiner +# Joiner (Zero Width Joiner) + +# [Not derivable] +Value: Number_Joiner +# Number_Joiner (forms ligatures between numbers for multiplication) + +# [Not derivable] +Value: Number +# Number (can be used as vowel-holders like consonant placeholders) +# Note: A number may even hold subjoined consonants which may in turn +# have been formed using a virama or a stacker, e.g. the sequence +# where THAI THAM LETTER LOW TA is subjoined to +# TAI THAM THAM DIGIT THREE using an invisible stacker. + +# [Not derivable] +Value: Brahmi_Joining_Number +# Brahmi Joining Number (may be joined by a Number_Joiner of the same +# script, e.g. in Brahmi) +# +# Note: These are different from Numbers, in the way that there is no known +# evidence of Brahmi Joining Numbers taking vowels or subjoined consonants. +# Until such evidence is found, implementations may assume that Brahmi +# Joining Numbers only participate in shaping with other Brahmi Joining +# Numbers. + +# [Not derivable] + File: UnicodeData Property: SPECIAL From c0ae922e527ccee15f94f51690ab6540f235977a Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 9 Oct 2023 12:42:46 +0200 Subject: [PATCH 07/10] Split the UCA checks into their own job, check UCD consistency (#562) --- .github/workflows/cli-build-instructions.yml | 118 +++++++++++++++---- py/copygenerateducd.py | 5 +- 2 files changed, 97 insertions(+), 26 deletions(-) mode change 100644 => 100755 py/copygenerateducd.py diff --git a/.github/workflows/cli-build-instructions.yml b/.github/workflows/cli-build-instructions.yml index 3fd9e8e56..24d4dce1c 100644 --- a/.github/workflows/cli-build-instructions.yml +++ b/.github/workflows/cli-build-instructions.yml @@ -81,8 +81,14 @@ jobs: run: | mkdir -p Generated/BIN - - name: Run command - Build and Test - run: MAVEN_OPTS="-ea" mvn -s .github/workflows/mvn-settings.xml package -DCLDR_DIR=$(cd ../cldr ; pwd) -DUNICODETOOLS_GEN_DIR=$(cd Generated; pwd) -DUNICODETOOLS_REPO_DIR=$(pwd) -DUVERSION=$CURRENT_UVERSION + # Since these are just examples to smoke-test the in-source build process, + # let’s not run the whole build and test suite, which is quite slow (6 min + # 26 s as of this writing). Just run the invariant tests and smoke-test + # MakeUnicodeFiles. We don’t even check that MakeUnicodeFiles doesn’t + # change anything, which makes little sense; but that is the job of the + # other job. + - name: Run invariant tests + run: MAVEN_OPTS="-ea" mvn -s .github/workflows/mvn-settings.xml test -am -pl unicodetools -Dtest=TestTestUnicodeInvariants -DfailIfNoTests=false -DCLDR_DIR=$(cd ../cldr ; pwd) -DUNICODETOOLS_GEN_DIR=$(cd Generated; pwd) -DUNICODETOOLS_REPO_DIR=$(pwd) -DUVERSION=$CURRENT_UVERSION env: GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} @@ -91,14 +97,15 @@ jobs: env: GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} - out-of-source-build: - name: Out-of-source Instructions + + # Out-of-source build. + ucd-and-smoke-tests: + name: Check UCD consistency, invariants, smoke-test generators runs-on: ubuntu-latest steps: - name: Checkout Unicode Tools uses: actions/checkout@v3 with: - repository: unicode-org/unicodetools path: unicodetools/mine/src - name: Get the CLDR_REF from pom.xml id: cldr_ref @@ -136,6 +143,30 @@ jobs: run: | mkdir -p unicodetools/mine/Generated/BIN + - name: Run command - Make Unicode Files + run: | + cd unicodetools/mine/src + mvn -s .github/workflows/mvn-settings.xml compile exec:java -Dexec.mainClass="org.unicode.text.UCD.Main" -Dexec.args="version $CURRENT_UVERSION build MakeUnicodeFiles" -am -pl unicodetools -DCLDR_DIR=$(cd ../../../cldr/mine/src ; pwd) -DUNICODETOOLS_GEN_DIR=$(cd ../Generated ; pwd) -DUNICODETOOLS_REPO_DIR=$(pwd) -DUVERSION=$CURRENT_UVERSION + env: + GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} + + - name: Check that UCD files are consistent + run: | + cd unicodetools/mine/src + ./py/copygenerateducd.py --out-of-source -y + git diff --compact-summary --exit-code || { + git diff --compact-summary | + awk '{ + if (previous) { + print "::error file="previous",title=File must be regenerated::Run org.unicode.text.UCD.Main build MakeUnicodeFiles and copy any changed files to unicodetools/data/ucd/dev." + } + previous=$1 + }' + exit 1 + } + + # Only test once we know the UCD is internally consistent. + # MakeUnicodeFiles is much faster than this anyway. - name: Run command - Build and Test run: | cd unicodetools/mine/src @@ -151,13 +182,6 @@ jobs: path: | unicodetools/mine/Generated/UnicodeTestResults.* - - name: Run command - Make Unicode Files - run: | - cd unicodetools/mine/src - mvn -s .github/workflows/mvn-settings.xml compile exec:java -Dexec.mainClass="org.unicode.text.UCD.Main" -Dexec.args="version $CURRENT_UVERSION build MakeUnicodeFiles" -am -pl unicodetools -DCLDR_DIR=$(cd ../../../cldr/mine/src ; pwd) -DUNICODETOOLS_GEN_DIR=$(cd ../Generated ; pwd) -DUNICODETOOLS_REPO_DIR=$(pwd) -DUVERSION=$CURRENT_UVERSION - env: - GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} - # https://github.com/unicode-org/unicodetools/blob/main/docs/emoji/aac.md#aacorderjava - name: Run command - AAC Order run: | @@ -166,18 +190,6 @@ jobs: env: GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} - # https://github.com/unicode-org/unicodetools/blob/main/docs/uca/index.md#tools--tests - # Note: Not running desuffixucd.py in UCA jobs because no version numbers detected in data file names - - name: Run command - UCA - collation validity log - run: | - cd unicodetools/mine/src - # invoke main() in class ...UCA.Main - mvn -s .github/workflows/mvn-settings.xml compile exec:java -Dexec.mainClass="org.unicode.text.UCA.Main" -Dexec.args="writeCollationValidityLog ICU" -am -pl unicodetools -DCLDR_DIR=$(cd ../../../cldr/mine/src ; pwd) -DUNICODETOOLS_GEN_DIR=$(cd ../Generated ; pwd) -DUNICODETOOLS_REPO_DIR=$(pwd) -DUVERSION=$CURRENT_UVERSION - # check for output file - compgen -G "../Generated/UCA/*/CheckCollationValidity.html" - env: - GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} - # https://github.com/unicode-org/unicodetools/blob/main/docs/idna.md - name: Run command - IDNA run: | @@ -252,3 +264,61 @@ jobs: mvn -s .github/workflows/mvn-settings.xml -Dexec.mainClass="org.unicode.propstest.CheckProperties" -Dexec.classpathScope=test test-compile -Dexec.args="COMPARE ALL $PREVIOUS_UVERSION" compile exec:java -am -pl unicodetools -DCLDR_DIR=$(cd ../../../cldr/mine/src ; pwd) -DUNICODETOOLS_GEN_DIR=$(cd ../Generated ; pwd) -DUNICODETOOLS_REPO_DIR=$(pwd) -DUVERSION=$CURRENT_UVERSION env: GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} + + # Out-of-source build. + uca: + name: Check UCA data + runs-on: ubuntu-latest + steps: + - name: Checkout Unicode Tools + uses: actions/checkout@v3 + with: + repository: unicode-org/unicodetools + path: unicodetools/mine/src + - name: Get the CLDR_REF from pom.xml + id: cldr_ref + run: echo "CLDR_REF="$(mvn --file unicodetools/mine/src/pom.xml help:evaluate -Dexpression=cldr.version -q -DforceStdout | cut -d- -f3) >> $GITHUB_OUTPUT && cat ${GITHUB_OUTPUT} + - name: Verify CLDR checkout ref + run: echo CLDR_REF="${{ steps.cldr_ref.outputs.CLDR_REF }}" && [ "${{ steps.cldr_ref.outputs.CLDR_REF }}x" != "x" ] # fail if empty + - name: Cache CLDR repository + uses: actions/cache@v3 + with: + path: cldr/mine/src + key: cldr-${{ steps.cldr_ref.outputs.CLDR_REF }} + restore-keys: | + cldr + - name: Check out CLDR + uses: actions/checkout@v3 + with: + repository: unicode-org/cldr + path: cldr/mine/src + ref: main + fetch-depth: 0 + - name: Switch CLDR to CLDR_REF + run: cd cldr/mine/src && git fetch && git checkout ${{ steps.cldr_ref.outputs.CLDR_REF }} + - name: Set up JDK 11 + uses: actions/setup-java@v1 + with: + java-version: 11 + - name: Cache local Maven repository + uses: actions/cache@v2 + with: + path: ~/.m2/repository + key: ${{ runner.os }}-maven-${{ hashFiles('**/pom.xml') }} + restore-keys: | + ${{ runner.os }}-maven- + - name: Set up out-of-source output dir + run: | + mkdir -p unicodetools/mine/Generated/BIN + + # https://github.com/unicode-org/unicodetools/blob/main/docs/uca/index.md#tools--tests + # Note: Not running desuffixucd.py in UCA jobs because no version numbers detected in data file names + - name: Run command - UCA - collation validity log + run: | + cd unicodetools/mine/src + # invoke main() in class ...UCA.Main + mvn -s .github/workflows/mvn-settings.xml compile exec:java -Dexec.mainClass="org.unicode.text.UCA.Main" -Dexec.args="writeCollationValidityLog ICU" -am -pl unicodetools -DCLDR_DIR=$(cd ../../../cldr/mine/src ; pwd) -DUNICODETOOLS_GEN_DIR=$(cd ../Generated ; pwd) -DUNICODETOOLS_REPO_DIR=$(pwd) -DUVERSION=$CURRENT_UVERSION + # check for output file + compgen -G "../Generated/UCA/*/CheckCollationValidity.html" + env: + GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} diff --git a/py/copygenerateducd.py b/py/copygenerateducd.py old mode 100644 new mode 100755 index a1a8f2f73..1b64f116b --- a/py/copygenerateducd.py +++ b/py/copygenerateducd.py @@ -17,9 +17,10 @@ def main(): + out_of_source = '--out-of-source' in sys.argv[1:] cwd = Path().cwd() uversion = os.getenv("CURRENT_UVERSION") - genucddir = cwd / "Generated" / "UCD" / uversion + genucddir = (cwd / ".." if out_of_source else cwd) / "Generated" / "UCD" / uversion if not genucddir.exists(): raise Exception(f"Generated directory not found at {genucddir.absolute()}") @@ -34,7 +35,7 @@ def main(): print("THE FOLLOWING FILES WILL BE MOVED:\n") print("\n".join([f"{str(p.name)} --> {devucddir / p.relative_to(genucddir)}" for p in to_move])) # noqa: E501 - confirm = bool(sys.argv[-1] == "-y") # enable running this in automation + confirm = bool("-y" in sys.argv[1:]) # enable running this in automation if not confirm: confirm = input("\nProceed [y/N]?").lower() == "y" From 57ae00dd10ca3a8dedf549a93fdfea12d0cbdf25 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 10 Oct 2023 16:57:39 +0200 Subject: [PATCH 08/10] Imbue ARABIC PEPET with the Alphabetic property (#569) --- unicodetools/data/ucd/dev/DerivedCoreProperties.txt | 5 +++-- unicodetools/data/ucd/dev/PropList.txt | 7 ++++--- 2 files changed, 7 insertions(+), 5 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 21cf3645d..1c09a3b3e 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: 2023-10-02, 12:41:01 GMT +# Date: 2023-10-10, 11:51:01 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -343,6 +343,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0860..086A ; Alphabetic # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 0870..0887 ; Alphabetic # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT 0889..088E ; Alphabetic # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0897 ; Alphabetic # Mn ARABIC PEPET 08A0..08C8 ; Alphabetic # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF 08C9 ; Alphabetic # Lm ARABIC SMALL FARSI YEH 08D4..08DF ; Alphabetic # Mn [12] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH WORD WAQFA @@ -1403,7 +1404,7 @@ 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: 138390 +# Total code points: 138391 # ================================================ diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt index 777e8a288..012d84953 100644 --- a/unicodetools/data/ucd/dev/PropList.txt +++ b/unicodetools/data/ucd/dev/PropList.txt @@ -1,5 +1,5 @@ -# PropList-15.1.0.txt -# Date: 2023-08-01, 21:56:53 GMT +# PropList-16.0.0.txt +# Date: 2023-10-10, 11:51:10 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -450,6 +450,7 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 081B..0823 ; Other_Alphabetic # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A 0825..0827 ; Other_Alphabetic # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082C ; Other_Alphabetic # Mn [4] SAMARITAN VOWEL SIGN LONG I..SAMARITAN VOWEL SIGN SUKUN +0897 ; Other_Alphabetic # Mn ARABIC PEPET 08D4..08DF ; Other_Alphabetic # Mn [12] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH WORD WAQFA 08E3..08E9 ; Other_Alphabetic # Mn [7] ARABIC TURNED DAMMA BELOW..ARABIC CURLY KASRATAN 08F0..0902 ; Other_Alphabetic # Mn [19] ARABIC OPEN FATHATAN..DEVANAGARI SIGN ANUSVARA @@ -834,7 +835,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 1F150..1F169 ; Other_Alphabetic # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Other_Alphabetic # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 1425 +# Total code points: 1426 # ================================================ From 106fd959305369a6b09ba8f5a273d4e959537357 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 10 Oct 2023 20:53:32 +0200 Subject: [PATCH 09/10] Ignore conflict markers in UcdLineParser (#568) --- .../src/main/java/org/unicode/props/UcdLineParser.java | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/unicodetools/src/main/java/org/unicode/props/UcdLineParser.java b/unicodetools/src/main/java/org/unicode/props/UcdLineParser.java index 712d5e0c0..c17f3c326 100644 --- a/unicodetools/src/main/java/org/unicode/props/UcdLineParser.java +++ b/unicodetools/src/main/java/org/unicode/props/UcdLineParser.java @@ -111,6 +111,11 @@ public boolean hasNext() { return false; } line = line2 = rawLines.next(); + if (line.startsWith("<<<<<<<") + || line.startsWith("=======") + || line.startsWith(">>>>>>>")) { + line2 = ""; + } ++stats.lineCount; final int hashPos = line2.indexOf('#'); if (hashPos >= 0) { From db60be5b265a3f7407d855b339ac42b0b9ab7fca Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 11 Oct 2023 15:53:21 +0200 Subject: [PATCH 10/10] Add an invariant relating Vowel_Dependent to Alphabetic (#570) --- .../resources/org/unicode/text/UCD/UnicodeInvariantTest.txt | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt index 8cb202e68..8ee8762b3 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt @@ -530,7 +530,10 @@ Show [\u20b9] # exceptions. Should such exceptions arise, they can be added to the definition of # $nonAlphabeticBindus to avoid a failure on this test. Let $nonAlphabeticBindus = [] -[\p{InSc=Bindu} - $nonAlphabeticBindus - \p{Alphabetic}] = [] +[\p{InSc=Bindu} - \p{Alphabetic}] = $nonAlphabeticBindus + +Let $nonAlphabeticDependentVowels = [\N{ORIYA SIGN OVERLINE}\N{THAI CHARACTER MAITAIKHU}\N{LIMBU SIGN KEMPHRENG}\N{SHARADA VOWEL MODIFIER MARK}\N{SHARADA EXTRA SHORT VOWEL MARK}] +[\p{InSC=Vowel_Dependent} - \p{Alphabetic}] = $nonAlphabeticDependentVowels ########################## # LineBreak property