From 6b9f06a685732a14d5a69bbeb12743f1b103f477 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Thu, 14 Nov 2024 21:17:45 +0100 Subject: [PATCH] Chisoi (#759) * UnicodeData.txt lines from L2/22-218R3 * LineBreak.txt lines from L2/22-218R3 * Scripts.txt * new block * Danda scx * Alphabetic for the anusvara, Diacritic for the virama * Regenerate UCD * GenerateEnums * mind the gap * Regenerate UCD * InMeowC from KenW * Regenerate UCD --- unicodetools/data/ucd/dev/Blocks.txt | 1 + unicodetools/data/ucd/dev/DerivedAge.txt | 6 ++- .../data/ucd/dev/DerivedCoreProperties.txt | 49 ++++++++++++++----- unicodetools/data/ucd/dev/EastAsianWidth.txt | 7 ++- .../data/ucd/dev/IndicPositionalCategory.txt | 4 +- .../data/ucd/dev/IndicSyllabicCategory.txt | 18 ++++++- unicodetools/data/ucd/dev/LineBreak.txt | 7 ++- .../data/ucd/dev/NormalizationTest.txt | 4 +- unicodetools/data/ucd/dev/PropList.txt | 8 +-- .../data/ucd/dev/PropertyValueAliases.txt | 4 +- .../data/ucd/dev/ScriptExtensions.txt | 6 +-- unicodetools/data/ucd/dev/Scripts.txt | 12 ++++- unicodetools/data/ucd/dev/UnicodeData.txt | 40 +++++++++++++++ .../data/ucd/dev/VerticalOrientation.txt | 7 ++- .../dev/auxiliary/GraphemeBreakProperty.txt | 6 ++- .../dev/auxiliary/SentenceBreakProperty.txt | 13 +++-- .../ucd/dev/auxiliary/WordBreakProperty.txt | 13 +++-- .../ucd/dev/extracted/DerivedBidiClass.txt | 13 +++-- .../dev/extracted/DerivedCombiningClass.txt | 13 +++-- .../dev/extracted/DerivedEastAsianWidth.txt | 9 +++- .../dev/extracted/DerivedGeneralCategory.txt | 19 ++++--- .../ucd/dev/extracted/DerivedJoiningType.txt | 6 ++- .../ucd/dev/extracted/DerivedLineBreak.txt | 17 ++++--- .../data/ucd/dev/extracted/DerivedName.txt | 44 ++++++++++++++++- .../ucd/dev/extracted/DerivedNumericType.txt | 7 +-- .../dev/extracted/DerivedNumericValues.txt | 34 ++++++++----- .../org/unicode/props/UcdPropertyValues.java | 2 + .../org/unicode/text/UCD/ShortBlockNames.txt | 1 + 28 files changed, 292 insertions(+), 78 deletions(-) diff --git a/unicodetools/data/ucd/dev/Blocks.txt b/unicodetools/data/ucd/dev/Blocks.txt index 13a98f8d0..99383f375 100644 --- a/unicodetools/data/ucd/dev/Blocks.txt +++ b/unicodetools/data/ucd/dev/Blocks.txt @@ -305,6 +305,7 @@ FFF0..FFFF; Specials 16AD0..16AFF; Bassa Vah 16B00..16B8F; Pahawh Hmong 16D40..16D7F; Kirat Rai +16D80..16DAF; Chisoi 16E40..16E9F; Medefaidrin 16F00..16F9F; Miao 16FE0..16FFF; Ideographic Symbols and Punctuation diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index 6eba838ff..d0731ac36 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-17.0.0.txt -# Date: 2024-11-14, 18:37:36 GMT +# Date: 2024-11-14, 19:48:01 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2085,7 +2085,9 @@ FDC8..FDCE ; 17.0 # [7] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIG 10ED0..10ED8 ; 17.0 # [9] ARABIC BIBLICAL END OF VERSE..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10EFA..10EFB ; 17.0 # [2] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW NOON 11B60..11B67 ; 17.0 # [8] SHARADA VOWEL SIGN OE..SHARADA VOWEL SIGN CANDRA O +16D80..16D9D ; 17.0 # [30] CHISOI LETTER A..CHISOI SIGN SISO +16DA0..16DA9 ; 17.0 # [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE -# Total code points: 115 +# Total code points: 155 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index c46405c3a..e901a471d 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-17.0.0.txt -# Date: 2024-11-14, 18:38:00 GMT +# Date: 2024-11-14, 19:48:24 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 @@ -1317,6 +1317,9 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 16D40..16D42 ; Alphabetic # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA 16D43..16D6A ; Alphabetic # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU 16D6B..16D6C ; Alphabetic # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D80..16D97 ; Alphabetic # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D98 ; Alphabetic # Mn CHISOI SIGN ANUSVARA +16D99..16D9C ; Alphabetic # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA 16E40..16E7F ; Alphabetic # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16F00..16F4A ; Alphabetic # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F4F ; Alphabetic # Mn MIAO SIGN CONSONANT MODIFIER BAR @@ -1448,7 +1451,7 @@ 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: 142810 +# Total code points: 142839 # ================================================ @@ -3471,6 +3474,8 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 16B40..16B43 ; Case_Ignorable # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM 16D40..16D42 ; Case_Ignorable # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA 16D6B..16D6C ; Case_Ignorable # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D98 ; Case_Ignorable # Mn CHISOI SIGN ANUSVARA +16D9D ; Case_Ignorable # Mn CHISOI SIGN SISO 16F4F ; Case_Ignorable # Mn MIAO SIGN CONSONANT MODIFIER BAR 16F8F..16F92 ; Case_Ignorable # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16F93..16F9F ; Case_Ignorable # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 @@ -3518,7 +3523,7 @@ 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: 2787 +# Total code points: 2789 # ================================================ @@ -6870,6 +6875,8 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 16D40..16D42 ; ID_Start # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA 16D43..16D6A ; ID_Start # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU 16D6B..16D6C ; ID_Start # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D80..16D97 ; ID_Start # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D99..16D9C ; ID_Start # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA 16E40..16E7F ; ID_Start # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16F00..16F4A ; ID_Start # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F50 ; ID_Start # Lo MIAO LETTER NASALIZATION @@ -6986,7 +6993,7 @@ 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: 141310 +# Total code points: 141338 # ================================================ @@ -8243,6 +8250,11 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 16D43..16D6A ; ID_Continue # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU 16D6B..16D6C ; ID_Continue # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16D70..16D79 ; ID_Continue # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16D80..16D97 ; ID_Continue # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D98 ; ID_Continue # Mn CHISOI SIGN ANUSVARA +16D99..16D9C ; ID_Continue # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA +16D9D ; ID_Continue # Mn CHISOI SIGN SISO +16DA0..16DA9 ; ID_Continue # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 16E40..16E7F ; ID_Continue # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16F00..16F4A ; ID_Continue # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F4F ; ID_Continue # Mn MIAO SIGN CONSONANT MODIFIER BAR @@ -8402,7 +8414,7 @@ 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: 144621 +# Total code points: 144661 # ================================================ @@ -9065,6 +9077,8 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 16D40..16D42 ; XID_Start # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA 16D43..16D6A ; XID_Start # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU 16D6B..16D6C ; XID_Start # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D80..16D97 ; XID_Start # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D99..16D9C ; XID_Start # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA 16E40..16E7F ; XID_Start # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16F00..16F4A ; XID_Start # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F50 ; XID_Start # Lo MIAO LETTER NASALIZATION @@ -9181,7 +9195,7 @@ 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: 141287 +# Total code points: 141315 # ================================================ @@ -10439,6 +10453,11 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 16D43..16D6A ; XID_Continue # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU 16D6B..16D6C ; XID_Continue # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16D70..16D79 ; XID_Continue # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16D80..16D97 ; XID_Continue # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D98 ; XID_Continue # Mn CHISOI SIGN ANUSVARA +16D99..16D9C ; XID_Continue # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA +16D9D ; XID_Continue # Mn CHISOI SIGN SISO +16DA0..16DA9 ; XID_Continue # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 16E40..16E7F ; XID_Continue # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16F00..16F4A ; XID_Continue # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F4F ; XID_Continue # Mn MIAO SIGN CONSONANT MODIFIER BAR @@ -10598,7 +10617,7 @@ 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: 144602 +# Total code points: 144642 # ================================================ @@ -11038,6 +11057,8 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 1612D..1612F ; Grapheme_Extend # Mn [3] GURUNG KHEMA SIGN ANUSVARA..GURUNG KHEMA SIGN THOLHOMA 16AF0..16AF4 ; Grapheme_Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Grapheme_Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16D98 ; Grapheme_Extend # Mn CHISOI SIGN ANUSVARA +16D9D ; Grapheme_Extend # Mn CHISOI SIGN SISO 16F4F ; Grapheme_Extend # Mn MIAO SIGN CONSONANT MODIFIER BAR 16F8F..16F92 ; Grapheme_Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16FE4 ; Grapheme_Extend # Mn KHITAN SMALL SCRIPT FILLER @@ -11074,7 +11095,7 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. E0020..E007F ; Grapheme_Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2229 +# Total code points: 2231 # ================================================ @@ -12649,6 +12670,9 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 16D6B..16D6C ; Grapheme_Base # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16D6D..16D6F ; Grapheme_Base # Po [3] KIRAT RAI SIGN YUPI..KIRAT RAI DOUBLE DANDA 16D70..16D79 ; Grapheme_Base # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16D80..16D97 ; Grapheme_Base # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D99..16D9C ; Grapheme_Base # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA +16DA0..16DA9 ; Grapheme_Base # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 16E40..16E7F ; Grapheme_Base # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; Grapheme_Base # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E97..16E9A ; Grapheme_Base # Po [4] MEDEFAIDRIN COMMA..MEDEFAIDRIN EXCLAMATION OH @@ -12864,7 +12888,7 @@ 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: 152809 +# Total code points: 152847 # ================================================ @@ -12936,8 +12960,9 @@ ABED ; Grapheme_Link # Mn MEETEI MAYEK APUN IYEK 11F41 ; Grapheme_Link # Mc KAWI SIGN KILLER 11F42 ; Grapheme_Link # Mn KAWI CONJOINER 1612F ; Grapheme_Link # Mn GURUNG KHEMA SIGN THOLHOMA +16D9D ; Grapheme_Link # Mn CHISOI SIGN SISO -# Total code points: 69 +# Total code points: 70 # ================================================ @@ -13377,6 +13402,8 @@ FF9E..FF9F ; InCB; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HA 1612D..1612F ; InCB; Extend # Mn [3] GURUNG KHEMA SIGN ANUSVARA..GURUNG KHEMA SIGN THOLHOMA 16AF0..16AF4 ; InCB; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; InCB; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16D98 ; InCB; Extend # Mn CHISOI SIGN ANUSVARA +16D9D ; InCB; Extend # Mn CHISOI SIGN SISO 16F4F ; InCB; Extend # Mn MIAO SIGN CONSONANT MODIFIER BAR 16F8F..16F92 ; InCB; Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16FE4 ; InCB; Extend # Mn KHITAN SMALL SCRIPT FILLER @@ -13414,6 +13441,6 @@ FF9E..FF9F ; InCB; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HA E0020..E007F ; InCB; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; InCB; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2228 +# Total code points: 2230 # EOF diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index d3582c914..034acfc2c 100644 --- a/unicodetools/data/ucd/dev/EastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/EastAsianWidth.txt @@ -1,5 +1,5 @@ # EastAsianWidth-17.0.0.txt -# Date: 2024-11-14, 18:38:06 GMT +# Date: 2024-11-14, 19:48:31 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2357,6 +2357,11 @@ FFFD ; A # So REPLACEMENT CHARACTER 16D6B..16D6C ; N # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16D6D..16D6F ; N # Po [3] KIRAT RAI SIGN YUPI..KIRAT RAI DOUBLE DANDA 16D70..16D79 ; N # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16D80..16D97 ; N # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D98 ; N # Mn CHISOI SIGN ANUSVARA +16D99..16D9C ; N # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA +16D9D ; N # Mn CHISOI SIGN SISO +16DA0..16DA9 ; N # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 16E40..16E7F ; N # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; N # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E97..16E9A ; N # Po [4] MEDEFAIDRIN COMMA..MEDEFAIDRIN EXCLAMATION OH diff --git a/unicodetools/data/ucd/dev/IndicPositionalCategory.txt b/unicodetools/data/ucd/dev/IndicPositionalCategory.txt index b71569272..876f0114c 100644 --- a/unicodetools/data/ucd/dev/IndicPositionalCategory.txt +++ b/unicodetools/data/ucd/dev/IndicPositionalCategory.txt @@ -1,5 +1,5 @@ # IndicPositionalCategory-17.0.0.txt -# Date: 2024-11-14, 18:38:07 GMT +# Date: 2024-11-14, 19:48:32 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -619,6 +619,7 @@ ABE5 ; Top # Mn MEETEI MAYEK VOWEL SIGN ANAP 11F5A ; Top # Mn KAWI SIGN NUKTA 1611E..16129 ; Top # Mn [12] GURUNG KHEMA VOWEL SIGN AA..GURUNG KHEMA VOWEL LENGTH MARK 1612D ; Top # Mn GURUNG KHEMA SIGN ANUSVARA +16D98 ; Top # Mn CHISOI SIGN ANUSVARA # Indic_Positional_Category=Bottom @@ -774,6 +775,7 @@ ABED ; Bottom # Mn MEETEI MAYEK APUN IYEK 11EF4 ; Bottom # Mn MAKASAR VOWEL SIGN U 11F38..11F3A ; Bottom # Mn [3] KAWI VOWEL SIGN U..KAWI VOWEL SIGN VOCALIC R 1612E..1612F ; Bottom # Mn [2] GURUNG KHEMA CONSONANT SIGN MEDIAL RA..GURUNG KHEMA SIGN THOLHOMA +16D9D ; Bottom # Mn CHISOI SIGN SISO # Indic_Positional_Category=Top_And_Bottom diff --git a/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt b/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt index 6c068793d..ad5958461 100644 --- a/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt +++ b/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt @@ -1,5 +1,5 @@ # IndicSyllabicCategory-17.0.0.txt -# Date: 2024-11-14, 18:38:07 GMT +# Date: 2024-11-14, 19:48:32 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -140,6 +140,7 @@ A980..A981 ; Bindu # Mn [2] JAVANESE SIGN PANYANGGA..JAVANESE SIGN CECAK 11F00..11F01 ; Bindu # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA 1612D ; Bindu # Mn GURUNG KHEMA SIGN ANUSVARA 16D40..16D41 ; Bindu # Lm [2] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN TONPI +16D98 ; Bindu # Mn CHISOI SIGN ANUSVARA # ================================================ @@ -338,6 +339,7 @@ ABED ; Pure_Killer # Mn MEETEI MAYEK APUN IYEK 11F41 ; Pure_Killer # Mc KAWI SIGN KILLER 1612F ; Pure_Killer # Mn GURUNG KHEMA SIGN THOLHOMA 16D6B..16D6C ; Pure_Killer # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D9D ; Pure_Killer # Mn CHISOI SIGN SISO # ================================================ @@ -773,6 +775,12 @@ A866 ; Vowel # Lo PHAGS-PA LETTER EE A922..A925 ; Vowel # Lo [4] KAYAH LI LETTER A..KAYAH LI LETTER OO A926..A92A ; Vowel # Mn [5] KAYAH LI VOWEL UE..KAYAH LI VOWEL O 11150..11154 ; Vowel # Lo [5] MAHAJANI LETTER A..MAHAJANI LETTER O +16D80 ; Vowel # Lo CHISOI LETTER A +16D82..16D83 ; Vowel # Lo [2] CHISOI LETTER AI..CHISOI LETTER AA +16D86 ; Vowel # Lo CHISOI LETTER E +16D89 ; Vowel # Lo CHISOI LETTER I +16D8F ; Vowel # Lo CHISOI LETTER U +16D92 ; Vowel # Lo CHISOI LETTER O # ================================================ @@ -972,6 +980,13 @@ ABD2..ABDA ; Consonant # Lo [9] MEETEI MAYEK LETTER GOK..MEETEI MAYEK LETTE 11F12..11F33 ; Consonant # Lo [34] KAWI LETTER KA..KAWI LETTER JNYA 16101..1611D ; Consonant # Lo [29] GURUNG KHEMA LETTER KA..GURUNG KHEMA LETTER SA 16D43..16D62 ; Consonant # Lo [32] KIRAT RAI LETTER A..KIRAT RAI LETTER HA +16D81 ; Consonant # Lo CHISOI LETTER BA +16D84..16D85 ; Consonant # Lo [2] CHISOI LETTER GA..CHISOI LETTER TA +16D87..16D88 ; Consonant # Lo [2] CHISOI LETTER SA..CHISOI LETTER NA +16D8A..16D8E ; Consonant # Lo [5] CHISOI LETTER KA..CHISOI LETTER RRA +16D90..16D91 ; Consonant # Lo [2] CHISOI LETTER DA..CHISOI LETTER LA +16D93..16D97 ; Consonant # Lo [5] CHISOI LETTER NYA..CHISOI LETTER PA +16D99..16D9C ; Consonant # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA # ================================================ @@ -1386,6 +1401,7 @@ ABF0..ABF9 ; Number # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NI 11F50..11F59 ; Number # Nd [10] KAWI DIGIT ZERO..KAWI DIGIT NINE 16130..16139 ; Number # Nd [10] GURUNG KHEMA DIGIT ZERO..GURUNG KHEMA DIGIT NINE 16D70..16D79 ; Number # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16DA0..16DA9 ; Number # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE # ================================================ diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 6cedc4b29..75368d39d 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,5 @@ # LineBreak-17.0.0.txt -# Date: 2024-11-14, 18:38:07 GMT +# Date: 2024-11-14, 19:48:32 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -3267,6 +3267,11 @@ FFFD ; AI # So REPLACEMENT CHARACTER 16D6D ; AL # Po KIRAT RAI SIGN YUPI 16D6E..16D6F ; BA # Po [2] KIRAT RAI DANDA..KIRAT RAI DOUBLE DANDA 16D70..16D79 ; NU # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16D80..16D97 ; AL # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D98 ; CM # Mn CHISOI SIGN ANUSVARA +16D99..16D9C ; AL # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA +16D9D ; CM # Mn CHISOI SIGN SISO +16DA0..16DA9 ; NU # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 16E40..16E7F ; AL # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; AL # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E97..16E98 ; BA # Po [2] MEDEFAIDRIN COMMA..MEDEFAIDRIN FULL STOP diff --git a/unicodetools/data/ucd/dev/NormalizationTest.txt b/unicodetools/data/ucd/dev/NormalizationTest.txt index c5e7583c7..d509d5415 100644 --- a/unicodetools/data/ucd/dev/NormalizationTest.txt +++ b/unicodetools/data/ucd/dev/NormalizationTest.txt @@ -1,5 +1,5 @@ # NormalizationTest-17.0.0.txt -# Date: 2024-11-14, 16:08:28 GMT +# Date: 2024-11-14, 19:48:38 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -18891,6 +18891,8 @@ FFEE;FFEE;FFEE;25CB;25CB; # (￮; ￮; ￮; ○; ○; ) HALFWIDTH WHITE CIRCLE 0061 16B35 0315 0300 05AE 0062;0061 05AE 16B35 0300 0315 0062;0061 05AE 16B35 0300 0315 0062;0061 05AE 16B35 0300 0315 0062;0061 05AE 16B35 0300 0315 0062; # (a◌𖬵◌̕◌̀◌֮b; a◌֮◌𖬵◌̀◌̕b; a◌֮◌𖬵◌̀◌̕b; a◌֮◌𖬵◌̀◌̕b; a◌֮◌𖬵◌̀◌̕b; ) LATIN SMALL LETTER A, PAHAWH HMONG MARK CIM HOM, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B 0061 0315 0300 05AE 16B36 0062;00E0 05AE 16B36 0315 0062;0061 05AE 0300 16B36 0315 0062;00E0 05AE 16B36 0315 0062;0061 05AE 0300 16B36 0315 0062; # (a◌̕◌̀◌֮◌𖬶b; à◌֮◌𖬶◌̕b; a◌֮◌̀◌𖬶◌̕b; à◌֮◌𖬶◌̕b; a◌֮◌̀◌𖬶◌̕b; ) LATIN SMALL LETTER A, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, PAHAWH HMONG MARK CIM TAUM, LATIN SMALL LETTER B 0061 16B36 0315 0300 05AE 0062;0061 05AE 16B36 0300 0315 0062;0061 05AE 16B36 0300 0315 0062;0061 05AE 16B36 0300 0315 0062;0061 05AE 16B36 0300 0315 0062; # (a◌𖬶◌̕◌̀◌֮b; a◌֮◌𖬶◌̀◌̕b; a◌֮◌𖬶◌̀◌̕b; a◌֮◌𖬶◌̀◌̕b; a◌֮◌𖬶◌̀◌̕b; ) LATIN SMALL LETTER A, PAHAWH HMONG MARK CIM TAUM, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B +0061 05B0 094D 3099 16D9D 0062;0061 3099 094D 16D9D 05B0 0062;0061 3099 094D 16D9D 05B0 0062;0061 3099 094D 16D9D 05B0 0062;0061 3099 094D 16D9D 05B0 0062; # (a◌ְ◌्◌゙◌𖶝b; a◌゙◌्◌𖶝◌ְb; a◌゙◌्◌𖶝◌ְb; a◌゙◌्◌𖶝◌ְb; a◌゙◌्◌𖶝◌ְb; ) LATIN SMALL LETTER A, HEBREW POINT SHEVA, DEVANAGARI SIGN VIRAMA, COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK, CHISOI SIGN SISO, LATIN SMALL LETTER B +0061 16D9D 05B0 094D 3099 0062;0061 3099 16D9D 094D 05B0 0062;0061 3099 16D9D 094D 05B0 0062;0061 3099 16D9D 094D 05B0 0062;0061 3099 16D9D 094D 05B0 0062; # (a◌𖶝◌ְ◌्◌゙b; a◌゙◌𖶝◌्◌ְb; a◌゙◌𖶝◌्◌ְb; a◌゙◌𖶝◌्◌ְb; a◌゙◌𖶝◌्◌ְb; ) LATIN SMALL LETTER A, CHISOI SIGN SISO, HEBREW POINT SHEVA, DEVANAGARI SIGN VIRAMA, COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK, LATIN SMALL LETTER B 0061 093C 16FF0 0334 16FF0 0062;0061 0334 16FF0 16FF0 093C 0062;0061 0334 16FF0 16FF0 093C 0062;0061 0334 16FF0 16FF0 093C 0062;0061 0334 16FF0 16FF0 093C 0062; # (a◌𖿰़◌̴𖿰b; a◌̴𖿰𖿰◌़b; a◌̴𖿰𖿰◌़b; a◌̴𖿰𖿰◌़b; a◌̴𖿰𖿰◌़b; ) LATIN SMALL LETTER A, DEVANAGARI SIGN NUKTA, VIETNAMESE ALTERNATE READING MARK CA, COMBINING TILDE OVERLAY, VIETNAMESE ALTERNATE READING MARK CA, LATIN SMALL LETTER B 0061 16FF0 093C 16FF0 0334 0062;0061 0334 16FF0 16FF0 093C 0062;0061 0334 16FF0 16FF0 093C 0062;0061 0334 16FF0 16FF0 093C 0062;0061 0334 16FF0 16FF0 093C 0062; # (a𖿰◌𖿰़◌̴b; a◌̴𖿰𖿰◌़b; a◌̴𖿰𖿰◌़b; a◌̴𖿰𖿰◌़b; a◌̴𖿰𖿰◌़b; ) LATIN SMALL LETTER A, VIETNAMESE ALTERNATE READING MARK CA, DEVANAGARI SIGN NUKTA, VIETNAMESE ALTERNATE READING MARK CA, COMBINING TILDE OVERLAY, LATIN SMALL LETTER B 0061 093C 16FF0 0334 16FF1 0062;0061 0334 16FF0 16FF1 093C 0062;0061 0334 16FF0 16FF1 093C 0062;0061 0334 16FF0 16FF1 093C 0062;0061 0334 16FF0 16FF1 093C 0062; # (a◌𖿰़◌̴𖿱b; a◌̴𖿰𖿱◌़b; a◌̴𖿰𖿱◌़b; a◌̴𖿰𖿱◌़b; a◌̴𖿰𖿱◌़b; ) LATIN SMALL LETTER A, DEVANAGARI SIGN NUKTA, VIETNAMESE ALTERNATE READING MARK CA, COMBINING TILDE OVERLAY, VIETNAMESE ALTERNATE READING MARK NHAY, LATIN SMALL LETTER B diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt index d41c02c99..ac90e4739 100644 --- a/unicodetools/data/ucd/dev/PropList.txt +++ b/unicodetools/data/ucd/dev/PropList.txt @@ -1,5 +1,5 @@ # PropList-17.0.0.txt -# Date: 2024-11-14, 18:38:19 GMT +# Date: 2024-11-14, 19:48:43 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -848,6 +848,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 1611E..16129 ; Other_Alphabetic # Mn [12] GURUNG KHEMA VOWEL SIGN AA..GURUNG KHEMA VOWEL LENGTH MARK 1612A..1612C ; Other_Alphabetic # Mc [3] GURUNG KHEMA CONSONANT SIGN MEDIAL YA..GURUNG KHEMA CONSONANT SIGN MEDIAL HA 1612D..1612E ; Other_Alphabetic # Mn [2] GURUNG KHEMA SIGN ANUSVARA..GURUNG KHEMA CONSONANT SIGN MEDIAL RA +16D98 ; Other_Alphabetic # Mn CHISOI SIGN ANUSVARA 16F4F ; Other_Alphabetic # Mn MIAO SIGN CONSONANT MODIFIER BAR 16F51..16F87 ; Other_Alphabetic # Mc [55] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN UI 16F8F..16F92 ; Other_Alphabetic # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW @@ -864,7 +865,7 @@ 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: 1505 +# Total code points: 1506 # ================================================ @@ -1138,6 +1139,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON 16AF0..16AF4 ; Diacritic # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Diacritic # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16D6B..16D6C ; Diacritic # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D9D ; Diacritic # Mn CHISOI SIGN SISO 16F8F..16F92 ; Diacritic # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16F93..16F9F ; Diacritic # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 16FF0..16FF1 ; Diacritic # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY @@ -1160,7 +1162,7 @@ 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: 1209 +# Total code points: 1210 # ================================================ diff --git a/unicodetools/data/ucd/dev/PropertyValueAliases.txt b/unicodetools/data/ucd/dev/PropertyValueAliases.txt index aee447d3e..5624118c0 100644 --- a/unicodetools/data/ucd/dev/PropertyValueAliases.txt +++ b/unicodetools/data/ucd/dev/PropertyValueAliases.txt @@ -1,5 +1,5 @@ # PropertyValueAliases-17.0.0.txt -# Date: 2024-11-14, 18:38:21 GMT +# Date: 2024-11-14, 19:48:45 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -197,6 +197,7 @@ blk; Cham ; Cham blk; Cherokee ; Cherokee blk; Cherokee_Sup ; Cherokee_Supplement blk; Chess_Symbols ; Chess_Symbols +blk; Chisoi ; Chisoi blk; Chorasmian ; Chorasmian blk; CJK ; CJK_Unified_Ideographs blk; CJK_Compat ; CJK_Compatibility @@ -1334,6 +1335,7 @@ sc ; Cans ; Canadian_Aboriginal sc ; Cari ; Carian sc ; Cham ; Cham sc ; Cher ; Cherokee +sc ; Chis ; Chisoi sc ; Chrs ; Chorasmian sc ; Copt ; Coptic ; Qaac sc ; Cpmn ; Cypro_Minoan diff --git a/unicodetools/data/ucd/dev/ScriptExtensions.txt b/unicodetools/data/ucd/dev/ScriptExtensions.txt index 27e16cbe4..f63e2cd5f 100644 --- a/unicodetools/data/ucd/dev/ScriptExtensions.txt +++ b/unicodetools/data/ucd/dev/ScriptExtensions.txt @@ -1,5 +1,5 @@ # ScriptExtensions-17.0.0.txt -# Date: 2024-10-16, 17:28:17 GMT +# Date: 2024-11-14, 19:49:02 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 @@ -81,8 +81,8 @@ 06D4 ; Arab Rohg # Po ARABIC FULL STOP 0951 ; Beng Deva Gran Gujr Guru Knda Latn Mlym Orya Shrd Taml Telu Tirh #Mn DEVANAGARI STRESS SIGN UDATTA 0952 ; Beng Deva Gran Gujr Guru Knda Latn Mlym Orya Taml Telu Tirh #Mn DEVANAGARI STRESS SIGN ANUDATTA -0964 ; Beng Deva Dogr Gong Gonm Gran Gujr Guru Knda Mahj Mlym Nand Onao Orya Sind Sinh Sylo Takr Taml Telu Tirh #Po DEVANAGARI DANDA -0965 ; Beng Deva Dogr Gong Gonm Gran Gujr Gukh Guru Knda Limb Mahj Mlym Nand Onao Orya Sind Sinh Sylo Takr Taml Telu Tirh #Po DEVANAGARI DOUBLE DANDA +0964 ; Beng Chis Deva Dogr Gong Gonm Gran Gujr Guru Knda Mahj Mlym Nand Onao Orya Sind Sinh Sylo Takr Taml Telu Tirh #Po DEVANAGARI DANDA +0965 ; Beng Chis Deva Dogr Gong Gonm Gran Gujr Gukh Guru Knda Limb Mahj Mlym Nand Onao Orya Sind Sinh Sylo Takr Taml Telu Tirh #Po DEVANAGARI DOUBLE DANDA 0966..096F ; Deva Dogr Kthi Mahj # Nd [10] DEVANAGARI DIGIT ZERO..DEVANAGARI DIGIT NINE 09E6..09EF ; Beng Cakm Sylo # Nd [10] BENGALI DIGIT ZERO..BENGALI DIGIT NINE 0A66..0A6F ; Guru Mult # Nd [10] GURMUKHI DIGIT ZERO..GURMUKHI DIGIT NINE diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 90997ecbf..8aa5b147f 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,5 +1,5 @@ # Scripts-17.0.0.txt -# Date: 2024-11-14, 18:38:37 GMT +# Date: 2024-11-14, 19:49:02 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 @@ -3137,6 +3137,16 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI # ================================================ +16D80..16D97 ; Chisoi # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D98 ; Chisoi # Mn CHISOI SIGN ANUSVARA +16D99..16D9C ; Chisoi # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA +16D9D ; Chisoi # Mn CHISOI SIGN SISO +16DA0..16DA9 ; Chisoi # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE + +# Total code points: 40 + +# ================================================ + 10940..1095C ; Sidetic # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 # Total code points: 29 diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index fcf03d716..1785a773b 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -30148,6 +30148,46 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 16D77;KIRAT RAI DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;; 16D78;KIRAT RAI DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;; 16D79;KIRAT RAI DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; +16D80;CHISOI LETTER A;Lo;0;L;;;;;N;;;;; +16D81;CHISOI LETTER BA;Lo;0;L;;;;;N;;;;; +16D82;CHISOI LETTER AI;Lo;0;L;;;;;N;;;;; +16D83;CHISOI LETTER AA;Lo;0;L;;;;;N;;;;; +16D84;CHISOI LETTER GA;Lo;0;L;;;;;N;;;;; +16D85;CHISOI LETTER TA;Lo;0;L;;;;;N;;;;; +16D86;CHISOI LETTER E;Lo;0;L;;;;;N;;;;; +16D87;CHISOI LETTER SA;Lo;0;L;;;;;N;;;;; +16D88;CHISOI LETTER NA;Lo;0;L;;;;;N;;;;; +16D89;CHISOI LETTER I;Lo;0;L;;;;;N;;;;; +16D8A;CHISOI LETTER KA;Lo;0;L;;;;;N;;;;; +16D8B;CHISOI LETTER RA;Lo;0;L;;;;;N;;;;; +16D8C;CHISOI LETTER MA;Lo;0;L;;;;;N;;;;; +16D8D;CHISOI LETTER HA;Lo;0;L;;;;;N;;;;; +16D8E;CHISOI LETTER RRA;Lo;0;L;;;;;N;;;;; +16D8F;CHISOI LETTER U;Lo;0;L;;;;;N;;;;; +16D90;CHISOI LETTER DA;Lo;0;L;;;;;N;;;;; +16D91;CHISOI LETTER LA;Lo;0;L;;;;;N;;;;; +16D92;CHISOI LETTER O;Lo;0;L;;;;;N;;;;; +16D93;CHISOI LETTER NYA;Lo;0;L;;;;;N;;;;; +16D94;CHISOI LETTER NGA;Lo;0;L;;;;;N;;;;; +16D95;CHISOI LETTER CA;Lo;0;L;;;;;N;;;;; +16D96;CHISOI LETTER JA;Lo;0;L;;;;;N;;;;; +16D97;CHISOI LETTER PA;Lo;0;L;;;;;N;;;;; +16D98;CHISOI SIGN ANUSVARA;Mn;0;NSM;;;;;N;;;;; +16D99;CHISOI LETTER YA;Lo;0;L;;;;;N;;;;; +16D9A;CHISOI LETTER DDA;Lo;0;L;;;;;N;;;;; +16D9B;CHISOI LETTER TTA;Lo;0;L;;;;;N;;;;; +16D9C;CHISOI LETTER JARAHA;Lo;0;L;;;;;N;;;;; +16D9D;CHISOI SIGN SISO;Mn;9;NSM;;;;;N;;;;; +16DA0;CHISOI DIGIT ZERO;Nd;0;L;;0;0;0;N;;;;; +16DA1;CHISOI DIGIT ONE;Nd;0;L;;1;1;1;N;;;;; +16DA2;CHISOI DIGIT TWO;Nd;0;L;;2;2;2;N;;;;; +16DA3;CHISOI DIGIT THREE;Nd;0;L;;3;3;3;N;;;;; +16DA4;CHISOI DIGIT FOUR;Nd;0;L;;4;4;4;N;;;;; +16DA5;CHISOI DIGIT FIVE;Nd;0;L;;5;5;5;N;;;;; +16DA6;CHISOI DIGIT SIX;Nd;0;L;;6;6;6;N;;;;; +16DA7;CHISOI DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;; +16DA8;CHISOI DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;; +16DA9;CHISOI DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; 16E40;MEDEFAIDRIN CAPITAL LETTER M;Lu;0;L;;;;;N;;;;16E60; 16E41;MEDEFAIDRIN CAPITAL LETTER S;Lu;0;L;;;;;N;;;;16E61; 16E42;MEDEFAIDRIN CAPITAL LETTER V;Lu;0;L;;;;;N;;;;16E62; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index cc5f22a4e..f7589f767 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ # VerticalOrientation-17.0.0.txt -# Date: 2024-11-14, 18:38:40 GMT +# Date: 2024-11-14, 19:49:05 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 @@ -2185,6 +2185,11 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 16D6B..16D6C ; R # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16D6D..16D6F ; R # Po [3] KIRAT RAI SIGN YUPI..KIRAT RAI DOUBLE DANDA 16D70..16D79 ; R # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16D80..16D97 ; R # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D98 ; R # Mn CHISOI SIGN ANUSVARA +16D99..16D9C ; R # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA +16D9D ; R # Mn CHISOI SIGN SISO +16DA0..16DA9 ; R # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 16E40..16E7F ; R # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; R # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E97..16E9A ; R # Po [4] MEDEFAIDRIN COMMA..MEDEFAIDRIN EXCLAMATION OH diff --git a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt index 38d8320b2..48351bad9 100644 --- a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt @@ -1,5 +1,5 @@ # GraphemeBreakProperty-17.0.0.txt -# Date: 2024-11-14, 18:38:07 GMT +# Date: 2024-11-14, 19:48:31 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -462,6 +462,8 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1612D..1612F ; Extend # Mn [3] GURUNG KHEMA SIGN ANUSVARA..GURUNG KHEMA SIGN THOLHOMA 16AF0..16AF4 ; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16D98 ; Extend # Mn CHISOI SIGN ANUSVARA +16D9D ; Extend # Mn CHISOI SIGN SISO 16F4F ; Extend # Mn MIAO SIGN CONSONANT MODIFIER BAR 16F8F..16F92 ; Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16FE4 ; Extend # Mn KHITAN SMALL SCRIPT FILLER @@ -499,7 +501,7 @@ 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: 2234 +# Total code points: 2236 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index ea5954271..848e6705c 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ # SentenceBreakProperty-17.0.0.txt -# Date: 2024-11-14, 18:38:38 GMT +# Date: 2024-11-14, 19:49:03 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 @@ -556,6 +556,8 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1612D..1612F ; Extend # Mn [3] GURUNG KHEMA SIGN ANUSVARA..GURUNG KHEMA SIGN THOLHOMA 16AF0..16AF4 ; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16D98 ; Extend # Mn CHISOI SIGN ANUSVARA +16D9D ; Extend # Mn CHISOI SIGN SISO 16F4F ; Extend # Mn MIAO SIGN CONSONANT MODIFIER BAR 16F51..16F87 ; Extend # Mc [55] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN UI 16F8F..16F92 ; Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW @@ -593,7 +595,7 @@ 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: 2640 +# Total code points: 2642 # ================================================ @@ -2520,6 +2522,8 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 16D40..16D42 ; OLetter # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA 16D43..16D6A ; OLetter # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU 16D6B..16D6C ; OLetter # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D80..16D97 ; OLetter # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D99..16D9C ; OLetter # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA 16F00..16F4A ; OLetter # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F50 ; OLetter # Lo MIAO LETTER NASALIZATION 16F93..16F9F ; OLetter # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 @@ -2600,7 +2604,7 @@ 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: 136945 +# Total code points: 136973 # ================================================ @@ -2675,6 +2679,7 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 16AC0..16AC9 ; Numeric # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16B50..16B59 ; Numeric # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 16D70..16D79 ; Numeric # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16DA0..16DA9 ; Numeric # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 1CCF0..1CCF9 ; Numeric # Nd [10] OUTLINED DIGIT ZERO..OUTLINED DIGIT NINE 1D7CE..1D7FF ; Numeric # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E140..1E149 ; Numeric # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE @@ -2684,7 +2689,7 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Numeric # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 775 +# Total code points: 785 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index df639a405..b42092680 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-17.0.0.txt -# Date: 2024-11-14, 18:38:40 GMT +# Date: 2024-11-14, 19:49:05 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 @@ -592,6 +592,8 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1612D..1612F ; Extend # Mn [3] GURUNG KHEMA SIGN ANUSVARA..GURUNG KHEMA SIGN THOLHOMA 16AF0..16AF4 ; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16D98 ; Extend # Mn CHISOI SIGN ANUSVARA +16D9D ; Extend # Mn CHISOI SIGN SISO 16F4F ; Extend # Mn MIAO SIGN CONSONANT MODIFIER BAR 16F51..16F87 ; Extend # Mc [55] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN UI 16F8F..16F92 ; Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW @@ -630,7 +632,7 @@ 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: 2644 +# Total code points: 2646 # ================================================ @@ -1265,6 +1267,8 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 16D40..16D42 ; ALetter # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA 16D43..16D6A ; ALetter # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU 16D6B..16D6C ; ALetter # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D80..16D97 ; ALetter # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D99..16D9C ; ALetter # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA 16E40..16E7F ; ALetter # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16F00..16F4A ; ALetter # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F50 ; ALetter # Lo MIAO LETTER NASALIZATION @@ -1363,7 +1367,7 @@ 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: 33832 +# Total code points: 33860 # ================================================ @@ -1481,6 +1485,7 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 16AC0..16AC9 ; Numeric # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16B50..16B59 ; Numeric # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 16D70..16D79 ; Numeric # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16DA0..16DA9 ; Numeric # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 1CCF0..1CCF9 ; Numeric # Nd [10] OUTLINED DIGIT ZERO..OUTLINED DIGIT NINE 1D7CE..1D7FF ; Numeric # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E140..1E149 ; Numeric # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE @@ -1490,7 +1495,7 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Numeric # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 774 +# Total code points: 784 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index e4ed9cadf..6dee40eac 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-17.0.0.txt -# Date: 2024-11-14, 18:37:57 GMT +# Date: 2024-11-14, 19:48:22 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 @@ -1095,6 +1095,9 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 16D6B..16D6C ; L # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16D6D..16D6F ; L # Po [3] KIRAT RAI SIGN YUPI..KIRAT RAI DOUBLE DANDA 16D70..16D79 ; L # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16D80..16D97 ; L # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D99..16D9C ; L # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA +16DA0..16DA9 ; L # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 16E40..16E7F ; L # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; L # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E97..16E9A ; L # Po [4] MEDEFAIDRIN COMMA..MEDEFAIDRIN EXCLAMATION OH @@ -1216,8 +1219,8 @@ 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 815305 code points not listed here. -# Total code points: 1095478 +# The above property value applies to 815265 code points not listed here. +# Total code points: 1095476 # ================================================ @@ -2386,6 +2389,8 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 1612D..1612F ; NSM # Mn [3] GURUNG KHEMA SIGN ANUSVARA..GURUNG KHEMA SIGN THOLHOMA 16AF0..16AF4 ; NSM # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; NSM # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16D98 ; NSM # Mn CHISOI SIGN ANUSVARA +16D9D ; NSM # Mn CHISOI SIGN SISO 16F4F ; NSM # Mn MIAO SIGN CONSONANT MODIFIER BAR 16F8F..16F92 ; NSM # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16FE4 ; NSM # Mn KHITAN SMALL SCRIPT FILLER @@ -2418,7 +2423,7 @@ 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: 2064 +# Total code points: 2066 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index d9a17a78c..7ef663a65 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-17.0.0.txt -# Date: 2024-11-14, 18:37:59 GMT +# Date: 2024-11-14, 19:48:24 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 @@ -1836,6 +1836,10 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 16D6B..16D6C ; 0 # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16D6D..16D6F ; 0 # Po [3] KIRAT RAI SIGN YUPI..KIRAT RAI DOUBLE DANDA 16D70..16D79 ; 0 # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16D80..16D97 ; 0 # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D98 ; 0 # Mn CHISOI SIGN ANUSVARA +16D99..16D9C ; 0 # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA +16DA0..16DA9 ; 0 # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 16E40..16E7F ; 0 # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; 0 # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E97..16E9A ; 0 # Po [4] MEDEFAIDRIN COMMA..MEDEFAIDRIN EXCLAMATION OH @@ -2070,8 +2074,8 @@ 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 821466 code points not listed here. -# Total code points: 1113149 +# The above property value applies to 821426 code points not listed here. +# Total code points: 1113148 # ================================================ @@ -2208,8 +2212,9 @@ ABED ; 9 # Mn MEETEI MAYEK APUN IYEK 11F41 ; 9 # Mc KAWI SIGN KILLER 11F42 ; 9 # Mn KAWI CONJOINER 1612F ; 9 # Mn GURUNG KHEMA SIGN THOLHOMA +16D9D ; 9 # Mn CHISOI SIGN SISO -# Total code points: 69 +# Total code points: 70 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index 3c0cb2d75..0b91e12ca 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-17.0.0.txt -# Date: 2024-11-14, 18:38:02 GMT +# Date: 2024-11-14, 19:48:26 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 @@ -1876,6 +1876,11 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 16D6B..16D6C ; N # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16D6D..16D6F ; N # Po [3] KIRAT RAI SIGN YUPI..KIRAT RAI DOUBLE DANDA 16D70..16D79 ; N # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16D80..16D97 ; N # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D98 ; N # Mn CHISOI SIGN ANUSVARA +16D99..16D9C ; N # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA +16D9D ; N # Mn CHISOI SIGN SISO +16DA0..16DA9 ; N # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 16E40..16E7F ; N # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; N # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E97..16E9A ; N # Po [4] MEDEFAIDRIN COMMA..MEDEFAIDRIN EXCLAMATION OH @@ -2114,7 +2119,7 @@ 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 760984 code points not listed here. +# The above property value applies to 760944 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 145d3bc46..93cce79d6 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-17.0.0.txt -# Date: 2024-11-14, 18:38:02 GMT +# Date: 2024-11-14, 19:48:27 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 @@ -567,7 +567,9 @@ FFFE..FFFF ; Cn # [2] .. 16B62 ; Cn # 16B78..16B7C ; Cn # [5] .. 16B90..16D3F ; Cn # [432] .. -16D7A..16E3F ; Cn # [198] .. +16D7A..16D7F ; Cn # [6] .. +16D9E..16D9F ; Cn # [2] .. +16DAA..16E3F ; Cn # [150] .. 16E9B..16EFF ; Cn # [101] .. 16F4B..16F4E ; Cn # [4] .. 16F88..16F8E ; Cn # [7] .. @@ -742,7 +744,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819418 +# Total code points: 819378 # ================================================ @@ -2640,6 +2642,8 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 16B63..16B77 ; Lo # [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; Lo # [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ 16D43..16D6A ; Lo # [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU +16D80..16D97 ; Lo # [24] CHISOI LETTER A..CHISOI LETTER PA +16D99..16D9C ; Lo # [4] CHISOI LETTER YA..CHISOI LETTER JARAHA 16F00..16F4A ; Lo # [75] MIAO LETTER PA..MIAO LETTER RTE 16F50 ; Lo # MIAO LETTER NASALIZATION 17000..187F7 ; Lo # [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 @@ -2711,7 +2715,7 @@ 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: 136513 +# Total code points: 136541 # ================================================ @@ -3047,6 +3051,8 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 1612D..1612F ; Mn # [3] GURUNG KHEMA SIGN ANUSVARA..GURUNG KHEMA SIGN THOLHOMA 16AF0..16AF4 ; Mn # [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Mn # [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16D98 ; Mn # CHISOI SIGN ANUSVARA +16D9D ; Mn # CHISOI SIGN SISO 16F4F ; Mn # MIAO SIGN CONSONANT MODIFIER BAR 16F8F..16F92 ; Mn # [4] MIAO TONE RIGHT..MIAO TONE BELOW 16FE4 ; Mn # KHITAN SMALL SCRIPT FILLER @@ -3079,7 +3085,7 @@ 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: 2056 +# Total code points: 2058 # ================================================ @@ -3360,6 +3366,7 @@ FF10..FF19 ; Nd # [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 16AC0..16AC9 ; Nd # [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16B50..16B59 ; Nd # [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 16D70..16D79 ; Nd # [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16DA0..16DA9 ; Nd # [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 1CCF0..1CCF9 ; Nd # [10] OUTLINED DIGIT ZERO..OUTLINED DIGIT NINE 1D7CE..1D7FF ; Nd # [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E140..1E149 ; Nd # [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE @@ -3369,7 +3376,7 @@ FF10..FF19 ; Nd # [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E950..1E959 ; Nd # [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Nd # [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 760 +# Total code points: 770 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt index 9560720aa..d505d6ad3 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt @@ -1,5 +1,5 @@ # DerivedJoiningType-17.0.0.txt -# Date: 2024-11-14, 18:38:03 GMT +# Date: 2024-11-14, 19:48:28 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -550,6 +550,8 @@ FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATI 1612D..1612F ; T # Mn [3] GURUNG KHEMA SIGN ANUSVARA..GURUNG KHEMA SIGN THOLHOMA 16AF0..16AF4 ; T # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; T # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16D98 ; T # Mn CHISOI SIGN ANUSVARA +16D9D ; T # Mn CHISOI SIGN SISO 16F4F ; T # Mn MIAO SIGN CONSONANT MODIFIER BAR 16F8F..16F92 ; T # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16FE4 ; T # Mn KHITAN SMALL SCRIPT FILLER @@ -587,6 +589,6 @@ 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: 2221 +# Total code points: 2223 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 45434e051..8656e73c8 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-17.0.0.txt -# Date: 2024-11-14, 18:38:04 GMT +# Date: 2024-11-14, 19:48:28 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -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 757538 code points not listed here. -# Total code points: 895006 +# The above property value applies to 757498 code points not listed here. +# Total code points: 894966 # ================================================ @@ -548,6 +548,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 16AC0..16AC9 ; NU # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16B50..16B59 ; NU # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 16D70..16D79 ; NU # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16DA0..16DA9 ; NU # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 1CCF0..1CCF9 ; NU # Nd [10] OUTLINED DIGIT ZERO..OUTLINED DIGIT NINE 1D7CE..1D7FF ; NU # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E140..1E149 ; NU # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE @@ -557,7 +558,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 1E950..1E959 ; NU # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; NU # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 695 +# Total code points: 705 # ================================================ @@ -1442,6 +1443,8 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 16D43..16D6A ; AL # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU 16D6B..16D6C ; AL # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16D6D ; AL # Po KIRAT RAI SIGN YUPI +16D80..16D97 ; AL # Lo [24] CHISOI LETTER A..CHISOI LETTER PA +16D99..16D9C ; AL # Lo [4] CHISOI LETTER YA..CHISOI LETTER JARAHA 16E40..16E7F ; AL # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; AL # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E99..16E9A ; AL # Po [2] MEDEFAIDRIN SYMBOL AIVA..MEDEFAIDRIN EXCLAMATION OH @@ -1617,7 +1620,7 @@ 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: 26754 +# Total code points: 26782 # ================================================ @@ -2359,6 +2362,8 @@ FFF9..FFFB ; CM # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTAT 1612D..1612F ; CM # Mn [3] GURUNG KHEMA SIGN ANUSVARA..GURUNG KHEMA SIGN THOLHOMA 16AF0..16AF4 ; CM # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; CM # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16D98 ; CM # Mn CHISOI SIGN ANUSVARA +16D9D ; CM # Mn CHISOI SIGN SISO 16F4F ; CM # Mn MIAO SIGN CONSONANT MODIFIER BAR 16F51..16F87 ; CM # Mc [55] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN UI 16F8F..16F92 ; CM # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW @@ -2398,7 +2403,7 @@ 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: 2508 +# Total code points: 2510 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 006451cad..f127fc3d1 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-17.0.0.txt -# Date: 2024-11-14, 18:38:04 GMT +# Date: 2024-11-14, 19:48:28 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -36819,6 +36819,46 @@ FFFD ; REPLACEMENT CHARACTER 16D77 ; KIRAT RAI DIGIT SEVEN 16D78 ; KIRAT RAI DIGIT EIGHT 16D79 ; KIRAT RAI DIGIT NINE +16D80 ; CHISOI LETTER A +16D81 ; CHISOI LETTER BA +16D82 ; CHISOI LETTER AI +16D83 ; CHISOI LETTER AA +16D84 ; CHISOI LETTER GA +16D85 ; CHISOI LETTER TA +16D86 ; CHISOI LETTER E +16D87 ; CHISOI LETTER SA +16D88 ; CHISOI LETTER NA +16D89 ; CHISOI LETTER I +16D8A ; CHISOI LETTER KA +16D8B ; CHISOI LETTER RA +16D8C ; CHISOI LETTER MA +16D8D ; CHISOI LETTER HA +16D8E ; CHISOI LETTER RRA +16D8F ; CHISOI LETTER U +16D90 ; CHISOI LETTER DA +16D91 ; CHISOI LETTER LA +16D92 ; CHISOI LETTER O +16D93 ; CHISOI LETTER NYA +16D94 ; CHISOI LETTER NGA +16D95 ; CHISOI LETTER CA +16D96 ; CHISOI LETTER JA +16D97 ; CHISOI LETTER PA +16D98 ; CHISOI SIGN ANUSVARA +16D99 ; CHISOI LETTER YA +16D9A ; CHISOI LETTER DDA +16D9B ; CHISOI LETTER TTA +16D9C ; CHISOI LETTER JARAHA +16D9D ; CHISOI SIGN SISO +16DA0 ; CHISOI DIGIT ZERO +16DA1 ; CHISOI DIGIT ONE +16DA2 ; CHISOI DIGIT TWO +16DA3 ; CHISOI DIGIT THREE +16DA4 ; CHISOI DIGIT FOUR +16DA5 ; CHISOI DIGIT FIVE +16DA6 ; CHISOI DIGIT SIX +16DA7 ; CHISOI DIGIT SEVEN +16DA8 ; CHISOI DIGIT EIGHT +16DA9 ; CHISOI DIGIT NINE 16E40 ; MEDEFAIDRIN CAPITAL LETTER M 16E41 ; MEDEFAIDRIN CAPITAL LETTER S 16E42 ; MEDEFAIDRIN CAPITAL LETTER V @@ -45482,6 +45522,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 155113 +# Total code points: 155153 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedNumericType.txt b/unicodetools/data/ucd/dev/extracted/DerivedNumericType.txt index 8e48d0b85..720458961 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedNumericType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedNumericType.txt @@ -1,5 +1,5 @@ -# DerivedNumericType-16.0.0.txt -# Date: 2024-04-30, 21:48:20 GMT +# DerivedNumericType-17.0.0.txt +# Date: 2024-11-14, 19:48:30 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 @@ -284,6 +284,7 @@ FF10..FF19 ; Decimal # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 16AC0..16AC9 ; Decimal # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16B50..16B59 ; Decimal # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 16D70..16D79 ; Decimal # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +16DA0..16DA9 ; Decimal # Nd [10] CHISOI DIGIT ZERO..CHISOI DIGIT NINE 1CCF0..1CCF9 ; Decimal # Nd [10] OUTLINED DIGIT ZERO..OUTLINED DIGIT NINE 1D7CE..1D7FF ; Decimal # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E140..1E149 ; Decimal # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE @@ -293,6 +294,6 @@ FF10..FF19 ; Decimal # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E950..1E959 ; Decimal # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Decimal # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 760 +# Total code points: 770 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedNumericValues.txt b/unicodetools/data/ucd/dev/extracted/DerivedNumericValues.txt index ae1f99c0f..bb4d4cb05 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedNumericValues.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedNumericValues.txt @@ -1,5 +1,5 @@ -# DerivedNumericValues-16.0.0.txt -# Date: 2024-04-30, 21:48:20 GMT +# DerivedNumericValues-17.0.0.txt +# Date: 2024-11-14, 19:48:31 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -116,6 +116,7 @@ FF10 ; 0.0 ; ; 0 # Nd FULLWIDTH DIGIT ZERO 16AC0 ; 0.0 ; ; 0 # Nd TANGSA DIGIT ZERO 16B50 ; 0.0 ; ; 0 # Nd PAHAWH HMONG DIGIT ZERO 16D70 ; 0.0 ; ; 0 # Nd KIRAT RAI DIGIT ZERO +16DA0 ; 0.0 ; ; 0 # Nd CHISOI DIGIT ZERO 16E80 ; 0.0 ; ; 0 # No MEDEFAIDRIN DIGIT ZERO 1CCF0 ; 0.0 ; ; 0 # Nd OUTLINED DIGIT ZERO 1D2C0 ; 0.0 ; ; 0 # No KAKTOVIK NUMERAL ZERO @@ -134,7 +135,7 @@ FF10 ; 0.0 ; ; 0 # Nd FULLWIDTH DIGIT ZERO 1F10B..1F10C ; 0.0 ; ; 0 # No [2] DINGBAT CIRCLED SANS-SERIF DIGIT ZERO..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO 1FBF0 ; 0.0 ; ; 0 # Nd SEGMENTED DIGIT ZERO -# Total code points: 96 +# Total code points: 97 # ================================================ @@ -542,6 +543,7 @@ FF11 ; 1.0 ; ; 1 # Nd FULLWIDTH DIGIT ONE 16AC1 ; 1.0 ; ; 1 # Nd TANGSA DIGIT ONE 16B51 ; 1.0 ; ; 1 # Nd PAHAWH HMONG DIGIT ONE 16D71 ; 1.0 ; ; 1 # Nd KIRAT RAI DIGIT ONE +16DA1 ; 1.0 ; ; 1 # Nd CHISOI DIGIT ONE 16E81 ; 1.0 ; ; 1 # No MEDEFAIDRIN DIGIT ONE 16E94 ; 1.0 ; ; 1 # No MEDEFAIDRIN DIGIT ONE ALTERNATE FORM 1CCF1 ; 1.0 ; ; 1 # Nd OUTLINED DIGIT ONE @@ -569,7 +571,7 @@ FF11 ; 1.0 ; ; 1 # Nd FULLWIDTH DIGIT ONE 1FBF1 ; 1.0 ; ; 1 # Nd SEGMENTED DIGIT ONE 2092A ; 1.0 ; ; 1 # Lo CJK UNIFIED IDEOGRAPH-2092A -# Total code points: 152 +# Total code points: 153 # ================================================ @@ -704,6 +706,7 @@ FF12 ; 2.0 ; ; 2 # Nd FULLWIDTH DIGIT TWO 16AC2 ; 2.0 ; ; 2 # Nd TANGSA DIGIT TWO 16B52 ; 2.0 ; ; 2 # Nd PAHAWH HMONG DIGIT TWO 16D72 ; 2.0 ; ; 2 # Nd KIRAT RAI DIGIT TWO +16DA2 ; 2.0 ; ; 2 # Nd CHISOI DIGIT TWO 16E82 ; 2.0 ; ; 2 # No MEDEFAIDRIN DIGIT TWO 16E95 ; 2.0 ; ; 2 # No MEDEFAIDRIN DIGIT TWO ALTERNATE FORM 1CCF2 ; 2.0 ; ; 2 # Nd OUTLINED DIGIT TWO @@ -731,7 +734,7 @@ FF12 ; 2.0 ; ; 2 # Nd FULLWIDTH DIGIT TWO 1FBF2 ; 2.0 ; ; 2 # Nd SEGMENTED DIGIT TWO 22390 ; 2.0 ; ; 2 # Lo CJK UNIFIED IDEOGRAPH-22390 -# Total code points: 154 +# Total code points: 155 # ================================================ @@ -858,6 +861,7 @@ FF13 ; 3.0 ; ; 3 # Nd FULLWIDTH DIGIT THREE 16AC3 ; 3.0 ; ; 3 # Nd TANGSA DIGIT THREE 16B53 ; 3.0 ; ; 3 # Nd PAHAWH HMONG DIGIT THREE 16D73 ; 3.0 ; ; 3 # Nd KIRAT RAI DIGIT THREE +16DA3 ; 3.0 ; ; 3 # Nd CHISOI DIGIT THREE 16E83 ; 3.0 ; ; 3 # No MEDEFAIDRIN DIGIT THREE 16E96 ; 3.0 ; ; 3 # No MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 1CCF3 ; 3.0 ; ; 3 # Nd OUTLINED DIGIT THREE @@ -887,7 +891,7 @@ FF13 ; 3.0 ; ; 3 # Nd FULLWIDTH DIGIT THREE 22998 ; 3.0 ; ; 3 # Lo CJK UNIFIED IDEOGRAPH-22998 23B1B ; 3.0 ; ; 3 # Lo CJK UNIFIED IDEOGRAPH-23B1B -# Total code points: 152 +# Total code points: 153 # ================================================ @@ -1009,6 +1013,7 @@ FF14 ; 4.0 ; ; 4 # Nd FULLWIDTH DIGIT FOUR 16AC4 ; 4.0 ; ; 4 # Nd TANGSA DIGIT FOUR 16B54 ; 4.0 ; ; 4 # Nd PAHAWH HMONG DIGIT FOUR 16D74 ; 4.0 ; ; 4 # Nd KIRAT RAI DIGIT FOUR +16DA4 ; 4.0 ; ; 4 # Nd CHISOI DIGIT FOUR 16E84 ; 4.0 ; ; 4 # No MEDEFAIDRIN DIGIT FOUR 1CCF4 ; 4.0 ; ; 4 # Nd OUTLINED DIGIT FOUR 1D2C4 ; 4.0 ; ; 4 # No KAKTOVIK NUMERAL FOUR @@ -1036,7 +1041,7 @@ FF14 ; 4.0 ; ; 4 # Nd FULLWIDTH DIGIT FOUR 200E2 ; 4.0 ; ; 4 # Lo CJK UNIFIED IDEOGRAPH-200E2 2626D ; 4.0 ; ; 4 # Lo CJK UNIFIED IDEOGRAPH-2626D -# Total code points: 143 +# Total code points: 144 # ================================================ @@ -1161,6 +1166,7 @@ FF15 ; 5.0 ; ; 5 # Nd FULLWIDTH DIGIT FIVE 16AC5 ; 5.0 ; ; 5 # Nd TANGSA DIGIT FIVE 16B55 ; 5.0 ; ; 5 # Nd PAHAWH HMONG DIGIT FIVE 16D75 ; 5.0 ; ; 5 # Nd KIRAT RAI DIGIT FIVE +16DA5 ; 5.0 ; ; 5 # Nd CHISOI DIGIT FIVE 16E85 ; 5.0 ; ; 5 # No MEDEFAIDRIN DIGIT FIVE 1CCF5 ; 5.0 ; ; 5 # Nd OUTLINED DIGIT FIVE 1D2C5 ; 5.0 ; ; 5 # No KAKTOVIK NUMERAL FIVE @@ -1187,7 +1193,7 @@ FF15 ; 5.0 ; ; 5 # Nd FULLWIDTH DIGIT FIVE 1FBF5 ; 5.0 ; ; 5 # Nd SEGMENTED DIGIT FIVE 20121 ; 5.0 ; ; 5 # Lo CJK UNIFIED IDEOGRAPH-20121 -# Total code points: 141 +# Total code points: 142 # ================================================ @@ -1299,6 +1305,7 @@ FF16 ; 6.0 ; ; 6 # Nd FULLWIDTH DIGIT SIX 16AC6 ; 6.0 ; ; 6 # Nd TANGSA DIGIT SIX 16B56 ; 6.0 ; ; 6 # Nd PAHAWH HMONG DIGIT SIX 16D76 ; 6.0 ; ; 6 # Nd KIRAT RAI DIGIT SIX +16DA6 ; 6.0 ; ; 6 # Nd CHISOI DIGIT SIX 16E86 ; 6.0 ; ; 6 # No MEDEFAIDRIN DIGIT SIX 1CCF6 ; 6.0 ; ; 6 # Nd OUTLINED DIGIT SIX 1D2C6 ; 6.0 ; ; 6 # No KAKTOVIK NUMERAL SIX @@ -1323,7 +1330,7 @@ FF16 ; 6.0 ; ; 6 # Nd FULLWIDTH DIGIT SIX 1FBF6 ; 6.0 ; ; 6 # Nd SEGMENTED DIGIT SIX 20AEA ; 6.0 ; ; 6 # Lo CJK UNIFIED IDEOGRAPH-20AEA -# Total code points: 125 +# Total code points: 126 # ================================================ @@ -1433,6 +1440,7 @@ FF17 ; 7.0 ; ; 7 # Nd FULLWIDTH DIGIT SEVEN 16AC7 ; 7.0 ; ; 7 # Nd TANGSA DIGIT SEVEN 16B57 ; 7.0 ; ; 7 # Nd PAHAWH HMONG DIGIT SEVEN 16D77 ; 7.0 ; ; 7 # Nd KIRAT RAI DIGIT SEVEN +16DA7 ; 7.0 ; ; 7 # Nd CHISOI DIGIT SEVEN 16E87 ; 7.0 ; ; 7 # No MEDEFAIDRIN DIGIT SEVEN 1CCF7 ; 7.0 ; ; 7 # Nd OUTLINED DIGIT SEVEN 1D2C7 ; 7.0 ; ; 7 # No KAKTOVIK NUMERAL SEVEN @@ -1457,7 +1465,7 @@ FF17 ; 7.0 ; ; 7 # Nd FULLWIDTH DIGIT SEVEN 1FBF7 ; 7.0 ; ; 7 # Nd SEGMENTED DIGIT SEVEN 20001 ; 7.0 ; ; 7 # Lo CJK UNIFIED IDEOGRAPH-20001 -# Total code points: 125 +# Total code points: 126 # ================================================ @@ -1564,6 +1572,7 @@ FF18 ; 8.0 ; ; 8 # Nd FULLWIDTH DIGIT EIGHT 16AC8 ; 8.0 ; ; 8 # Nd TANGSA DIGIT EIGHT 16B58 ; 8.0 ; ; 8 # Nd PAHAWH HMONG DIGIT EIGHT 16D78 ; 8.0 ; ; 8 # Nd KIRAT RAI DIGIT EIGHT +16DA8 ; 8.0 ; ; 8 # Nd CHISOI DIGIT EIGHT 16E88 ; 8.0 ; ; 8 # No MEDEFAIDRIN DIGIT EIGHT 1CCF8 ; 8.0 ; ; 8 # Nd OUTLINED DIGIT EIGHT 1D2C8 ; 8.0 ; ; 8 # No KAKTOVIK NUMERAL EIGHT @@ -1587,7 +1596,7 @@ FF18 ; 8.0 ; ; 8 # Nd FULLWIDTH DIGIT EIGHT 1F109 ; 8.0 ; ; 8 # No DIGIT EIGHT COMMA 1FBF8 ; 8.0 ; ; 8 # Nd SEGMENTED DIGIT EIGHT -# Total code points: 120 +# Total code points: 121 # ================================================ @@ -1697,6 +1706,7 @@ FF19 ; 9.0 ; ; 9 # Nd FULLWIDTH DIGIT NINE 16AC9 ; 9.0 ; ; 9 # Nd TANGSA DIGIT NINE 16B59 ; 9.0 ; ; 9 # Nd PAHAWH HMONG DIGIT NINE 16D79 ; 9.0 ; ; 9 # Nd KIRAT RAI DIGIT NINE +16DA9 ; 9.0 ; ; 9 # Nd CHISOI DIGIT NINE 16E89 ; 9.0 ; ; 9 # No MEDEFAIDRIN DIGIT NINE 1CCF9 ; 9.0 ; ; 9 # Nd OUTLINED DIGIT NINE 1D2C9 ; 9.0 ; ; 9 # No KAKTOVIK NUMERAL NINE @@ -1721,7 +1731,7 @@ FF19 ; 9.0 ; ; 9 # Nd FULLWIDTH DIGIT NINE 1FBF9 ; 9.0 ; ; 9 # Nd SEGMENTED DIGIT NINE 2F890 ; 9.0 ; ; 9 # Lo CJK COMPATIBILITY IDEOGRAPH-2F890 -# Total code points: 126 +# Total code points: 127 # ================================================ diff --git a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java index 8e497e96f..2b5d727e2 100644 --- a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java +++ b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java @@ -221,6 +221,7 @@ public enum Block_Values implements Named { Cherokee("Cherokee"), Cherokee_Supplement("Cherokee_Sup"), Chess_Symbols("Chess_Symbols"), + Chisoi("Chisoi"), Chorasmian("Chorasmian"), CJK_Unified_Ideographs("CJK"), CJK_Compatibility("CJK_Compat"), @@ -1864,6 +1865,7 @@ public enum Script_Values implements Named { Carian("Cari"), Cham("Cham"), Cherokee("Cher"), + Chisoi("Chis"), Chorasmian("Chrs"), Coptic("Copt", "Qaac"), Cypro_Minoan("Cpmn"), diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt index bf082107a..4c5f819cc 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt @@ -42,6 +42,7 @@ Cham ; Cham Cherokee ; Cherokee Cherokee_Sup ; Cherokee_Supplement Chess_Symbols ; Chess_Symbols +Chisoi ; Chisoi Chorasmian ; Chorasmian CJK_Compat ; CJK_Compatibility CJK_Compat_Forms ; CJK_Compatibility_Forms