diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index 4f59a0c5e..1924ef93d 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: 2024-11-15, 15:32:19 GMT +# Date: 2024-11-15, 15:57:18 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 @@ -2041,9 +2041,7 @@ A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L 13460..143FA ; 16.0 # [3995] EGYPTIAN HIEROGLYPH-13460..EGYPTIAN HIEROGLYPH-143FA 16100..16139 ; 16.0 # [58] GURUNG KHEMA LETTER A..GURUNG KHEMA DIGIT NINE 16D40..16D79 ; 16.0 # [58] KIRAT RAI SIGN ANUSVARA..KIRAT RAI DIGIT NINE -187F8..187FF ; 16.0 # [8] TANGUT IDEOGRAPH-187F8..TANGUT IDEOGRAPH-187FF 18CFF ; 16.0 # KHITAN SMALL SCRIPT CHARACTER-18CFF -18D09..18D1C ; 16.0 # [20] TANGUT IDEOGRAPH-18D09..TANGUT IDEOGRAPH-18D1C 1CC00..1CCF9 ; 16.0 # [250] UP-POINTING GO-KART..OUTLINED DIGIT NINE 1CD00..1CEB3 ; 16.0 # [436] BLOCK OCTANT-3..BLACK RIGHT TRIANGLE CARET 1E5D0..1E5FA ; 16.0 # [43] OL ONAL LETTER O..OL ONAL DIGIT NINE @@ -2059,7 +2057,7 @@ A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L 1FAE9 ; 16.0 # FACE WITH BAGS UNDER EYES 1FBCB..1FBEF ; 16.0 # [37] WHITE CROSS MARK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 5213 +# Total code points: 5185 # ================================================ @@ -2094,8 +2092,10 @@ FDC8..FDCE ; 17.0 # [7] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIG 16EA0..16EB8 ; 17.0 # [25] BERIA ERFE CAPITAL LETTER ARKAB..BERIA ERFE CAPITAL LETTER AY 16EBB..16ED3 ; 17.0 # [25] BERIA ERFE SMALL LETTER ARKAB..BERIA ERFE SMALL LETTER AY 16FF2..16FF6 ; 17.0 # [5] CHINESE SMALL SIMPLIFIED ER..YANGQIN SIGN SLOW TWO BEATS +187F8..187FF ; 17.0 # [8] TANGUT IDEOGRAPH-187F8..TANGUT IDEOGRAPH-187FF +18D09..18D1E ; 17.0 # [22] TANGUT IDEOGRAPH-18D09..TANGUT IDEOGRAPH-18D1E 18D80..18D81 ; 17.0 # [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770 -# Total code points: 266 +# Total code points: 296 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 7f8bb3478..8ae667717 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: 2024-11-15, 15:32:46 GMT +# Date: 2024-11-15, 15:57:42 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 @@ -1338,7 +1338,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 16FF2..16FF3 ; Alphabetic # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER 16FF4..16FF6 ; Alphabetic # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS 17000..18CD5 ; Alphabetic # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5 -18CFF..18D1C ; Alphabetic # Lo [30] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1C +18CFF..18D1E ; Alphabetic # Lo [32] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1E 18D80..18D81 ; Alphabetic # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770 1AFF0..1AFF3 ; Alphabetic # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 1AFF5..1AFFB ; Alphabetic # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 @@ -1458,7 +1458,7 @@ 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: 142968 +# Total code points: 142970 # ================================================ @@ -6910,7 +6910,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 16FF2..16FF3 ; ID_Start # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER 16FF4..16FF6 ; ID_Start # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS 17000..18CD5 ; ID_Start # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5 -18CFF..18D1C ; ID_Start # Lo [30] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1C +18CFF..18D1E ; ID_Start # Lo [32] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1E 18D80..18D81 ; ID_Start # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770 1AFF0..1AFF3 ; ID_Start # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 1AFF5..1AFFB ; ID_Start # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 @@ -7019,7 +7019,7 @@ 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: 141467 +# Total code points: 141469 # ================================================ @@ -8301,7 +8301,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 16FF2..16FF3 ; ID_Continue # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER 16FF4..16FF6 ; ID_Continue # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS 17000..18CD5 ; ID_Continue # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5 -18CFF..18D1C ; ID_Continue # Lo [30] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1C +18CFF..18D1E ; ID_Continue # Lo [32] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1E 18D80..18D81 ; ID_Continue # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770 1AFF0..1AFF3 ; ID_Continue # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 1AFF5..1AFFB ; ID_Continue # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 @@ -8448,7 +8448,7 @@ 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: 144800 +# Total code points: 144802 # ================================================ @@ -9127,7 +9127,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 16FF2..16FF3 ; XID_Start # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER 16FF4..16FF6 ; XID_Start # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS 17000..18CD5 ; XID_Start # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5 -18CFF..18D1C ; XID_Start # Lo [30] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1C +18CFF..18D1E ; XID_Start # Lo [32] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1E 18D80..18D81 ; XID_Start # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770 1AFF0..1AFF3 ; XID_Start # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 1AFF5..1AFFB ; XID_Start # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 @@ -9236,7 +9236,7 @@ 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: 141444 +# Total code points: 141446 # ================================================ @@ -10519,7 +10519,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 16FF2..16FF3 ; XID_Continue # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER 16FF4..16FF6 ; XID_Continue # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS 17000..18CD5 ; XID_Continue # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5 -18CFF..18D1C ; XID_Continue # Lo [30] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1C +18CFF..18D1E ; XID_Continue # Lo [32] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1E 18D80..18D81 ; XID_Continue # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770 1AFF0..1AFF3 ; XID_Continue # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 1AFF5..1AFFB ; XID_Continue # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 @@ -10666,7 +10666,7 @@ 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: 144781 +# Total code points: 144783 # ================================================ @@ -12741,7 +12741,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 16FF2..16FF3 ; Grapheme_Base # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER 16FF4..16FF6 ; Grapheme_Base # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS 17000..18CD5 ; Grapheme_Base # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5 -18CFF..18D1C ; Grapheme_Base # Lo [30] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1C +18CFF..18D1E ; Grapheme_Base # Lo [32] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1E 18D80..18D81 ; Grapheme_Base # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770 1AFF0..1AFF3 ; Grapheme_Base # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 1AFF5..1AFFB ; Grapheme_Base # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 @@ -12945,7 +12945,7 @@ 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: 152986 +# Total code points: 152988 # ================================================ diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index 19ce796cb..c4ec8dd03 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: 2024-11-15, 15:32:54 GMT +# Date: 2024-11-15, 15:57:48 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2388,7 +2388,7 @@ FFFD ; A # So REPLACEMENT CHARACTER 18800..18AFF ; W # Lo [768] TANGUT COMPONENT-001..TANGUT COMPONENT-768 18B00..18CD5 ; W # Lo [470] KHITAN SMALL SCRIPT CHARACTER-18B00..KHITAN SMALL SCRIPT CHARACTER-18CD5 18CFF ; W # Lo KHITAN SMALL SCRIPT CHARACTER-18CFF -18D00..18D1C ; W # Lo [29] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D1C +18D00..18D1E ; W # Lo [31] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D1E 18D80..18D81 ; W # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770 1AFF0..1AFF3 ; W # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 1AFF5..1AFFB ; W # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index dac04fee7..3645e8540 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: 2024-11-15, 15:32:55 GMT +# Date: 2024-11-15, 15:57:49 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 @@ -3299,7 +3299,7 @@ FFFD ; AI # So REPLACEMENT CHARACTER 18800..18AFF ; ID # Lo [768] TANGUT COMPONENT-001..TANGUT COMPONENT-768 18B00..18CD5 ; AL # Lo [470] KHITAN SMALL SCRIPT CHARACTER-18B00..KHITAN SMALL SCRIPT CHARACTER-18CD5 18CFF ; AL # Lo KHITAN SMALL SCRIPT CHARACTER-18CFF -18D00..18D1C ; ID # Lo [29] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D1C +18D00..18D1E ; ID # Lo [31] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D1E 18D80..18D81 ; ID # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770 1AFF0..1AFF3 ; AL # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 1AFF5..1AFFB ; AL # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt index e43a9d672..a9eb0c5ab 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: 2024-11-15, 15:33:06 GMT +# Date: 2024-11-15, 15:58:01 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 @@ -881,7 +881,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM 16FF2..16FF3 ; Ideographic # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER 16FF4..16FF6 ; Ideographic # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS 17000..18CD5 ; Ideographic # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5 -18CFF..18D1C ; Ideographic # Lo [30] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1C +18CFF..18D1E ; Ideographic # Lo [32] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1E 18D80..18D81 ; Ideographic # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770 1B170..1B2FB ; Ideographic # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 20000..2A6DF ; Ideographic # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF @@ -894,7 +894,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM 30000..3134A ; Ideographic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Ideographic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 106512 +# Total code points: 106514 # ================================================ diff --git a/unicodetools/data/ucd/dev/PropertyValueAliases.txt b/unicodetools/data/ucd/dev/PropertyValueAliases.txt index 1b2611436..03d7a8b30 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: 2024-11-15, 15:33:08 GMT +# Date: 2024-11-15, 15:58:03 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 diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 3c8922f9d..0b3d28238 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: 2024-11-15, 15:33:26 GMT +# Date: 2024-11-15, 15:58:19 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 @@ -2769,10 +2769,10 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI 16FE0 ; Tangut # Lm TANGUT ITERATION MARK 17000..18AFF ; Tangut # Lo [6912] TANGUT IDEOGRAPH-17000..TANGUT COMPONENT-768 -18D00..18D1C ; Tangut # Lo [29] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D1C +18D00..18D1E ; Tangut # Lo [31] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D1E 18D80..18D81 ; Tangut # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770 -# Total code points: 6944 +# Total code points: 6946 # ================================================ diff --git a/unicodetools/data/ucd/dev/TangutSources.txt b/unicodetools/data/ucd/dev/TangutSources.txt index ad9bc8c48..401b8d8bc 100644 --- a/unicodetools/data/ucd/dev/TangutSources.txt +++ b/unicodetools/data/ucd/dev/TangutSources.txt @@ -34,7 +34,9 @@ # # The following abbreviations are used in kTGT_MergedSrc: # -# H2004 = Hán Xiǎománg (韓小忙), 西夏文正字研究 (Xīxiàwén Zhèngzì Yánjiū) +# H2021 = Hán Xiǎománg (韩小忙), 西夏文词典: 世俗文献部分 (Xīxiàwén Cídiǎn: Shìsú Wénxiàn Bùfēn) +# [Tangut Word Dictionary: Secular Literature Part, 9 vols.]. 2021. +# H2004 = Hán Xiǎománg (韩小忙), 西夏文正字研究 (Xīxiàwén Zhèngzì Yánjiū) # [Research into the Correct Forms of Tangut Characters]. 2004. # L1986 = Lǐ Fànwén (李範文), 同音研究 (Tóngyīn Yánjiū) # [Study of the Homophones]. Yinchuan. 1986 @@ -12403,5 +12405,12 @@ U+18D1B kTGT_MergedSrc N5217-27 U+18D1B kRSTUnicode 36.7 U+18D1C kTGT_MergedSrc N5217-28 U+18D1C kRSTUnicode 141.9 +<<<<<<< HEAD +U+18D1D kTGT_MergedSrc H2021-309801 +U+18D1D kRSTUnicode 106.13 +U+18D1E kTGT_MergedSrc H2021-834001 +U+18D1E kRSTUnicode 579.14 +======= +>>>>>>> la-vache/main # EOF diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 9b4883e11..e69059b21 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -31786,7 +31786,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 18CD5;KHITAN SMALL SCRIPT CHARACTER-18CD5;Lo;0;L;;;;;N;;;;; 18CFF;KHITAN SMALL SCRIPT CHARACTER-18CFF;Lo;0;L;;;;;N;;;;; 18D00;;Lo;0;L;;;;;N;;;;; -18D1C;;Lo;0;L;;;;;N;;;;; +18D1E;;Lo;0;L;;;;;N;;;;; 18D80;TANGUT COMPONENT-769;Lo;0;L;;;;;N;;;;; 18D81;TANGUT COMPONENT-770;Lo;0;L;;;;;N;;;;; 1AFF0;KATAKANA LETTER MINNAN TONE-2;Lm;0;L;;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index 5bbf7de08..6e52d34f5 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: 2024-11-15, 15:33:29 GMT +# Date: 2024-11-15, 15:58:22 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 @@ -2220,8 +2220,8 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 18B00..18CD5 ; U # Lo [470] KHITAN SMALL SCRIPT CHARACTER-18B00..KHITAN SMALL SCRIPT CHARACTER-18CD5 18CD6..18CFE ; U # Cn [41] .. 18CFF ; U # Lo KHITAN SMALL SCRIPT CHARACTER-18CFF -18D00..18D1C ; U # Lo [29] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D1C -18D1D..18D7F ; U # Cn [99] .. +18D00..18D1E ; U # Lo [31] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D1E +18D1F..18D7F ; U # Cn [97] .. 18D80..18D81 ; U # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770 18D82..18DFF ; U # Cn [126] .. 1AFF0..1AFF3 ; U # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index fb85e384f..b42d7d2a2 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: 2024-11-15, 15:33:27 GMT +# Date: 2024-11-15, 15:58:20 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 @@ -2537,7 +2537,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 16FF2..16FF3 ; OLetter # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER 16FF4..16FF6 ; OLetter # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS 17000..18CD5 ; OLetter # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5 -18CFF..18D1C ; OLetter # Lo [30] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1C +18CFF..18D1E ; OLetter # Lo [32] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1E 18D80..18D81 ; OLetter # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770 1AFF0..1AFF3 ; OLetter # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 1AFF5..1AFFB ; OLetter # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 @@ -2611,7 +2611,7 @@ 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: 137052 +# Total code points: 137054 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 697a45bd1..671fe74ae 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: 2024-11-15, 15:32:43 GMT +# Date: 2024-11-15, 15:57:39 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1117,7 +1117,7 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 16FF2..16FF3 ; L # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER 16FF4..16FF6 ; L # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS 17000..18CD5 ; L # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5 -18CFF..18D1C ; L # Lo [30] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1C +18CFF..18D1E ; L # Lo [32] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1E 18D80..18D81 ; L # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770 1AFF0..1AFF3 ; L # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 1AFF5..1AFFB ; L # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 @@ -1227,7 +1227,7 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER F0000..FFFFD ; L # Co [65534] .. 100000..10FFFD; L # Co [65534] .. -# The above property value applies to 815126 code points not listed here. +# The above property value applies to 815124 code points not listed here. # Total code points: 1095476 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index 46158468b..17176ce34 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: 2024-11-15, 15:32:46 GMT +# Date: 2024-11-15, 15:57:41 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 @@ -1862,7 +1862,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 16FF2..16FF3 ; 0 # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER 16FF4..16FF6 ; 0 # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS 17000..18CD5 ; 0 # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5 -18CFF..18D1C ; 0 # Lo [30] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1C +18CFF..18D1E ; 0 # Lo [32] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1E 18D80..18D81 ; 0 # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770 1AFF0..1AFF3 ; 0 # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 1AFF5..1AFFB ; 0 # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 @@ -2082,7 +2082,7 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] .. 100000..10FFFD; 0 # Co [65534] .. -# The above property value applies to 821287 code points not listed here. +# The above property value applies to 821285 code points not listed here. # Total code points: 1113148 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index 3980c0bd6..2216c60d6 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: 2024-11-15, 15:32:48 GMT +# Date: 2024-11-15, 15:57:44 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 @@ -2127,8 +2127,8 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 760805 code points not listed here. -# Total code points: 792390 +# The above property value applies to 760803 code points not listed here. +# Total code points: 792388 # ================================================ @@ -2533,7 +2533,7 @@ FE6A..FE6B ; W # Po [2] SMALL PERCENT SIGN..SMALL COMMERCIAL AT 16FE4 ; W # Mn KHITAN SMALL SCRIPT FILLER 16FF0..16FF1 ; W # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY 17000..18CD5 ; W # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5 -18CFF..18D1C ; W # Lo [30] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1C +18CFF..18D1E ; W # Lo [32] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1E 18D80..18D81 ; W # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770 1AFF0..1AFF3 ; W # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 1AFF5..1AFFB ; W # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 @@ -2604,7 +2604,7 @@ FE6A..FE6B ; W # Po [2] SMALL PERCENT SIGN..SMALL COMMERCIAL AT 31350..323AF ; W # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF # The above property value applies to 60482 code points not listed here. -# Total code points: 182645 +# Total code points: 182647 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index 43491004f..caa0df6ae 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: 2024-11-15, 15:32:49 GMT +# Date: 2024-11-15, 15:57:44 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 @@ -581,7 +581,7 @@ FFFE..FFFF ; Cn # [2] .. 16FE5..16FEF ; Cn # [11] .. 16FF7..16FFF ; Cn # [9] .. 18CD6..18CFE ; Cn # [41] .. -18D1D..18D7F ; Cn # [99] .. +18D1F..18D7F ; Cn # [97] .. 18D82..1AFEF ; Cn # [8814] .. 1AFF4 ; Cn # 1AFFC ; Cn # @@ -748,7 +748,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819239 +# Total code points: 819237 # ================================================ @@ -2657,7 +2657,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 16F00..16F4A ; Lo # [75] MIAO LETTER PA..MIAO LETTER RTE 16F50 ; Lo # MIAO LETTER NASALIZATION 17000..18CD5 ; Lo # [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5 -18CFF..18D1C ; Lo # [30] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1C +18CFF..18D1E ; Lo # [32] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1E 18D80..18D81 ; Lo # [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770 1B000..1B122 ; Lo # [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU 1B132 ; Lo # HIRAGANA LETTER SMALL KO @@ -2725,7 +2725,7 @@ 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: 136614 +# Total code points: 136616 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 9c3549d4d..4c63f1980 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: 2024-11-15, 15:32:51 GMT +# Date: 2024-11-15, 15:57:46 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -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 757359 code points not listed here. -# Total code points: 894827 +# The above property value applies to 757357 code points not listed here. +# Total code points: 894825 # ================================================ @@ -1778,7 +1778,7 @@ FFE4 ; ID # So FULLWIDTH BROKEN BAR 11F45..11F4F ; ID # Po [11] KAWI PUNCTUATION SECTION MARKER..KAWI PUNCTUATION CLOSING SPIRAL 16FF4..16FF6 ; ID # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS 17000..18AFF ; ID # Lo [6912] TANGUT IDEOGRAPH-17000..TANGUT COMPONENT-768 -18D00..18D1C ; ID # Lo [29] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D1C +18D00..18D1E ; ID # Lo [31] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D1E 18D80..18D81 ; ID # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770 1B000..1B122 ; ID # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU 1B170..1B2FB ; ID # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -1868,7 +1868,7 @@ FFE4 ; ID # So FULLWIDTH BROKEN BAR 31350..323AF ; ID # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF # The above property value applies to 61865 code points not listed here. -# Total code points: 172454 +# Total code points: 172456 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index e4d2fbd56..4b1c2cfd9 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: 2024-11-15, 15:32:51 GMT +# Date: 2024-11-15, 15:57:46 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -37986,7 +37986,7 @@ FFFD ; REPLACEMENT CHARACTER 18AFF ; TANGUT COMPONENT-768 18B00..18CD5 ; KHITAN SMALL SCRIPT CHARACTER-* 18CFF ; KHITAN SMALL SCRIPT CHARACTER-* -18D00..18D1C ; TANGUT IDEOGRAPH-* +18D00..18D1E ; TANGUT IDEOGRAPH-* 18D80 ; TANGUT COMPONENT-769 18D81 ; TANGUT COMPONENT-770 1AFF0 ; KATAKANA LETTER MINNAN TONE-2 @@ -45633,6 +45633,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 155292 +# Total code points: 155294 # EOF diff --git a/unicodetools/src/main/java/org/unicode/text/UCD/UCD.java b/unicodetools/src/main/java/org/unicode/text/UCD/UCD.java index a3ae7da1d..22a7b0f12 100644 --- a/unicodetools/src/main/java/org/unicode/text/UCD/UCD.java +++ b/unicodetools/src/main/java/org/unicode/text/UCD/UCD.java @@ -1309,9 +1309,8 @@ public static int mapToRepresentative(int ch, int rCompositeVersion) { // Unicode 12 added TANGUT IDEOGRAPH-187F2..TANGUT IDEOGRAPH-187F7. return TANGUT_BASE; } - // REMOVE BEFORE FLIGHT: The actual version will be greater than 0x100000. - if (ch <= 0x187FF && rCompositeVersion >= 0x100000) { - // Unicode [..] added TANGUT IDEOGRAPH-187F8..TANGUT IDEOGRAPH-187FF. + if (ch <= 0x187FF && rCompositeVersion >= 0x110000) { + // Unicode 17 added TANGUT IDEOGRAPH-187F8..TANGUT IDEOGRAPH-187FF. return TANGUT_BASE; } } @@ -1326,9 +1325,12 @@ public static int mapToRepresentative(int ch, int rCompositeVersion) { if (ch <= 0x18D08) { return TANGUT_SUP_BASE; // 18D00..18D08 Tangut Ideograph Supplement } - // REMOVE BEFORE FLIGHT: The actual version will be greater than 0x100000. - if (ch <= 0x18D1C && rCompositeVersion >= 0x100000) { - // Unicode [..] added TANGUT IDEOGRAPH-18D09..TANGUT IDEOGRAPH-18D1C. + if (ch <= 0x18D1C && rCompositeVersion >= 0x110000) { + // Unicode 17 added TANGUT IDEOGRAPH-18D09..TANGUT IDEOGRAPH-18D1C. + return TANGUT_SUP_BASE; + } + if (ch <= 0x18D1E && rCompositeVersion >= 0x110000) { + // Unicode 17 added TANGUT IDEOGRAPH-18D1D..TANGUT IDEOGRAPH-18D1E. return TANGUT_SUP_BASE; } } diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/TODO-MISSING-RMG-ISSUE.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/TODO-MISSING-RMG-ISSUE.txt new file mode 100644 index 000000000..21a9644c8 --- /dev/null +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/TODO-MISSING-RMG-ISSUE.txt @@ -0,0 +1,18 @@ +# [Template for property comparison tests of character encoding proposals] +# [RMG ISSUE TITLE] +# https://github.com/unicode-org/utc-release-management/issues/[RMG ISSUE NUMBER] + +# Names always differ. +# Age always differs since these tests are comparing additions to pre-existing characters. +Ignoring Name Age: + +# Ignore the security and IDNA properties, as these are not yet included for provisionally assigned characters. +Ignoring Confusable_MA Identifier_Status Identifier_Type Idn_Status Idn_Mapping Idn_2008: + +Ignoring kRSTUnicode kTGT_MergedSrc: +Propertywise [\x{18D00}\x{18D1D}\x{18D1E}] AreAlike +end Ignoring; + +end Ignoring; + +end Ignoring; \ No newline at end of file