Skip to content

Commit e9cb075

Browse files
authored
2 Tangut components and 28 Tangut ideographs (#578)
* UnicodeData.txt and hardcoded ranges from L2/23-246 * LineBreak.txt * new block * Regenerate UCD * GenerateEnums * EAW=W * Regenerate UCD * SUP * script * Regenerate UCD * Do not break UnicodeData ranges * Regenerate UCD * sources * Tangut Components Supplement to vo=U * Regenerate UCD * Ideographic * Regenerate UCD
1 parent 0bdae18 commit e9cb075

24 files changed

+184
-93
lines changed

unicodetools/data/ucd/dev/Blocks.txt

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -315,6 +315,7 @@ FFF0..FFFF; Specials
315315
18800..18AFF; Tangut Components
316316
18B00..18CFF; Khitan Small Script
317317
18D00..18D7F; Tangut Supplement
318+
18D80..18DFF; Tangut Components Supplement
318319
1AFF0..1AFFF; Kana Extended-B
319320
1B000..1B0FF; Kana Supplement
320321
1B100..1B12F; Kana Extended-A

unicodetools/data/ucd/dev/DerivedAge.txt

Lines changed: 6 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# DerivedAge-17.0.0.txt
2-
# Date: 2024-11-15, 15:06:00 GMT
2+
# Date: 2024-11-15, 15:32:19 GMT
33
# © 2024 Unicode®, Inc.
44
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
55
# For terms of use and license, see https://www.unicode.org/terms_of_use.html
@@ -2041,7 +2041,9 @@ A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L
20412041
13460..143FA ; 16.0 # [3995] EGYPTIAN HIEROGLYPH-13460..EGYPTIAN HIEROGLYPH-143FA
20422042
16100..16139 ; 16.0 # [58] GURUNG KHEMA LETTER A..GURUNG KHEMA DIGIT NINE
20432043
16D40..16D79 ; 16.0 # [58] KIRAT RAI SIGN ANUSVARA..KIRAT RAI DIGIT NINE
2044+
187F8..187FF ; 16.0 # [8] TANGUT IDEOGRAPH-187F8..TANGUT IDEOGRAPH-187FF
20442045
18CFF ; 16.0 # KHITAN SMALL SCRIPT CHARACTER-18CFF
2046+
18D09..18D1C ; 16.0 # [20] TANGUT IDEOGRAPH-18D09..TANGUT IDEOGRAPH-18D1C
20452047
1CC00..1CCF9 ; 16.0 # [250] UP-POINTING GO-KART..OUTLINED DIGIT NINE
20462048
1CD00..1CEB3 ; 16.0 # [436] BLOCK OCTANT-3..BLACK RIGHT TRIANGLE CARET
20472049
1E5D0..1E5FA ; 16.0 # [43] OL ONAL LETTER O..OL ONAL DIGIT NINE
@@ -2057,7 +2059,7 @@ A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L
20572059
1FAE9 ; 16.0 # FACE WITH BAGS UNDER EYES
20582060
1FBCB..1FBEF ; 16.0 # [37] WHITE CROSS MARK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE
20592061

2060-
# Total code points: 5185
2062+
# Total code points: 5213
20612063

20622064
# ================================================
20632065

@@ -2092,7 +2094,8 @@ FDC8..FDCE ; 17.0 # [7] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIG
20922094
16EA0..16EB8 ; 17.0 # [25] BERIA ERFE CAPITAL LETTER ARKAB..BERIA ERFE CAPITAL LETTER AY
20932095
16EBB..16ED3 ; 17.0 # [25] BERIA ERFE SMALL LETTER ARKAB..BERIA ERFE SMALL LETTER AY
20942096
16FF2..16FF6 ; 17.0 # [5] CHINESE SMALL SIMPLIFIED ER..YANGQIN SIGN SLOW TWO BEATS
2097+
18D80..18D81 ; 17.0 # [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770
20952098

2096-
# Total code points: 264
2099+
# Total code points: 266
20972100

20982101
# EOF

unicodetools/data/ucd/dev/DerivedCoreProperties.txt

Lines changed: 25 additions & 25 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# DerivedCoreProperties-17.0.0.txt
2-
# Date: 2024-11-15, 15:06:24 GMT
2+
# Date: 2024-11-15, 15:32:46 GMT
33
# © 2024 Unicode®, Inc.
44
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
55
# For terms of use and license, see https://www.unicode.org/terms_of_use.html
@@ -1337,9 +1337,9 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG
13371337
16FF0..16FF1 ; Alphabetic # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY
13381338
16FF2..16FF3 ; Alphabetic # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER
13391339
16FF4..16FF6 ; Alphabetic # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
1340-
17000..187F7 ; Alphabetic # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7
1341-
18800..18CD5 ; Alphabetic # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5
1342-
18CFF..18D08 ; Alphabetic # Lo [10] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D08
1340+
17000..18CD5 ; Alphabetic # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5
1341+
18CFF..18D1C ; Alphabetic # Lo [30] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1C
1342+
18D80..18D81 ; Alphabetic # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770
13431343
1AFF0..1AFF3 ; Alphabetic # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
13441344
1AFF5..1AFFB ; Alphabetic # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
13451345
1AFFD..1AFFE ; Alphabetic # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
@@ -1458,7 +1458,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG
14581458
30000..3134A ; Alphabetic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
14591459
31350..323AF ; Alphabetic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
14601460

1461-
# Total code points: 142938
1461+
# Total code points: 142968
14621462

14631463
# ================================================
14641464

@@ -6909,9 +6909,9 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
69096909
16FE3 ; ID_Start # Lm OLD CHINESE ITERATION MARK
69106910
16FF2..16FF3 ; ID_Start # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER
69116911
16FF4..16FF6 ; ID_Start # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
6912-
17000..187F7 ; ID_Start # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7
6913-
18800..18CD5 ; ID_Start # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5
6914-
18CFF..18D08 ; ID_Start # Lo [10] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D08
6912+
17000..18CD5 ; ID_Start # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5
6913+
18CFF..18D1C ; ID_Start # Lo [30] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1C
6914+
18D80..18D81 ; ID_Start # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770
69156915
1AFF0..1AFF3 ; ID_Start # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
69166916
1AFF5..1AFFB ; ID_Start # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
69176917
1AFFD..1AFFE ; ID_Start # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
@@ -7019,7 +7019,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
70197019
30000..3134A ; ID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
70207020
31350..323AF ; ID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
70217021

7022-
# Total code points: 141437
7022+
# Total code points: 141467
70237023

70247024
# ================================================
70257025

@@ -8300,9 +8300,9 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN
83008300
16FF0..16FF1 ; ID_Continue # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY
83018301
16FF2..16FF3 ; ID_Continue # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER
83028302
16FF4..16FF6 ; ID_Continue # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
8303-
17000..187F7 ; ID_Continue # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7
8304-
18800..18CD5 ; ID_Continue # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5
8305-
18CFF..18D08 ; ID_Continue # Lo [10] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D08
8303+
17000..18CD5 ; ID_Continue # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5
8304+
18CFF..18D1C ; ID_Continue # Lo [30] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1C
8305+
18D80..18D81 ; ID_Continue # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770
83068306
1AFF0..1AFF3 ; ID_Continue # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
83078307
1AFF5..1AFFB ; ID_Continue # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
83088308
1AFFD..1AFFE ; ID_Continue # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
@@ -8448,7 +8448,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN
84488448
31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
84498449
E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
84508450

8451-
# Total code points: 144770
8451+
# Total code points: 144800
84528452

84538453
# ================================================
84548454

@@ -9126,9 +9126,9 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
91269126
16FE3 ; XID_Start # Lm OLD CHINESE ITERATION MARK
91279127
16FF2..16FF3 ; XID_Start # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER
91289128
16FF4..16FF6 ; XID_Start # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
9129-
17000..187F7 ; XID_Start # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7
9130-
18800..18CD5 ; XID_Start # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5
9131-
18CFF..18D08 ; XID_Start # Lo [10] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D08
9129+
17000..18CD5 ; XID_Start # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5
9130+
18CFF..18D1C ; XID_Start # Lo [30] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1C
9131+
18D80..18D81 ; XID_Start # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770
91329132
1AFF0..1AFF3 ; XID_Start # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
91339133
1AFF5..1AFFB ; XID_Start # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
91349134
1AFFD..1AFFE ; XID_Start # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
@@ -9236,7 +9236,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
92369236
30000..3134A ; XID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
92379237
31350..323AF ; XID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
92389238

9239-
# Total code points: 141414
9239+
# Total code points: 141444
92409240

92419241
# ================================================
92429242

@@ -10518,9 +10518,9 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA
1051810518
16FF0..16FF1 ; XID_Continue # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY
1051910519
16FF2..16FF3 ; XID_Continue # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER
1052010520
16FF4..16FF6 ; XID_Continue # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
10521-
17000..187F7 ; XID_Continue # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7
10522-
18800..18CD5 ; XID_Continue # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5
10523-
18CFF..18D08 ; XID_Continue # Lo [10] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D08
10521+
17000..18CD5 ; XID_Continue # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5
10522+
18CFF..18D1C ; XID_Continue # Lo [30] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1C
10523+
18D80..18D81 ; XID_Continue # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770
1052410524
1AFF0..1AFF3 ; XID_Continue # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
1052510525
1AFF5..1AFFB ; XID_Continue # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
1052610526
1AFFD..1AFFE ; XID_Continue # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
@@ -10666,7 +10666,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA
1066610666
31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
1066710667
E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
1066810668

10669-
# Total code points: 144751
10669+
# Total code points: 144781
1067010670

1067110671
# ================================================
1067210672

@@ -12740,9 +12740,9 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME
1274012740
16FE3 ; Grapheme_Base # Lm OLD CHINESE ITERATION MARK
1274112741
16FF2..16FF3 ; Grapheme_Base # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER
1274212742
16FF4..16FF6 ; Grapheme_Base # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
12743-
17000..187F7 ; Grapheme_Base # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7
12744-
18800..18CD5 ; Grapheme_Base # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5
12745-
18CFF..18D08 ; Grapheme_Base # Lo [10] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D08
12743+
17000..18CD5 ; Grapheme_Base # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5
12744+
18CFF..18D1C ; Grapheme_Base # Lo [30] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1C
12745+
18D80..18D81 ; Grapheme_Base # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770
1274612746
1AFF0..1AFF3 ; Grapheme_Base # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
1274712747
1AFF5..1AFFB ; Grapheme_Base # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
1274812748
1AFFD..1AFFE ; Grapheme_Base # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
@@ -12945,7 +12945,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME
1294512945
30000..3134A ; Grapheme_Base # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
1294612946
31350..323AF ; Grapheme_Base # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
1294712947

12948-
# Total code points: 152956
12948+
# Total code points: 152986
1294912949

1295012950
# ================================================
1295112951

unicodetools/data/ucd/dev/EastAsianWidth.txt

Lines changed: 4 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# EastAsianWidth-17.0.0.txt
2-
# Date: 2024-11-15, 15:06:30 GMT
2+
# Date: 2024-11-15, 15:32:54 GMT
33
# © 2024 Unicode®, Inc.
44
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
55
# For terms of use and license, see https://www.unicode.org/terms_of_use.html
@@ -2384,11 +2384,12 @@ FFFD ; A # So REPLACEMENT CHARACTER
23842384
16FF0..16FF1 ; W # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY
23852385
16FF2..16FF3 ; N # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER
23862386
16FF4..16FF6 ; N # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
2387-
17000..187F7 ; W # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7
2387+
17000..187FF ; W # Lo [6144] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187FF
23882388
18800..18AFF ; W # Lo [768] TANGUT COMPONENT-001..TANGUT COMPONENT-768
23892389
18B00..18CD5 ; W # Lo [470] KHITAN SMALL SCRIPT CHARACTER-18B00..KHITAN SMALL SCRIPT CHARACTER-18CD5
23902390
18CFF ; W # Lo KHITAN SMALL SCRIPT CHARACTER-18CFF
2391-
18D00..18D08 ; W # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08
2391+
18D00..18D1C ; W # Lo [29] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D1C
2392+
18D80..18D81 ; W # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770
23922393
1AFF0..1AFF3 ; W # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
23932394
1AFF5..1AFFB ; W # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
23942395
1AFFD..1AFFE ; W # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8

unicodetools/data/ucd/dev/LineBreak.txt

Lines changed: 4 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# LineBreak-17.0.0.txt
2-
# Date: 2024-11-15, 15:06:31 GMT
2+
# Date: 2024-11-15, 15:32:55 GMT
33
# © 2024 Unicode®, Inc.
44
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
55
# For terms of use and license, see https://www.unicode.org/terms_of_use.html
@@ -3295,11 +3295,12 @@ FFFD ; AI # So REPLACEMENT CHARACTER
32953295
16FF0..16FF1 ; CM # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY
32963296
16FF2..16FF3 ; NS # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER
32973297
16FF4..16FF6 ; ID # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
3298-
17000..187F7 ; ID # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7
3298+
17000..187FF ; ID # Lo [6144] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187FF
32993299
18800..18AFF ; ID # Lo [768] TANGUT COMPONENT-001..TANGUT COMPONENT-768
33003300
18B00..18CD5 ; AL # Lo [470] KHITAN SMALL SCRIPT CHARACTER-18B00..KHITAN SMALL SCRIPT CHARACTER-18CD5
33013301
18CFF ; AL # Lo KHITAN SMALL SCRIPT CHARACTER-18CFF
3302-
18D00..18D08 ; ID # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08
3302+
18D00..18D1C ; ID # Lo [29] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D1C
3303+
18D80..18D81 ; ID # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770
33033304
1AFF0..1AFF3 ; AL # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
33043305
1AFF5..1AFFB ; AL # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
33053306
1AFFD..1AFFE ; AL # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8

unicodetools/data/ucd/dev/PropList.txt

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# PropList-17.0.0.txt
2-
# Date: 2024-11-15, 15:06:43 GMT
2+
# Date: 2024-11-15, 15:33:06 GMT
33
# © 2024 Unicode®, Inc.
44
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
55
# For terms of use and license, see https://www.unicode.org/terms_of_use.html
@@ -880,9 +880,9 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
880880
16FE4 ; Ideographic # Mn KHITAN SMALL SCRIPT FILLER
881881
16FF2..16FF3 ; Ideographic # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER
882882
16FF4..16FF6 ; Ideographic # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
883-
17000..187F7 ; Ideographic # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7
884-
18800..18CD5 ; Ideographic # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5
885-
18CFF..18D08 ; Ideographic # Lo [10] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D08
883+
17000..18CD5 ; Ideographic # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5
884+
18CFF..18D1C ; Ideographic # Lo [30] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1C
885+
18D80..18D81 ; Ideographic # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770
886886
1B170..1B2FB ; Ideographic # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
887887
20000..2A6DF ; Ideographic # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF
888888
2A700..2B739 ; Ideographic # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739
@@ -894,7 +894,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
894894
30000..3134A ; Ideographic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
895895
31350..323AF ; Ideographic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
896896

897-
# Total code points: 106482
897+
# Total code points: 106512
898898

899899
# ================================================
900900

unicodetools/data/ucd/dev/PropertyValueAliases.txt

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# PropertyValueAliases-17.0.0.txt
2-
# Date: 2024-11-14, 22:51:32 GMT
2+
# Date: 2024-11-15, 15:33:08 GMT
33
# © 2024 Unicode®, Inc.
44
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
55
# For terms of use and license, see https://www.unicode.org/terms_of_use.html
@@ -467,6 +467,7 @@ blk; Tamil_Sup ; Tamil_Supplement
467467
blk; Tangsa ; Tangsa
468468
blk; Tangut ; Tangut
469469
blk; Tangut_Components ; Tangut_Components
470+
blk; Tangut_Components_Sup ; Tangut_Components_Supplement
470471
blk; Tangut_Sup ; Tangut_Supplement
471472
blk; Telugu ; Telugu
472473
blk; Thaana ; Thaana

unicodetools/data/ucd/dev/Scripts.txt

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# Scripts-17.0.0.txt
2-
# Date: 2024-11-15, 15:07:02 GMT
2+
# Date: 2024-11-15, 15:33:26 GMT
33
# © 2024 Unicode®, Inc.
44
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
55
# For terms of use and license, see https://www.unicode.org/terms_of_use.html
@@ -2768,11 +2768,11 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
27682768
# ================================================
27692769

27702770
16FE0 ; Tangut # Lm TANGUT ITERATION MARK
2771-
17000..187F7 ; Tangut # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7
2772-
18800..18AFF ; Tangut # Lo [768] TANGUT COMPONENT-001..TANGUT COMPONENT-768
2773-
18D00..18D08 ; Tangut # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08
2771+
17000..18AFF ; Tangut # Lo [6912] TANGUT IDEOGRAPH-17000..TANGUT COMPONENT-768
2772+
18D00..18D1C ; Tangut # Lo [29] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D1C
2773+
18D80..18D81 ; Tangut # Lo [2] TANGUT COMPONENT-769..TANGUT COMPONENT-770
27742774

2775-
# Total code points: 6914
2775+
# Total code points: 6944
27762776

27772777
# ================================================
27782778

0 commit comments

Comments
 (0)