Skip to content

Commit 30dd6f0

Browse files
jowilcojowilco
authored
Jurchen Small Script characters (#1226)
* Jurchen Small Script characters
1 parent bf4acfc commit 30dd6f0

18 files changed

+94
-54
lines changed

‎unicodetools/data/ucd/dev/DerivedAge.txt‎

Lines changed: 3 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# DerivedAge-18.0.0.txt
2-
# Date: 2025-11-11, 17:09:53 GMT
2+
# Date: 2025-11-11, 17:40:05 GMT
33
# © 2025 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
@@ -2123,10 +2123,11 @@ FDC8..FDCE ; 17.0 # [7] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIG
21232123
# Newly assigned in Unicode 18.0.0 (September, 2025)
21242124

21252125
20C2..20C3 ; 18.0 # [2] RUFIYAA SIGN..UAE DIRHAM SIGN
2126+
18CD6..18CDA ; 18.0 # [5] KHITAN SMALL SCRIPT CHARACTER-18CD6..KHITAN SMALL SCRIPT CHARACTER-18CDA
21262127
18D1F..18D20 ; 18.0 # [2] TANGUT IDEOGRAPH-18D1F..TANGUT IDEOGRAPH-18D20
21272128
1F7DB ; 18.0 # BULLET IN DOUBLE CIRCLE
21282129
1F7F1..1F7FF ; 18.0 # [15] CIRCLE WITH DOUBLE VERTICAL AND HORIZONTAL LINE..RHOMBUS
21292130

2130-
# Total code points: 20
2131+
# Total code points: 25
21312132

21322133
# EOF

‎unicodetools/data/ucd/dev/DerivedCoreProperties.txt‎

Lines changed: 13 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# DerivedCoreProperties-18.0.0.txt
2-
# Date: 2025-11-11, 17:10:13 GMT
2+
# Date: 2025-11-11, 17:40:24 GMT
33
# © 2025 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
@@ -1335,7 +1335,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG
13351335
16FF0..16FF1 ; Alphabetic # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY
13361336
16FF2..16FF3 ; Alphabetic # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER
13371337
16FF4..16FF6 ; Alphabetic # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
1338-
17000..18CD5 ; Alphabetic # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5
1338+
17000..18CDA ; Alphabetic # Lo [7387] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CDA
13391339
18CFF..18D20 ; Alphabetic # Lo [34] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D20
13401340
18D80..18DF2 ; Alphabetic # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883
13411341
1AFF0..1AFF3 ; Alphabetic # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
@@ -1466,7 +1466,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG
14661466
30000..3134A ; Alphabetic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
14671467
31350..33479 ; Alphabetic # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
14681468

1469-
# Total code points: 147423
1469+
# Total code points: 147428
14701470

14711471
# ================================================
14721472

@@ -6922,7 +6922,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
69226922
16FE3 ; ID_Start # Lm OLD CHINESE ITERATION MARK
69236923
16FF2..16FF3 ; ID_Start # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER
69246924
16FF4..16FF6 ; ID_Start # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
6925-
17000..18CD5 ; ID_Start # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5
6925+
17000..18CDA ; ID_Start # Lo [7387] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CDA
69266926
18CFF..18D20 ; ID_Start # Lo [34] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D20
69276927
18D80..18DF2 ; ID_Start # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883
69286928
1AFF0..1AFF3 ; ID_Start # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
@@ -7038,7 +7038,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
70387038
30000..3134A ; ID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
70397039
31350..33479 ; ID_Start # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
70407040

7041-
# Total code points: 145918
7041+
# Total code points: 145923
70427042

70437043
# ================================================
70447044

@@ -8313,7 +8313,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN
83138313
16FF0..16FF1 ; ID_Continue # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY
83148314
16FF2..16FF3 ; ID_Continue # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER
83158315
16FF4..16FF6 ; ID_Continue # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
8316-
17000..18CD5 ; ID_Continue # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5
8316+
17000..18CDA ; ID_Continue # Lo [7387] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CDA
83178317
18CFF..18D20 ; ID_Continue # Lo [34] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D20
83188318
18D80..18DF2 ; ID_Continue # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883
83198319
1AFF0..1AFF3 ; ID_Continue # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
@@ -8471,7 +8471,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN
84718471
31350..33479 ; ID_Continue # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
84728472
E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
84738473

8474-
# Total code points: 149242
8474+
# Total code points: 149247
84758475

84768476
# ================================================
84778477

@@ -9146,7 +9146,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
91469146
16FE3 ; XID_Start # Lm OLD CHINESE ITERATION MARK
91479147
16FF2..16FF3 ; XID_Start # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER
91489148
16FF4..16FF6 ; XID_Start # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
9149-
17000..18CD5 ; XID_Start # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5
9149+
17000..18CDA ; XID_Start # Lo [7387] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CDA
91509150
18CFF..18D20 ; XID_Start # Lo [34] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D20
91519151
18D80..18DF2 ; XID_Start # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883
91529152
1AFF0..1AFF3 ; XID_Start # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
@@ -9262,7 +9262,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
92629262
30000..3134A ; XID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
92639263
31350..33479 ; XID_Start # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
92649264

9265-
# Total code points: 145895
9265+
# Total code points: 145900
92669266

92679267
# ================================================
92689268

@@ -10538,7 +10538,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA
1053810538
16FF0..16FF1 ; XID_Continue # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY
1053910539
16FF2..16FF3 ; XID_Continue # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER
1054010540
16FF4..16FF6 ; XID_Continue # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
10541-
17000..18CD5 ; XID_Continue # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5
10541+
17000..18CDA ; XID_Continue # Lo [7387] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CDA
1054210542
18CFF..18D20 ; XID_Continue # Lo [34] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D20
1054310543
18D80..18DF2 ; XID_Continue # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883
1054410544
1AFF0..1AFF3 ; XID_Continue # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
@@ -10696,7 +10696,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA
1069610696
31350..33479 ; XID_Continue # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
1069710697
E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
1069810698

10699-
# Total code points: 149223
10699+
# Total code points: 149228
1070010700

1070110701
# ================================================
1070210702

@@ -12768,7 +12768,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME
1276812768
16FE3 ; Grapheme_Base # Lm OLD CHINESE ITERATION MARK
1276912769
16FF2..16FF3 ; Grapheme_Base # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER
1277012770
16FF4..16FF6 ; Grapheme_Base # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
12771-
17000..18CD5 ; Grapheme_Base # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5
12771+
17000..18CDA ; Grapheme_Base # Lo [7387] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CDA
1277212772
18CFF..18D20 ; Grapheme_Base # Lo [34] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D20
1277312773
18D80..18DF2 ; Grapheme_Base # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883
1277412774
1AFF0..1AFF3 ; Grapheme_Base # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
@@ -12985,7 +12985,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME
1298512985
30000..3134A ; Grapheme_Base # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
1298612986
31350..33479 ; Grapheme_Base # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
1298712987

12988-
# Total code points: 157514
12988+
# Total code points: 157519
1298912989

1299012990
# ================================================
1299112991

‎unicodetools/data/ucd/dev/EastAsianWidth.txt‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2380,7 +2380,7 @@ FFFD ; A # So REPLACEMENT CHARACTER
23802380
16FF4..16FF6 ; W # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
23812381
17000..187FF ; W # Lo [6144] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187FF
23822382
18800..18AFF ; W # Lo [768] TANGUT COMPONENT-001..TANGUT COMPONENT-768
2383-
18B00..18CD5 ; W # Lo [470] KHITAN SMALL SCRIPT CHARACTER-18B00..KHITAN SMALL SCRIPT CHARACTER-18CD5
2383+
18B00..18CDA ; W # Lo [475] KHITAN SMALL SCRIPT CHARACTER-18B00..KHITAN SMALL SCRIPT CHARACTER-18CDA
23842384
18CFF ; W # Lo KHITAN SMALL SCRIPT CHARACTER-18CFF
23852385
18D00..18D20 ; W # Lo [33] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D20
23862386
18D80..18DF2 ; W # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883

‎unicodetools/data/ucd/dev/LineBreak.txt‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3291,7 +3291,7 @@ FFFD ; AI # So REPLACEMENT CHARACTER
32913291
16FF4..16FF6 ; ID # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
32923292
17000..187FF ; ID # Lo [6144] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187FF
32933293
18800..18AFF ; ID # Lo [768] TANGUT COMPONENT-001..TANGUT COMPONENT-768
3294-
18B00..18CD5 ; AL # Lo [470] KHITAN SMALL SCRIPT CHARACTER-18B00..KHITAN SMALL SCRIPT CHARACTER-18CD5
3294+
18B00..18CDA ; AL # Lo [475] KHITAN SMALL SCRIPT CHARACTER-18B00..KHITAN SMALL SCRIPT CHARACTER-18CDA
32953295
18CFF ; AL # Lo KHITAN SMALL SCRIPT CHARACTER-18CFF
32963296
18D00..18D20 ; ID # Lo [33] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D20
32973297
18D80..18DF2 ; ID # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883

‎unicodetools/data/ucd/dev/NamesList.txt‎

Lines changed: 15 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -52727,6 +52727,21 @@ FFFF <not a character>
5272752727
18CD3 KHITAN SMALL SCRIPT CHARACTER-18CD3
5272852728
18CD4 KHITAN SMALL SCRIPT CHARACTER-18CD4
5272952729
18CD5 KHITAN SMALL SCRIPT CHARACTER-18CD5
52730+
@ Jurchen Small Script characters
52731+
@+ Characters tentatively identified as Jurchen Small Script, encoded in
52732+
the Khitan Small Script block due to similar clustering structure and
52733+
limited evidence. This set also includes 18C3E.
52734+
x (khitan small script character-18c3e - 18C3E)
52735+
18CD6 KHITAN SMALL SCRIPT CHARACTER-18CD6
52736+
* used in Jurchen Small Script
52737+
18CD7 KHITAN SMALL SCRIPT CHARACTER-18CD7
52738+
* used in Jurchen Small Script
52739+
18CD8 KHITAN SMALL SCRIPT CHARACTER-18CD8
52740+
* used in Jurchen Small Script
52741+
18CD9 KHITAN SMALL SCRIPT CHARACTER-18CD9
52742+
* used in Jurchen Small Script
52743+
18CDA KHITAN SMALL SCRIPT CHARACTER-18CDA
52744+
* used in Jurchen Small Script
5273052745
@ Indication of missing character
5273152746
18CFF KHITAN SMALL SCRIPT CHARACTER-18CFF
5273252747
* represents a lost or illegible character

‎unicodetools/data/ucd/dev/PropList.txt‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# PropList-18.0.0.txt
2-
# Date: 2025-11-10, 23:51:58 GMT
2+
# Date: 2025-11-11, 17:40:40 GMT
33
# © 2025 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
@@ -883,7 +883,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
883883
16FE4 ; Ideographic # Mn KHITAN SMALL SCRIPT FILLER
884884
16FF2..16FF3 ; Ideographic # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER
885885
16FF4..16FF6 ; Ideographic # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
886-
17000..18CD5 ; Ideographic # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5
886+
17000..18CDA ; Ideographic # Lo [7387] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CDA
887887
18CFF..18D20 ; Ideographic # Lo [34] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D20
888888
18D80..18DF2 ; Ideographic # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883
889889
1B170..1B2FB ; Ideographic # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
@@ -896,7 +896,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
896896
30000..3134A ; Ideographic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
897897
31350..33479 ; Ideographic # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
898898

899-
# Total code points: 110945
899+
# Total code points: 110950
900900

901901
# ================================================
902902

‎unicodetools/data/ucd/dev/Scripts.txt‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -2973,10 +2973,10 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
29732973
# ================================================
29742974

29752975
16FE4 ; Khitan_Small_Script # Mn KHITAN SMALL SCRIPT FILLER
2976-
18B00..18CD5 ; Khitan_Small_Script # Lo [470] KHITAN SMALL SCRIPT CHARACTER-18B00..KHITAN SMALL SCRIPT CHARACTER-18CD5
2976+
18B00..18CDA ; Khitan_Small_Script # Lo [475] KHITAN SMALL SCRIPT CHARACTER-18B00..KHITAN SMALL SCRIPT CHARACTER-18CDA
29772977
18CFF ; Khitan_Small_Script # Lo KHITAN SMALL SCRIPT CHARACTER-18CFF
29782978

2979-
# Total code points: 472
2979+
# Total code points: 477
29802980

29812981
# ================================================
29822982

‎unicodetools/data/ucd/dev/UnicodeData.txt‎

Lines changed: 5 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -31741,7 +31741,11 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
3174131741
18CD3;KHITAN SMALL SCRIPT CHARACTER-18CD3;Lo;0;L;;;;;N;;;;;
3174231742
18CD4;KHITAN SMALL SCRIPT CHARACTER-18CD4;Lo;0;L;;;;;N;;;;;
3174331743
18CD5;KHITAN SMALL SCRIPT CHARACTER-18CD5;Lo;0;L;;;;;N;;;;;
31744-
18CFF;KHITAN SMALL SCRIPT CHARACTER-18CFF;Lo;0;L;;;;;N;;;;;
31744+
18CD6;KHITAN SMALL SCRIPT CHARACTER-18CD6;Lo;0;L;;;;;N;;;;;
31745+
18CD7;KHITAN SMALL SCRIPT CHARACTER-18CD7;Lo;0;L;;;;;N;;;;;
31746+
18CD8;KHITAN SMALL SCRIPT CHARACTER-18CD8;Lo;0;L;;;;;N;;;;;
31747+
18CD9;KHITAN SMALL SCRIPT CHARACTER-18CD9;Lo;0;L;;;;;N;;;;;
31748+
18CDA;KHITAN SMALL SCRIPT CHARACTER-18CDA;Lo;0;L;;;;;N;;;;; 18CFF;KHITAN SMALL SCRIPT CHARACTER-18CFF;Lo;0;L;;;;;N;;;;;
3174531749
18D00;<Tangut Ideograph Supplement, First>;Lo;0;L;;;;;N;;;;;
3174631750
18D20;<Tangut Ideograph Supplement, Last>;Lo;0;L;;;;;N;;;;;
3174731751
18D80;TANGUT COMPONENT-769;Lo;0;L;;;;;N;;;;;

‎unicodetools/data/ucd/dev/VerticalOrientation.txt‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -2217,8 +2217,8 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA
22172217
16FF7..16FFF ; U # Cn [9] <reserved-16FF7>..<reserved-16FFF>
22182218
17000..187FF ; U # Lo [6144] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187FF
22192219
18800..18AFF ; U # Lo [768] TANGUT COMPONENT-001..TANGUT COMPONENT-768
2220-
18B00..18CD5 ; U # Lo [470] KHITAN SMALL SCRIPT CHARACTER-18B00..KHITAN SMALL SCRIPT CHARACTER-18CD5
2221-
18CD6..18CFE ; U # Cn [41] <reserved-18CD6>..<reserved-18CFE>
2220+
18B00..18CDA ; U # Lo [475] KHITAN SMALL SCRIPT CHARACTER-18B00..KHITAN SMALL SCRIPT CHARACTER-18CDA
2221+
18CDB..18CFE ; U # Cn [36] <reserved-18CDB>..<reserved-18CFE>
22222222
18CFF ; U # Lo KHITAN SMALL SCRIPT CHARACTER-18CFF
22232223
18D00..18D20 ; U # Lo [33] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D20
22242224
18D21..18D7F ; U # Cn [95] <reserved-18D21>..<reserved-18D7F>

‎unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# SentenceBreakProperty-18.0.0.txt
2-
# Date: 2025-11-10, 23:52:16 GMT
2+
# Date: 2025-11-11, 17:40:55 GMT
33
# © 2025 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
@@ -2535,7 +2535,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
25352535
16FE3 ; OLetter # Lm OLD CHINESE ITERATION MARK
25362536
16FF2..16FF3 ; OLetter # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER
25372537
16FF4..16FF6 ; OLetter # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
2538-
17000..18CD5 ; OLetter # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5
2538+
17000..18CDA ; OLetter # Lo [7387] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CDA
25392539
18CFF..18D20 ; OLetter # Lo [34] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D20
25402540
18D80..18DF2 ; OLetter # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883
25412541
1AFF0..1AFF3 ; OLetter # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
@@ -2616,7 +2616,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
26162616
30000..3134A ; OLetter # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
26172617
31350..33479 ; OLetter # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
26182618

2619-
# Total code points: 141503
2619+
# Total code points: 141508
26202620

26212621
# ================================================
26222622

0 commit comments

Comments
 (0)