Skip to content

Commit 24d6aa3

Browse files
committed
Merge remote-tracking branch 'la-vache/main' into arabic-crown-letters
2 parents bd9ac12 + 30dd6f0 commit 24d6aa3

32 files changed

+4755
-4804
lines changed

unicodetools/data/security/dev/IdentifierType.txt

Lines changed: 4507 additions & 4639 deletions
Large diffs are not rendered by default.

unicodetools/data/security/dev/confusables.txt

Lines changed: 11 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# confusables.txt
2-
# Date: 2025-10-25, 07:52:31 GMT
2+
# Date: 2025-11-12, 00:37:27 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
@@ -7550,6 +7550,8 @@ FA0C ; 5140 ; MA # ( 兀 → 兀 ) CJK COMPATIBILITY IDEOGRAPH-FA0C → CJK UNIF
75507550

75517551
FA74 ; 5145 ; MA # ( 充 → 充 ) CJK COMPATIBILITY IDEOGRAPH-FA74 → CJK UNIFIED IDEOGRAPH-5145 #
75527552

7553+
5151 ; 514C ; MA # ( 兑 → 兌 ) CJK UNIFIED IDEOGRAPH-5151 → CJK UNIFIED IDEOGRAPH-514C #
7554+
75537555
FA32 ; 514D ; MA # ( 免 → 免 ) CJK COMPATIBILITY IDEOGRAPH-FA32 → CJK UNIFIED IDEOGRAPH-514D #
75547556
2F80E ; 514D ; MA # ( 免 → 免 ) CJK COMPATIBILITY IDEOGRAPH-2F80E → CJK UNIFIED IDEOGRAPH-514D #
75557557

@@ -7950,6 +7952,8 @@ FA04 ; 5B85 ; MA # ( 宅 → 宅 ) CJK COMPATIBILITY IDEOGRAPH-FA04 → CJK UNIF
79507952

79517953
2F86D ; 5BC3 ; MA # ( 寃 → 寃 ) CJK COMPATIBILITY IDEOGRAPH-2F86D → CJK UNIFIED IDEOGRAPH-5BC3 #
79527954

7955+
96BA ; 5BC9 ; MA # ( 隺 → 寉 ) CJK UNIFIED IDEOGRAPH-96BA → CJK UNIFIED IDEOGRAPH-5BC9 #
7956+
79537957
2F86E ; 5BD8 ; MA # ( 寘 → 寘 ) CJK COMPATIBILITY IDEOGRAPH-2F86E → CJK UNIFIED IDEOGRAPH-5BD8 #
79547958

79557959
F95F ; 5BE7 ; MA # ( 寧 → 寧 ) CJK COMPATIBILITY IDEOGRAPH-F95F → CJK UNIFIED IDEOGRAPH-5BE7 #
@@ -9341,6 +9345,8 @@ F9C2 ; 84FC ; MA # ( 蓼 → 蓼 ) CJK COMPATIBILITY IDEOGRAPH-F9C2 → CJK UNIF
93419345

93429346
2F9AC ; 8564 ; MA # ( 蕤 → 蕤 ) CJK COMPATIBILITY IDEOGRAPH-2F9AC → CJK UNIFIED IDEOGRAPH-8564 #
93439347

9348+
32A8F ; 2EDB5 ; MA # ( 𲪏 → 𮶵 ) CJK UNIFIED IDEOGRAPH-32A8F → CJK UNIFIED IDEOGRAPH-2EDB5 #
9349+
93449350
2F9AD ; 26F2C ; MA # ( 𦼬 → 𦼬 ) CJK COMPATIBILITY IDEOGRAPH-2F9AD → CJK UNIFIED IDEOGRAPH-26F2C #
93459351

93469352
F923 ; 85CD ; MA # ( 藍 → 藍 ) CJK COMPATIBILITY IDEOGRAPH-F923 → CJK UNIFIED IDEOGRAPH-85CD #
@@ -9581,6 +9587,8 @@ F937 ; 8DEF ; MA # ( 路 → 路 ) CJK COMPATIBILITY IDEOGRAPH-F937 → CJK UNIF
95819587

95829588
2F9D ; 8EAB ; MA #* ( ⾝ → 身 ) KANGXI RADICAL BODY → CJK UNIFIED IDEOGRAPH-8EAB #
95839589

9590+
8EB2 ; 8EB1 ; MA # ( 躲 → 躱 ) CJK UNIFIED IDEOGRAPH-8EB2 → CJK UNIFIED IDEOGRAPH-8EB1 #
9591+
95849592
F902 ; 8ECA ; MA # ( 車 → 車 ) CJK COMPATIBILITY IDEOGRAPH-F902 → CJK UNIFIED IDEOGRAPH-8ECA #
95859593
2F9E ; 8ECA ; MA #* ( ⾞ → 車 ) KANGXI RADICAL CART → CJK UNIFIED IDEOGRAPH-8ECA #
95869594

@@ -9810,6 +9818,7 @@ FACA ; 97FF ; MA # ( 響 → 響 ) CJK COMPATIBILITY IDEOGRAPH-FACA → CJK UNIF
98109818
FACB ; 980B ; MA # ( 頋 → 頋 ) CJK COMPATIBILITY IDEOGRAPH-FACB → CJK UNIFIED IDEOGRAPH-980B #
98119819
2F9FE ; 980B ; MA # ( 頋 → 頋 ) CJK COMPATIBILITY IDEOGRAPH-2F9FE → CJK UNIFIED IDEOGRAPH-980B #
98129820
2F9FF ; 980B ; MA # ( 頋 → 頋 ) CJK COMPATIBILITY IDEOGRAPH-2F9FF → CJK UNIFIED IDEOGRAPH-980B #
9821+
2EA07 ; 980B ; MA # ( 𮨇 → 頋 ) CJK UNIFIED IDEOGRAPH-2EA07 → CJK UNIFIED IDEOGRAPH-980B #
98139822

98149823
F9B4 ; 9818 ; MA # ( 領 → 領 ) CJK COMPATIBILITY IDEOGRAPH-F9B4 → CJK UNIFIED IDEOGRAPH-9818 #
98159824

@@ -10014,5 +10023,5 @@ FACE ; 9F9C ; MA # ( 龜 → 龜 ) CJK COMPATIBILITY IDEOGRAPH-FACE → CJK UNIF
1001410023

1001510024
2FD5 ; 9FA0 ; MA #* ( ⿕ → 龠 ) KANGXI RADICAL FLUTE → CJK UNIFIED IDEOGRAPH-9FA0 #
1001610025

10017-
# total: 6605
10026+
# total: 6610
1001810027

unicodetools/data/security/dev/confusablesSummary.txt

Lines changed: 20 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# confusablesSummary.txt
2-
# Date: 2025-10-25, 07:52:31 GMT
2+
# Date: 2025-11-12, 00:37:27 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
@@ -14197,6 +14197,10 @@
1419714197
(‎ 充 ‎) 5145 CJK UNIFIED IDEOGRAPH-5145
1419814198
← (‎ 充 ‎) FA74 CJK COMPATIBILITY IDEOGRAPH-FA74
1419914199

14200+
# 兌 兑
14201+
(‎ 兌 ‎) 514C CJK UNIFIED IDEOGRAPH-514C
14202+
← (‎ 兑 ‎) 5151 CJK UNIFIED IDEOGRAPH-5151
14203+
1420014204
# 免 免 免
1420114205
(‎ 免 ‎) 514D CJK UNIFIED IDEOGRAPH-514D
1420214206
← (‎ 免 ‎) FA32 CJK COMPATIBILITY IDEOGRAPH-FA32
@@ -14734,6 +14738,10 @@
1473414738
(‎ 寃 ‎) 5BC3 CJK UNIFIED IDEOGRAPH-5BC3
1473514739
← (‎ 寃 ‎) 2F86D CJK COMPATIBILITY IDEOGRAPH-2F86D
1473614740

14741+
# 寉 隺
14742+
(‎ 寉 ‎) 5BC9 CJK UNIFIED IDEOGRAPH-5BC9
14743+
← (‎ 隺 ‎) 96BA CJK UNIFIED IDEOGRAPH-96BA
14744+
1473714745
# 寘 寘
1473814746
(‎ 寘 ‎) 5BD8 CJK UNIFIED IDEOGRAPH-5BD8
1473914747
← (‎ 寘 ‎) 2F86E CJK COMPATIBILITY IDEOGRAPH-2F86E
@@ -16715,6 +16723,10 @@
1671516723
(‎ 躗 ‎) 8E97 CJK UNIFIED IDEOGRAPH-8E97
1671616724
← (‎ 躛 ‎) 8E9B CJK UNIFIED IDEOGRAPH-8E9B
1671716725

16726+
# 躱 躲
16727+
(‎ 躱 ‎) 8EB1 CJK UNIFIED IDEOGRAPH-8EB1
16728+
← (‎ 躲 ‎) 8EB2 CJK UNIFIED IDEOGRAPH-8EB2
16729+
1671816730
# 軔 軔
1671916731
(‎ 軔 ‎) 8ED4 CJK UNIFIED IDEOGRAPH-8ED4
1672016732
← (‎ 軔 ‎) 2F9DE CJK COMPATIBILITY IDEOGRAPH-2F9DE
@@ -16956,8 +16968,9 @@
1695616968
← (‎ 響 ‎) FA69 CJK COMPATIBILITY IDEOGRAPH-FA69
1695716969
← (‎ 響 ‎) FACA CJK COMPATIBILITY IDEOGRAPH-FACA
1695816970

16959-
# 頋 頋 頋 頋
16971+
# 頋 𮨇 頋 頋 頋
1696016972
(‎ 頋 ‎) 980B CJK UNIFIED IDEOGRAPH-980B
16973+
← (‎ 𮨇 ‎) 2EA07 CJK UNIFIED IDEOGRAPH-2EA07
1696116974
← (‎ 頋 ‎) FACB CJK COMPATIBILITY IDEOGRAPH-FACB
1696216975
← (‎ 頋 ‎) 2F9FE CJK COMPATIBILITY IDEOGRAPH-2F9FE
1696316976
← (‎ 頋 ‎) 2F9FF CJK COMPATIBILITY IDEOGRAPH-2F9FF
@@ -17872,5 +17885,9 @@
1787217885
(‎ 𪘀 ‎) 2A600 CJK UNIFIED IDEOGRAPH-2A600
1787317886
← (‎ 𪘀 ‎) 2FA1D CJK COMPATIBILITY IDEOGRAPH-2FA1D
1787417887

17875-
# total : 7659
17888+
# 𮶵 𲪏
17889+
(‎ 𮶵 ‎) 2EDB5 CJK UNIFIED IDEOGRAPH-2EDB5
17890+
← (‎ 𲪏 ‎) 32A8F CJK UNIFIED IDEOGRAPH-32A8F
17891+
17892+
# total : 7664
1787617893

unicodetools/data/security/dev/data/source/confusables-source.txt

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -5811,3 +5811,10 @@ A8CF ; 007C 007C # SAURASHTRA DOUBLE DANDA
58115811
17C4 ; 17C1 17B6
58125812
17C7 ; 0983
58135813
11303 ; 0983
5814+
5815+
# CJK confusables from UTC #185 Action Items
5816+
5BC9 ; 96BA
5817+
8EB1 ; 8EB2
5818+
514C ; 5151
5819+
980B ; 2EA07
5820+
2EDB5 ; 32A8F

unicodetools/data/security/dev/data/source/formatted-source.txt

Lines changed: 11 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# formatted-source.txt
2-
# Date: 2025-10-25, 07:52:30 GMT
2+
# Date: 2025-11-12, 00:37:25 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
@@ -4400,6 +4400,8 @@
44004400
513F ; 16FF2 # ( 儿 ~ 𖿲 ) CJK UNIFIED IDEOGRAPH-513F ~ CHINESE SMALL SIMPLIFIED ER
44014401
513F ; 3126 # ( 儿 ~ ㄦ ) CJK UNIFIED IDEOGRAPH-513F ~ BOPOMOFO LETTER ER
44024402

4403+
514C ; 5151 # ( 兌 ~ 兑 ) CJK UNIFIED IDEOGRAPH-514C ~ CJK UNIFIED IDEOGRAPH-5151
4404+
44034405
5553 ; 555F # ( 啓 ~ 啟 ) CJK UNIFIED IDEOGRAPH-5553 ~ CJK UNIFIED IDEOGRAPH-555F
44044406

44054407
5861 ; 586B # ( 塡 ~ 填 ) CJK UNIFIED IDEOGRAPH-5861 ~ CJK UNIFIED IDEOGRAPH-586B
@@ -4408,6 +4410,8 @@
44084410

44094411
5AAF ; 5B00 # ( 媯 ~ 嬀 ) CJK UNIFIED IDEOGRAPH-5AAF ~ CJK UNIFIED IDEOGRAPH-5B00
44104412

4413+
5BC9 ; 96BA # ( 寉 ~ 隺 ) CJK UNIFIED IDEOGRAPH-5BC9 ~ CJK UNIFIED IDEOGRAPH-96BA
4414+
44114415
5CC0 ; 2B73A # ( 峀 ~ 𫜺 ) CJK UNIFIED IDEOGRAPH-5CC0 ~ CJK UNIFIED IDEOGRAPH-2B73A
44124416

44134417
5DFF ; 5E02 # ( 巿 ~ 市 ) CJK UNIFIED IDEOGRAPH-5DFF ~ CJK UNIFIED IDEOGRAPH-5E02
@@ -4462,12 +4466,16 @@
44624466

44634467
8E97 ; 8E9B # ( 躗 ~ 躛 ) CJK UNIFIED IDEOGRAPH-8E97 ~ CJK UNIFIED IDEOGRAPH-8E9B
44644468

4469+
8EB1 ; 8EB2 # ( 躱 ~ 躲 ) CJK UNIFIED IDEOGRAPH-8EB1 ~ CJK UNIFIED IDEOGRAPH-8EB2
4470+
44654471
8EFF ; 8F27 # ( 軿 ~ 輧 ) CJK UNIFIED IDEOGRAPH-8EFF ~ CJK UNIFIED IDEOGRAPH-8F27
44664472

44674473
8FB6 ; 2ECC # ( 辶 ~ ⻌ ) CJK UNIFIED IDEOGRAPH-8FB6 ~ CJK RADICAL SIMPLIFIED WALK
44684474

44694475
93AD ; 93AE # ( 鎭 ~ 鎮 ) CJK UNIFIED IDEOGRAPH-93AD ~ CJK UNIFIED IDEOGRAPH-93AE
44704476

4477+
980B ; 2EA07 # ( 頋 ~ 𮨇 ) CJK UNIFIED IDEOGRAPH-980B ~ CJK UNIFIED IDEOGRAPH-2EA07
4478+
44714479
9E42 ; 9E43 # ( 鹂 ~ 鹃 ) CJK UNIFIED IDEOGRAPH-9E42 ~ CJK UNIFIED IDEOGRAPH-9E43
44724480

44734481
A04A ; A49E # ( ꁊ ~ ꒞ ) YI SYLLABLE PUT ~ YI RADICAL PUT
@@ -4768,6 +4776,8 @@ A99D ; A9A3 # ( ꦝ ~ ꦣ ) JAVANESE LETTER DDA ~ JAVANESE LETTER DA MAHAPRANA
47684776

47694777
2D161 ; 2F82D # ( 𭅡 ~ 卑 ) CJK UNIFIED IDEOGRAPH-2D161 ~ CJK COMPATIBILITY IDEOGRAPH-2F82D
47704778

4779+
2EDB5 ; 32A8F # ( 𮶵 ~ 𲪏 ) CJK UNIFIED IDEOGRAPH-2EDB5 ~ CJK UNIFIED IDEOGRAPH-32A8F
4780+
47714781
31E7C ; 2F96E # ( 𱹼 ~ 緇 ) CJK UNIFIED IDEOGRAPH-31E7C ~ CJK COMPATIBILITY IDEOGRAPH-2F96E
47724782

47734783
FB54 ; FBE6 # ( ‎ﭔ‎ ~ ‎ﯦ‎ ) ARABIC LETTER BEEH INITIAL FORM ~ ARABIC LETTER E INITIAL FORM

unicodetools/data/ucd/dev/DerivedAge.txt

Lines changed: 4 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# DerivedAge-18.0.0.txt
2-
# Date: 2025-11-11, 12:31:38 GMT
2+
# Date: 2025-11-12, 22:34:41 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
@@ -2122,13 +2122,14 @@ FDC8..FDCE ; 17.0 # [7] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIG
21222122

21232123
# Newly assigned in Unicode 18.0.0 (September, 2025)
21242124

2125-
20C3 ; 18.0 # UAE DIRHAM SIGN
2125+
20C2..20C3 ; 18.0 # [2] RUFIYAA SIGN..UAE DIRHAM SIGN
21262126
10ED9..10EEE ; 18.0 # [22] ARABIC CROWN LETTER BEH..ARABIC CROWN LETTER YEH
21272127
10EF9 ; 18.0 # ARABIC MARK CROWN
2128+
18CD6..18CDA ; 18.0 # [5] KHITAN SMALL SCRIPT CHARACTER-18CD6..KHITAN SMALL SCRIPT CHARACTER-18CDA
21282129
18D1F..18D20 ; 18.0 # [2] TANGUT IDEOGRAPH-18D1F..TANGUT IDEOGRAPH-18D20
21292130
1F7DB ; 18.0 # BULLET IN DOUBLE CIRCLE
21302131
1F7F1..1F7FF ; 18.0 # [15] CIRCLE WITH DOUBLE VERTICAL AND HORIZONTAL LINE..RHOMBUS
21312132

2132-
# Total code points: 42
2133+
# Total code points: 48
21332134

21342135
# EOF

unicodetools/data/ucd/dev/DerivedCoreProperties.txt

Lines changed: 14 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# DerivedCoreProperties-18.0.0.txt
2-
# Date: 2025-11-11, 12:32:04 GMT
2+
# Date: 2025-11-12, 22:35:08 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
@@ -1336,7 +1336,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG
13361336
16FF0..16FF1 ; Alphabetic # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY
13371337
16FF2..16FF3 ; Alphabetic # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER
13381338
16FF4..16FF6 ; Alphabetic # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
1339-
17000..18CD5 ; Alphabetic # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5
1339+
17000..18CDA ; Alphabetic # Lo [7387] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CDA
13401340
18CFF..18D20 ; Alphabetic # Lo [34] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D20
13411341
18D80..18DF2 ; Alphabetic # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883
13421342
1AFF0..1AFF3 ; Alphabetic # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
@@ -1467,7 +1467,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG
14671467
30000..3134A ; Alphabetic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
14681468
31350..33479 ; Alphabetic # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
14691469

1470-
# Total code points: 147445
1470+
# Total code points: 147450
14711471

14721472
# ================================================
14731473

@@ -6924,7 +6924,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
69246924
16FE3 ; ID_Start # Lm OLD CHINESE ITERATION MARK
69256925
16FF2..16FF3 ; ID_Start # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER
69266926
16FF4..16FF6 ; ID_Start # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
6927-
17000..18CD5 ; ID_Start # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5
6927+
17000..18CDA ; ID_Start # Lo [7387] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CDA
69286928
18CFF..18D20 ; ID_Start # Lo [34] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D20
69296929
18D80..18DF2 ; ID_Start # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883
69306930
1AFF0..1AFF3 ; ID_Start # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
@@ -7040,7 +7040,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
70407040
30000..3134A ; ID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
70417041
31350..33479 ; ID_Start # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
70427042

7043-
# Total code points: 145940
7043+
# Total code points: 145945
70447044

70457045
# ================================================
70467046

@@ -8316,7 +8316,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN
83168316
16FF0..16FF1 ; ID_Continue # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY
83178317
16FF2..16FF3 ; ID_Continue # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER
83188318
16FF4..16FF6 ; ID_Continue # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
8319-
17000..18CD5 ; ID_Continue # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5
8319+
17000..18CDA ; ID_Continue # Lo [7387] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CDA
83208320
18CFF..18D20 ; ID_Continue # Lo [34] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D20
83218321
18D80..18DF2 ; ID_Continue # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883
83228322
1AFF0..1AFF3 ; ID_Continue # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
@@ -8474,7 +8474,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN
84748474
31350..33479 ; ID_Continue # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
84758475
E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
84768476

8477-
# Total code points: 149265
8477+
# Total code points: 149270
84788478

84798479
# ================================================
84808480

@@ -9150,7 +9150,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
91509150
16FE3 ; XID_Start # Lm OLD CHINESE ITERATION MARK
91519151
16FF2..16FF3 ; XID_Start # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER
91529152
16FF4..16FF6 ; XID_Start # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
9153-
17000..18CD5 ; XID_Start # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5
9153+
17000..18CDA ; XID_Start # Lo [7387] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CDA
91549154
18CFF..18D20 ; XID_Start # Lo [34] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D20
91559155
18D80..18DF2 ; XID_Start # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883
91569156
1AFF0..1AFF3 ; XID_Start # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
@@ -9266,7 +9266,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
92669266
30000..3134A ; XID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
92679267
31350..33479 ; XID_Start # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
92689268

9269-
# Total code points: 145917
9269+
# Total code points: 145922
92709270

92719271
# ================================================
92729272

@@ -10543,7 +10543,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA
1054310543
16FF0..16FF1 ; XID_Continue # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY
1054410544
16FF2..16FF3 ; XID_Continue # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER
1054510545
16FF4..16FF6 ; XID_Continue # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
10546-
17000..18CD5 ; XID_Continue # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5
10546+
17000..18CDA ; XID_Continue # Lo [7387] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CDA
1054710547
18CFF..18D20 ; XID_Continue # Lo [34] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D20
1054810548
18D80..18DF2 ; XID_Continue # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883
1054910549
1AFF0..1AFF3 ; XID_Continue # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
@@ -10701,7 +10701,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA
1070110701
31350..33479 ; XID_Continue # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
1070210702
E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
1070310703

10704-
# Total code points: 149246
10704+
# Total code points: 149251
1070510705

1070610706
# ================================================
1070710707

@@ -11791,8 +11791,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE
1179111791
208D ; Grapheme_Base # Ps SUBSCRIPT LEFT PARENTHESIS
1179211792
208E ; Grapheme_Base # Pe SUBSCRIPT RIGHT PARENTHESIS
1179311793
2090..209C ; Grapheme_Base # Lm [13] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER T
11794-
20A0..20C1 ; Grapheme_Base # Sc [34] EURO-CURRENCY SIGN..SAUDI RIYAL SIGN
11795-
20C3 ; Grapheme_Base # Sc UAE DIRHAM SIGN
11794+
20A0..20C3 ; Grapheme_Base # Sc [36] EURO-CURRENCY SIGN..UAE DIRHAM SIGN
1179611795
2100..2101 ; Grapheme_Base # So [2] ACCOUNT OF..ADDRESSED TO THE SUBJECT
1179711796
2102 ; Grapheme_Base # L& DOUBLE-STRUCK CAPITAL C
1179811797
2103..2106 ; Grapheme_Base # So [4] DEGREE CELSIUS..CADA UNA
@@ -12775,7 +12774,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME
1277512774
16FE3 ; Grapheme_Base # Lm OLD CHINESE ITERATION MARK
1277612775
16FF2..16FF3 ; Grapheme_Base # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER
1277712776
16FF4..16FF6 ; Grapheme_Base # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
12778-
17000..18CD5 ; Grapheme_Base # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5
12777+
17000..18CDA ; Grapheme_Base # Lo [7387] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CDA
1277912778
18CFF..18D20 ; Grapheme_Base # Lo [34] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D20
1278012779
18D80..18DF2 ; Grapheme_Base # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883
1278112780
1AFF0..1AFF3 ; Grapheme_Base # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
@@ -12992,7 +12991,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME
1299212991
30000..3134A ; Grapheme_Base # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
1299312992
31350..33479 ; Grapheme_Base # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
1299412993

12995-
# Total code points: 157535
12994+
# Total code points: 157541
1299612995

1299712996
# ================================================
1299812997

unicodetools/data/ucd/dev/EastAsianWidth.txt

Lines changed: 2 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -977,8 +977,7 @@
977977
20A9 ; H # Sc WON SIGN
978978
20AA..20AB ; N # Sc [2] NEW SHEQEL SIGN..DONG SIGN
979979
20AC ; A # Sc EURO SIGN
980-
20AD..20C1 ; N # Sc [21] KIP SIGN..SAUDI RIYAL SIGN
981-
20C3 ; N # Sc UAE DIRHAM SIGN
980+
20AD..20C3 ; N # Sc [23] KIP SIGN..UAE DIRHAM SIGN
982981
20D0..20DC ; N # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE
983982
20DD..20E0 ; N # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH
984983
20E1 ; N # Mn COMBINING LEFT RIGHT ARROW ABOVE
@@ -2382,7 +2381,7 @@ FFFD ; A # So REPLACEMENT CHARACTER
23822381
16FF4..16FF6 ; W # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS
23832382
17000..187FF ; W # Lo [6144] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187FF
23842383
18800..18AFF ; W # Lo [768] TANGUT COMPONENT-001..TANGUT COMPONENT-768
2385-
18B00..18CD5 ; W # Lo [470] KHITAN SMALL SCRIPT CHARACTER-18B00..KHITAN SMALL SCRIPT CHARACTER-18CD5
2384+
18B00..18CDA ; W # Lo [475] KHITAN SMALL SCRIPT CHARACTER-18B00..KHITAN SMALL SCRIPT CHARACTER-18CDA
23862385
18CFF ; W # Lo KHITAN SMALL SCRIPT CHARACTER-18CFF
23872386
18D00..18D20 ; W # Lo [33] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D20
23882387
18D80..18DF2 ; W # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883

0 commit comments

Comments
 (0)