🌐 AI搜索 & 代理 主页
Skip to content

Commit 952a43f

Browse files
authored
Capital ɼ (#943)
* UnicodeData.txt lines * lb=AL * Latin * Regenerate UCD * A test * Fill in the template * Ignore IDNA2008_Category * Update the test for modifier ɼ now that ɼ is part of a case pair
1 parent b6cb648 commit 952a43f

19 files changed

+110
-57
lines changed

unicodetools/data/ucd/dev/CaseFolding.txt

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# CaseFolding-18.0.0.txt
2-
# Date: 2025-11-28, 16:35:16 GMT
2+
# Date: 2025-11-28, 16:57:47 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
@@ -1251,6 +1251,7 @@ A7D6; C; A7D7; # LATIN CAPITAL LETTER MIDDLE SCOTS S
12511251
A7D8; C; A7D9; # LATIN CAPITAL LETTER SIGMOID S
12521252
A7DA; C; A7DB; # LATIN CAPITAL LETTER LAMBDA
12531253
A7DC; C; 019B; # LATIN CAPITAL LETTER LAMBDA WITH STROKE
1254+
A7E2; C; 027C; # LATIN CAPITAL LETTER R WITH LONG LEG
12541255
A7F5; C; A7F6; # LATIN CAPITAL LETTER REVERSED HALF H
12551256
AB6C; C; AB4B; # LATIN CAPITAL LETTER SCRIPT R
12561257
AB6D; C; AB4C; # LATIN CAPITAL LETTER SCRIPT R WITH RING

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: 2025-11-28, 16:35:17 GMT
2+
# Date: 2025-11-28, 16:57:48 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
@@ -2131,6 +2131,7 @@ FDC8..FDCE ; 17.0 # [7] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIG
21312131
208F ; 18.0 # MODIFIER LETTER HIGH AND LOW VERTICAL LINE
21322132
209D..209F ; 18.0 # [3] LATIN SUBSCRIPT SMALL LETTER W..LATIN SUBSCRIPT SMALL LETTER Z
21332133
20C2..20C3 ; 18.0 # [2] RUFIYAA SIGN..UAE DIRHAM SIGN
2134+
A7E2 ; 18.0 # LATIN CAPITAL LETTER R WITH LONG LEG
21342135
AB6C..AB6D ; 18.0 # [2] LATIN CAPITAL LETTER SCRIPT R..LATIN CAPITAL LETTER SCRIPT R WITH RING
21352136
107BB..107BF ; 18.0 # [5] MODIFIER LETTER SMALL TURNED T..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR
21362137
10ED9..10EEE ; 18.0 # [22] ARABIC CROWN LETTER BEH..ARABIC CROWN LETTER YEH
@@ -2155,6 +2156,6 @@ AB6C..AB6D ; 18.0 # [2] LATIN CAPITAL LETTER SCRIPT R..LATIN CAPITAL LETTER
21552156
2B81E ; 18.0 # CJK UNIFIED IDEOGRAPH-2B81E
21562157
3D000..3FC3F ; 18.0 # [11328] SEAL CHARACTER-3D000..SEAL CHARACTER-3FC3F
21572158

2158-
# Total code points: 12834
2159+
# Total code points: 12835
21592160

21602161
# EOF

unicodetools/data/ucd/dev/DerivedCoreProperties.txt

Lines changed: 28 additions & 17 deletions
Large diffs are not rendered by default.

unicodetools/data/ucd/dev/DerivedNormalizationProps.txt

Lines changed: 7 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# DerivedNormalizationProps-18.0.0.txt
2-
# Date: 2025-11-28, 16:35:46 GMT
2+
# Date: 2025-11-28, 16:58:16 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
@@ -5473,6 +5473,7 @@ A7D6 ; NFKC_CF; A7D7 # L& LATIN CAPITAL LETTER MIDDLE S
54735473
A7D8 ; NFKC_CF; A7D9 # L& LATIN CAPITAL LETTER SIGMOID S
54745474
A7DA ; NFKC_CF; A7DB # L& LATIN CAPITAL LETTER LAMBDA
54755475
A7DC ; NFKC_CF; 019B # L& LATIN CAPITAL LETTER LAMBDA WITH STROKE
5476+
A7E2 ; NFKC_CF; 027C # L& LATIN CAPITAL LETTER R WITH LONG LEG
54765477
A7F1 ; NFKC_CF; 0073 # Lm MODIFIER LETTER CAPITAL S
54775478
A7F2 ; NFKC_CF; 0063 # Lm MODIFIER LETTER CAPITAL C
54785479
A7F3 ; NFKC_CF; 0066 # Lm MODIFIER LETTER CAPITAL F
@@ -9258,7 +9259,7 @@ E0080..E00FF ; NFKC_CF; # Cn [128] <reserved-E0080>..<reserved-E
92589259
E0100..E01EF ; NFKC_CF; # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
92599260
E01F0..E0FFF ; NFKC_CF; # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
92609261

9261-
# Total code points: 10653
9262+
# Total code points: 10654
92629263

92639264
# ================================================
92649265

@@ -11706,6 +11707,7 @@ A7D6 ; NFKC_SCF; A7D7 # L& LATIN CAPITAL LETTER MIDDLE
1170611707
A7D8 ; NFKC_SCF; A7D9 # L& LATIN CAPITAL LETTER SIGMOID S
1170711708
A7DA ; NFKC_SCF; A7DB # L& LATIN CAPITAL LETTER LAMBDA
1170811709
A7DC ; NFKC_SCF; 019B # L& LATIN CAPITAL LETTER LAMBDA WITH STROKE
11710+
A7E2 ; NFKC_SCF; 027C # L& LATIN CAPITAL LETTER R WITH LONG LEG
1170911711
A7F1 ; NFKC_SCF; 0073 # Lm MODIFIER LETTER CAPITAL S
1171011712
A7F2 ; NFKC_SCF; 0063 # Lm MODIFIER LETTER CAPITAL C
1171111713
A7F3 ; NFKC_SCF; 0066 # Lm MODIFIER LETTER CAPITAL F
@@ -15491,7 +15493,7 @@ E0080..E00FF ; NFKC_SCF; # Cn [128] <reserved-E0080>..<reserved-
1549115493
E0100..E01EF ; NFKC_SCF; # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
1549215494
E01F0..E0FFF ; NFKC_SCF; # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
1549315495

15494-
# Total code points: 10615
15496+
# Total code points: 10616
1549515497

1549615498
# ================================================
1549715499

@@ -16271,6 +16273,7 @@ A7D6 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER MID
1627116273
A7D8 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER SIGMOID S
1627216274
A7DA ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER LAMBDA
1627316275
A7DC ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER LAMBDA WITH STROKE
16276+
A7E2 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER R WITH LONG LEG
1627416277
A7F1..A7F4 ; Changes_When_NFKC_Casefolded # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q
1627516278
A7F5 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER REVERSED HALF H
1627616279
A7F8..A7F9 ; Changes_When_NFKC_Casefolded # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
@@ -16523,6 +16526,6 @@ E0080..E00FF ; Changes_When_NFKC_Casefolded # Cn [128] <reserved-E0080>..<reser
1652316526
E0100..E01EF ; Changes_When_NFKC_Casefolded # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
1652416527
E01F0..E0FFF ; Changes_When_NFKC_Casefolded # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
1652516528

16526-
# Total code points: 10653
16529+
# Total code points: 10654
1652716530

1652816531
# EOF

unicodetools/data/ucd/dev/EastAsianWidth.txt

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# EastAsianWidth-18.0.0.txt
2-
# Date: 2025-11-28, 16:35:50 GMT
2+
# Date: 2025-11-28, 16:58:20 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
@@ -1550,6 +1550,7 @@ A789..A78A ; N # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQ
15501550
A78B..A78E ; N # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT
15511551
A78F ; N # Lo LATIN LETTER SINOLOGICAL DOT
15521552
A790..A7DC ; N # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE
1553+
A7E2 ; N # Lu LATIN CAPITAL LETTER R WITH LONG LEG
15531554
A7F1..A7F4 ; N # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q
15541555
A7F5..A7F6 ; N # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H
15551556
A7F7 ; N # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I

unicodetools/data/ucd/dev/LineBreak.txt

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# LineBreak-18.0.0.txt
2-
# Date: 2025-11-28, 16:35:51 GMT
2+
# Date: 2025-11-28, 16:58:21 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
@@ -1579,6 +1579,7 @@ A789..A78A ; AL # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQ
15791579
A78B..A78E ; AL # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT
15801580
A78F ; AL # Lo LATIN LETTER SINOLOGICAL DOT
15811581
A790..A7DC ; AL # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE
1582+
A7E2 ; AL # Lu LATIN CAPITAL LETTER R WITH LONG LEG
15821583
A7F1..A7F4 ; AL # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q
15831584
A7F5..A7F6 ; AL # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H
15841585
A7F7 ; AL # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I

unicodetools/data/ucd/dev/Scripts.txt

Lines changed: 3 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# Scripts-18.0.0.txt
2-
# Date: 2025-11-28, 16:36:21 GMT
2+
# Date: 2025-11-28, 16:58:52 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
@@ -683,6 +683,7 @@ A771..A787 ; Latin # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSU
683683
A78B..A78E ; Latin # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT
684684
A78F ; Latin # Lo LATIN LETTER SINOLOGICAL DOT
685685
A790..A7DC ; Latin # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE
686+
A7E2 ; Latin # L& LATIN CAPITAL LETTER R WITH LONG LEG
686687
A7F1..A7F4 ; Latin # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q
687688
A7F5..A7F6 ; Latin # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H
688689
A7F7 ; Latin # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I
@@ -707,7 +708,7 @@ FF41..FF5A ; Latin # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN
707708
1DFD0..1DFF2 ; Latin # Lm [35] LATIN SUBSCRIPT SMALL LETTER GAMMA..MODIFIER LETTER SMALL T WITH CURL
708709
1DFF5..1DFFF ; Latin # Lm [11] MODIFIER LETTER SMALL D WITH PALATAL HOOK..MODIFIER LETTER SMALL T WITH HOOK AND RETROFLEX HOOK
709710

710-
# Total code points: 1598
711+
# Total code points: 1599
711712

712713
# ================================================
713714

unicodetools/data/ucd/dev/UnicodeData.txt

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -634,7 +634,7 @@
634634
0279;LATIN SMALL LETTER TURNED R;Ll;0;L;;;;;N;;;;;
635635
027A;LATIN SMALL LETTER TURNED R WITH LONG LEG;Ll;0;L;;;;;N;;;;;
636636
027B;LATIN SMALL LETTER TURNED R WITH HOOK;Ll;0;L;;;;;N;LATIN SMALL LETTER TURNED R HOOK;;;;
637-
027C;LATIN SMALL LETTER R WITH LONG LEG;Ll;0;L;;;;;N;;;;;
637+
027C;LATIN SMALL LETTER R WITH LONG LEG;Ll;0;L;;;;;N;;;A7E2;;A7E2
638638
027D;LATIN SMALL LETTER R WITH TAIL;Ll;0;L;;;;;N;LATIN SMALL LETTER R HOOK;;2C64;;2C64
639639
027E;LATIN SMALL LETTER R WITH FISHHOOK;Ll;0;L;;;;;N;LATIN SMALL LETTER FISHHOOK R;;;;
640640
027F;LATIN SMALL LETTER REVERSED R WITH FISHHOOK;Ll;0;L;;;;;N;LATIN SMALL LETTER REVERSED FISHHOOK R;;;;
@@ -14339,6 +14339,7 @@ A7D9;LATIN SMALL LETTER SIGMOID S;Ll;0;L;;;;;N;;;A7D8;;A7D8
1433914339
A7DA;LATIN CAPITAL LETTER LAMBDA;Lu;0;L;;;;;N;;;;A7DB;
1434014340
A7DB;LATIN SMALL LETTER LAMBDA;Ll;0;L;;;;;N;;;A7DA;;A7DA
1434114341
A7DC;LATIN CAPITAL LETTER LAMBDA WITH STROKE;Lu;0;L;;;;;N;;;;019B;
14342+
A7E2;LATIN CAPITAL LETTER R WITH LONG LEG;Lu;0;L;;;;;N;;;;027C;
1434214343
A7F1;MODIFIER LETTER CAPITAL S;Lm;0;L;<super> 0053;;;;N;;;;;
1434314344
A7F2;MODIFIER LETTER CAPITAL C;Lm;0;L;<super> 0043;;;;N;;;;;
1434414345
A7F3;MODIFIER LETTER CAPITAL F;Lm;0;L;<super> 0046;;;;N;;;;;

unicodetools/data/ucd/dev/VerticalOrientation.txt

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# VerticalOrientation-18.0.0.txt
2-
# Date: 2025-11-28, 16:36:24 GMT
2+
# Date: 2025-11-28, 16:58:54 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
@@ -1367,6 +1367,7 @@ A789..A78A ; R # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQ
13671367
A78B..A78E ; R # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT
13681368
A78F ; R # Lo LATIN LETTER SINOLOGICAL DOT
13691369
A790..A7DC ; R # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE
1370+
A7E2 ; R # Lu LATIN CAPITAL LETTER R WITH LONG LEG
13701371
A7F1..A7F4 ; R # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q
13711372
A7F5..A7F6 ; R # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H
13721373
A7F7 ; R # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I

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

Lines changed: 3 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# SentenceBreakProperty-18.0.0.txt
2-
# Date: 2025-11-28, 16:36:22 GMT
2+
# Date: 2025-11-28, 16:58:52 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
@@ -1959,6 +1959,7 @@ A7D6 ; Upper # L& LATIN CAPITAL LETTER MIDDLE SCOTS S
19591959
A7D8 ; Upper # L& LATIN CAPITAL LETTER SIGMOID S
19601960
A7DA ; Upper # L& LATIN CAPITAL LETTER LAMBDA
19611961
A7DC ; Upper # L& LATIN CAPITAL LETTER LAMBDA WITH STROKE
1962+
A7E2 ; Upper # L& LATIN CAPITAL LETTER R WITH LONG LEG
19621963
A7F5 ; Upper # L& LATIN CAPITAL LETTER REVERSED HALF H
19631964
AB6C..AB6D ; Upper # L& [2] LATIN CAPITAL LETTER SCRIPT R..LATIN CAPITAL LETTER SCRIPT R WITH RING
19641965
FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z
@@ -2014,7 +2015,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT
20142015
1F150..1F169 ; Upper # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
20152016
1F170..1F189 ; Upper # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z
20162017

2017-
# Total code points: 1998
2018+
# Total code points: 1999
20182019

20192020
# ================================================
20202021

0 commit comments

Comments
 (0)