Skip to content

Commit 12c6e39

Browse files
authored
Seal (#1229)
* code changes for seal * UnicodeData & new block * Block=Seal * LineBreak looks good * Script=Seal * GenerateEnums for Script=Seal * Regenerate UCD * Test stub * GenerateEnums for the seal properties * Add SealSources.txt * Supply @missing lines * Regenerate P(V)A * Reasonable tests * Regenerate UCD * Tests pass
1 parent be57132 commit 12c6e39

33 files changed

+66662
-37
lines changed

unicodetools/data/ucd/dev/Blocks.txt

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -375,6 +375,7 @@ FFF0..FFFF; Specials
375375
30000..3134F; CJK Unified Ideographs Extension G
376376
31350..323AF; CJK Unified Ideographs Extension H
377377
323B0..3347F; CJK Unified Ideographs Extension J
378+
3D000..3FC3F; Seal
378379
E0000..E007F; Tags
379380
E0100..E01EF; Variation Selectors Supplement
380381
F0000..FFFFF; Supplementary Private Use Area-A

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: 2025-11-12, 22:34:41 GMT
2+
# Date: 2025-11-14, 13:42:45 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
@@ -2129,7 +2129,8 @@ FDC8..FDCE ; 17.0 # [7] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIG
21292129
18D1F..18D20 ; 18.0 # [2] TANGUT IDEOGRAPH-18D1F..TANGUT IDEOGRAPH-18D20
21302130
1F7DB ; 18.0 # BULLET IN DOUBLE CIRCLE
21312131
1F7F1..1F7FF ; 18.0 # [15] CIRCLE WITH DOUBLE VERTICAL AND HORIZONTAL LINE..RHOMBUS
2132+
3D000..3FC3F ; 18.0 # [11328] SEAL CHARACTER-3D000..SEAL CHARACTER-3FC3F
21322133

2133-
# Total code points: 48
2134+
# Total code points: 11376
21342135

21352136
# EOF

unicodetools/data/ucd/dev/DerivedCoreProperties.txt

Lines changed: 13 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# DerivedCoreProperties-18.0.0.txt
2-
# Date: 2025-11-12, 22:35:08 GMT
2+
# Date: 2025-11-14, 13:43:09 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
@@ -1466,8 +1466,9 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG
14661466
2F800..2FA1D ; Alphabetic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
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
1469+
3D000..3FC3F ; Alphabetic # Lo [11328] SEAL CHARACTER-3D000..SEAL CHARACTER-3FC3F
14691470

1470-
# Total code points: 147450
1471+
# Total code points: 158778
14711472

14721473
# ================================================
14731474

@@ -7039,8 +7040,9 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
70397040
2F800..2FA1D ; ID_Start # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
70407041
30000..3134A ; ID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
70417042
31350..33479 ; ID_Start # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
7043+
3D000..3FC3F ; ID_Start # Lo [11328] SEAL CHARACTER-3D000..SEAL CHARACTER-3FC3F
70427044

7043-
# Total code points: 145945
7045+
# Total code points: 157273
70447046

70457047
# ================================================
70467048

@@ -8472,9 +8474,10 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN
84728474
2F800..2FA1D ; ID_Continue # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
84738475
30000..3134A ; ID_Continue # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
84748476
31350..33479 ; ID_Continue # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
8477+
3D000..3FC3F ; ID_Continue # Lo [11328] SEAL CHARACTER-3D000..SEAL CHARACTER-3FC3F
84758478
E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
84768479

8477-
# Total code points: 149270
8480+
# Total code points: 160598
84788481

84798482
# ================================================
84808483

@@ -9265,8 +9268,9 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
92659268
2F800..2FA1D ; XID_Start # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
92669269
30000..3134A ; XID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
92679270
31350..33479 ; XID_Start # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
9271+
3D000..3FC3F ; XID_Start # Lo [11328] SEAL CHARACTER-3D000..SEAL CHARACTER-3FC3F
92689272

9269-
# Total code points: 145922
9273+
# Total code points: 157250
92709274

92719275
# ================================================
92729276

@@ -10699,9 +10703,10 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA
1069910703
2F800..2FA1D ; XID_Continue # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
1070010704
30000..3134A ; XID_Continue # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
1070110705
31350..33479 ; XID_Continue # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
10706+
3D000..3FC3F ; XID_Continue # Lo [11328] SEAL CHARACTER-3D000..SEAL CHARACTER-3FC3F
1070210707
E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
1070310708

10704-
# Total code points: 149251
10709+
# Total code points: 160579
1070510710

1070610711
# ================================================
1070710712

@@ -12990,8 +12995,9 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME
1299012995
2F800..2FA1D ; Grapheme_Base # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
1299112996
30000..3134A ; Grapheme_Base # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
1299212997
31350..33479 ; Grapheme_Base # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
12998+
3D000..3FC3F ; Grapheme_Base # Lo [11328] SEAL CHARACTER-3D000..SEAL CHARACTER-3FC3F
1299312999

12994-
# Total code points: 157541
13000+
# Total code points: 168869
1299513001

1299613002
# ================================================
1299713003

unicodetools/data/ucd/dev/EastAsianWidth.txt

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# EastAsianWidth-18.0.0.txt
2-
# Date: 2025-11-11, 12:32:11 GMT
2+
# Date: 2025-11-14, 13:43:14 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
@@ -2714,7 +2714,9 @@ FFFD ; A # So REPLACEMENT CHARACTER
27142714
30000..3134A ; W # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
27152715
3134B..3134F ; W # Cn [5] <reserved-3134B>..<reserved-3134F>
27162716
31350..33479 ; W # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
2717-
3347A..3FFFD ; W # Cn [52100] <reserved-3347A>..<reserved-3FFFD>
2717+
3347A..3CFFF ; W # Cn [39814] <reserved-3347A>..<reserved-3CFFF>
2718+
3D000..3FC3F ; W # Lo [11328] SEAL CHARACTER-3D000..SEAL CHARACTER-3FC3F
2719+
3FC40..3FFFD ; W # Cn [958] <reserved-3FC40>..<reserved-3FFFD>
27182720
E0001 ; N # Cf LANGUAGE TAG
27192721
E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG
27202722
E0100..E01EF ; A # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256

unicodetools/data/ucd/dev/LineBreak.txt

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# LineBreak-18.0.0.txt
2-
# Date: 2025-11-11, 12:32:14 GMT
2+
# Date: 2025-11-14, 13:43:17 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
@@ -3701,7 +3701,9 @@ FFFD ; AI # So REPLACEMENT CHARACTER
37013701
30000..3134A ; ID # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
37023702
3134B..3134F ; ID # Cn [5] <reserved-3134B>..<reserved-3134F>
37033703
31350..33479 ; ID # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
3704-
3347A..3FFFD ; ID # Cn [52100] <reserved-3347A>..<reserved-3FFFD>
3704+
3347A..3CFFF ; ID # Cn [39814] <reserved-3347A>..<reserved-3CFFF>
3705+
3D000..3FC3F ; ID # Lo [11328] SEAL CHARACTER-3D000..SEAL CHARACTER-3FC3F
3706+
3FC40..3FFFD ; ID # Cn [958] <reserved-3FC40>..<reserved-3FFFD>
37053707
E0001 ; CM # Cf LANGUAGE TAG
37063708
E0020..E007F ; CM # Cf [96] TAG SPACE..CANCEL TAG
37073709
E0100..E01EF ; CM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256

unicodetools/data/ucd/dev/PropList.txt

Lines changed: 3 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# PropList-18.0.0.txt
2-
# Date: 2025-11-12, 22:35:31 GMT
2+
# Date: 2025-11-14, 13:43:29 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
@@ -895,8 +895,9 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
895895
2F800..2FA1D ; Ideographic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
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
898+
3D000..3FC3F ; Ideographic # Lo [11328] SEAL CHARACTER-3D000..SEAL CHARACTER-3FC3F
898899

899-
# Total code points: 110950
900+
# Total code points: 122278
900901

901902
# ================================================
902903

unicodetools/data/ucd/dev/PropertyAliases.txt

Lines changed: 6 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# PropertyAliases-18.0.0.txt
2-
# Date: 2025-11-11, 02:15:48 GMT
2+
# Date: 2025-11-14, 13:43:31 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
@@ -111,6 +111,10 @@ kEH_HG ; kEH_HG
111111
kEH_IFAO ; kEH_IFAO
112112
kEH_JSesh ; kEH_JSesh
113113
kNSHU_DubenSrc ; kNSHU_DubenSrc
114+
kSEAL_CCZSrc ; kSEAL_CCZSrc
115+
kSEAL_DYCSrc ; kSEAL_DYCSrc
116+
kSEAL_QJZSrc ; kSEAL_QJZSrc
117+
kSEAL_THXSrc ; kSEAL_THXSrc
114118
kTGT_MergedSrc ; kTGT_MergedSrc
115119
na ; Name
116120
na1 ; Unicode_1_Name
@@ -228,6 +232,6 @@ XO_NFKC ; Expands_On_NFKC
228232
XO_NFKD ; Expands_On_NFKD
229233

230234
# ================================================
231-
# Total: 147
235+
# Total: 151
232236

233237
# EOF

unicodetools/data/ucd/dev/PropertyValueAliases.txt

Lines changed: 19 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# PropertyValueAliases-18.0.0.txt
2-
# Date: 2025-11-11, 12:28:40 GMT
2+
# Date: 2025-11-14, 13:43:31 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
@@ -423,6 +423,7 @@ blk; Rumi ; Rumi_Numeral_Symbols
423423
blk; Runic ; Runic
424424
blk; Samaritan ; Samaritan
425425
blk; Saurashtra ; Saurashtra
426+
blk; Seal ; Seal
426427
blk; Sharada ; Sharada
427428
blk; Sharada_Sup ; Sharada_Supplement
428429
blk; Shavian ; Shavian
@@ -1457,6 +1458,7 @@ sc ; Runr ; Runic
14571458
sc ; Samr ; Samaritan
14581459
sc ; Sarb ; Old_South_Arabian
14591460
sc ; Saur ; Saurashtra
1461+
sc ; Seal ; Seal
14601462
sc ; Sgnw ; SignWriting
14611463
sc ; Shaw ; Shavian
14621464
sc ; Shrd ; Sharada
@@ -1739,6 +1741,22 @@ kEH_NoRotate; Y ; Yes ; T
17391741

17401742
# @missing: 0000..10FFFF; kNSHU_DubenSrc; <none>
17411743

1744+
# kSEAL_CCZSrc (kSEAL_CCZSrc)
1745+
1746+
# @missing: 0000..10FFFF; kSEAL_CCZSrc; <none>
1747+
1748+
# kSEAL_DYCSrc (kSEAL_DYCSrc)
1749+
1750+
# @missing: 0000..10FFFF; kSEAL_DYCSrc; <none>
1751+
1752+
# kSEAL_QJZSrc (kSEAL_QJZSrc)
1753+
1754+
# @missing: 0000..10FFFF; kSEAL_QJZSrc; <none>
1755+
1756+
# kSEAL_THXSrc (kSEAL_THXSrc)
1757+
1758+
# @missing: 0000..10FFFF; kSEAL_THXSrc; <none>
1759+
17421760
# kTGT_MergedSrc (kTGT_MergedSrc)
17431761

17441762
# @missing: 0000..10FFFF; kTGT_MergedSrc; <none>

unicodetools/data/ucd/dev/Scripts.txt

Lines changed: 7 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# Scripts-18.0.0.txt
2-
# Date: 2025-11-11, 12:32:49 GMT
2+
# Date: 2025-11-14, 13:43:46 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
@@ -3180,4 +3180,10 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
31803180

31813181
# Total code points: 50
31823182

3183+
# ================================================
3184+
3185+
3D000..3FC3F ; Seal # Lo [11328] SEAL CHARACTER-3D000..SEAL CHARACTER-3FC3F
3186+
3187+
# Total code points: 11328
3188+
31833189
# EOF

0 commit comments

Comments
 (0)