Skip to content

Commit 0f8bddb

Browse files
committed
Unicode 17 beta ctt.txt & Idna2008.txt
generated by Ken from the latest allkeys.txt & IdnaMappingTable.txt to sync with the recent repertoire changes
1 parent ce39bf4 commit 0f8bddb

File tree

2 files changed

+13
-19
lines changed

2 files changed

+13
-19
lines changed

unicodetools/data/idna/dev/Idna2008.txt

Lines changed: 8 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# Idna2008-17.0.0.txt
2-
# Date: 2025-01-29, 17:04:43 GMT [KW]
2+
# Date: 2025-05-02, 07:27:27 GMT [KW]
33
# Copyright 2025 Unicode, Inc.
44
# For terms of use and license, see https://www.unicode.org/terms_of_use.html
55
#
@@ -1550,8 +1550,8 @@
15501550
208F ; UNASSIGNED # <reserved-208F>
15511551
2090..209C ; DISALLOWED # LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER T
15521552
209D..209F ; UNASSIGNED # <reserved-209D>..<reserved-209F>
1553-
20A0..20C0 ; DISALLOWED # EURO-CURRENCY SIGN..SOM SIGN
1554-
20C1..20CF ; UNASSIGNED # <reserved-20C1>..<reserved-20CF>
1553+
20A0..20C1 ; DISALLOWED # EURO-CURRENCY SIGN..SAUDI RIYAL SIGN
1554+
20C2..20CF ; UNASSIGNED # <reserved-20C2>..<reserved-20CF>
15551555
20D0..20F0 ; DISALLOWED # COMBINING LEFT HARPOON ABOVE..COMBINING ASTERISK ABOVE
15561556
20F1..20FF ; UNASSIGNED # <reserved-20F1>..<reserved-20FF>
15571557
2100..214D ; DISALLOWED # ACCOUNT OF..AKTIESELSKAB
@@ -2294,8 +2294,8 @@ FFF9..FFFF ; DISALLOWED # INTERLINEAR ANNOTATION ANCHOR..<noncharacter-FFFF>
22942294
10920..10939; PVALID # LYDIAN LETTER A..LYDIAN LETTER C
22952295
1093A..1093E; UNASSIGNED # <reserved-1093A>..<reserved-1093E>
22962296
1093F ; DISALLOWED # LYDIAN TRIANGULAR MARK
2297-
10940..1095C; PVALID # SIDETIC LETTER N01..SIDETIC LETTER N29
2298-
1095D..1097F; UNASSIGNED # <reserved-1095D>..<reserved-1097F>
2297+
10940..10959; PVALID # SIDETIC LETTER N01..SIDETIC LETTER N26
2298+
1095A..1097F; UNASSIGNED # <reserved-1095A>..<reserved-1097F>
22992299
10980..109B7; PVALID # MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA
23002300
109B8..109BB; UNASSIGNED # <reserved-109B8>..<reserved-109BB>
23012301
109BC..109BD; DISALLOWED # MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF
@@ -3076,12 +3076,10 @@ FFF9..FFFF ; DISALLOWED # INTERLINEAR ANNOTATION ANCHOR..<noncharacter-FFFF>
30763076
1FFFE..1FFFF; DISALLOWED # <noncharacter-1FFFE>..<noncharacter-1FFFF>
30773077
20000..2A6DF; PVALID # CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF
30783078
2A6E0..2A6FF; UNASSIGNED # <reserved-2A6E0>..<reserved-2A6FF>
3079-
2A700..2B73E; PVALID # CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B73E
3080-
2B73F ; UNASSIGNED # <reserved-2B73F>
3081-
2B740..2B81D; PVALID # CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
3079+
2A700..2B81D; PVALID # CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B81D
30823080
2B81E..2B81F; UNASSIGNED # <reserved-2B81E>..<reserved-2B81F>
3083-
2B820..2CEA1; PVALID # CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
3084-
2CEA2..2CEAF; UNASSIGNED # <reserved-2CEA2>..<reserved-2CEAF>
3081+
2B820..2CEAD; PVALID # CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEAD
3082+
2CEAE..2CEAF; UNASSIGNED # <reserved-2CEAE>..<reserved-2CEAF>
30853083
2CEB0..2EBE0; PVALID # CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
30863084
2EBE1..2EBEF; UNASSIGNED # <reserved-2EBE1>..<reserved-2EBEF>
30873085
2EBF0..2EE5D; PVALID # CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D

unicodetools/data/uca/dev/ctt.txt

Lines changed: 5 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -9,7 +9,7 @@
99
% Note that ISO/IEC TR 14652:2004 has been replaced by ISO/IEC TR 30112:2014.
1010

1111
% Autogenerated Common Template Table
12-
% Date: 2025-02-19, 12:23:54 GMT
12+
% Date: 2025-04-24, 12:08:06 GMT
1313
% CTT Table Name: CTT_V17_0
1414
% Generated from unidata-17.0.0.txt
1515

@@ -9788,6 +9788,7 @@ collating-element <UAABC_AAAF> from "<UAABC><UAAAF>" % collation-element for reo
97889788
<S20BE> % LARI SIGN
97899789
<S20BF> % BITCOIN SIGN
97909790
<S20C0> % SOM SIGN
9791+
<S20C1> % SAUDI RIYAL SIGN
97919792
<S0030> % DIGIT ZERO
97929793
<S0031> % DIGIT ONE
97939794
<S0032> % DIGIT TWO
@@ -21182,9 +21183,6 @@ collating-element <UAABC_AAAF> from "<UAABC><UAAAF>" % collation-element for reo
2118221183
<S10957> % SIDETIC LETTER N24
2118321184
<S10958> % SIDETIC LETTER N25
2118421185
<S10959> % SIDETIC LETTER N26
21185-
<S1095A> % SIDETIC LETTER N27
21186-
<S1095B> % SIDETIC LETTER N28
21187-
<S1095C> % SIDETIC LETTER N29
2118821186
<S10300> % OLD ITALIC LETTER A
2118921187
<S10301> % OLD ITALIC LETTER BE
2119021188
<S10302> % OLD ITALIC LETTER KE
@@ -40105,6 +40103,7 @@ collating-element <UAABC_AAAF> from "<UAABC><UAAAF>" % collation-element for reo
4010540103
<U20BE> <S20BE>;<BASE>;<MIN>;<SFFFF> % LARI SIGN
4010640104
<U20BF> <S20BF>;<BASE>;<MIN>;<SFFFF> % BITCOIN SIGN
4010740105
<U20C0> <S20C0>;<BASE>;<MIN>;<SFFFF> % SOM SIGN
40106+
<U20C1> <S20C1>;<BASE>;<MIN>;<SFFFF> % SAUDI RIYAL SIGN
4010840107
<U0030> <S0030>;<BASE>;<MIN>;<SFFFF> % DIGIT ZERO
4010940108
<U0660> <S0030>;<BASE>;<MIN>;<SFFFF> % ARABIC-INDIC DIGIT ZERO
4011040109
<U06F0> <S0030>;<BASE>;<MIN>;<SFFFF> % EXTENDED ARABIC-INDIC DIGIT ZERO
@@ -59346,9 +59345,6 @@ collating-element <UAABC_AAAF> from "<UAABC><UAAAF>" % collation-element for reo
5934659345
<U10957> <S10957>;<BASE>;<MIN>;<SFFFF> % SIDETIC LETTER N24
5934759346
<U10958> <S10958>;<BASE>;<MIN>;<SFFFF> % SIDETIC LETTER N25
5934859347
<U10959> <S10959>;<BASE>;<MIN>;<SFFFF> % SIDETIC LETTER N26
59349-
<U1095A> <S1095A>;<BASE>;<MIN>;<SFFFF> % SIDETIC LETTER N27
59350-
<U1095B> <S1095B>;<BASE>;<MIN>;<SFFFF> % SIDETIC LETTER N28
59351-
<U1095C> <S1095C>;<BASE>;<MIN>;<SFFFF> % SIDETIC LETTER N29
5935259348
<U10300> <S10300>;<BASE>;<MIN>;<SFFFF> % OLD ITALIC LETTER A
5935359349
<U10301> <S10301>;<BASE>;<MIN>;<SFFFF> % OLD ITALIC LETTER BE
5935459350
<U10302> <S10302>;<BASE>;<MIN>;<SFFFF> % OLD ITALIC LETTER KE
@@ -69837,9 +69833,9 @@ collating-element <UAABC_AAAF> from "<UAABC><UAAAF>" % collation-element for reo
6983769833
% WEIGHT_BASE = 0xFB80 for Extension A through Extension I Han characters.
6983869834
% cp >= 0x03400 && cp <= 0x04DBF % Ext. A
6983969835
% cp >= 0x20000 && cp <= 0x2A6DF % Ext. B
69840-
% cp >= 0x2A700 && cp <= 0x2B73E % Ext. C
69836+
% cp >= 0x2A700 && cp <= 0x2B73F % Ext. C
6984169837
% cp >= 0x2B740 && cp <= 0x2B81D % Ext. D
69842-
% cp >= 0x2B820 && cp <= 0x2CEA1 % Ext. E
69838+
% cp >= 0x2B820 && cp <= 0x2CEAD % Ext. E
6984369839
% cp >= 0x2CEB0 && cp <= 0x2EBE0 % Ext. F
6984469840
% cp >= 0x2EBF0 && cp <= 0x2EE5D % Ext. I
6984569841
% cp >= 0x30000 && cp <= 0x3134A % Ext. G

0 commit comments

Comments
 (0)