CVS commit: src/share/locale/ctype
Module Name:src Committed By: wiz Date: Wed Dec 21 06:25:35 UTC 2022 Modified Files: src/share/locale/ctype: en_US.UTF-8.src Log Message: Update Unicode tables to 15.0.0. This is based on the tables provided by perl 5.37.7. To generate a diff of this commit: cvs rdiff -u -r1.9 -r1.10 src/share/locale/ctype/en_US.UTF-8.src Please note that diffs are not public domain; they are subject to the copyright notices on the relevant files. Modified files: Index: src/share/locale/ctype/en_US.UTF-8.src diff -u src/share/locale/ctype/en_US.UTF-8.src:1.9 src/share/locale/ctype/en_US.UTF-8.src:1.10 --- src/share/locale/ctype/en_US.UTF-8.src:1.9 Tue Dec 20 23:08:51 2022 +++ src/share/locale/ctype/en_US.UTF-8.src Wed Dec 21 06:25:35 2022 @@ -1,4 +1,4 @@ -/* $NetBSD: en_US.UTF-8.src,v 1.9 2022/12/20 23:08:51 wiz Exp $ */ +/* $NetBSD: en_US.UTF-8.src,v 1.10 2022/12/21 06:25:35 wiz Exp $ */ /* * COPYRIGHT AND PERMISSION NOTICE @@ -40,7 +40,7 @@ ENCODING"UTF8" VARIABLECODESET=UTF-8 -/* Unicode Version 14.0.0 */ +/* Unicode Version 15.0.0 */ /* * U+ - U+007F : Basic Latin @@ -1192,9 +1192,9 @@ TODIGIT < 0x0bf2 1000 > * U+0C00 - U+0C7F : Telugu */ -ALPHA 0x0c00 - 0x0c03 0x0c05 - 0x0c0c 0x0c0e - 0x0c10 0x0c12 - 0x0c28 -ALPHA 0x0c2a - 0x0c39 0x0c3d - 0x0c44 0x0c46 - 0x0c48 0x0c4a - 0x0c4c -ALPHA 0x0c55 - 0x0c56 0x0c58 - 0x0c5a 0x0c5d 0x0c60 - 0x0c63 +ALPHA 0x0c00 - 0x0c0c 0x0c0e - 0x0c10 0x0c12 - 0x0c28 0x0c2a - 0x0c39 +ALPHA 0x0c3d - 0x0c44 0x0c46 - 0x0c48 0x0c4a - 0x0c4c 0x0c55 - 0x0c56 +ALPHA 0x0c58 - 0x0c5a 0x0c5d 0x0c60 - 0x0c63 DIGIT 0x0c66 - 0x0c6f GRAPH 0x0c00 - 0x0c0c 0x0c0e - 0x0c10 0x0c12 - 0x0c28 0x0c2a - 0x0c39 GRAPH 0x0c3c - 0x0c44 0x0c46 - 0x0c48 0x0c4a - 0x0c4d 0x0c55 - 0x0c56 @@ -1205,7 +1205,7 @@ PRINT 0x0c00 - 0x0c0c 0x0c0e - 0x0c PRINT 0x0c3c - 0x0c44 0x0c46 - 0x0c48 0x0c4a - 0x0c4d 0x0c55 - 0x0c56 PRINT 0x0c58 - 0x0c5a 0x0c5d 0x0c60 - 0x0c63 0x0c66 - 0x0c6f PRINT 0x0c77 - 0x0c7f -SPECIAL 0x0c04 0x0c3c 0x0c4d 0x0c78 - 0x0c7e +SPECIAL 0x0c3c 0x0c4d 0x0c78 - 0x0c7e SWIDTH0 0x0c00 0x0c04 0x0c3c 0x0c3e - 0x0c40 0x0c46 - 0x0c48 SWIDTH0 0x0c4a - 0x0c4d 0x0c55 - 0x0c56 0x0c62 - 0x0c63 SWIDTH1 0x0c01 - 0x0c03 0x0c05 - 0x0c0c 0x0c0e - 0x0c10 0x0c12 - 0x0c28 @@ -1223,23 +1223,23 @@ TODIGIT < 0x0c7c - 0x0c7e : 1 > ALPHA 0x0c80 - 0x0c83 0x0c85 - 0x0c8c 0x0c8e - 0x0c90 0x0c92 - 0x0ca8 ALPHA 0x0caa - 0x0cb3 0x0cb5 - 0x0cb9 0x0cbd - 0x0cc4 0x0cc6 - 0x0cc8 ALPHA 0x0cca - 0x0ccc 0x0cd5 - 0x0cd6 0x0cdd - 0x0cde 0x0ce0 - 0x0ce3 -ALPHA 0x0cf1 - 0x0cf2 +ALPHA 0x0cf1 - 0x0cf3 DIGIT 0x0ce6 - 0x0cef GRAPH 0x0c80 - 0x0c8c 0x0c8e - 0x0c90 0x0c92 - 0x0ca8 0x0caa - 0x0cb3 GRAPH 0x0cb5 - 0x0cb9 0x0cbc - 0x0cc4 0x0cc6 - 0x0cc8 0x0cca - 0x0ccd GRAPH 0x0cd5 - 0x0cd6 0x0cdd - 0x0cde 0x0ce0 - 0x0ce3 0x0ce6 - 0x0cef -GRAPH 0x0cf1 - 0x0cf2 +GRAPH 0x0cf1 - 0x0cf3 PUNCT 0x0c84 PRINT 0x0c80 - 0x0c8c 0x0c8e - 0x0c90 0x0c92 - 0x0ca8 0x0caa - 0x0cb3 PRINT 0x0cb5 - 0x0cb9 0x0cbc - 0x0cc4 0x0cc6 - 0x0cc8 0x0cca - 0x0ccd PRINT 0x0cd5 - 0x0cd6 0x0cdd - 0x0cde 0x0ce0 - 0x0ce3 0x0ce6 - 0x0cef -PRINT 0x0cf1 - 0x0cf2 +PRINT 0x0cf1 - 0x0cf3 SPECIAL 0x0cbc 0x0ccd SWIDTH0 0x0c81 0x0cbc 0x0cbf 0x0cc6 0x0ccc - 0x0ccd 0x0ce2 - 0x0ce3 SWIDTH1 0x0c80 0x0c82 - 0x0c8c 0x0c8e - 0x0c90 0x0c92 - 0x0ca8 SWIDTH1 0x0caa - 0x0cb3 0x0cb5 - 0x0cb9 0x0cbd - 0x0cbe 0x0cc0 - 0x0cc4 SWIDTH1 0x0cc7 - 0x0cc8 0x0cca - 0x0ccb 0x0cd5 - 0x0cd6 0x0cdd - 0x0cde -SWIDTH1 0x0ce0 - 0x0ce1 0x0ce6 - 0x0cef 0x0cf1 - 0x0cf2 +SWIDTH1 0x0ce0 - 0x0ce1 0x0ce6 - 0x0cef 0x0cf1 - 0x0cf3 TODIGIT < 0x0ce6 - 0x0cef : 0x > @@ -1314,13 +1314,13 @@ ALPHA 0x0ea7 - 0x0eb9 0x0ebb - 0x0e ALPHA 0x0edc - 0x0edf DIGIT 0x0ed0 - 0x0ed9 GRAPH 0x0e81 - 0x0e82 0x0e84 0x0e86 - 0x0e8a 0x0e8c - 0x0ea3 0x0ea5 -GRAPH 0x0ea7 - 0x0ebd 0x0ec0 - 0x0ec4 0x0ec6 0x0ec8 - 0x0ecd +GRAPH 0x0ea7 - 0x0ebd 0x0ec0 - 0x0ec4 0x0ec6 0x0ec8 - 0x0ece GRAPH 0x0ed0 - 0x0ed9 0x0edc - 0x0edf PRINT 0x0e81 - 0x0e82 0x0e84 0x0e86 - 0x0e8a 0x0e8c - 0x0ea3 0x0ea5 -PRINT 0x0ea7 - 0x0ebd 0x0ec0 - 0x0ec4 0x0ec6 0x0ec8 - 0x0ecd +PRINT 0x0ea7 - 0x0ebd 0x0ec0 - 0x0ec4 0x0ec6 0x0ec8 - 0x0ece PRINT 0x0ed0 - 0x0ed9 0x0edc - 0x0edf -SPECIAL 0x0eba 0x0ec8 - 0x0ecc -SWIDTH0 0x0eb1 0x0eb4 - 0x0ebc 0x0ec8 - 0x0ecd +SPECIAL 0x0eba 0x0ec8 - 0x0ecc 0x0ece +SWIDTH0 0x0eb1 0x0eb4 - 0x0ebc 0x0ec8 - 0x0ece SWIDTH1 0x0e81 - 0x0e82 0x0e84 0x0e86 - 0x0e8a 0x0e8c - 0x0ea3 0x0ea5 SWIDTH1 0x0ea7 - 0x0eb0 0x0eb2 - 0x0eb3 0x0ebd 0x0ec0 - 0x0ec4 0x0ec6 SWIDTH1 0x0ed0 - 0x0ed9 0x0edc - 0x0edf @@ -1331,7 +1331,7 @@ TODIGIT < 0x0ed0 - 0x0ed9 : 0x > * U+0F00 - U+0FFF : Tibetan */ -ALPHA 0x0f00 0x0f40 - 0x0f47 0x0f49 - 0x0f6c
CVS commit: src/share/locale/ctype
Module Name:src Committed By: wiz Date: Wed Dec 21 06:25:35 UTC 2022 Modified Files: src/share/locale/ctype: en_US.UTF-8.src Log Message: Update Unicode tables to 15.0.0. This is based on the tables provided by perl 5.37.7. To generate a diff of this commit: cvs rdiff -u -r1.9 -r1.10 src/share/locale/ctype/en_US.UTF-8.src Please note that diffs are not public domain; they are subject to the copyright notices on the relevant files.
CVS commit: src/share/locale/ctype
Module Name:src Committed By: wiz Date: Tue Dec 20 23:08:51 UTC 2022 Modified Files: src/share/locale/ctype: en_US.UTF-8.src Log Message: Update Unicode tables. These tables are for Unicode 14.0.0 using the data provided with perl 5.36.0. To generate a diff of this commit: cvs rdiff -u -r1.8 -r1.9 src/share/locale/ctype/en_US.UTF-8.src Please note that diffs are not public domain; they are subject to the copyright notices on the relevant files. Modified files: Index: src/share/locale/ctype/en_US.UTF-8.src diff -u src/share/locale/ctype/en_US.UTF-8.src:1.8 src/share/locale/ctype/en_US.UTF-8.src:1.9 --- src/share/locale/ctype/en_US.UTF-8.src:1.8 Tue Dec 20 23:06:08 2022 +++ src/share/locale/ctype/en_US.UTF-8.src Tue Dec 20 23:08:51 2022 @@ -1,5 +1,4 @@ -/* $NetBSD: en_US.UTF-8.src,v 1.8 2022/12/20 23:06:08 wiz Exp $ */ -/* $OpenBSD: en_US.UTF-8.src,v 1.12 2021/05/16 22:48:05 afresh1 Exp $ */ +/* $NetBSD: en_US.UTF-8.src,v 1.9 2022/12/20 23:08:51 wiz Exp $ */ /* * COPYRIGHT AND PERMISSION NOTICE @@ -41,7 +40,7 @@ ENCODING"UTF8" VARIABLECODESET=UTF-8 -/* Unicode Version 13.0.0 */ +/* Unicode Version 14.0.0 */ /* * U+ - U+007F : Basic Latin @@ -907,14 +906,14 @@ ALPHA 0x06d5 - 0x06dc 0x06e1 - 0x06 ALPHA 0x06ff CONTROL 0x061c DIGIT 0x0660 - 0x0669 0x06f0 - 0x06f9 -GRAPH 0x0600 - 0x061c 0x061e - 0x06ff -PUNCT 0x0606 - 0x060f 0x061b 0x061e - 0x061f 0x066a - 0x066d 0x06d4 +GRAPH 0x0600 - 0x06ff +PUNCT 0x0606 - 0x060f 0x061b 0x061d - 0x061f 0x066a - 0x066d 0x06d4 PUNCT 0x06de 0x06e9 0x06fd - 0x06fe -PRINT 0x0600 - 0x061c 0x061e - 0x06ff +PRINT 0x0600 - 0x06ff SPECIAL 0x0600 - 0x0605 0x0658 0x06dd 0x06df - 0x06e0 0x06ea - 0x06ec SWIDTH0 0x0600 - 0x0605 0x0610 - 0x061a 0x061c 0x064b - 0x065f 0x0670 SWIDTH0 0x06d6 - 0x06dd 0x06df - 0x06e4 0x06e7 - 0x06e8 0x06ea - 0x06ed -SWIDTH1 0x0606 - 0x060f 0x061b 0x061e - 0x064a 0x0660 - 0x066f +SWIDTH1 0x0606 - 0x060f 0x061b 0x061d - 0x064a 0x0660 - 0x066f SWIDTH1 0x0671 - 0x06d5 0x06de 0x06e5 - 0x06e6 0x06e9 0x06ee - 0x06ff TODIGIT < 0x0660 - 0x0669 : 0x > @@ -1006,21 +1005,28 @@ SWIDTH1 0x0860 - 0x086a /* - * U+0870 - U+089F : No_Block + * U+0870 - U+089F : Arabic Extended-B */ +ALPHA 0x0870 - 0x0887 0x0889 - 0x088e +GRAPH 0x0870 - 0x088e 0x0890 - 0x0891 0x0898 - 0x089f +PUNCT 0x0888 +PRINT 0x0870 - 0x088e 0x0890 - 0x0891 0x0898 - 0x089f +SPECIAL 0x0890 - 0x0891 0x0898 - 0x089f +SWIDTH0 0x0890 - 0x0891 0x0898 - 0x089f +SWIDTH1 0x0870 - 0x088e + /* * U+08A0 - U+08FF : Arabic Extended-A */ -ALPHA 0x08a0 - 0x08b4 0x08b6 - 0x08c7 0x08d4 - 0x08df 0x08e3 - 0x08e9 -ALPHA 0x08f0 - 0x08ff -GRAPH 0x08a0 - 0x08b4 0x08b6 - 0x08c7 0x08d3 - 0x08ff -PRINT 0x08a0 - 0x08b4 0x08b6 - 0x08c7 0x08d3 - 0x08ff -SPECIAL 0x08d3 0x08e0 - 0x08e2 0x08ea - 0x08ef -SWIDTH0 0x08d3 - 0x08ff -SWIDTH1 0x08a0 - 0x08b4 0x08b6 - 0x08c7 +ALPHA 0x08a0 - 0x08c9 0x08d4 - 0x08df 0x08e3 - 0x08e9 0x08f0 - 0x08ff +GRAPH 0x08a0 - 0x08ff +PRINT 0x08a0 - 0x08ff +SPECIAL 0x08ca - 0x08d3 0x08e0 - 0x08e2 0x08ea - 0x08ef +SWIDTH0 0x08ca - 0x08ff +SWIDTH1 0x08a0 - 0x08c9 /* @@ -1188,20 +1194,22 @@ TODIGIT < 0x0bf2 1000 > ALPHA 0x0c00 - 0x0c03 0x0c05 - 0x0c0c 0x0c0e - 0x0c10 0x0c12 - 0x0c28 ALPHA 0x0c2a - 0x0c39 0x0c3d - 0x0c44 0x0c46 - 0x0c48 0x0c4a - 0x0c4c -ALPHA 0x0c55 - 0x0c56 0x0c58 - 0x0c5a 0x0c60 - 0x0c63 +ALPHA 0x0c55 - 0x0c56 0x0c58 - 0x0c5a 0x0c5d 0x0c60 - 0x0c63 DIGIT 0x0c66 - 0x0c6f GRAPH 0x0c00 - 0x0c0c 0x0c0e - 0x0c10 0x0c12 - 0x0c28 0x0c2a - 0x0c39 -GRAPH 0x0c3d - 0x0c44 0x0c46 - 0x0c48 0x0c4a - 0x0c4d 0x0c55 - 0x0c56 -GRAPH 0x0c58 - 0x0c5a 0x0c60 - 0x0c63 0x0c66 - 0x0c6f 0x0c77 - 0x0c7f +GRAPH 0x0c3c - 0x0c44 0x0c46 - 0x0c48 0x0c4a - 0x0c4d 0x0c55 - 0x0c56 +GRAPH 0x0c58 - 0x0c5a 0x0c5d 0x0c60 - 0x0c63 0x0c66 - 0x0c6f +GRAPH 0x0c77 - 0x0c7f PUNCT 0x0c77 0x0c7f PRINT 0x0c00 - 0x0c0c 0x0c0e - 0x0c10 0x0c12 - 0x0c28 0x0c2a - 0x0c39 -PRINT 0x0c3d - 0x0c44 0x0c46 - 0x0c48 0x0c4a - 0x0c4d 0x0c55 - 0x0c56 -PRINT 0x0c58 - 0x0c5a 0x0c60 - 0x0c63 0x0c66 - 0x0c6f 0x0c77 - 0x0c7f -SPECIAL 0x0c04 0x0c4d 0x0c78 - 0x0c7e -SWIDTH0 0x0c00 0x0c04 0x0c3e - 0x0c40 0x0c46 - 0x0c48 0x0c4a - 0x0c4d -SWIDTH0 0x0c55 - 0x0c56 0x0c62 - 0x0c63 +PRINT 0x0c3c - 0x0c44 0x0c46 - 0x0c48 0x0c4a - 0x0c4d 0x0c55 - 0x0c56 +PRINT 0x0c58 - 0x0c5a 0x0c5d 0x0c60 - 0x0c63 0x0c66 - 0x0c6f +PRINT 0x0c77 - 0x0c7f +SPECIAL 0x0c04 0x0c3c 0x0c4d 0x0c78 - 0x0c7e +SWIDTH0 0x0c00 0x0c04 0x0c3c 0x0c3e - 0x0c40 0x0c46 - 0x0c48 +SWIDTH0 0x0c4a - 0x0c4d 0x0c55 - 0x0c56 0x0c62 - 0x0c63 SWIDTH1 0x0c01 - 0x0c03 0x0c05 - 0x0c0c 0x0c0e - 0x0c10 0x0c12 - 0x0c28 -SWIDTH1 0x0c2a - 0x0c39 0x0c3d 0x0c41 - 0x0c44 0x0c58 - 0x0c5a +SWIDTH1
CVS commit: src/share/locale/ctype
Module Name:src Committed By: wiz Date: Tue Dec 20 23:08:51 UTC 2022 Modified Files: src/share/locale/ctype: en_US.UTF-8.src Log Message: Update Unicode tables. These tables are for Unicode 14.0.0 using the data provided with perl 5.36.0. To generate a diff of this commit: cvs rdiff -u -r1.8 -r1.9 src/share/locale/ctype/en_US.UTF-8.src Please note that diffs are not public domain; they are subject to the copyright notices on the relevant files.
CVS commit: src/share/locale/ctype
Module Name:src Committed By: wiz Date: Tue Dec 20 23:07:57 UTC 2022 Modified Files: src/share/locale/ctype: gen_ctype_utf8.pl Log Message: Add NetBSD RCS Id header instead of OpenBSD one. To generate a diff of this commit: cvs rdiff -u -r1.1 -r1.2 src/share/locale/ctype/gen_ctype_utf8.pl Please note that diffs are not public domain; they are subject to the copyright notices on the relevant files.
CVS commit: src/share/locale/ctype
Module Name:src
Committed By: wiz
Date: Tue Dec 20 23:07:57 UTC 2022
Modified Files:
src/share/locale/ctype: gen_ctype_utf8.pl
Log Message:
Add NetBSD RCS Id header instead of OpenBSD one.
To generate a diff of this commit:
cvs rdiff -u -r1.1 -r1.2 src/share/locale/ctype/gen_ctype_utf8.pl
Please note that diffs are not public domain; they are subject to the
copyright notices on the relevant files.
Modified files:
Index: src/share/locale/ctype/gen_ctype_utf8.pl
diff -u src/share/locale/ctype/gen_ctype_utf8.pl:1.1 src/share/locale/ctype/gen_ctype_utf8.pl:1.2
--- src/share/locale/ctype/gen_ctype_utf8.pl:1.1 Tue Dec 20 23:06:08 2022
+++ src/share/locale/ctype/gen_ctype_utf8.pl Tue Dec 20 23:07:57 2022
@@ -47,7 +47,7 @@ my @maps = qw(
my ( $blocks_ranges_ref, $blocks_maps_ref ) = prop_invmap("Block");
-print "/*\t\$" . 'OpenBSD' . "\$\t*/\n";
+print "/*\t\$" . 'NetBSD' . "\$\t*/\n";
print <<'EOL';
/*
CVS commit: src/share/locale/ctype
Module Name:src Committed By: wiz Date: Tue Dec 20 23:06:08 UTC 2022 Modified Files: src/share/locale/ctype: en_US.UTF-8.src Added Files: src/share/locale/ctype: gen_ctype_utf8.pl Log Message: Update unicode tables. This version of the file, and the generator script, come from OpenBSD. The script was written by Andrew Fresh. The file covers the encodings from Unicode 13.0.0, based on the files distributed with perl 5.32.1. To generate a diff of this commit: cvs rdiff -u -r1.7 -r1.8 src/share/locale/ctype/en_US.UTF-8.src cvs rdiff -u -r0 -r1.1 src/share/locale/ctype/gen_ctype_utf8.pl Please note that diffs are not public domain; they are subject to the copyright notices on the relevant files.
CVS commit: src/share/locale/ctype
Module Name:src Committed By: rin Date: Mon Oct 17 11:20:30 UTC 2022 Modified Files: src/share/locale/ctype: en_US.UTF-8.src Log Message: Add "Emoji & Pictographs" character definitions from Unicode 15.0.0 (previously 10.0.0): http://www.unicode.org/charts/ They are classified as PUNCT, which has been used for characters other than blank, alphabetic, or digit ones. Glyph widths are taken from "East Asian Width": https://www.unicode.org/Public/15.0.0/ucd/EastAsianWidth.txt Characters of "F" or "W" are classified to SWIDTH2, and others are to SWIDTH1, as usual. See also: https://www.unicode.org/reports/tr11/ XXX It would be really nice if someone could check and update characters in categories other than Emoji... To generate a diff of this commit: cvs rdiff -u -r1.6 -r1.7 src/share/locale/ctype/en_US.UTF-8.src Please note that diffs are not public domain; they are subject to the copyright notices on the relevant files. Modified files: Index: src/share/locale/ctype/en_US.UTF-8.src diff -u src/share/locale/ctype/en_US.UTF-8.src:1.6 src/share/locale/ctype/en_US.UTF-8.src:1.7 --- src/share/locale/ctype/en_US.UTF-8.src:1.6 Sun Jun 3 07:54:51 2018 +++ src/share/locale/ctype/en_US.UTF-8.src Mon Oct 17 11:20:29 2022 @@ -1,4 +1,4 @@ -/* $NetBSD: en_US.UTF-8.src,v 1.6 2018/06/03 07:54:51 rin Exp $ */ +/* $NetBSD: en_US.UTF-8.src,v 1.7 2022/10/17 11:20:29 rin Exp $ */ /* $FreeBSD: /repoman/r/ncvs/src/share/mklocale/UTF-8.src,v 1.1 2004/03/27 08:14:14 tjr Exp $ */ /* @@ -1848,10 +1848,16 @@ SWIDTH1 0x25a0 - 0x25ff * U+2600 - U+26FF : Miscellaneous Symbols */ -GRAPH 0x2600 - 0x2613 0x2616 0x2617 0x2619 - 0x267d 0x2680 - 0x2689 -PUNCT 0x2600 - 0x2613 0x2616 0x2617 0x2619 - 0x267d 0x2680 - 0x2689 -PRINT 0x2600 - 0x2613 0x2616 0x2617 0x2619 - 0x267d 0x2680 - 0x2689 -SWIDTH1 0x2600 - 0x2613 0x2616 0x2617 0x2619 - 0x267d 0x2680 - 0x2689 +GRAPH 0x2600 - 0x26ff +PUNCT 0x2600 - 0x26ff +PRINT 0x2600 - 0x26ff +SWIDTH1 0x2600 - 0x2613 0x2616 - 0x2647 0x2654 - 0x267e 0x2680 - 0x2692 +SWIDTH1 0x2694 - 0x26a0 0x26a2 - 0x26a9 0x26ac - 0x26bc 0x26bf - 0x26c3 +SWIDTH1 0x26c6 - 0x26cd 0x26cf - 0x26d3 0x26d5 - 0x26e9 0x26eb - 0x26f1 +SWIDTH1 0x26f4 0x26f6 - 0x26f9 0x26fb - 0x26fc 0x26fe - 0x26ff +SWIDTH2 0x2614 - 0x2615 0x2648 - 0x2653 0x267f 0x2693 0x26a1 +SWIDTH2 0x26aa - 0x26ab 0x26bd - 0x26be 0x26c4 - 0x26c5 0x26ce +SWIDTH2 0x26d4 0x26ea 0x26f2 - 0x26f3 0x26f5 0x26fa 0x26fd /* @@ -2435,28 +2441,39 @@ SWIDTH1 0x1f650 - 0x1f67f * U+1F680 - U+1F6FF : Transport and Map Symbols */ -GRAPH 0x1f680 - 0x1f6d4 0x1f6e0 - 0x1f6ec 0x1f6f0 - 0x1f6f8 -PUNCT 0x1f680 - 0x1f6d4 0x1f6e0 - 0x1f6ec 0x1f6f0 - 0x1f6f8 -PRINT 0x1f680 - 0x1f6d4 0x1f6e0 - 0x1f6ec 0x1f6f0 - 0x1f6f8 +GRAPH 0x1f680 - 0x1f6d7 0x1f6dc - 0x1f6ec 0x1f6f0 - 0x1f6fc +PUNCT 0x1f680 - 0x1f6d7 0x1f6dc - 0x1f6ec 0x1f6f0 - 0x1f6fc +PRINT 0x1f680 - 0x1f6d7 0x1f6dc - 0x1f6ec 0x1f6f0 - 0x1f6fc SWIDTH1 0x1f6c6 - 0x1f6cb 0x1f6cd - 0x1f6cf 0x1f6d3 - 0x1f6d4 SWIDTH1 0x1f6e0 - 0x1f6ea 0x1f6f0 - 0x1f6f3 -SWIDTH2 0x1f680 - 0x1f6c5 0x1f6cc 0x1f6d0 - 0x1f6d2 0x1f6eb - 0x1f6ec -SWIDTH2 0x1f6f4 - 0x1f6f8 +SWIDTH2 0x1f680 - 0x1f6c5 0x1f6cc 0x1f6d0 - 0x1f6d2 0x1f6d5 - 0x1f6d7 +SWIDTH2 0x1f6dc - 0x1f6df 0x1f6eb - 0x1f6ec 0x1f6f4 - 0x1f6fc /* * U+1F900 - U+1F9FF : Supplemental Symbols and Pictographs */ -GRAPH 0x1f900 - 0x1f90b 0x1f910 - 0x1f93e 0x1f940 - 0x1f94c -GRAPH 0x1f950 - 0x1f96b 0x1f980 - 0x1f997 0x1f9c0 0x1f9d0 - 0x1f9e6 -PUNCT 0x1f900 - 0x1f90b 0x1f910 - 0x1f93e 0x1f940 - 0x1f94c -PUNCT 0x1f950 - 0x1f96b 0x1f980 - 0x1f997 0x1f9c0 0x1f9d0 - 0x1f9e6 -PRINT 0x1f900 - 0x1f90b 0x1f910 - 0x1f93e 0x1f940 - 0x1f94c -PRINT 0x1f950 - 0x1f96b 0x1f980 - 0x1f997 0x1f9c0 0x1f9d0 - 0x1f9e6 -SWIDTH1 0x1f900 - 0x1f90b -SWIDTH2 0x1f910 - 0x1f93e 0x1f940 - 0x1f94c 0x1f950 - 0x1f96b -SWIDTH2 0x1f980 - 0x1f997 0x1f9c0 0x1f9d0 - 0x1f9e6 +GRAPH 0x1f900 - 0x1f9ff +PUNCT 0x1f900 - 0x1f9ff +PRINT 0x1f900 - 0x1f9ff +SWIDTH1 0x1f900 - 0x1f90b 0x1f93b 0x1f946 +SWIDTH2 0x1f90c - 0x1f93a 0x1f93c - 0x1f945 0x1f947 - 0x1f9ff + + +/* + * U+1FA70 - U+1FAFF : Symbols and Pictographs Extended-A + */ + +GRAPH 0x1fa70 - 0x1fa7c 0x1fa80 - 0x1fa88 0x1fa90 - 0x1fabd +GRAPH 0x1fabf - 0x1fac5 0x1face - 0x1fadb 0x1fae0 - 0x1fae8 +GRAPH 0x1faf0 - 0x1faf8 +PUNCT 0x1fa70 - 0x1fa7c 0x1fa80 - 0x1fa88 0x1fa90 - 0x1fabd +PUNCT 0x1fabf - 0x1fac5 0x1face - 0x1fadb 0x1fae0 - 0x1fae8 +PUNCT 0x1faf0 - 0x1faf8 +SWIDTH2 0x1fa70 - 0x1fa7c 0x1fa80 - 0x1fa88 0x1fa90 - 0x1fabd +SWIDTH2 0x1fabf - 0x1fac5 0x1face - 0x1fadb 0x1fae0 - 0x1fae8 +SWIDTH2 0x1faf0 - 0x1faf8 /*
CVS commit: src/share/locale/ctype
Module Name:src Committed By: rin Date: Mon Oct 17 11:20:30 UTC 2022 Modified Files: src/share/locale/ctype: en_US.UTF-8.src Log Message: Add "Emoji & Pictographs" character definitions from Unicode 15.0.0 (previously 10.0.0): http://www.unicode.org/charts/ They are classified as PUNCT, which has been used for characters other than blank, alphabetic, or digit ones. Glyph widths are taken from "East Asian Width": https://www.unicode.org/Public/15.0.0/ucd/EastAsianWidth.txt Characters of "F" or "W" are classified to SWIDTH2, and others are to SWIDTH1, as usual. See also: https://www.unicode.org/reports/tr11/ XXX It would be really nice if someone could check and update characters in categories other than Emoji... To generate a diff of this commit: cvs rdiff -u -r1.6 -r1.7 src/share/locale/ctype/en_US.UTF-8.src Please note that diffs are not public domain; they are subject to the copyright notices on the relevant files.
CVS commit: src/share/locale/ctype
Module Name:src Committed By: rin Date: Sun Jun 3 07:54:51 UTC 2018 Modified Files: src/share/locale/ctype: en_US.UTF-8.src Log Message: Add characters in "Emoji & Pictographs" from Unicode 10.0.0: http://www.unicode.org/charts/ They are classified as PUNCT, which is historically used for characters other than blank, alphabetic, or digit ones. Glyph widths are taken from "East Asian Width": https://www.unicode.org/Public/10.0.0/ucd/EastAsianWidth.txt Characters of "F" or "W" are classified to SWIDTH2, and others are classified to SWIDTH1, as implicitly done in the previous revisions. Should address problems like PR bin/53323. Discussed with soda@. We thank Takuya SHIOZAKI (tshiozak@) for useful comments. To generate a diff of this commit: cvs rdiff -u -r1.5 -r1.6 src/share/locale/ctype/en_US.UTF-8.src Please note that diffs are not public domain; they are subject to the copyright notices on the relevant files.
CVS commit: src/share/locale/ctype
Module Name:src Committed By: rin Date: Sun Jun 3 07:54:51 UTC 2018 Modified Files: src/share/locale/ctype: en_US.UTF-8.src Log Message: Add characters in "Emoji & Pictographs" from Unicode 10.0.0: http://www.unicode.org/charts/ They are classified as PUNCT, which is historically used for characters other than blank, alphabetic, or digit ones. Glyph widths are taken from "East Asian Width": https://www.unicode.org/Public/10.0.0/ucd/EastAsianWidth.txt Characters of "F" or "W" are classified to SWIDTH2, and others are classified to SWIDTH1, as implicitly done in the previous revisions. Should address problems like PR bin/53323. Discussed with soda@. We thank Takuya SHIOZAKI (tshiozak@) for useful comments. To generate a diff of this commit: cvs rdiff -u -r1.5 -r1.6 src/share/locale/ctype/en_US.UTF-8.src Please note that diffs are not public domain; they are subject to the copyright notices on the relevant files. Modified files: Index: src/share/locale/ctype/en_US.UTF-8.src diff -u src/share/locale/ctype/en_US.UTF-8.src:1.5 src/share/locale/ctype/en_US.UTF-8.src:1.6 --- src/share/locale/ctype/en_US.UTF-8.src:1.5 Wed Aug 8 18:40:37 2012 +++ src/share/locale/ctype/en_US.UTF-8.src Sun Jun 3 07:54:51 2018 @@ -1,4 +1,4 @@ -/* $NetBSD: en_US.UTF-8.src,v 1.5 2012/08/08 18:40:37 tnozaki Exp $ */ +/* $NetBSD: en_US.UTF-8.src,v 1.6 2018/06/03 07:54:51 rin Exp $ */ /* $FreeBSD: /repoman/r/ncvs/src/share/mklocale/UTF-8.src,v 1.1 2004/03/27 08:14:14 tjr Exp $ */ /* @@ -1858,19 +1858,15 @@ SWIDTH1 0x2600 - 0x2613 0x2616 0x261 * U+2700 - U+27BF : Dingbats */ -GRAPH 0x2701 - 0x2704 0x2706 - 0x2709 0x270c - 0x2727 0x2729 - 0x274b -GRAPH 0x274d 0x274f - 0x2752 0x2756 0x2758 - 0x275e 0x2761 - 0x2794 -GRAPH 0x2798 - 0x27af 0x27b1 - 0x27be -PUNCT 0x2701 - 0x2704 0x2706 - 0x2709 0x270c - 0x2727 0x2729 - 0x274b -PUNCT 0x274d 0x274f - 0x2752 0x2756 0x2758 - 0x275e 0x2761 - 0x2775 -PUNCT 0x2794 0x2798 - 0x27af 0x27b1 - 0x27be -PRINT 0x2701 - 0x2704 0x2706 - 0x2709 0x270c - 0x2727 0x2729 - 0x274b -PRINT 0x274d 0x274f - 0x2752 0x2756 0x2758 - 0x275e 0x2761 - 0x2794 -PRINT 0x2798 - 0x27af 0x27b1 - 0x27be +GRAPH 0x2700 - 0x27bf +PUNCT 0x2700 - 0x2775 0x2794 - 0x27bf +PRINT 0x2700 - 0x27bf SPECIAL 0x2776 - 0x2793 -SWIDTH1 0x2701 - 0x2704 0x2706 - 0x2709 0x270c - 0x2727 0x2729 - 0x274b -SWIDTH1 0x274d 0x274f - 0x2752 0x2756 0x2758 - 0x275e 0x2761 - 0x2794 -SWIDTH1 0x2798 - 0x27af 0x27b1 - 0x27be +SWIDTH1 0x2700 - 0x2704 0x2706 - 0x2709 0x270c - 0x2727 0x2729 - 0x274b +SWIDTH1 0x274d 0x274f - 0x2752 0x2756 0x2758 - 0x2794 0x2798 - 0x27af +SWIDTH1 0x27b1 - 0x27be +SWIDTH2 0x2705 0x270a - 0x270b 0x2728 0x274c 0x274e 0x2753 - 0x2755 +SWIDTH2 0x2757 0x2795 - 0x2797 0x27b0 0x27bf /* @@ -2396,6 +2392,74 @@ SWIDTH1 0x1d7ce - 0x1d7ff /* + * U+1F300 - U+1F5FF : Miscellaneous Symbols and Pictographs + */ + +GRAPH 0x1f300 - 0x1f5ff +PUNCT 0x1f300 - 0x1f5ff +PRINT 0x1f300 - 0x1f5ff +SWIDTH1 0x1f321 - 0x1f32c 0x1f336 0x1f37d 0x1f394 - 0x1f39f +SWIDTH1 0x1f3cb - 0x1f3ce 0x1f3d4 - 0x1f3df 0x1f3f1 - 0x1f3f3 +SWIDTH1 0x1f3f5 - 0x1f3f7 0x1f43f 0x1f441 0x1f4fd - 0x1f4fe +SWIDTH1 0x1f53e - 0x1f54a 0x1f54f 0x1f568 - 0x1f579 0x1f57b - 0x1f594 +SWIDTH1 0x1f597 - 0x1f5a3 0x1f5a5 - 0x1f5fa +SWIDTH2 0x1f300 - 0x1f320 0x1f32d - 0x1f335 0x1f337 - 0x1f37c +SWIDTH2 0x1f37e - 0x1f393 0x1f3a0 - 0x1f3ca 0x1f3cf - 0x1f3d3 +SWIDTH2 0x1f3e0 - 0x1f3f0 0x1f3f4 0x1f3f8 - 0x1f43e 0x1f440 +SWIDTH2 0x1f442 - 0x1f4fc 0x1f4ff - 0x1f53d 0x1f54b - 0x1f54e +SWIDTH2 0x1f550 - 0x1f567 0x1f57a 0x1f595 - 0x1f596 0x1f5a4 +SWIDTH2 0x1f5fb - 0x1f5ff + + +/* + * U+1F600 - U+1F64F : Emoticons + */ + +GRAPH 0x1f600 - 0x1f64f +PUNCT 0x1f600 - 0x1f64f +PRINT 0x1f600 - 0x1f64f +SWIDTH2 0x1f600 - 0x1f64f + + +/* + * U+1F650 - U+1F67F : Ornamental Dingbats + */ + +GRAPH 0x1f650 - 0x1f67f +PUNCT 0x1f650 - 0x1f67f +PRINT 0x1f650 - 0x1f67f +SWIDTH1 0x1f650 - 0x1f67f + + +/* + * U+1F680 - U+1F6FF : Transport and Map Symbols + */ + +GRAPH 0x1f680 - 0x1f6d4 0x1f6e0 - 0x1f6ec 0x1f6f0 - 0x1f6f8 +PUNCT 0x1f680 - 0x1f6d4 0x1f6e0 - 0x1f6ec 0x1f6f0 - 0x1f6f8 +PRINT 0x1f680 - 0x1f6d4 0x1f6e0 - 0x1f6ec 0x1f6f0 - 0x1f6f8 +SWIDTH1 0x1f6c6 - 0x1f6cb 0x1f6cd - 0x1f6cf 0x1f6d3 - 0x1f6d4 +SWIDTH1 0x1f6e0 - 0x1f6ea 0x1f6f0 - 0x1f6f3 +SWIDTH2 0x1f680 - 0x1f6c5 0x1f6cc 0x1f6d0 - 0x1f6d2 0x1f6eb - 0x1f6ec +SWIDTH2 0x1f6f4 - 0x1f6f8 + + +/* + * U+1F900 - U+1F9FF : Supplemental Symbols and Pictographs + */ + +GRAPH 0x1f900 - 0x1f90b 0x1f910 - 0x1f93e 0x1f940 - 0x1f94c +GRAPH 0x1f950 - 0x1f96b 0x1f980 - 0x1f997 0x1f9c0 0x1f9d0 - 0x1f9e6 +PUNCT 0x1f900 - 0x1f90b 0x1f910 - 0x1f93e 0x1f940 - 0x1f94c +PUNCT 0x1f950 - 0x1f96b 0x1f980 - 0x1f997 0x1f9c0 0x1f9d0 - 0x1f9e6 +PRINT 0x1f900 - 0x1f90b 0x1f910 -
CVS commit: src/share/locale/ctype
Module Name:src Committed By: tnozaki Date: Wed Aug 8 18:40:37 UTC 2012 Modified Files: src/share/locale/ctype: en_US.UTF-8.src Log Message: fix PR lib/46772 wcwidth of combining characters. patch probyted by yamt@, thanks. To generate a diff of this commit: cvs rdiff -u -r1.4 -r1.5 src/share/locale/ctype/en_US.UTF-8.src Please note that diffs are not public domain; they are subject to the copyright notices on the relevant files. Modified files: Index: src/share/locale/ctype/en_US.UTF-8.src diff -u src/share/locale/ctype/en_US.UTF-8.src:1.4 src/share/locale/ctype/en_US.UTF-8.src:1.5 --- src/share/locale/ctype/en_US.UTF-8.src:1.4 Thu Feb 10 18:12:42 2005 +++ src/share/locale/ctype/en_US.UTF-8.src Wed Aug 8 18:40:37 2012 @@ -1,4 +1,4 @@ -/* $NetBSD: en_US.UTF-8.src,v 1.4 2005/02/10 18:12:42 tnozaki Exp $ */ +/* $NetBSD: en_US.UTF-8.src,v 1.5 2012/08/08 18:40:37 tnozaki Exp $ */ /* $FreeBSD: /repoman/r/ncvs/src/share/mklocale/UTF-8.src,v 1.1 2004/03/27 08:14:14 tjr Exp $ */ /* @@ -493,7 +493,7 @@ SWIDTH1 0x02b0 - 0x02ee GRAPH 0x0300 - 0x034f 0x0360 - 0x036f PRINT 0x0300 - 0x034f 0x0360 - 0x036f -SWIDTH1 0x0300 - 0x034f 0x0360 - 0x036f +SWIDTH0 0x0300 - 0x034f 0x0360 - 0x036f MAPUPPER 0x0345 0x0399
CVS commit: src/share/locale/ctype
Module Name:src Committed By: tnozaki Date: Wed Aug 8 18:40:37 UTC 2012 Modified Files: src/share/locale/ctype: en_US.UTF-8.src Log Message: fix PR lib/46772 wcwidth of combining characters. patch probyted by yamt@, thanks. To generate a diff of this commit: cvs rdiff -u -r1.4 -r1.5 src/share/locale/ctype/en_US.UTF-8.src Please note that diffs are not public domain; they are subject to the copyright notices on the relevant files.
