summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorbjoern <bjoern@localhost>2005-08-18 18:20:52 +0000
committerbjoern <bjoern@localhost>2005-08-18 18:20:52 +0000
commitd312880e5f347fa46b19b945ce7e9ed6f41574c8 (patch)
treea2d6dd96ef0c4425c918e05510a0c8390266fa44
parent01562ade78c9bc0706bd2c2079b98ebbb2b2468d (diff)
downloadmarkup-validator-d312880e5f347fa46b19b945ce7e9ed6f41574c8.zip
markup-validator-d312880e5f347fa46b19b945ce7e9ed6f41574c8.tar.gz
markup-validator-d312880e5f347fa46b19b945ce7e9ed6f41574c8.tar.bz2
Use Encode::Alias to restore support for some charset names
-rwxr-xr-xhttpd/cgi-bin/check30
1 files changed, 28 insertions, 2 deletions
diff --git a/httpd/cgi-bin/check b/httpd/cgi-bin/check
index c02e4c5..f06af2f 100755
--- a/httpd/cgi-bin/check
+++ b/httpd/cgi-bin/check
@@ -9,7 +9,7 @@
# This source code is available under the license at:
# http://www.w3.org/Consortium/Legal/copyright-software
#
-# $Id: check,v 1.443 2005-08-18 03:45:08 bjoern Exp $
+# $Id: check,v 1.444 2005-08-18 18:20:52 bjoern Exp $
#
# Disable buffering on STDOUT!
@@ -48,6 +48,7 @@ use HTTP::Headers::Auth qw(); # Needs to be imported after other HTTP::*.
use URI qw();
use URI::Escape qw(uri_escape);
use Encode qw();
+use Encode::Alias qw();
use HTML::Encoding 0.52 qw();
use SGML::Parser::OpenSP 0.99 qw();
@@ -189,7 +190,7 @@ Directory not readable (permission denied): @_r
#
# Strings
- $VERSION = q$Revision: 1.443 $;
+ $VERSION = q$Revision: 1.444 $;
$VERSION =~ s/Revision: ([\d\.]+) /$1/;
#
@@ -450,6 +451,31 @@ unless ($File->{Charset}->{Use}) { # No charset given...
&abort_if_error_flagged($File, O_CHARSET|O_DOCTYPE);
#
+# Encode alias definitions. This might not be the best
+# place for them, feel free to move them elsewhere.
+
+# implicit bidi, but character encoding is the same
+Encode::Alias::define_alias('iso-8859-6-i', 'iso-8859-6');
+
+# implicit bidi, but character encoding is the same
+Encode::Alias::define_alias('iso-8859-8-i', 'iso-8859-8');
+
+# 0xA0 is U+00A0 in ISO-8859-11 but undefined in tis-620
+# other than that the character encodings are equivalent
+Encode::Alias::define_alias('tis-620', 'iso-8859-11');
+
+# Encode::Byte does not know 'macintosh' but MacRoman
+Encode::Alias::define_alias('macintosh', 'MacRoman');
+
+# x-mac-roman is the non-standard version of 'macintosh'
+Encode::Alias::define_alias('x-mac-roman', 'MacRoman');
+
+# Encode only knows the long hand version of 'ksc_5601'
+Encode::Alias::define_alias('ksc_5601', 'KS_C_5601-1987');
+
+# gb18030 requires Encode::HanExtra but no additional alias
+
+#
# Always transcode, even if the content claims to be UTF-8
$File = transcode($File);
&abort_if_error_flagged($File, O_CHARSET);