- From: Ville Skytta via cvs-syncmail <cvsmail@w3.org>
- Date: Mon, 29 Jun 2009 19:57:53 +0000
- To: www-validator-cvs@w3.org
Update of /sources/public/validator/httpd/cgi-bin In directory hutz:/tmp/cvs-serv25579/httpd/cgi-bin Modified Files: check Log Message: Move Encode alias definitions to charset.cfg, register also our non-recommended but recognized aliases. Index: check =================================================================== RCS file: /sources/public/validator/httpd/cgi-bin/check,v retrieving revision 1.664 retrieving revision 1.665 diff -u -d -r1.664 -r1.665 --- check 29 Jun 2009 18:21:16 -0000 1.664 +++ check 29 Jun 2009 19:57:51 -0000 1.665 @@ -191,6 +191,12 @@ } # + # Register Encode aliases. + while (my ($key, $value) = each %{$CFG->{Charsets}}) { + Encode::Alias::define_alias($key, $1) if ($value =~ /^[AX] (\S+)/); + } + + # # Set debug flag. if ($CFG->{'Allow Debug'}) { $DEBUG = TRUE if $ENV{W3C_VALIDATOR_DEBUG} || $CFG->{'Enable Debug'}; @@ -568,31 +574,6 @@ # Abort if an error was flagged while finding the encoding. &abort_if_error_flagged($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 - $File->{Charset}->{Default} = FALSE; unless ($File->{Charset}->{Use}) { # No charset given... $File->{Charset}->{Use} = 'utf-8'; @@ -601,7 +582,6 @@ &add_warning('W04', {W04_charset => "UTF-8"}); } - # Always transcode, even if the content claims to be UTF-8 $File = transcode($File); if (($File->{ContentType} eq "text/html") and ($File->{Charset}->{Default}) and $File->{'Error Flagged'}) {
Received on Monday, 29 June 2009 19:58:06 UTC