diff options
| -rwxr-xr-x | httpd/cgi-bin/check | 62 |
1 files changed, 23 insertions, 39 deletions
diff --git a/httpd/cgi-bin/check b/httpd/cgi-bin/check index 302b7d1..19d63e9 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 1.157 2001-07-22 18:47:40 link Exp $ +# $Id: check,v 1.158 2001-07-22 19:33:16 link Exp $ # # We need Perl 5.004. @@ -80,9 +80,9 @@ my $element_ref = 'http://www.htmlhelp.com/reference/html40/'; # # Strings -$VERSION = q$Revision: 1.157 $; +$VERSION = q$Revision: 1.158 $; $VERSION =~ s/Revision: ([\d\.]+) /$1/; -$DATE = q$Date: 2001-07-22 18:47:40 $; +$DATE = q$Date: 2001-07-22 19:33:16 $; $MAINTAINER = 'gerald@w3.org'; $NOTICE = ''; # "<p><strong>Note: This service will be ...</strong>"; @@ -283,39 +283,11 @@ if ($q->param('charset')) { } # -# If we find a XML declaration with charset information, -# we take it into account. -# @@ needs to handle declarations that span more than one line -if (${$File->{Content}}[0] =~ - /^<\?xml[^>]*\sencoding\s*=\s*([\"\'])([A-Za-z][A-Za-z0-9._\-]*)\1/) { - $File->{XML_Charset} = lc $2; -} - -# -# If we find a META element with charset information, we take it into account. -foreach my $line (@{$File->{Content}}) { - # @@ needs to handle meta elements that span more than one line - if ($line =~ /<meta/i) { - if ($line =~ /charset\s*=[\s\"\']*([^\s;\"\'>]*)/i) { - $File->{META_Charset} = lc $1; - last; - } elsif ($line =~ /<body/i || $line =~ /<body/i) { - last; - } - } -} - -# # Figure out which charset was detected. -if ($File->{HTTP_Charset}) { - $File->{Charset} = $File->{HTTP_Charset}; -} elsif ($File->{XML_Charset}) { - $File->{Charset} = $File->{XML_Charset}; -} elsif ($File->{META_Charset}) { - $File->{Charset} = $File->{META_Charset}; -} else { - $File->{Charset} = 'unknown'; -} +if ($File->{HTTP_Charset}) {$File->{Charset} = $File->{HTTP_Charset}} +elsif ($File->{XML_Charset}) {$File->{Charset} = $File->{XML_Charset}} +elsif ($File->{META_Charset}) {$File->{Charset} = $File->{META_Charset}} +else { $File->{Charset} = 'unknown'} # Figure out which charset to use for validation. $File->{Use_Charset} = $File->{Form_Charset} ? @@ -1576,13 +1548,25 @@ EOF sub preparse { my $File = shift; - my $dtd = sub {return if $File->{Root}; ($File->{Root}, $File->{DOCTYPE}) = shift =~ m(<!DOCTYPE\s+(\w+)\s+PUBLIC\s+(?:[\'\"])([^\"\']+)(?:[\"\']).*>)si}; -# my $dtd = sub {print "DTD: ", shift(), "\n"}; -# my $pi = sub {print "PI: ", shift(), "\n"}; + my $dtd = sub { + return if $File->{Root}; + ($File->{Root}, $File->{DOCTYPE}) = shift =~ m(<!DOCTYPE\s+(\w+)\s+PUBLIC\s+(?:[\'\"])([^\"\']+)(?:[\"\']).*>)si; + }; + my $pi = sub { + my $pi = shift; + $pi =~ m(<\?xml[^>]*\sencoding\s*=\s*([\"\'])([A-Za-z][A-Za-z0-9._\-]*)\1)s; + $File->{XML_Charset} = lc $2; + }; my $start = sub { my $tag = shift; my $attr = shift; if ($File->{Root}) { + if (lc $tag eq 'meta') { + if (lc $attr->{'http-equiv'} eq 'content-type') { + $attr->{content} =~ m(charset\s*=\s*[\"\']*([^\s;\"\'>]*))s; + $File->{META_Charset} = lc $1; + } + } return unless $tag eq $File->{Root}; } else { $File->{Root} = $tag; @@ -1595,7 +1579,7 @@ sub preparse { $p->ignore_elements('BODY'); $p->ignore_elements('body'); $p->handler(declaration => $dtd, 'text'); -# $p->handler(process => $pi, 'text'); + $p->handler(process => $pi, 'text'); $p->handler(start => $start, 'tag,attr'); $p->parse(join "\n", @{$File->{Content}}); |