- From: Martin Duerst <duerst@dev.w3.org>
- Date: Wed, 22 Sep 2004 00:48:39 +0000
- To: www-validator-cvs@w3.org
Update of /sources/public/validator/httpd/cgi-bin
In directory hutz:/tmp/cvs-serv21045
Modified Files:
check
Log Message:
moved preparse_meta close to other charset-related code
Index: check
===================================================================
RCS file: /sources/public/validator/httpd/cgi-bin/check,v
retrieving revision 1.344
retrieving revision 1.345
diff -u -d -r1.344 -r1.345
--- check 22 Sep 2004 00:46:12 -0000 1.344
+++ check 22 Sep 2004 00:48:37 -0000 1.345
@@ -1930,59 +1930,6 @@
}
#
-# Do an initial parse of the Document Entity to extract charset from HTML <meta>.
-# (still also extracts FPI)
-sub preparse_meta {
- my $File = shift;
-
- #
- # Reset DOCTYPE, Root, and Charset (for second invocation).
- $File->{Charset}->{META} = '';
- $File->{DOCTYPE} = '';
- $File->{Root} = '';
-
- my $dtd = sub {
- return if $File->{Root};
- ($File->{Root}, $File->{DOCTYPE}) = shift =~ m(<!DOCTYPE\s+(\w+)\s+PUBLIC\s+(?:[\'\"])([^\"\']+)(?:[\"\']).*>)si;
- };
-
- my $start = sub {
- my $tag = shift;
- my $attr = shift;
- my %attr = map {lc($_) => $attr->{$_}} keys %{$attr};
-
- if ($File->{Root}) {
- if (lc $tag eq 'meta') {
- if (lc $attr{'http-equiv'} eq 'content-type') {
- if ($attr{content} =~ m(charset\s*=[\s\"\']*([^\s;\"\'>]*))si) {
- $File->{Charset}->{META} = lc $1;
- }
- }
- }
- return unless $tag eq $File->{Root};
- } else {
- $File->{Root} = $tag;
- }
- if ($attr->{xmlns}) {$File->{Namespace} = $attr->{xmlns}};
- };
-
- my $p = HTML::Parser->new(api_version => 3);
- $p->xml_mode(TRUE);
- $p->ignore_elements('BODY');
- $p->ignore_elements('body');
- $p->handler(declaration => $dtd, 'text');
- $p->handler(start => $start, 'tag,attr');
- $p->parse(join "\n", @{$File->{Content}});
-
- $File->{DOCTYPE} = '' unless defined $File->{DOCTYPE};
- $File->{DOCTYPE} =~ s(^\s+){ }g;
- $File->{DOCTYPE} =~ s(\s+$){ }g;
- $File->{DOCTYPE} =~ s(\s+) { }g;
-
- return $File;
-}
-
-#
# Print out the raw ESIS output for debugging.
sub show_esis ($) {
print <<'EOF';
@@ -2220,6 +2167,59 @@
#
+# Do an initial parse of the Document Entity to extract charset from HTML <meta>.
+# (still also extracts FPI)
+sub preparse_meta {
+ my $File = shift;
+
+ #
+ # Reset DOCTYPE, Root, and Charset (for second invocation).
+ $File->{Charset}->{META} = '';
+ $File->{DOCTYPE} = '';
+ $File->{Root} = '';
+
+ my $dtd = sub {
+ return if $File->{Root};
+ ($File->{Root}, $File->{DOCTYPE}) = shift =~ m(<!DOCTYPE\s+(\w+)\s+PUBLIC\s+(?:[\'\"])([^\"\']+)(?:[\"\']).*>)si;
+ };
+
+ my $start = sub {
+ my $tag = shift;
+ my $attr = shift;
+ my %attr = map {lc($_) => $attr->{$_}} keys %{$attr};
+
+ if ($File->{Root}) {
+ if (lc $tag eq 'meta') {
+ if (lc $attr{'http-equiv'} eq 'content-type') {
+ if ($attr{content} =~ m(charset\s*=[\s\"\']*([^\s;\"\'>]*))si) {
+ $File->{Charset}->{META} = lc $1;
+ }
+ }
+ }
+ return unless $tag eq $File->{Root};
+ } else {
+ $File->{Root} = $tag;
+ }
+ if ($attr->{xmlns}) {$File->{Namespace} = $attr->{xmlns}};
+ };
+
+ my $p = HTML::Parser->new(api_version => 3);
+ $p->xml_mode(TRUE);
+ $p->ignore_elements('BODY');
+ $p->ignore_elements('body');
+ $p->handler(declaration => $dtd, 'text');
+ $p->handler(start => $start, 'tag,attr');
+ $p->parse(join "\n", @{$File->{Content}});
+
+ $File->{DOCTYPE} = '' unless defined $File->{DOCTYPE};
+ $File->{DOCTYPE} =~ s(^\s+){ }g;
+ $File->{DOCTYPE} =~ s(\s+$){ }g;
+ $File->{DOCTYPE} =~ s(\s+) { }g;
+
+ return $File;
+}
+
+#
# Check charset conflicts and add any warnings necessary.
sub charset_conflicts {
my $File = shift;
Received on Wednesday, 22 September 2004 00:48:39 UTC