W3C home > Mailing lists > Public > www-validator-cvs@w3.org > September 2004

validator/httpd/cgi-bin check,1.342,1.343

From: Martin Duerst <duerst@dev.w3.org>
Date: Wed, 22 Sep 2004 00:40:42 +0000
To: www-validator-cvs@w3.org
Message-ID: <E1C9vBa-00062E-DN@lionel-hutz.w3.org>

Update of /sources/public/validator/httpd/cgi-bin
In directory hutz:/tmp/cvs-serv23184

Modified Files:
	check 
Log Message:
spliting up &preparse into two subs

Index: check
===================================================================
RCS file: /sources/public/validator/httpd/cgi-bin/check,v
retrieving revision 1.342
retrieving revision 1.343
diff -u -d -r1.342 -r1.343
--- check	17 Sep 2004 14:36:23 -0000	1.342
+++ check	22 Sep 2004 00:40:40 -0000	1.343
@@ -440,7 +440,7 @@
 #
 # Try to extract META charset
 # (works only if ascii-based and reasonably clean before <meta>)
-$File = &preparse($File);
+$File = &preparse_meta($File);
 unless ($File->{Charset}->{Use}) {
   $File->{Charset}->{Use} = $File->{Charset}->{META};
 }
@@ -607,7 +607,7 @@
 
 #
 # Try to extract a DOCTYPE or xmlns.
-$File = &preparse($File);
+$File = &preparse_doctype($File);
 
 
 #
@@ -1886,8 +1886,62 @@
 
 
 #
-# Do an initial parse of the Document Entity to extract charset and FPI.
-sub preparse {
+# Do an initial parse of the Document Entity to extract FPI.
+# (still also extracts charset)
+sub preparse_doctype {
+  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;
+}
+
+#
+# Do an initial parse of the Document Entity to extract charset from HTML <meta>.
+# (still also extracts FPI)
+sub preparse_meta {
   my $File = shift;
 
   #
Received on Wednesday, 22 September 2004 00:40:43 UTC

This archive was generated by hypermail 2.4.0 : Friday, 17 January 2020 23:02:07 UTC