W3C HTML Validation Service Results

Note: This service will be ..."; umask( 022 ); my $weblint = "/usr/bin/weblint"; my $html32_doctype = qq{}; my $html40t_doctype = qq{}; my $html40f_doctype = qq{}; my $xhtmlt_doctype = qq{ plain text version strings ############################################################################# my %pub_ids = ( '-//IETF//DTD HTML Level 0//EN//2.0', 'HTML 0.0', '-//IETF//DTD HTML Strict Level 0//EN//2.0', 'Strict HTML 0.0', '-//IETF//DTD HTML 2.0 Level 1//EN', 'HTML 1.0', '-//IETF//DTD HTML 2.0 Strict Level 1//EN', 'Strict HTML 1.0', '-//IETF//DTD HTML 2.0 Strict//EN', 'Strict HTML 2.0', '-//IETF//DTD HTML 2.0//EN', 'HTML 2.0', '-//IETF//DTD HTML 2.1E//EN', 'HTML 2.1E', '-//AS//DTD HTML 3.0 asWedit + extensions//EN', 'HTML 3.0 (AdvaSoft version)', '-//IETF//DTD HTML 3.0//EN', 'HTML 3.0 (Beta)', '-//W3O//DTD W3 HTML Strict 3.0//EN//', 'Strict HTML 3.0 (Beta)', '-//Sun Microsystems Corp.//DTD HotJava HTML//EN', 'Hotjava-HTML', '-//Sun Microsystems Corp.//DTD HotJava Strict HTML//EN', 'Strict Hotjava-HTML', '-//WebTechs//DTD Mozilla HTML 2.0//EN', 'Netscape-HTML', '-//Netscape Comm. Corp. Strict//DTD HTML//EN', 'Strict Netscape-HTML', '-//Microsoft//DTD Internet Explorer 2.0 HTML//EN', 'MSIE-HTML', '-//Microsoft//DTD Internet Explorer 2.0 HTML Strict//EN', 'Strict MSIE-HTML', '-//Microsoft//DTD Internet Explorer 3.0 HTML//EN', 'MSIE 3.0 HTML', '-//Microsoft//DTD Internet Explorer 3.0 HTML Strict//EN', 'Strict MSIE 3.0 HTML', '-//OReilly and Associates//DTD HTML Extended 1.0//EN', 'O\'Reilly HTML Extended v1.0', '-//OReilly and Associates//DTD HTML Extended Relaxed 1.0//EN', 'O\'Reilly HTML Extended Relaxed v1.0', '-//IETF//DTD HTML V2.2//EN', 'HTML 2.2', '-//W3C//DTD HTML 1996-01//EN', 'HTML 1996-01', '-//W3C//DTD HTML 3.2 Final//EN', 'HTML 3.2', '-//W3C//DTD HTML Experimental 970421//EN', 'HTML 3.2 + Style', '+//Silmaril//DTD HTML Pro v0r11 19970101//EN', 'HTML Pro', '-//Spyglass//DTD HTML 2.0 Extended//EN', 'Spyglass HTML 2.0 Extended', 'http://www.w3.org/MarkUp/Cougar/Cougar.dtd', 'HTML Level "Cougar"', '-//W3C//DTD HTML 4.0//EN', 'HTML 4.0 Strict', '-//W3C//DTD HTML 4.0 Transitional//EN', 'HTML 4.0 Transitional', '-//W3C//DTD HTML 4.0 Frameset//EN', 'HTML 4.0 Frameset', '-//W3C//DTD HTML 4.01//EN', 'HTML 4.01 Strict', '-//W3C//DTD HTML 4.01 Transitional//EN', 'HTML 4.01 Transitional', '-//W3C//DTD HTML 4.01 Frameset//EN', 'HTML 4.01 Frameset', '-//W3C//DTD XHTML 1.0 Strict//EN', 'XHTML 1.0 Strict', '-//W3C//DTD XHTML 1.0 Transitional//EN', 'XHTML 1.0 Transitional', '-//W3C//DTD XHTML 1.0 Frameset//EN', 'XHTML 1.0 Frameset', 'XML', 'XML' ); ############################################################################# # Array of errors -> fragment identifiers for error explanation links ############################################################################# my %frag = ( 'entity end not allowed in comment', 'unterm-comment-1', 'name start character invalid only s and comment allowed in comment declaration', 'unterm-comment-2', 'name character invalid only s and comment allowed in comment declaration', 'unterm-comment-2', 'unknown declaration type FOO', 'bad-comment', 'character FOO not allowed in attribute specification list', 'attr-char', 'an attribute value must be a literal unless it contains only name characters', 'attr-quoted', 'syntax of attribute value does not conform to declared value', 'bad-attr-char', 'length of attribute value must not exceed LITLEN less NORMSEP', 'name-length', 'element FOO undefined', 'undef-tag', 'element FOO not allowed here', 'not-allowed', 'there is no attribute FOO', 'undef-attr', 'FOO is not a member of the group specified in the declared value of this attribute', 'undef-attr-val', 'FOO is not a member of a group specified for any attribute', 'bad-abbrev-attr', 'end tag for FOO omitted but its declaration does not permit this', 'no-end-tag', 'end tag for element FOO which is not open', 'floating-close', 'end tag for FOO which is not finished', 'omitted-content', 'start tag for FOO omitted but its declaration does not permit this', 'no-start-tag', 'general entity FOO not defined and no default entity', 'bad-entity', 'non SGML character number', 'bad-char', 'cannot generate system identifier for entity FOO', 'bad-pub-id' # 'error', 'frag', # 'character data is not allowed here', 'frag', ); ############################################################################# # Set up some signal handlers in case we get killed (darned impatient people...) ############################################################################# $SIG{'TERM'} = 'erase_stuff'; $SIG{'KILL'} = 'erase_stuff'; $SIG{'PIPE'} = 'IGNORE'; # $SIG{'CHLD'} = 'erase_stuff'; ############################################################################# # Process CGI variables ############################################################################# # # Create a new CGI object. my $q = new CGI; # # Backwards compatibility; see # http://lists.w3.org/Archives/Public/www-validator/1999JulSep/0197 # http://lists.w3.org/Archives/Public/www-validator/1999JulSep/0212 if (scalar $q->param) { foreach my $param ($q->param) { $q->param($param, TRUE) unless $q->param($param); } } # # Futz the URI so "/referer" works. if ($q->path_info eq '/referer') { $q->param('uri', $q->referer); } # # Use "url" unless a "uri" was also given. if ($q->param('url') and not $q->param('uri')) { $q->param('uri', $q->param('url')); } # # Send them to the homepage unless we can extract a URI from either of the # acceptable sources: uri, url or /referer. &redirect_to_home_page unless length($q->param('uri')) > 5; # # Munge the URI to include commonly omitted prefixes/suffixes. $q->param('uri', $q->param('uri') . '/') unless $q->param('uri') =~ m(/); $q->param('uri', 'http://' . $q->param('uri')) if $q->param('uri') =~ m(^www)i; ############################################################################# # Output validation results ############################################################################# my $header = <<"EOF"; Content-Type: text/html $html40t_doctype W3C HTML Validation Service Results

(There are other types of URIs, too, but only http:// URIs are currently supported by this service.)

Sorry, I am unable to validate this document because its returned content-type was $content_type, which is not currently supported by this service.

Document Checked

Note: experimental XML support was added to this service on Aug 31, 1999, but it is not quite working yet; stay tuned to the www-validator mailing list for updates, and please do not trust this service\'s output for XML documents in the meantime.

I couldn't parse this document, because it " . "uses a public\n identifier that's not in my catalog!\n

I couldn't parse this document, because it " . "makes reference to\n a system-specific file instead of " . "simply using a public identifier\n to specify the " . "level of HTML being used.\n

To show your readers that you have taken the care to create an interoperable Web page, you may display this icon on any page that validates. Here is the HTML you could use to add this icon to your Web page:

If you like, you can download a copy of this image to keep in your local web directory, and change the HTML fragment above to reference your local image rather than the one on this server.

\n Congratulations, this document validates as the document type specified! (I don't have an icon for this one yet, sorry.)\n

If you would like to create a link to this page (i.e., this validation result) to make it easier to re-validate this page in the future or to allow others to validate your page, the URI is:

Weblint Results

Outline

Below is an outline for this document, automatically generated from the heading tags (<H1> through <H6>.)

EOF my $prevlevel = 0; my $indent = 0; my $level = 0; for (1 .. $#esis) { my $line = $esis[$_]; next unless $line =~ /^\(H([1-6])$/i; $prevlevel = $level; $level = $1; print " \n" x ($prevlevel - $level); # perl is so cool. if ($level - $prevlevel == 1) { print "

A level $i heading is missing!\n); } if ($level - $prevlevel > 1) { print "

\n"; } $line = ''; my $heading = ''; until (substr($line, 0, 3) =~ /^\)H$level/i) { $line = $esis[$_++]; if ($line =~ /^-/) { my $headcont = $line; substr($headcont, 0, 1) = " "; $headcont =~ s/\\n/ /g; $heading .= $headcont; } elsif ($line =~ /^AALT CDATA( .+)/) { my $headcont = $1; $headcont =~ s/\\n/ /g; $heading .= $headcont; } } $heading = substr($heading, 1); # chop the leading '-' or ' '. $heading =~ s/&/&/go; $heading =~ s/$heading\n"; } print " \n" x $level; print <<'EOF';

If this does not look like a real outline, it is likely that the heading tags are not being used properly. (Headings should reflect the logical structure of the document; they should not be used simply to add emphasis, or to change the font size.)

EOF } if ( $q->param('ss') ) { print <<'EOF';

Source Listing

Below is the source input I used for this validation:

EOF print "

\n";
    if ( $guessed_doctype ) {
	my $gd = "$doctype\n";
	$gd =~ s/&/&/go; $gd =~ s/\n";
}

if ($q->param('sp')) {
  print <<'EOF';
  
    
    Parse Tree
    
      Note that this feature is still under construction! I am trying to make
      this easier to read somehow, with little success.
    
EOF
    if ($q->param('noatt')) {
      print <<'EOF';
    
      I am excluding the attributes, as you requested.
    
EOF
    } else {
      print <<'EOF';
    
      It helps a bit if you select the "don't show attributes" option on the
      form.
    
EOF
    }

  my $indent   = 0;
  my $prevdata = '';

  print "\n";
  foreach my $line (@esis) {
    if ($q->param('noatt')) {
      next if $line =~ /^A/;
      next if $line =~ /^\(A$/;
      next if $line =~ /^\)A$/;
    }

    #
    # Experimental: skip data if it's only newlines and space.
    $line =~ s/\\n/ /g;
    $line =~ s/\\011/ /g;
    $line =~ s/\s+/ /g;
    next if $line =~ /^-\s*$/;

    if ($line =~ /^-/) {
      substr($line, 0, 1) = ' ';
      $prevdata .= $line;
      next;
    } elsif ($prevdata) {
      $prevdata =~ s/&/&/go;
      $prevdata =~ s/$1<\/STRONG>>/;
    $printme =~ s/^\)(.*)/<\/$1<\/STRONG>>/;
    print ' ' x $indent, $printme, "\n";
    if ($line =~ /^\(/) {
      $indent += 2;
    }
  }
  print "
\n";
}

&clean_up_and_exit;

sub output_doctype_spiel {

    print <<"EOF";

    
      You should make the first line of your HTML document a DOCTYPE
      declaration, like this:
    

          <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2//EN">
      <HTML>
	<HEAD>
	  <TITLE>Title</TITLE>
	</HEAD>

	<BODY>
	  <-- ... body of document ... -->
	</BODY>
      </HTML>

    
      Or, if you are using features from HTML 4.0,
      one of these:
    

          <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0//EN">
      <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
      <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Frameset//EN">

EOF

}

sub output_closing {

    print <<"EOF";




  
  Gerald Oskoboiny

  $cvsdate





EOF

}

sub erase_stuff {

    unlink $temp           or warn "unlink($temp) returned: $!\n";
    unlink "$temp.esis"    or warn "unlink($temp.esis) returned: $!\n";
    unlink "$temp.weblint" or warn "unlink($temp.weblint) returned: $!\n";

}

sub make_log_entry {

    my $msgindex;

    open(LOG,">>$logfile") || die "couldn't append to log: $!";
    print LOG "$ENV{REMOTE_HOST}\t$validity $version\t", $q->param('uri'), "\n";
    foreach $msgindex (keys %undef_frag) {
	print LOG "frag not defined for msgindex: $msgindex\n";
    }
    close( LOG ) || die "couldn't close log: $!";

}

sub clean_up_and_exit {

    &output_closing;
    &erase_stuff;
#    &make_log_entry;
    exit;

}

sub redirect_to_home_page {

    print "Status: 302 Moved Permanently\n";
    print "Content-Type: text/html\n";
    print "Location: http://validator.w3.org/\n\n";
    print "Moved!\n";
    print "\n";
    print "  Please see the validation service's home page.\n";
    print "\n";

    &clean_up_and_exit;

}

sub build_jump_links {

    my $text;
    my $count = 0;

    $count++ if $q->param('ss');
    $count++ if $q->param('sp');
    $count++ if $q->param('weblint');
    $count++ if $q->param('outline');

    if ( $count ) {
	$text .= "  \n    Jump to: ";
	if ( $q->param('weblint') ) {
	    $text .= "Weblint Results";
	    $count--;
	    $text .= " or " if ( $count == 1 );
	    $text .= ", "   if ( $count >  1 );
	}
	if ( $q->param('outline') ) {
	    $text .= "Outline";
	    $count--;
	    $text .= " or " if ( $count == 1 );
	    $text .= ", "   if ( $count >  1 );
	}
	if ( $q->param('ss') ) {
	    $text .= "Source Listing";
	    $count--;
	    $text .= " or " if ( $count == 1 );
	    $text .= ", "   if ( $count >  1 );
	}
	if ( $q->param('sp') ) {
	    $text .= "Parse Tree";
	}
	$text .= ".\n  \n\n";
    }
    return $text;

}

sub check_for_doctype {
    # check if the document has a doctype; if it doesn't, try to
    # guess an appropriate one given the elements used
    #
    # returns 2 values:
    #
    # first value: 0 or 1:
    #     if 0, there was a doctype already present;
    #     if 1, there wasn't a doctype
    #
    # second value:
    #     the inferred doctype, if any

    my $fileref = shift;		# a reference to @file, for efficiency
    my @file = @$fileref;		# dereference $fileref

    foreach $count (0..$#file) {
	$line = $file[$count];

	# does an HTML element precede the doctype on the same line?
	last if $line =~ /<[a-z].*//go;	# strip comments,
	    # so the next line doesn't find commented-out markup etc.
	    # (this doesn't handle multi-line comments, unfortunately)

	last if ( $line =~ /<[a-z]/i );		# found an element

    }

    # do several loops of increasing lengths to avoid iterating over
    # the whole file if possible.
    #
    # these heuristics could be improved a lot.

    foreach $line (@file[0..20]) {
	return 1, $xhtmlt_doctype if $line =~ /xmlns\s*=/i;
    }

    foreach $line (@file[0..20]) {
	return 1, $html40f_doctype if $line =~ //i;
	return 1, $html32_doctype if $line =~ /<[h0-9p]*\s*align\s*=\s*center>/i;
    }

    # no luck earlier; guess HTML 4.0 transitional
    return 1, $html40t_doctype;

}

sub print_401_auth_required_message {

    my $resource = shift;
    my $realm = shift;
    my $authHeader = shift;

    print <<"EOF";
Status: 401 Authorization Required
WWW-Authenticate: $authHeader
Connection: close
Content-Type: text/html



401 Authorization Required

Authorization Required

  Sorry, I am not authorized to access the specified URI.



  The URI you specified,



  $resource



  returned a 401 "authorization required" response when I tried
  to download it.



  You should have been prompted by your browser for a
  username/password pair; if you had supplied this information, I
  would have forwarded it to your server for authorization to
  access the resource. You can use your browser's "reload" function
  to try again, if you wish.



  Of course, you may not want to trust me with this information,
  which is fine. I can tell you that I don't log it or do
  anything else nasty with it, and you can download the source for
  this service to see what it does, but you have no guarantee
  that this is actually the code I'm using; you basically have to
  decide whether to trust me or not. :-)



  Note that you shouldn't use HTTP Basic Authentication for
  anything which really needs to be private, since the password
  goes across the network unencrypted.

EOF

}

sub print_unknown_http_error_message {

    my $uri = shift;
    my $code = shift;
    my $message = shift;

    print <<"EOF";
  
    I got the following unexpected response when trying to
    retrieve $uri:
  

  
    $code $message
  

  
    Please make sure you have entered the URI correctly.
  

EOF

}

sub output_css_validator_blurb {

    my $uri = shift;

    print <<"EOHD";
  
    If you use CSS
    in your document, you should also check
    it for validity using W3C's CSS
    Validation Service.
  

EOHD

}