diff options
| -rwxr-xr-x | htdocs/docs/errors.html | 20 | ||||
| -rw-r--r-- | htdocs/results.css | 13 | ||||
| -rwxr-xr-x | httpd/cgi-bin/check | 98 |
3 files changed, 95 insertions, 36 deletions
diff --git a/htdocs/docs/errors.html b/htdocs/docs/errors.html index 1f1869c..613a4fd 100755 --- a/htdocs/docs/errors.html +++ b/htdocs/docs/errors.html @@ -8,8 +8,8 @@ <link rel="stylesheet" type="text/css" href="/base.css" /> <meta name="keywords" content="HTML, Hypertext Markup Language, Validation, W3C HTML Validation Service" /> <meta name="description" content="W3C's easy-to-use HTML validation service, based on an SGML parser." /> - <meta name="revision" content="$Id: errors.html,v 1.7 2001-07-14 22:19:59 link Exp $" /> - <meta name="modified" content="$Date: 2001-07-14 22:19:59 $" /> + <meta name="revision" content="$Id: errors.html,v 1.8 2001-07-24 10:18:31 link Exp $" /> + <meta name="modified" content="$Date: 2001-07-24 10:18:31 $" /> </head> <body bgcolor="#FFFFFF" text="#000000" link="#0000ee" vlink="#551a8b"> @@ -559,6 +559,20 @@ the previous error referred to. </p> </dd> + <dt><a id="utf8-bom" name="utf8-bom">"UTF-8 'BOM' detected and removed"</a></dt> + <dd> + <p> + The document contained an UTF-8 encoded UNICODE Byte Order mark as + the first character and we have removed before parsing. The legality + of a UTF-8 encoded BOM in XML is controversial and many XML Processors + do not allow it. To be on the safe side you should avoid using the + BOM in UTF-8 encoded documents. + </p> + <p> + Note, though, that the BOM in <em>UTF-16</em> encoded documents + is non-controverial and handled by all conforming XML Processors. + </p> + </dd> </dl> <hr /> @@ -567,7 +581,7 @@ src="http://validator.w3.org/images/vxhtml10" height="31" width="88" align="right" border="0" alt="Valid XHTML 1.0!" /></a> <a href="/feedback.html">Webmaster</a><br /> - $Date: 2001-07-14 22:19:59 $ + $Date: 2001-07-24 10:18:31 $ </address> </body> diff --git a/htdocs/results.css b/htdocs/results.css index 4b00e1c..947b1ba 100644 --- a/htdocs/results.css +++ b/htdocs/results.css @@ -1,7 +1,7 @@ /* style sheet for the validator's results page */ -/* $Id: results.css,v 1.4 2001-06-25 19:22:09 link Exp $ */ +/* $Id: results.css,v 1.5 2001-07-24 10:18:30 link Exp $ */ .markup { color: red; @@ -30,3 +30,14 @@ td { h1.title img { vertical-align: middle; } + + +.Warning { + width: 75ex; + background: yellow; + border: solid; + border-color: black; + margin: .2em; + padding: .5em; + text-align: justify; +} diff --git a/httpd/cgi-bin/check b/httpd/cgi-bin/check index 940ae44..1637c5f 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 1.160 2001-07-24 09:54:56 link Exp $ +# $Id: check,v 1.161 2001-07-24 10:18:31 link Exp $ # # We need Perl 5.004. @@ -80,9 +80,9 @@ my $element_ref = 'http://www.htmlhelp.com/reference/html40/'; # # Strings -$VERSION = q$Revision: 1.160 $; +$VERSION = q$Revision: 1.161 $; $VERSION =~ s/Revision: ([\d\.]+) /$1/; -$DATE = q$Date: 2001-07-24 09:54:56 $; +$DATE = q$Date: 2001-07-24 10:18:31 $; $MAINTAINER = 'gerald@w3.org'; $NOTICE = ''; # "<p><strong>Note: This service will be ...</strong>"; @@ -257,10 +257,27 @@ EOF # # +# Detect and remove a UTF-8 BOM. +$File->{Content}[0] =~ s/^\xEF\xBB\xBF// + and &add_warning(<<".EOF."); + UTF-8 'BOM' detected and removed. (See the + <a href="$faqerrloc#utf8-bom">explanation</a> for details.) +.EOF. + + +# # Override DOCTYPE if user asked for it. if (defined $q->param('doctype') and not $q->param('doctype') =~ /Inline/i) { $File->{Content} = &supress_doctype($File->{Content}); unshift @{$File->{Content}}, $doctypes->{$q->param('doctype')}; + my $dtd = ent($q->param('doctype')); + &add_warning(<<".EOF."); + <strong>DOCTYPE Override in effect!</strong> Any DOCTYPE Declaration in the + document has been supressed and the DOCTYPE for «<code>$dtd</code>» + inserted instead. The document will not be Valid until you alter the source + file to reflect this new DOCTYPE. +.EOF. + $File->{Tentative} = TRUE; # Tag it as Invalid. } # @@ -352,34 +369,39 @@ if ($File->{HTTP_Charset} ne $File->{META_Charset} and $File->{HTTP_Charset} ne '' and $File->{META_Charset} ne '' and $File->{Charset} ne 'unknown') { - &add_warning( <<"EOHD"); - The character encoding specified in the HTTP - header ("<code>$File->{HTTP_Charset}</code>") is different from the one - specified in the META element ("<code>$File->{META_Charset}</code>"). - I will use "<code>$File->{Charset}</code>" for this validation. + &add_warning(<<"EOHD"); + <strong>Character Encoding mismatch!</strong> + The character encoding specified in the HTTP header + («<code>$File->{HTTP_Charset}</code>») is different from the + one specified in the META element + («<code>$File->{META_Charset}</code>»). + I will use «<code>$File->{Charset}</code>» for this validation. EOHD } elsif ($File->{HTTP_Charset} ne $File->{XML_Charset} and $File->{HTTP_Charset} ne '' and $File->{XML_Charset} ne '' and $File->{Charset} ne 'unknown') { - &add_warning( <<"EOHD"); - The character encoding specified in the HTTP - header ("<code>$File->{HTTP_Charset}</code>") is different from the one - specified in the XML declaration ("<code>$File->{XML_Charset}</code>"). - I will use "<code>$File->{Charset}</code>" for this validation. + &add_warning(<<"EOHD"); + <strong>Character Encoding mismatch!</strong> + The character encoding specified in the HTTP header + («<code>$File->{HTTP_Charset}</code>») is different from the + one specified in the XML declaration + («<code>$File->{XML_Charset}</code>»). + I will use «<code>$File->{Charset}</code>» for this validation. EOHD } if ($File->{Use_Charset} ne $File->{Charset}) { - &add_warning( <<"EOHD"); - Detected character encoding ($File->{Charset}) and - selected character encoding ($File->{Use_Charset}) - differ. Tentative validation only. + &add_warning(<<"EOHD"); + <strong>Character Encoding Override in effect!</strong> + The detected character encoding + («<code>$File->{Charset}</code>») has been supressed and the + character encoding («<code>$File->{Use_Charset}</code>») + used instead. The document will not be Valid until you alter the source + file to reflect this new Character Encoding. EOHD + $File->{Tentative} = TRUE; } -$File->{Content}[0] =~ s/^\xEF\xBB\xBF// - and &add_warning("UTF-8 'BOM' detected and removed."); - { # block for character conversion and checking my @lines; unless ($File->{Use_Charset} eq 'utf-8' or $File->{Use_Charset} eq 'unknown') { @@ -522,7 +544,7 @@ $version = $pub_ids->{$fpi} || 'unknown'; if ($File->{Type} eq 'xml' or $File->{Type} eq 'xhtml') { &add_table("Document Type", $version); if ($File->{Type} eq 'xhtml' and $File->{Namespace} ne 'http://www.w3.org/1999/xhtml') { - &add_warning ("Unknown namespace for text/html document!"); + &add_warning ("Unknown namespace («<code>$File->{Namespace}</code>») for text/html document!"); if ($File->{Namespace} ne '') { &add_table("Root Namespace", "<a href='$File->{Namespace}'>$File->{Namespace}</a>"); @@ -579,10 +601,23 @@ EOHD Below are the results of attempting to parse this document with an SGML parser. </p> - EOHD } +if (defined $File->{Tentative}) { + print <<".EOF."; + <p class="Warning"> + Please note that you have chosen one or more options that alter the content + of the document before Validation. Even if no errors are reported below, + the document will not be Valid until you manually make the changes we have + performed automatically. Specifically, since you used some of the options + that Override a property of the document (e.g. the DOCTYPE or Character + Encoding), you must make the same change to the source document before it + can be valid. + </p> +.EOF. +} + if (scalar @{$File->{Errors}}) { $q->param('ss', TRUE); &report_errors($File) @@ -633,17 +668,12 @@ sub print_table { print " </table></form>\n"; } -sub add_warning { - push @{$File->{Warnings}}, shift; -} +sub add_warning {push @{$File->{Warnings}}, shift}; sub print_warnings { - my $warning; return unless defined @{$File->{Warnings}}; print " <div><h2>Warnings</h2>\n <ul>\n"; - for $warning (@{$File->{Warnings}}) { - print " <li class='warning'>$warning</li>\n"; - } + print qq( <li>Warning: $_</li>\n) for @{$File->{Warnings}}; print " </ul></div>\n"; } @@ -1222,7 +1252,8 @@ sub report_valid { } else { print "\n <pre>\n No errors found!</pre>\n\n"; } - unless ($version eq 'unknown') { + + unless ($version eq 'unknown' or defined $File->{Tentative}) { if ($version =~ /^HTML 2\.0$/) { $image_uri = "${abs_svc_uri}images/vh20"; $alttext = "Valid HTML 2.0!"; @@ -1277,6 +1308,7 @@ sub report_valid { $image_uri = "${abs_svc_uri}images/vhhj"; $alttext = "Valid Hotjava-HTML!"; } + if (defined $image_uri) { print <<"EOHD"; <p> @@ -1307,7 +1339,9 @@ EOHD } } if ($File->{Type} eq 'xml' and not $File->{DOCTYPE}) { - print " <p>\n Congratulations, this document is well-formed XML.\n </p>\n"; + print " <p>Congratulations, this document is well-formed XML.</p>\n"; + } elsif (defined $File->{Tentative}) { + print " <p>\n This document would validate as the document type specified if you updated it to match the Options used.\n </p>\n"; } elsif ($version eq 'unknown' or not defined $image_uri) { print " <p>\n Congratulations, this document validates as the document type specified! (I don't have an icon for this one yet, sorry.)\n </p>\n"; } @@ -1566,7 +1600,7 @@ sub preparse { if (lc $tag eq 'meta') { if (lc $attr{'http-equiv'} eq 'content-type') { $attr{content} =~ m(charset\s*=[\s\"\']*([^\s;\"\'>]*))si; - $File->{META_Charset} = lc $1; + $File->{META_Charset} = lc $1; } } return unless $tag eq $File->{Root}; |