- From: Ville Skytta via cvs-syncmail <cvsmail@w3.org>
- Date: Mon, 23 Nov 2009 22:49:25 +0000
- To: www-validator-cvs@w3.org
Update of /sources/public/validator/httpd/cgi-bin In directory hutz:/tmp/cvs-serv20681/httpd/cgi-bin Modified Files: check Log Message: Wrap long comment lines. Index: check =================================================================== RCS file: /sources/public/validator/httpd/cgi-bin/check,v retrieving revision 1.723 retrieving revision 1.724 diff -u -d -r1.723 -r1.724 --- check 23 Nov 2009 22:37:41 -0000 1.723 +++ check 23 Nov 2009 22:49:23 -0000 1.724 @@ -578,9 +578,10 @@ # # 1. check if there's a doctype # 2. if there is a doctype, parse/validate against that DTD -# 3. if no doctype, check for an xmlns= attribute on the first element, or XML declaration -# 4. if no doctype and XML mode, check for XML well-formedness -# 5. otherwise , punt. +# 3. if no doctype, check for an xmlns= attribute on the first element, or +# XML declaration +# 4. if no doctype and XML mode, check for XML well-formedness +# 5. otherwise, punt. # # @@ -631,12 +632,15 @@ $xmlparser->validation(0); $xmlparser->load_ext_dtd(0); - # [NOT] loading the XML catalog for entities resolution as it seems to cause a lot of unnecessary DTD/entities fetching (requires >= 1.53 if enabled) + # [NOT] loading the XML catalog for entities resolution as it seems to + # cause a lot of unnecessary DTD/entities fetching (requires >= 1.53 if + # enabled) #$xmlparser->load_catalog(catfile($CFG->{Paths}->{SGML}->{Library}, 'xml.soc')); my $xml_string = join "\n", @{$File->{Content}}; - # the XML parser will check the value of encoding attribute in XML declaration - # so we have to amend it to reflect transcoding. see Bug 4867 + # the XML parser will check the value of encoding attribute in XML + # declaration so we have to amend it to reflect transcoding. + # see Bug 4867 $xml_string =~ s/(<\?xml.*) (encoding[\x20|\x09|\x0D|\x0A]*=[\x20|\x09|\x0D|\x0A]*(?:"[A-Za-z][a-zA-Z0-9_-]+"|'[A-Za-z][a-zA-Z0-9_-]+')) (.*\?>)/$1encoding="utf-8"$3/sx; @@ -668,8 +672,8 @@ $err->{type} = "E"; $err->{msg} = $err_obj->message(); - # The validator will sometimes fail to dereference entities files - # we're filtering the bogus resulting error + # The validator will sometimes fail to dereference entities + # files; we're filtering the resulting bogus error if ($err->{msg} =~ /Entity '\w+' not defined/) { $err = undef; next; @@ -702,12 +706,14 @@ $got_error_message = 1; } - # then we skip the second line, which shows the context (we don't use that) + # then we skip the second line, which shows the context + # (we don't use that) elsif ($got_error_message and !$got_quoted_line) { $got_quoted_line = 1; } - # we now take the third line, with the pointer to the error's column + # we now take the third line, with the pointer to the error's + # column elsif (($msg_line =~ /(\s+)\^/) and $got_error_message and $got_quoted_line) @@ -737,11 +743,13 @@ # http://bugzilla.gnome.org/show_bug.cgi?id=424017 $xmlwf_error_col = "> 80"; - # non-int line number will trigger the proper behavior in report_error + # non-int line number will trigger the proper behavior + # in report_error } } - # when we have all the info (one full error message), proceed and move on to the next error + # when we have all the info (one full error message), proceed + # and move on to the next error if ((defined $xmlwf_error_line) and (defined $xmlwf_error_col) and (defined $xmlwf_error_msg)) @@ -760,8 +768,8 @@ $err->{type} = "E"; $err->{msg} = $xmlwf_error_msg; - # The validator will sometimes fail to dereference entities files - # we're filtering the bogus resulting error + # The validator will sometimes fail to dereference entities + # files; we're filtering the resulting bogus error if ($err->{msg} =~ /Entity '\w+' not defined/) { $xmlwf_error_line = undef; $xmlwf_error_col = undef; @@ -806,8 +814,8 @@ (($File->{Root} eq "svg") or @{$File->{Namespaces}} > 1)) { - # we send doctypeless SVG, or any doctypeless XML document with multiple namespaces found, to a different engine - # WARNING this is experimental. + # we send doctypeless SVG, or any doctypeless XML document with multiple + # namespaces found, to a different engine. WARNING this is experimental. if ($CFG->{External}->{CompoundXML}) { $File = &compoundxml_validate($File); &add_warning( @@ -930,8 +938,10 @@ $template = &get_template($File, 'ucn_output.tmpl'); } elsif ($File->{Opt}->{Output} eq 'soap12') { - if ($CFG->{'Enable SOAP'} != 1) - { # API disabled - ideally this should have been sent before performing validation... + if ($CFG->{'Enable SOAP'} != 1) { + + # API disabled - ideally this should have been sent before performing + # validation... print CGI::header( -status => 503, -content_language => "en", @@ -943,8 +953,8 @@ elsif ($File->{'Error Flagged'}) { # should send SOAP fault message $template = &get_template($File, 'soap_fault.tmpl'); - # we fill the soap fault template - #with the variables that had been passed to the HTML fatal error template + # we fill the soap fault template with the variables that had been + # passed to the HTML fatal error template my $errtmpl = &get_template($File, 'fatal-error.tmpl'); foreach my $fparam ($errtmpl->param()) { $template->param($fparam => $errtmpl->param($fparam)); @@ -1074,9 +1084,11 @@ my $content = &get_content($File, $res); return $File if $File->{'Error Flagged'}; - # and now we parse according to http://wiki.whatwg.org/wiki/Validator.nu_XML_Output - # I wish we could use XML::LibXML::Reader here. but SHAME on those major - # unix distributions still shipping with libxml2 2.6.16… 4 years after its release + # and now we parse according to + # http://wiki.whatwg.org/wiki/Validator.nu_XML_Output + # I wish we could use XML::LibXML::Reader here. but SHAME on those + # major unix distributions still shipping with libxml2 2.6.16… 4 years + # after its release my $xml_reader = XML::LibXML->new(); my $xmlDOM; eval { $xmlDOM = $xml_reader->parse_string($content); }; @@ -1102,8 +1114,9 @@ $File->{'Is Valid'} = FALSE; } elsif ($message_type eq "info") { - $err->{type} = "I" - ; # by default - we find warnings in the type attribute (below) + + # by default - we find warnings in the type attribute (below) + $err->{type} = "I"; } if ($message_node->hasAttributes()) { my @attributelist = $message_node->attributes(); @@ -1192,8 +1205,8 @@ # Pass original bytes, Content-Type and charset as-is. # We trust that our and validator.nu's interpretation of line numbers - # is the same later when displaying error contexts (regardless of EOL chars - # used in the document). + # is the same later when displaying error contexts (regardless of EOL + # chars used in the document). if ($File->{'Direct Input'}) { $req->content_type("text/html; charset=UTF-8"); @@ -1229,9 +1242,11 @@ my $content = &get_content($File, $res); return $File if $File->{'Error Flagged'}; - # and now we parse according to http://wiki.whatwg.org/wiki/Validator.nu_XML_Output - # I wish we could use XML::LibXML::Reader here. but SHAME on those major - # unix distributions still shipping with libxml2 2.6.16… 4 years after its release + # and now we parse according to + # http://wiki.whatwg.org/wiki/Validator.nu_XML_Output + # I wish we could use XML::LibXML::Reader here. but SHAME on those + # major unix distributions still shipping with libxml2 2.6.16… 4 years + # after its release my $xml_reader = XML::LibXML->new(); my $xmlDOM; eval { $xmlDOM = $xml_reader->parse_string($content); }; @@ -1253,8 +1268,9 @@ $html5_error_msg, $html5_error_expl ); - # TODO: non-document errors should receive different/better treatment, - # but this is better than hiding all problems for now (#6747) + # TODO: non-document errors should receive different/better + # treatment, but this is better than hiding all problems for now + # (#6747) if ($message_type eq "error" || $message_type eq "non-document-error") { @@ -1262,8 +1278,9 @@ $File->{'Is Valid'} = FALSE; } elsif ($message_type eq "info") { - $err->{type} = "I" - ; # by default - we find warnings in the type attribute (below) + + # by default - we find warnings in the type attribute (below) + $err->{type} = "I"; } if ($message_node->hasAttributes()) { my @attributelist = $message_node->attributes(); @@ -1528,8 +1545,9 @@ my $number_of_warnings = ""; # textual form of $num_errors # The following is a bit hack-ish, but will enable us to have some logic - # for a human-readable display of the number, with cases for 0, 1, 2 and above - # (the case of 2 appears to be useful for localization in some languages where the plural is different for 2, and above) + # for a human-readable display of the number, with cases for 0, 1, 2 and + # above (the case of 2 appears to be useful for localization in some + # languages where the plural is different for 2, and above) if ($num_errors > 1) { $T->param(number_of_errors_is_0 => FALSE); @@ -1696,10 +1714,10 @@ unless ($ua->is_protocol_supported($uri)) { $File->{'Error Flagged'} = TRUE; my $tmpl = &get_template($File, 'fatal-error.tmpl'); - if (($uri->canonical() eq "1")) - #if uri param is empty (also for empty direct or upload), it's been set to TRUE in sub prepCGI() - { + # If uri param is empty (also for empty direct or upload), it's been + # set to TRUE in sub prepCGI() + if ($uri->canonical() eq "1") { $tmpl->param(fatal_no_content => TRUE); } else { @@ -1758,7 +1776,8 @@ my $no200url = undef; if (!$File->{Opt}->{No200}) { - # $File->{URI} not set yet; setting it non-local has side effects + # $File->{URI} not set yet; setting it non-local has side + # effects local $File->{URI} = $uri->as_string; local $File->{Opt}->{No200} = TRUE; $no200url = &self_url_file($File); @@ -1767,8 +1786,8 @@ my $warning = $res->header("Client-Warning"); if ($warning && $warning =~ /Internal response/i) { - # Response doc generated internally by LWP, no need to show that info - # nor to provide error doc validation link to it. + # Response doc generated internally by LWP, no need to show + # that info nor to provide error doc validation link to it. $warning = undef; $no200url = undef; } @@ -1886,8 +1905,8 @@ $prefill_Template->param(fragment => $File->{Bytes}); $File->{Bytes} = $prefill_Template->output(); - # Let's force the view source so that the user knows what we've put around - # their code. + # Let's force the view source so that the user knows what we've put + # around their code. $File->{Opt}->{'Show Source'} = TRUE; # Ignore doctype overrides (#5132). @@ -1962,7 +1981,8 @@ fatal_decode_errmsg => $errmsg, fatal_decode_cenc => $cenc, - # Include URI because it might be a subsystem (eg. HTML5 validator) one + # Include URI because it might be a subsystem + # (eg. HTML5 validator) one fatal_decode_uri => $uri, ); } @@ -2101,7 +2121,8 @@ $File->{DOCTYPE} eq 'about:legacy-compat') ); - # No Override if Fallback was requested, or if override is the same as detected + # No Override if Fallback was requested, or if override is the same as + # detected my $known = $CFG->{Types}->{$File->{DOCTYPE}}; if ($File->{Opt}->{FB}->{DOCTYPE} or ($known && $File->{Opt}->{DOCTYPE} eq $known->{Display})) @@ -2186,8 +2207,9 @@ # Hash to keep track of how many of each error is reported. my %Msgs; # Used to generate a UID for explanations. - # for the sake of readability, at least until the xmlwf errors have explanations, - # we push the errors from the XML parser at the END of the error list. + # for the sake of readability, at least until the xmlwf errors have + # explanations, we push the errors from the XML parser at the END of the + # error list. foreach my $errmsg (@{$File->{WF_Errors}}) { push @{$File->{Errors}}, $errmsg; } @@ -2283,7 +2305,8 @@ ) { - # index by num for errors and warnings only - info usually give context of error or warning + # index by num for errors and warnings only - info usually + # gives context of error or warning if (!exists $Errors_bytype{$err->{num}}) { $Errors_bytype{$err->{num}}->{instances} = []; my $msg_text; @@ -2293,7 +2316,7 @@ $msg_text =~ s/%2/Y/; } else - { ## FIXME ## we need a catalog of errors from our XML parser + { ## FIXME we need a catalog of errors from our XML parser $msg_text = "XML Parsing Error"; } $Errors_bytype{$err->{num}}->{expl} = $err->{expl}; @@ -2320,8 +2343,9 @@ } # we are not sorting errors by line, as it would break the position - # of auxiliary messages such as "start tag was here". We'll have to live with - # the fact that XML well-formedness errors are listed first, then validation errors + # of auxiliary messages such as "start tag was here". We'll have to live + # with the fact that XML well-formedness errors are listed first, then + # validation errors #else { # sort error by lines # @{$Errors} = sort {$a->{line} <=> $b->{line} } @{$Errors}; @@ -2426,7 +2450,8 @@ my $dtd = sub { return if $File->{Root}; - # TODO: The \s and \w are probably wrong now that the strings are utf8_on + # TODO: The \s and \w are probably wrong now that the strings are + # utf8_on my $declaration = shift; my $doctype_type; my $doctype_secondpart; @@ -2600,8 +2625,8 @@ if ($ENV{SERVER_SOFTWARE} and $ENV{SERVER_SOFTWARE} =~ /Microsoft-IIS/); - # apparently, with mod_perl2, $path_info is empty even if it should be filled - # working around that + # apparently, with mod_perl2, $path_info is empty even if it should be + # filled. working around that if (!$path_info && $File->{Env}->{'Self URI'} =~ /check\/referr?er$/) { $path_info = '/referer'; $File->{Env}->{'Self URI'} =~ s/\/referr?er$//; @@ -2786,13 +2811,15 @@ } elsif ($parseModeFromMimeType ne 'TBD') { - # if The mime type gives clear indication of whether the document is XML or not + # if The mime type gives clear indication of whether the document is + # XML or not if (($parseModeFromDoctype ne 'TBD') and ($parseModeFromDoctype ne 'HTML5') and ($parseModeFromMimeType ne $parseModeFromDoctype)) { - # if document-type recommended mode and content-type recommended mode clash, shoot a warning + # if document-type recommended mode and content-type recommended + # mode clash, shoot a warning # unknown doctypes will not trigger this # neither will html5 documents, which can be XML or not &add_warning( @@ -2839,8 +2866,7 @@ # the mime type is ambiguous (hence we didn't stop at the previous test) # and so was the doctype - # but we found an XML declaration - # so we use that. + # but we found an XML declaration so we use that. if ($File->{Mode} eq "") { $File->{Mode} = "DTD+" . $parseModeFromXMLDecl; } @@ -2856,7 +2882,8 @@ else { # this is the last case. We know that all modes are not TBD, - # yet mime type, doctype AND XML DECL tests have failed => we are saved by the presence of namespaces + # yet mime type, doctype AND XML DECL tests have failed => we are saved + # by the presence of namespaces if ($File->{Mode} eq "") { $File->{Mode} = "DTD+" . $parseModeFromNamespace; } @@ -2890,7 +2917,8 @@ # # Add a warning if there was charset info conflict (HTTP header, # XML declaration, or <meta> element). - # filtering out some of the warnings in direct input mode where HTTP encoding is a "fake" + # filtering out some of the warnings in direct input mode where HTTP + # encoding is a "fake" if (( charset_not_equal( $File->{Charset}->{HTTP}, $File->{Charset}->{XML} @@ -3017,7 +3045,8 @@ if ($@) { - # Transcoding failed - do it again line by line to find out exactly where + # Transcoding failed - do it again line by line to find out exactly + # where my $line_num = 0; foreach my $input_line (split /\r\n|\n|\r/, $input) { $line_num++; @@ -3073,7 +3102,7 @@ my %metah; foreach my $try (@first) { - # @@FIXME I think the old code used HTML::Parser xml mode, check this is ok + # @@FIXME I think the old code used HTML::Parser xml mode, check if ok my $meta = HTML::Encoding::encoding_from_meta_element($File->{Bytes}, $try); $metah{lc($meta)}++ if defined $meta and length $meta; @@ -3354,35 +3383,39 @@ if ($err->{num} eq '187') - # filtering out no "document type declaration; will parse without validation" - # if root element is not html and mode is xml... + # filtering out no "document type declaration; will parse without + # validation" if root element is not html and mode is xml... { - # since parsing was done without validation, result can only be "well-formed" + # since parsing was done without validation, result can only be + # "well-formed" if ($is_xml and lc($File->{Root}) ne 'html') { $File->{XMLWF_ONLY} = TRUE; W3C::Validator::MarkupValidator::add_warning('W09xml', {}); return; # don't report this as an error, just proceed } - # if mode is not XML, we do report the error. It should not happen in the case of <html> without doctype, - # in that case the error message will be #344 + # if mode is not XML, we do report the error. It should not happen in + # the case of <html> without doctype, in that case the error message + # will be #344 } if (($err->{num} eq '113') and ($err->{msg} =~ /xml:space/)) { # FIXME - # this is a problem with some of the "flattened" W3C DTDs, filtering them out to not confuse users. - # hoping to get the DTDs fixed, see http://lists.w3.org/Archives/Public/www-html-editor/2007AprJun/0010.html - return; # don't report this, just proceed + # this is a problem with some of the "flattened" W3C DTDs, filtering + # them out to not confuse users. hoping to get the DTDs fixed, see + # http://lists.w3.org/Archives/Public/www-html-editor/2007AprJun/0010.html + return; # don't report this, just proceed } if ($is_xml and $err->{num} eq '344' and $File->{Namespace}) { # we are in XML mode, we have a namespace, but no doctype. - # the validator will already have said "no doctype, falling back to default" above + # the validator will already have said "no doctype, falling back to + # default" above # no need to report this. - return; # don't report this, just proceed + return; # don't report this, just proceed } if (($err->{num} eq '248') or @@ -3390,8 +3423,8 @@ ($err->{num} eq '246')) { - # these two errors should be triggered by -wmin-tag to report shorttag used, - # but we're making them warnings, not errors + # these two errors should be triggered by -wmin-tag to report shorttag + # used, but we're making them warnings, not errors # see http://www.w3.org/TR/html4/appendix/notes.html#h-B.3.7 $err->{type} = "W"; }
Received on Monday, 23 November 2009 22:49:27 UTC