/[pub]/test/html-webhacc/cc.cgi
Suika

Diff of /test/html-webhacc/cc.cgi

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 1.21 by wakaba, Tue Sep 11 08:25:23 2007 UTC revision 1.59 by wakaba, Mon Jul 21 12:56:33 2008 UTC
# Line 4  use strict; Line 4  use strict;
4  use lib qw[/home/httpd/html/www/markup/html/whatpm  use lib qw[/home/httpd/html/www/markup/html/whatpm
5             /home/wakaba/work/manakai2/lib];             /home/wakaba/work/manakai2/lib];
6  use CGI::Carp qw[fatalsToBrowser];  use CGI::Carp qw[fatalsToBrowser];
 use Scalar::Util qw[refaddr];  
 use Time::HiRes qw/time/;  
7    
8  sub htescape ($) {    require WebHACC::Input;
   my $s = $_[0];  
   $s =~ s/&/&/g;  
   $s =~ s/</&lt;/g;  
   $s =~ s/>/&gt;/g;  
   $s =~ s/"/&quot;/g;  
   $s =~ s{([\x00-\x09\x0B-\x1F\x7F-\xA0\x{FEFF}\x{FFFC}-\x{FFFF}])}{  
     sprintf '<var>U+%04X</var>', ord $1;  
   }ge;  
   return $s;  
 } # htescape  
9    
10    use Message::CGI::HTTP;  {
11      require Message::CGI::HTTP;
12    my $http = Message::CGI::HTTP->new;    my $http = Message::CGI::HTTP->new;
13    
14      require WebHACC::Output;
15      my $out = WebHACC::Output->new;
16      $out->handle (*STDOUT);
17      $out->set_utf8;
18    
19    if ($http->get_meta_variable ('PATH_INFO') ne '/') {    if ($http->get_meta_variable ('PATH_INFO') ne '/') {
20      print STDOUT "Status: 404 Not Found\nContent-Type: text/plain; charset=us-ascii\n\n400";      $out->http_error (404);
21      exit;      exit;
22    }    }
23    
24    binmode STDOUT, ':utf8';    ## TODO: We need real conneg support...
25    $| = 1;    my $primary_language = 'en';
26      if ($ENV{HTTP_ACCEPT_LANGUAGE} =~ /ja/) {
27    require Message::DOM::DOMImplementation;      $primary_language = 'ja';
   my $dom = Message::DOM::DOMImplementation->new;  
   
   load_text_catalog ('en'); ## TODO: conneg  
   
   my @nav;  
   print STDOUT qq[Content-Type: text/html; charset=utf-8  
   
 <!DOCTYPE html>  
 <html lang="en">  
 <head>  
 <title>Web Document Conformance Checker (BETA)</title>  
 <link rel="stylesheet" href="../cc-style.css" type="text/css">  
 </head>  
 <body>  
 <h1><a href="../cc-interface">Web Document Conformance Checker</a>  
 (<em>beta</em>)</h1>  
 ];  
   
   $| = 0;  
   my $input = get_input_document ($http, $dom);  
   my $inner_html_element = $http->get_parameter ('e');  
   my $char_length = 0;  
   my %time;  
   
   print qq[  
 <div id="document-info" class="section">  
 <dl>  
 <dt>Request URI</dt>  
     <dd><code class="URI" lang="">&lt;<a href="@{[htescape $input->{request_uri}]}">@{[htescape $input->{request_uri}]}</a>&gt;</code></dd>  
 <dt>Document URI</dt>  
     <dd><code class="URI" lang="">&lt;<a href="@{[htescape $input->{uri}]}">@{[htescape $input->{uri}]}</a>&gt;</code></dd>  
 ]; # no </dl> yet  
   push @nav, ['#document-info' => 'Information'];  
   
 if (defined $input->{s}) {  
   $char_length = length $input->{s};  
   
   print STDOUT qq[  
 <dt>Base URI</dt>  
     <dd><code class="URI" lang="">&lt;<a href="@{[htescape $input->{base_uri}]}">@{[htescape $input->{base_uri}]}</a>&gt;</code></dd>  
 <dt>Internet Media Type</dt>  
     <dd><code class="MIME" lang="en">@{[htescape $input->{media_type}]}</code>  
     @{[$input->{media_type_overridden} ? '<em>(overridden)</em>' : '']}</dd>  
 <dt>Character Encoding</dt>  
     <dd>@{[defined $input->{charset} ? '<code class="charset" lang="en">'.htescape ($input->{charset}).'</code>' : '(none)']}  
     @{[$input->{charset_overridden} ? '<em>(overridden)</em>' : '']}</dd>  
 <dt>Length</dt>  
     <dd>$char_length byte@{[$char_length == 1 ? '' : 's']}</dd>  
 </dl>  
 </div>  
 ];  
   
   my $result = {conforming_min => 1, conforming_max => 1};  
   print_http_header_section ($input, $result);  
   
   my $doc;  
   my $el;  
   
   if ($input->{media_type} eq 'text/html') {  
     ($doc, $el) = print_syntax_error_html_section ($input, $result);  
     print_source_string_section (\($input->{s}), $input->{charset});  
   } elsif ({  
             'text/xml' => 1,  
             'application/atom+xml' => 1,  
             'application/rss+xml' => 1,  
             'application/svg+xml' => 1,  
             'application/xhtml+xml' => 1,  
             'application/xml' => 1,  
            }->{$input->{media_type}}) {  
     ($doc, $el) = print_syntax_error_xml_section ($input, $result);  
     print_source_string_section (\($input->{s}), $doc->input_encoding);  
   } else {  
     ## TODO: Change HTTP status code??  
     print_result_unknown_type_section ($input);  
28    }    }
29      $out->load_text_catalog ($primary_language);
   if (defined $doc or defined $el) {  
     print_structure_dump_section ($doc, $el);  
     my $elements = print_structure_error_section ($doc, $el, $result);  
     print_table_section ($elements->{table}) if @{$elements->{table}};  
     print_id_section ($elements->{id}) if keys %{$elements->{id}};  
     print_term_section ($elements->{term}) if keys %{$elements->{term}};  
     print_class_section ($elements->{class}) if keys %{$elements->{class}};  
   }  
   
   print_result_section ($result);  
 } else {  
   print STDOUT qq[</dl></div>];  
   print_result_input_error_section ($input);  
 }  
   
   print STDOUT qq[  
 <ul class="navigation" id="nav-items">  
 ];  
   for (@nav) {  
     print STDOUT qq[<li><a href="$_->[0]">$_->[1]</a></li>];  
   }  
   print STDOUT qq[  
 </ul>  
 </body>  
 </html>  
 ];  
   
   for (qw/decode parse parse_xml check/) {  
     next unless defined $time{$_};  
     open my $file, '>>', ".cc-$_.txt" or die ".cc-$_.txt: $!";  
     print $file $char_length, "\t", $time{$_}, "\n";  
   }  
   
 exit;  
   
 sub add_error ($$$) {  
   my ($layer, $err, $result) = @_;  
   if (defined $err->{level}) {  
     if ($err->{level} eq 's') {  
       $result->{$layer}->{should}++;  
       $result->{$layer}->{score_min} -= 2;  
       $result->{conforming_min} = 0;  
     } elsif ($err->{level} eq 'w' or $err->{level} eq 'g') {  
       $result->{$layer}->{warning}++;  
     } elsif ($err->{level} eq 'unsupported') {  
       $result->{$layer}->{unsupported}++;  
       $result->{unsupported} = 1;  
     } else {  
       $result->{$layer}->{must}++;  
       $result->{$layer}->{score_max} -= 2;  
       $result->{$layer}->{score_min} -= 2;  
       $result->{conforming_min} = 0;  
       $result->{conforming_max} = 0;  
     }  
   } else {  
     $result->{$layer}->{must}++;  
     $result->{$layer}->{score_max} -= 2;  
     $result->{$layer}->{score_min} -= 2;  
     $result->{conforming_min} = 0;  
     $result->{conforming_max} = 0;  
   }  
 } # add_error  
   
 sub print_http_header_section ($$) {  
   my ($input, $result) = @_;  
   return unless defined $input->{header_status_code} or  
       defined $input->{header_status_text} or  
       @{$input->{header_field}};  
     
   push @nav, ['#source-header' => 'HTTP Header'];  
   print STDOUT qq[<div id="source-header" class="section">  
 <h2>HTTP Header</h2>  
   
 <p><strong>Note</strong>: Due to the limitation of the  
 network library in use, the content of this section might  
 not be the real header.</p>  
   
 <table><tbody>  
 ];  
   
   if (defined $input->{header_status_code}) {  
     print STDOUT qq[<tr><th scope="row">Status code</th>];  
     print STDOUT qq[<td><code>@{[htescape ($input->{header_status_code})]}</code></td></tr>];  
   }  
   if (defined $input->{header_status_text}) {  
     print STDOUT qq[<tr><th scope="row">Status text</th>];  
     print STDOUT qq[<td><code>@{[htescape ($input->{header_status_text})]}</code></td></tr>];  
   }  
     
   for (@{$input->{header_field}}) {  
     print STDOUT qq[<tr><th scope="row"><code>@{[htescape ($_->[0])]}</code></th>];  
     print STDOUT qq[<td><code>@{[htescape ($_->[1])]}</code></td></tr>];  
   }  
   
   print STDOUT qq[</tbody></table></div>];  
 } # print_http_header_section  
   
 sub print_syntax_error_html_section ($$) {  
   my ($input, $result) = @_;  
     
   require Encode;  
   require Whatpm::HTML;  
   
   $input->{charset} ||= 'ISO-8859-1'; ## TODO: for now.  
30        
31    my $time1 = time;    $out->set_flush;
32    my $t = Encode::decode ($input->{charset}, $input->{s});    $out->http_header;
33    $time{decode} = time - $time1;    $out->html_header;
34      $out->unset_flush;
   print STDOUT qq[  
 <div id="parse-errors" class="section">  
 <h2>Parse Errors</h2>  
   
 <dl>];  
   push @nav, ['#parse-errors' => 'Parse Error'];  
   
   my $onerror = sub {  
     my (%opt) = @_;  
     my ($type, $cls, $msg) = get_text ($opt{type}, $opt{level});  
     if ($opt{column} > 0) {  
       print STDOUT qq[<dt class="$cls"><a href="#line-$opt{line}">Line $opt{line}</a> column $opt{column}</dt>\n];  
     } else {  
       $opt{line} = $opt{line} - 1 || 1;  
       print STDOUT qq[<dt class="$cls"><a href="#line-$opt{line}">Line $opt{line}</a></dt>\n];  
     }  
     $type =~ tr/ /-/;  
     $type =~ s/\|/%7C/g;  
     $msg .= qq[ [<a href="../error-description#@{[htescape ($type)]}">Description</a>]];  
     print STDOUT qq[<dd class="$cls">$msg</dd>\n];  
   
     add_error ('syntax', \%opt => $result);  
   };  
   
   my $doc = $dom->create_document;  
   my $el;  
   $time1 = time;  
   if (defined $inner_html_element and length $inner_html_element) {  
     $el = $doc->create_element_ns  
         ('http://www.w3.org/1999/xhtml', [undef, $inner_html_element]);  
     Whatpm::HTML->set_inner_html ($el, $t, $onerror);  
   } else {  
     Whatpm::HTML->parse_string ($t => $doc, $onerror);  
   }  
   $time{parse} = time - $time1;  
   
   print STDOUT qq[</dl></div>];  
   
   return ($doc, $el);  
 } # print_syntax_error_html_section  
   
 sub print_syntax_error_xml_section ($$) {  
   my ($input, $result) = @_;  
     
   require Message::DOM::XMLParserTemp;  
     
   print STDOUT qq[  
 <div id="parse-errors" class="section">  
 <h2>Parse Errors</h2>  
   
 <dl>];  
   push @nav, ['#parse-errors' => 'Parse Error'];  
   
   my $onerror = sub {  
     my $err = shift;  
     my $line = $err->location->line_number;  
     print STDOUT qq[<dt><a href="#line-$line">Line $line</a> column ];  
     print STDOUT $err->location->column_number, "</dt><dd>";  
     print STDOUT htescape $err->text, "</dd>\n";  
   
     add_error ('syntax', {type => $err->text,  
                 level => [  
                           $err->SEVERITY_FATAL_ERROR => 'm',  
                           $err->SEVERITY_ERROR => 'm',  
                           $err->SEVERITY_WARNING => 's',  
                          ]->[$err->severity]} => $result);  
   
     return 1;  
   };  
   
   my $time1 = time;  
   open my $fh, '<', \($input->{s});  
   my $doc = Message::DOM::XMLParserTemp->parse_byte_stream  
       ($fh => $dom, $onerror, charset => $input->{charset});  
   $time{parse_xml} = time - $time1;  
   
   print STDOUT qq[</dl></div>];  
   
   return ($doc, undef);  
 } # print_syntax_error_xml_section  
   
 sub print_source_string_section ($$) {  
   require Encode;  
   my $enc = Encode::find_encoding ($_[1]); ## TODO: charset name -> Perl name  
   return unless $enc;  
   
   my $s = \($enc->decode (${$_[0]}));  
   my $i = 1;                              
   push @nav, ['#source-string' => 'Source'];  
   print STDOUT qq[<div id="source-string" class="section">  
 <h2>Document Source</h2>  
 <ol lang="">\n];  
   if (length $$s) {  
     while ($$s =~ /\G([^\x0A]*?)\x0D?\x0A/gc) {  
       print STDOUT qq[<li id="line-$i">], htescape $1, "</li>\n";  
       $i++;  
     }  
     if ($$s =~ /\G([^\x0A]+)/gc) {  
       print STDOUT qq[<li id="line-$i">], htescape $1, "</li>\n";  
     }  
   } else {  
     print STDOUT q[<li id="line-1"></li>];  
   }  
   print STDOUT "</ol></div>";  
 } # print_input_string_section  
   
 sub print_document_tree ($) {  
   my $node = shift;  
   my $r = '<ol class="xoxo">';  
   
   my @node = ($node);  
   while (@node) {  
     my $child = shift @node;  
     unless (ref $child) {  
       $r .= $child;  
       next;  
     }  
   
     my $node_id = 'node-'.refaddr $child;  
     my $nt = $child->node_type;  
     if ($nt == $child->ELEMENT_NODE) {  
       my $child_nsuri = $child->namespace_uri;  
       $r .= qq[<li id="$node_id" class="tree-element"><code title="@{[defined $child_nsuri ? $child_nsuri : '']}">] . htescape ($child->tag_name) .  
           '</code>'; ## ISSUE: case  
   
       if ($child->has_attributes) {  
         $r .= '<ul class="attributes">';  
         for my $attr (sort {$a->[0] cmp $b->[0]} map { [$_->name, $_->value, $_->namespace_uri, 'node-'.refaddr $_] }  
                       @{$child->attributes}) {  
           $r .= qq[<li id="$attr->[3]" class="tree-attribute"><code title="@{[defined $_->[2] ? $_->[2] : '']}">] . htescape ($attr->[0]) . '</code> = '; ## ISSUE: case?  
           $r .= '<q>' . htescape ($attr->[1]) . '</q></li>'; ## TODO: children  
         }  
         $r .= '</ul>';  
       }  
   
       if ($child->has_child_nodes) {  
         $r .= '<ol class="children">';  
         unshift @node, @{$child->child_nodes}, '</ol></li>';  
       } else {  
         $r .= '</li>';  
       }  
     } elsif ($nt == $child->TEXT_NODE) {  
       $r .= qq'<li id="$node_id" class="tree-text"><q lang="">' . htescape ($child->data) . '</q></li>';  
     } elsif ($nt == $child->CDATA_SECTION_NODE) {  
       $r .= qq'<li id="$node_id" class="tree-cdata"><code>&lt;[CDATA[</code><q lang="">' . htescape ($child->data) . '</q><code>]]&gt;</code></li>';  
     } elsif ($nt == $child->COMMENT_NODE) {  
       $r .= qq'<li id="$node_id" class="tree-comment"><code>&lt;!--</code><q lang="">' . htescape ($child->data) . '</q><code>--&gt;</code></li>';  
     } elsif ($nt == $child->DOCUMENT_NODE) {  
       $r .= qq'<li id="$node_id" class="tree-document">Document';  
       $r .= qq[<ul class="attributes">];  
       $r .= qq[<li>@{[scalar get_text ('manakaiIsHTML:'.($child->manakai_is_html?1:0))]}</li>];  
       $r .= qq[<li>@{[scalar get_text ('manakaiCompatMode:'.$child->manakai_compat_mode)]}</li>];  
       unless ($child->manakai_is_html) {  
         $r .= qq[<li>XML version = <code>@{[htescape ($child->xml_version)]}</code></li>];  
         if (defined $child->xml_encoding) {  
           $r .= qq[<li>XML encoding = <code>@{[htescape ($child->xml_encoding)]}</code></li>];  
         } else {  
           $r .= qq[<li>XML encoding = (null)</li>];  
         }  
         $r .= qq[<li>XML standalone = @{[$child->xml_standalone ? 'true' : 'false']}</li>];  
       }  
       $r .= qq[</ul>];  
       if ($child->has_child_nodes) {  
         $r .= '<ol class="children">';  
         unshift @node, @{$child->child_nodes}, '</ol></li>';  
       }  
     } elsif ($nt == $child->DOCUMENT_TYPE_NODE) {  
       $r .= qq'<li id="$node_id" class="tree-doctype"><code>&lt;!DOCTYPE&gt;</code><ul class="attributes">';  
       $r .= qq[<li class="tree-doctype-name">Name = <q>@{[htescape ($child->name)]}</q></li>];  
       $r .= qq[<li class="tree-doctype-publicid">Public identifier = <q>@{[htescape ($child->public_id)]}</q></li>];  
       $r .= qq[<li class="tree-doctype-systemid">System identifier = <q>@{[htescape ($child->system_id)]}</q></li>];  
       $r .= '</ul></li>';  
     } elsif ($nt == $child->PROCESSING_INSTRUCTION_NODE) {  
       $r .= qq'<li id="$node_id" class="tree-id"><code>&lt;?@{[htescape ($child->target)]}</code> <q>@{[htescape ($child->data)]}</q><code>?&gt;</code></li>';  
     } else {  
       $r .= qq'<li id="$node_id" class="tree-unknown">@{[$child->node_type]} @{[htescape ($child->node_name)]}</li>'; # error  
     }  
   }  
35    
36    $r .= '</ol>';    my $input = get_input_document ($http);
37    print STDOUT $r;    $out->input ($input);
 } # print_document_tree  
   
 sub print_structure_dump_section ($$) {  
   my ($doc, $el) = @_;  
   
   print STDOUT qq[  
 <div id="document-tree" class="section">  
 <h2>Document Tree</h2>  
 ];  
   push @nav, ['#document-tree' => 'Tree'];  
   
   print_document_tree ($el || $doc);  
   
   print STDOUT qq[</div>];  
 } # print_structure_dump_section  
   
 sub print_structure_error_section ($$$) {  
   my ($doc, $el, $result) = @_;  
   
   print STDOUT qq[<div id="document-errors" class="section">  
 <h2>Document Errors</h2>  
   
 <dl>];  
   push @nav, ['#document-errors' => 'Document Error'];  
   
   require Whatpm::ContentChecker;  
   my $onerror = sub {  
     my %opt = @_;  
     my ($type, $cls, $msg) = get_text ($opt{type}, $opt{level}, $opt{node});  
     $type =~ tr/ /-/;  
     $type =~ s/\|/%7C/g;  
     $msg .= qq[ [<a href="../error-description#@{[htescape ($type)]}">Description</a>]];  
     print STDOUT qq[<dt class="$cls">] . get_node_link ($opt{node}) .  
         qq[</dt>\n<dd class="$cls">], $msg, "</dd>\n";  
     add_error ('structure', \%opt => $result);  
   };  
   
   my $elements;  
   my $time1 = time;  
   if ($el) {  
     $elements = Whatpm::ContentChecker->check_element ($el, $onerror);  
   } else {  
     $elements = Whatpm::ContentChecker->check_document ($doc, $onerror);  
   }  
   $time{check} = time - $time1;  
38    
39    print STDOUT qq[</dl></div>];    require WebHACC::Result;
40      my $result = WebHACC::Result->new;
41      $result->output ($out);
42      $result->{conforming_min} = 1;
43      $result->{conforming_max} = 1;
44    
45    return $elements;    $out->html ('<script src="../cc-script.js"></script>');
 } # print_structure_error_section  
46    
47  sub print_table_section ($) {    check_and_print ($input => $result => $out);
   my $tables = shift;  
     
   push @nav, ['#tables' => 'Tables'];  
   print STDOUT qq[  
 <div id="tables" class="section">  
 <h2>Tables</h2>  
   
 <!--[if IE]><script type="text/javascript" src="../excanvas.js"></script><![endif]-->  
 <script src="../table-script.js" type="text/javascript"></script>  
 <noscript>  
 <p><em>Structure of tables are visualized here if scripting is enabled.</em></p>  
 </noscript>  
 ];  
     
   require JSON;  
48        
49    my $i = 0;    $result->generate_result_section;
   for my $table_el (@$tables) {  
     $i++;  
     print STDOUT qq[<div class="section" id="table-$i"><h3>] .  
         get_node_link ($table_el) . q[</h3>];  
   
     ## TODO: Make |ContentChecker| return |form_table| result  
     ## so that this script don't have to run the algorithm twice.  
     my $table = Whatpm::HTMLTable->form_table ($table_el);  
       
     for (@{$table->{column_group}}, @{$table->{column}}, $table->{caption}) {  
       next unless $_;  
       delete $_->{element};  
     }  
       
     for (@{$table->{row_group}}) {  
       next unless $_;  
       next unless $_->{element};  
       $_->{type} = $_->{element}->manakai_local_name;  
       delete $_->{element};  
     }  
       
     for (@{$table->{cell}}) {  
       next unless $_;  
       for (@{$_}) {  
         next unless $_;  
         for (@$_) {  
           $_->{id} = refaddr $_->{element} if defined $_->{element};  
           delete $_->{element};  
           $_->{is_header} = $_->{is_header} ? 1 : 0;  
         }  
       }  
     }  
           
     print STDOUT '</div><script type="text/javascript">tableToCanvas (';  
     print STDOUT JSON::objToJson ($table);  
     print STDOUT qq[, document.getElementById ('table-$i'));</script>];  
   }  
     
   print STDOUT qq[</div>];  
 } # print_table_section  
50    
51  sub print_id_section ($) {    $out->nav_list;
   my $ids = shift;  
     
   push @nav, ['#identifiers' => 'IDs'];  
   print STDOUT qq[  
 <div id="identifiers" class="section">  
 <h2>Identifiers</h2>  
   
 <dl>  
 ];  
   for my $id (sort {$a cmp $b} keys %$ids) {  
     print STDOUT qq[<dt><code>@{[htescape $id]}</code></dt>];  
     for (@{$ids->{$id}}) {  
       print STDOUT qq[<dd>].get_node_link ($_).qq[</dd>];  
     }  
   }  
   print STDOUT qq[</dl></div>];  
 } # print_id_section  
52    
53  sub print_term_section ($) {    exit;
54    my $terms = shift;  }
     
   push @nav, ['#terms' => 'Terms'];  
   print STDOUT qq[  
 <div id="terms" class="section">  
 <h2>Terms</h2>  
   
 <dl>  
 ];  
   for my $term (sort {$a cmp $b} keys %$terms) {  
     print STDOUT qq[<dt>@{[htescape $term]}</dt>];  
     for (@{$terms->{$term}}) {  
       print STDOUT qq[<dd>].get_node_link ($_).qq[</dd>];  
     }  
   }  
   print STDOUT qq[</dl></div>];  
 } # print_term_section  
   
 sub print_class_section ($) {  
   my $classes = shift;  
     
   push @nav, ['#classes' => 'Classes'];  
   print STDOUT qq[  
 <div id="classes" class="section">  
 <h2>Classes</h2>  
   
 <dl>  
 ];  
   for my $class (sort {$a cmp $b} keys %$classes) {  
     print STDOUT qq[<dt><code>@{[htescape $class]}</code></dt>];  
     for (@{$classes->{$class}}) {  
       print STDOUT qq[<dd>].get_node_link ($_).qq[</dd>];  
     }  
   }  
   print STDOUT qq[</dl></div>];  
 } # print_class_section  
   
 sub print_result_section ($) {  
   my $result = shift;  
   
   print STDOUT qq[  
 <div id="result-summary" class="section">  
 <h2>Result</h2>];  
   
   if ($result->{unsupported} and $result->{conforming_max}) {    
     print STDOUT qq[<p class=uncertain id=result-para>The conformance  
         checker cannot decide whether the document is conforming or  
         not, since the document contains one or more unsupported  
         features.  The document might or might not be conforming.</p>];  
   } elsif ($result->{conforming_min}) {  
     print STDOUT qq[<p class=PASS id=result-para>No conformance-error is  
         found in this document.</p>];  
   } elsif ($result->{conforming_max}) {  
     print STDOUT qq[<p class=SEE-RESULT id=result-para>This document  
         is <strong>likely <em>non</em>-conforming</strong>, but in rare case  
         it might be conforming.</p>];  
   } else {  
     print STDOUT qq[<p class=FAIL id=result-para>This document is  
         <strong><em>non</em>-conforming</strong>.</p>];  
   }  
55    
56    print STDOUT qq[<table>  sub check_and_print ($$$) {
57  <colgroup><col><colgroup><col><col><col><colgroup><col>    my ($input, $result, $out) = @_;
58  <thead>    my $original_input = $out->input;
59  <tr><th scope=col></th><th scope=col><em class=rfc2119>MUST</em>-level    $out->input ($input);
 Errors</th><th scope=col><em class=rfc2119>SHOULD</em>-level  
 Errors</th><th scope=col>Warnings</th><th scope=col>Score</th></tr>  
 </thead><tbody>];  
   
   my $must_error = 0;  
   my $should_error = 0;  
   my $warning = 0;  
   my $score_min = 0;  
   my $score_max = 0;  
   my $score_base = 20;  
   my $score_unit = $score_base / 100;  
   for (  
     [Transfer => 'transfer', ''],  
     [Character => 'char', ''],  
     [Syntax => 'syntax', '#parse-errors'],  
     [Structure => 'structure', '#document-errors'],  
   ) {  
     $must_error += ($result->{$_->[1]}->{must} += 0);  
     $should_error += ($result->{$_->[1]}->{should} += 0);  
     $warning += ($result->{$_->[1]}->{warning} += 0);  
     $score_min += (($result->{$_->[1]}->{score_min} *= $score_unit) += $score_base);  
     $score_max += (($result->{$_->[1]}->{score_max} *= $score_unit) += $score_base);  
   
     my $uncertain = $result->{$_->[1]}->{unsupported} ? '?' : '';  
     my $label = $_->[0];  
     if ($result->{$_->[1]}->{must} or  
         $result->{$_->[1]}->{should} or  
         $result->{$_->[1]}->{warning} or  
         $result->{$_->[1]}->{unsupported}) {  
       $label = qq[<a href="$_->[2]">$label</a>];  
     }  
60    
61      print STDOUT qq[<tr class="@{[$uncertain ? 'uncertain' : '']}"><th scope=row>$label</th><td class="@{[$result->{$_->[1]}->{must} ? 'FAIL' : '']}">$result->{$_->[1]}->{must}$uncertain</td><td class="@{[$result->{$_->[1]}->{should} ? 'SEE-RESULT' : '']}">$result->{$_->[1]}->{should}$uncertain</td><td>$result->{$_->[1]}->{warning}$uncertain</td>];    $input->generate_info_section ($result);
     if ($uncertain) {  
       print qq[<td class="@{[$result->{$_->[1]}->{must} ? 'FAIL' : $result->{$_->[1]}->{should} ? 'SEE-RESULT' : '']}">&#x2212;&#x221E;..$result->{$_->[1]}->{score_max}</td>];  
     } elsif ($result->{$_->[1]}->{score_min} != $result->{$_->[1]}->{score_max}) {  
       print qq[<td class="@{[$result->{$_->[1]}->{must} ? 'FAIL' : 'SEE-RESULT']}">$result->{$_->[1]}->{score_min}..$result->{$_->[1]}->{score_max}</td></tr>];  
     } else {  
       print qq[<td class="@{[$result->{$_->[1]}->{must} ? 'FAIL' : '']}">$result->{$_->[1]}->{score_min}</td></tr>];  
     }  
   }  
62    
63    $score_max += $score_base;    $input->generate_transfer_sections ($result);
64    
65    print STDOUT qq[    unless (defined $input->{s}) {
66  <tr class=uncertain><th scope=row>Semantics</th><td>0?</td><td>0?</td><td>0?</td><td>&#x2212;&#x221E;..$score_base</td></tr>      $result->{conforming_min} = 0;
67  </tbody>      return;
 <tfoot><tr class=uncertain><th scope=row>Total</th>  
 <td class="@{[$must_error ? 'FAIL' : '']}">$must_error?</td>  
 <td class="@{[$should_error ? 'SEE-RESULT' : '']}">$should_error?</td>  
 <td>$warning?</td>  
 <td class="@{[$must_error ? 'FAIL' : $should_error ? 'SEE-RESULT' : '']}"><strong>&#x2212;&#x221E;..$score_max</strong></td></tr></tfoot>  
 </table>  
   
 <p><strong>Important</strong>: This conformance checking service  
 is <em>under development</em>.  The result above might be <em>wrong</em>.</p>  
 </div>];  
   push @nav, ['#result-summary' => 'Result'];  
 } # print_result_section  
   
 sub print_result_unknown_type_section ($) {  
   my $input = shift;  
   
   print STDOUT qq[  
 <div id="result-summary" class="section">  
 <p><em>Media type <code class="MIME" lang="en">@{[htescape $input->{media_type}]}</code> is not supported!</em></p>  
 </div>  
 ];  
   push @nav, ['#result-summary' => 'Result'];  
 } # print_result_unknown_type_section  
   
 sub print_result_input_error_section ($) {  
   my $input = shift;  
   print STDOUT qq[<div class="section" id="result-summary">  
 <p><em><strong>Input Error</strong>: @{[htescape ($input->{error_status_text})]}</em></p>  
 </div>];  
   push @nav, ['#result-summary' => 'Result'];  
 } # print_Result_input_error_section  
   
 sub get_node_path ($) {  
   my $node = shift;  
   my @r;  
   while (defined $node) {  
     my $rs;  
     if ($node->node_type == 1) {  
       $rs = $node->manakai_local_name;  
       $node = $node->parent_node;  
     } elsif ($node->node_type == 2) {  
       $rs = '@' . $node->manakai_local_name;  
       $node = $node->owner_element;  
     } elsif ($node->node_type == 3) {  
       $rs = '"' . $node->data . '"';  
       $node = $node->parent_node;  
     } elsif ($node->node_type == 9) {  
       @r = ('') unless @r;  
       $rs = '';  
       $node = $node->parent_node;  
     } else {  
       $rs = '#' . $node->node_type;  
       $node = $node->parent_node;  
     }  
     unshift @r, $rs;  
68    }    }
   return join '/', @r;  
 } # get_node_path  
   
 sub get_node_link ($) {  
   return qq[<a href="#node-@{[refaddr $_[0]]}">] .  
       htescape (get_node_path ($_[0])) . qq[</a>];  
 } # get_node_link  
   
 {  
   my $Msg = {};  
69    
70  sub load_text_catalog ($) {    my $checker_class = {
71    my $lang = shift; # MUST be a canonical lang name      'text/cache-manifest' => 'WebHACC::Language::CacheManifest',
72    open my $file, '<', "cc-msg.$lang.txt" or die "$0: cc-msg.$lang.txt: $!";      'text/css' => 'WebHACC::Language::CSS',
73    while (<$file>) {      'text/html' => 'WebHACC::Language::HTML',
74      if (s/^([^;]+);([^;]*);//) {      'text/x-webidl' => 'WebHACC::Language::WebIDL',
75        my ($type, $cls, $msg) = ($1, $2, $_);  
76        $msg =~ tr/\x0D\x0A//d;      'text/xml' => 'WebHACC::Language::XML',
77        $Msg->{$type} = [$cls, $msg];      'application/atom+xml' => 'WebHACC::Language::XML',
78      }      'application/rss+xml' => 'WebHACC::Language::XML',
79        'image/svg+xml' => 'WebHACC::Language::XML',
80        'application/xhtml+xml' => 'WebHACC::Language::XML',
81        'application/xml' => 'WebHACC::Language::XML',
82        ## TODO: Should we make all XML MIME Types fall
83        ## into this category?
84    
85        ## NOTE: This type has different model from normal XML types.
86        'application/rdf+xml' => 'WebHACC::Language::XML',
87      }->{$input->{media_type}} || 'WebHACC::Language::Default';
88    
89      eval qq{ require $checker_class } or die "$0: Loading $checker_class: $@";
90      my $checker = $checker_class->new;
91      $checker->input ($input);
92      $checker->output ($out);
93      $checker->result ($result);
94    
95      ## TODO: A cache manifest MUST be text/cache-manifest
96      ## TODO: WebIDL media type "text/x-webidl"
97    
98      $checker->generate_syntax_error_section;
99      $checker->generate_source_string_section;
100    
101      my @subdoc;
102      $checker->onsubdoc (sub {
103        push @subdoc, shift;
104      });
105    
106      $checker->generate_structure_dump_section;
107      $checker->generate_structure_error_section;
108      $checker->generate_additional_sections;
109    
110      my $id_prefix = 0;
111      for my $_subinput (@subdoc) {
112        my $subinput = WebHACC::Input::Subdocument->new (++$id_prefix);
113        $subinput->{$_} = $_subinput->{$_} for keys %$_subinput;
114        $subinput->{base_uri} = $subinput->{container_node}->base_uri
115            unless defined $subinput->{base_uri};
116        $subinput->{parent_input} = $input;
117    
118        $subinput->start_section ($result);
119        check_and_print ($subinput => $result => $out);
120        $subinput->end_section ($result);
121    }    }
 } # load_text_catalog  
122    
123  sub get_text ($) {    $out->input ($original_input);
124    my ($type, $level, $node) = @_;  } # check_and_print
   $type = $level . ':' . $type if defined $level;  
   my @arg;  
   {  
     if (defined $Msg->{$type}) {  
       my $msg = $Msg->{$type}->[1];  
       $msg =~ s{<var>\$([0-9]+)</var>}{  
         defined $arg[$1] ? htescape ($arg[$1]) : '(undef)';  
       }ge;  
       $msg =~ s{<var>{\@([A-Za-z0-9:_.-]+)}</var>}{  
         UNIVERSAL::can ($node, 'get_attribute_ns')  
             ? htescape ($node->get_attribute_ns (undef, $1)) : ''  
       }ge;  
       $msg =~ s{<var>{\@}</var>}{  
         UNIVERSAL::can ($node, 'value') ? htescape ($node->value) : ''  
       }ge;  
       $msg =~ s{<var>{local-name}</var>}{  
         UNIVERSAL::can ($node, 'manakai_local_name')  
           ? htescape ($node->manakai_local_name) : ''  
       }ge;  
       $msg =~ s{<var>{element-local-name}</var>}{  
         (UNIVERSAL::can ($node, 'owner_element') and  
          $node->owner_element)  
           ? htescape ($node->owner_element->manakai_local_name)  
           : ''  
       }ge;  
       return ($type, $Msg->{$type}->[0], $msg);  
     } elsif ($type =~ s/:([^:]*)$//) {  
       unshift @arg, $1;  
       redo;  
     }  
   }  
   return ($type, '', htescape ($_[0]));  
 } # get_text  
125    
126  }  sub get_input_document ($) {
127      my $http = shift;
128    
129  sub get_input_document ($$) {    require Message::DOM::DOMImplementation;
130    my ($http, $dom) = @_;    my $dom = Message::DOM::DOMImplementation->new;
131    
132    my $request_uri = $http->get_parameter ('uri');    require Encode;
133    my $r = {};    my $request_uri = Encode::decode ('utf-8', $http->get_parameter ('uri'));
134      my $r = WebHACC::Input->new;
135    if (defined $request_uri and length $request_uri) {    if (defined $request_uri and length $request_uri) {
136      my $uri = $dom->create_uri_reference ($request_uri);      my $uri = $dom->create_uri_reference ($request_uri);
137      unless ({      unless ({
138               http => 1,               http => 1,
139              }->{lc $uri->uri_scheme}) {              }->{lc $uri->uri_scheme}) {
140        return {uri => $request_uri, request_uri => $request_uri,        $r = WebHACC::Input::Error->new;
141                error_status_text => 'URI scheme not allowed'};        $r->{uri} = $request_uri;
142          $r->{request_uri} = $request_uri;
143          $r->{error_status_text} = 'URL scheme not allowed';
144      }      }
145    
146      require Message::Util::HostPermit;      require Message::Util::HostPermit;
# Line 794  Deny ipv6=0::0/0 Line 167  Deny ipv6=0::0/0
167  Allow host=*  Allow host=*
168  EOH  EOH
169      unless ($host_permit->check ($uri->uri_host, $uri->uri_port || 80)) {      unless ($host_permit->check ($uri->uri_host, $uri->uri_port || 80)) {
170        return {uri => $request_uri, request_uri => $request_uri,        my $r = WebHACC::Input::Error->new;
171                error_status_text => 'Connection to the host is forbidden'};        $r->{uri} = $request_uri;
172          $r->{request_uri} = $request_uri;
173          $r->{error_status_text} = 'Connection to the host is forbidden';
174          return $r;
175      }      }
176    
177      require LWP::UserAgent;      require LWP::UserAgent;
# Line 807  EOH Line 183  EOH
183      $ua->protocols_allowed ([qw/http/]);      $ua->protocols_allowed ([qw/http/]);
184      $ua->max_size (1000_000);      $ua->max_size (1000_000);
185      my $req = HTTP::Request->new (GET => $request_uri);      my $req = HTTP::Request->new (GET => $request_uri);
186        $req->header ('Accept-Encoding' => 'identity, *; q=0');
187      my $res = $ua->request ($req);      my $res = $ua->request ($req);
188      ## TODO: 401 sets |is_success| true.      ## TODO: 401 sets |is_success| true.
189      if ($res->is_success or $http->get_parameter ('error-page')) {      if ($res->is_success or $http->get_parameter ('error-page')) {
# Line 816  EOH Line 193  EOH
193    
194        ## TODO: More strict parsing...        ## TODO: More strict parsing...
195        my $ct = $res->header ('Content-Type');        my $ct = $res->header ('Content-Type');
196        if (defined $ct and $ct =~ m#^([0-9A-Za-z._+-]+/[0-9A-Za-z._+-]+)#) {        if (defined $ct and $ct =~ /;\s*charset\s*=\s*"?([^\s;"]+)"?/i) {
         $r->{media_type} = lc $1;  
       }  
       if (defined $ct and $ct =~ /;\s*charset\s*=\s*"?(\S+)"?/i) {  
197          $r->{charset} = lc $1;          $r->{charset} = lc $1;
198          $r->{charset} =~ tr/\\//d;          $r->{charset} =~ tr/\\//d;
199            $r->{official_charset} = $r->{charset};
200        }        }
201    
202        my $input_charset = $http->get_parameter ('charset');        my $input_charset = $http->get_parameter ('charset');
# Line 829  EOH Line 204  EOH
204          $r->{charset_overridden}          $r->{charset_overridden}
205              = (not defined $r->{charset} or $r->{charset} ne $input_charset);              = (not defined $r->{charset} or $r->{charset} ne $input_charset);
206          $r->{charset} = $input_charset;          $r->{charset} = $input_charset;
207        }        }
208    
209          ## TODO: Support for HTTP Content-Encoding
210    
211        $r->{s} = ''.$res->content;        $r->{s} = ''.$res->content;
212    
213          require Whatpm::ContentType;
214          ($r->{official_type}, $r->{media_type})
215              = Whatpm::ContentType->get_sniffed_type
216                  (get_file_head => sub {
217                     return substr $r->{s}, 0, shift;
218                   },
219                   http_content_type_byte => $ct,
220                   has_http_content_encoding =>
221                       defined $res->header ('Content-Encoding'),
222                   supported_image_types => {});
223      } else {      } else {
224        $r->{uri} = $res->request->uri;        $r->{uri} = $res->request->uri;
225        $r->{request_uri} = $request_uri;        $r->{request_uri} = $request_uri;
# Line 852  EOH Line 240  EOH
240      $r->{charset} = ''.$http->get_parameter ('_charset_');      $r->{charset} = ''.$http->get_parameter ('_charset_');
241      $r->{charset} =~ s/\s+//g;      $r->{charset} =~ s/\s+//g;
242      $r->{charset} = 'utf-8' if $r->{charset} eq '';      $r->{charset} = 'utf-8' if $r->{charset} eq '';
243        $r->{official_charset} = $r->{charset};
244      $r->{header_field} = [];      $r->{header_field} = [];
245    
246        require Whatpm::ContentType;
247        ($r->{official_type}, $r->{media_type})
248            = Whatpm::ContentType->get_sniffed_type
249                (get_file_head => sub {
250                   return substr $r->{s}, 0, shift;
251                 },
252                 http_content_type_byte => undef,
253                 has_http_content_encoding => 0,
254                 supported_image_types => {});
255    }    }
256    
257    my $input_format = $http->get_parameter ('i');    my $input_format = $http->get_parameter ('i');
# Line 869  EOH Line 268  EOH
268    if ($r->{media_type} eq 'text/xml') {    if ($r->{media_type} eq 'text/xml') {
269      unless (defined $r->{charset}) {      unless (defined $r->{charset}) {
270        $r->{charset} = 'us-ascii';        $r->{charset} = 'us-ascii';
271          $r->{official_charset} = $r->{charset};
272      } elsif ($r->{charset_overridden} and $r->{charset} eq 'us-ascii') {      } elsif ($r->{charset_overridden} and $r->{charset} eq 'us-ascii') {
273        $r->{charset_overridden} = 0;        $r->{charset_overridden} = 0;
274      }      }
# Line 880  EOH Line 280  EOH
280      return $r;      return $r;
281    }    }
282    
283      $r->{inner_html_element} = $http->get_parameter ('e');
284    
285    return $r;    return $r;
286  } # get_input_document  } # get_input_document
287    
# Line 912  Wakaba <w@suika.fam.cx>. Line 314  Wakaba <w@suika.fam.cx>.
314    
315  =head1 LICENSE  =head1 LICENSE
316    
317  Copyright 2007 Wakaba <w@suika.fam.cx>  Copyright 2007-2008 Wakaba <w@suika.fam.cx>
318    
319  This library is free software; you can redistribute it  This library is free software; you can redistribute it
320  and/or modify it under the same terms as Perl itself.  and/or modify it under the same terms as Perl itself.
Legend:
Removed from v.1.21  
changed lines
  Added in v.1.59
admin@suikawiki.org
 ViewVC Help
Powered by ViewVC 1.1.24