/[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 1.23 by wakaba, Mon Nov 5 09:33:52 2007 UTC revision 1.30 by wakaba, Sat Feb 9 12:22:19 2008 UTC
# Line 52  sub htescape ($) { Line 52  sub htescape ($) {
52    
53    $| = 0;    $| = 0;
54    my $input = get_input_document ($http, $dom);    my $input = get_input_document ($http, $dom);
   my $inner_html_element = $http->get_parameter ('e');  
55    my $char_length = 0;    my $char_length = 0;
56    my %time;    my %time;
57    
# Line 62  sub htescape ($) { Line 61  sub htescape ($) {
61  <dt>Request URI</dt>  <dt>Request URI</dt>
62      <dd><code class="URI" lang="">&lt;<a href="@{[htescape $input->{request_uri}]}">@{[htescape $input->{request_uri}]}</a>&gt;</code></dd>      <dd><code class="URI" lang="">&lt;<a href="@{[htescape $input->{request_uri}]}">@{[htescape $input->{request_uri}]}</a>&gt;</code></dd>
63  <dt>Document URI</dt>  <dt>Document URI</dt>
64      <dd><code class="URI" lang="">&lt;<a href="@{[htescape $input->{uri}]}">@{[htescape $input->{uri}]}</a>&gt;</code></dd>      <dd><code class="URI" lang="">&lt;<a href="@{[htescape $input->{uri}]}" id=anchor-document-uri>@{[htescape $input->{uri}]}</a>&gt;</code>
65        <script>
66          document.title = '<'
67              + document.getElementById ('anchor-document-uri').href + '> \\u2014 '
68              + document.title;
69        </script></dd>
70  ]; # no </dl> yet  ]; # no </dl> yet
71    push @nav, ['#document-info' => 'Information'];    push @nav, ['#document-info' => 'Information'];
72    
# Line 74  if (defined $input->{s}) { Line 78  if (defined $input->{s}) {
78      <dd><code class="URI" lang="">&lt;<a href="@{[htescape $input->{base_uri}]}">@{[htescape $input->{base_uri}]}</a>&gt;</code></dd>      <dd><code class="URI" lang="">&lt;<a href="@{[htescape $input->{base_uri}]}">@{[htescape $input->{base_uri}]}</a>&gt;</code></dd>
79  <dt>Internet Media Type</dt>  <dt>Internet Media Type</dt>
80      <dd><code class="MIME" lang="en">@{[htescape $input->{media_type}]}</code>      <dd><code class="MIME" lang="en">@{[htescape $input->{media_type}]}</code>
81      @{[$input->{media_type_overridden} ? '<em>(overridden)</em>' : '']}</dd>      @{[$input->{media_type_overridden} ? '<em>(overridden)</em>' : defined $input->{official_type} ? $input->{media_type} eq $input->{official_type} ? '' : '<em>(sniffed; official type is: <code class=MIME lang=en>'.htescape ($input->{official_type}).'</code>)' : '<em>(sniffed)</em>']}</dd>
82  <dt>Character Encoding</dt>  <dt>Character Encoding</dt>
83      <dd>@{[defined $input->{charset} ? '<code class="charset" lang="en">'.htescape ($input->{charset}).'</code>' : '(none)']}      <dd>@{[defined $input->{charset} ? '<code class="charset" lang="en">'.htescape ($input->{charset}).'</code>' : '(none)']}
84      @{[$input->{charset_overridden} ? '<em>(overridden)</em>' : '']}</dd>      @{[$input->{charset_overridden} ? '<em>(overridden)</em>' : '']}</dd>
# Line 93  if (defined $input->{s}) { Line 97  if (defined $input->{s}) {
97    
98    if ($input->{media_type} eq 'text/html') {    if ($input->{media_type} eq 'text/html') {
99      ($doc, $el) = print_syntax_error_html_section ($input, $result);      ($doc, $el) = print_syntax_error_html_section ($input, $result);
100      print_source_string_section (\($input->{s}), $input->{charset});      print_source_string_section
101            (\($input->{s}), $input->{charset} || $doc->input_encoding);
102    } elsif ({    } elsif ({
103              'text/xml' => 1,              'text/xml' => 1,
104              'application/atom+xml' => 1,              'application/atom+xml' => 1,
# Line 110  if (defined $input->{s}) { Line 115  if (defined $input->{s}) {
115      print_source_string_section (\($input->{s}), 'utf-8');      print_source_string_section (\($input->{s}), 'utf-8');
116    } else {    } else {
117      ## TODO: Change HTTP status code??      ## TODO: Change HTTP status code??
118      print_result_unknown_type_section ($input);      print_result_unknown_type_section ($input, $result);
119    }    }
120    
121    if (defined $doc or defined $el) {    if (defined $doc or defined $el) {
# Line 143  if (defined $input->{s}) { Line 148  if (defined $input->{s}) {
148  </html>  </html>
149  ];  ];
150    
151    for (qw/decode parse parse_xml parse_manifest check check_manifest/) {    for (qw/decode parse parse_html parse_xml parse_manifest
152              check check_manifest/) {
153      next unless defined $time{$_};      next unless defined $time{$_};
154      open my $file, '>>', ".cc-$_.txt" or die ".cc-$_.txt: $!";      open my $file, '>>', ".cc-$_.txt" or die ".cc-$_.txt: $!";
155      print $file $char_length, "\t", $time{$_}, "\n";      print $file $char_length, "\t", $time{$_}, "\n";
# Line 160  sub add_error ($$$) { Line 166  sub add_error ($$$) {
166        $result->{conforming_min} = 0;        $result->{conforming_min} = 0;
167      } elsif ($err->{level} eq 'w' or $err->{level} eq 'g') {      } elsif ($err->{level} eq 'w' or $err->{level} eq 'g') {
168        $result->{$layer}->{warning}++;        $result->{$layer}->{warning}++;
169      } elsif ($err->{level} eq 'unsupported') {      } elsif ($err->{level} eq 'u' or $err->{level} eq 'unsupported') {
170        $result->{$layer}->{unsupported}++;        $result->{$layer}->{unsupported}++;
171        $result->{unsupported} = 1;        $result->{unsupported} = 1;
172      } else {      } else {
# Line 218  sub print_syntax_error_html_section ($$) Line 224  sub print_syntax_error_html_section ($$)
224        
225    require Encode;    require Encode;
226    require Whatpm::HTML;    require Whatpm::HTML;
   
   $input->{charset} ||= 'ISO-8859-1'; ## TODO: for now.  
227        
   my $time1 = time;  
   my $t = Encode::decode ($input->{charset}, $input->{s});  
   $time{decode} = time - $time1;  
   
228    print STDOUT qq[    print STDOUT qq[
229  <div id="parse-errors" class="section">  <div id="parse-errors" class="section">
230  <h2>Parse Errors</h2>  <h2>Parse Errors</h2>
# Line 252  sub print_syntax_error_html_section ($$) Line 252  sub print_syntax_error_html_section ($$)
252    
253    my $doc = $dom->create_document;    my $doc = $dom->create_document;
254    my $el;    my $el;
255    $time1 = time;    my $inner_html_element = $http->get_parameter ('e');
256    if (defined $inner_html_element and length $inner_html_element) {    if (defined $inner_html_element and length $inner_html_element) {
257        $input->{charset} ||= 'windows-1252'; ## TODO: for now.
258        my $time1 = time;
259        my $t = Encode::decode ($input->{charset}, $input->{s});
260        $time{decode} = time - $time1;
261        
262      $el = $doc->create_element_ns      $el = $doc->create_element_ns
263          ('http://www.w3.org/1999/xhtml', [undef, $inner_html_element]);          ('http://www.w3.org/1999/xhtml', [undef, $inner_html_element]);
264        $time1 = time;
265      Whatpm::HTML->set_inner_html ($el, $t, $onerror);      Whatpm::HTML->set_inner_html ($el, $t, $onerror);
266        $time{parse} = time - $time1;
267    } else {    } else {
268      Whatpm::HTML->parse_string ($t => $doc, $onerror);      my $time1 = time;
269        Whatpm::HTML->parse_byte_string
270            ($input->{charset}, $input->{s} => $doc, $onerror);
271        $time{parse_html} = time - $time1;
272    }    }
273    $time{parse} = time - $time1;    $doc->manakai_charset ($input->{official_charset})
274          if defined $input->{official_charset};
275      
276    print STDOUT qq[</dl></div>];    print STDOUT qq[</dl></div>];
277    
278    return ($doc, $el);    return ($doc, $el);
# Line 301  sub print_syntax_error_xml_section ($$) Line 312  sub print_syntax_error_xml_section ($$)
312    my $doc = Message::DOM::XMLParserTemp->parse_byte_stream    my $doc = Message::DOM::XMLParserTemp->parse_byte_stream
313        ($fh => $dom, $onerror, charset => $input->{charset});        ($fh => $dom, $onerror, charset => $input->{charset});
314    $time{parse_xml} = time - $time1;    $time{parse_xml} = time - $time1;
315      $doc->manakai_charset ($input->{official_charset})
316          if defined $input->{official_charset};
317    
318    print STDOUT qq[</dl></div>];    print STDOUT qq[</dl></div>];
319    
# Line 390  sub print_document_tree ($) { Line 403  sub print_document_tree ($) {
403          $r .= '<ul class="attributes">';          $r .= '<ul class="attributes">';
404          for my $attr (sort {$a->[0] cmp $b->[0]} map { [$_->name, $_->value, $_->namespace_uri, 'node-'.refaddr $_] }          for my $attr (sort {$a->[0] cmp $b->[0]} map { [$_->name, $_->value, $_->namespace_uri, 'node-'.refaddr $_] }
405                        @{$child->attributes}) {                        @{$child->attributes}) {
406            $r .= qq[<li id="$attr->[3]" class="tree-attribute"><code title="@{[defined $_->[2] ? $_->[2] : '']}">] . htescape ($attr->[0]) . '</code> = '; ## ISSUE: case?            $r .= qq[<li id="$attr->[3]" class="tree-attribute"><code title="@{[defined $attr->[2] ? htescape ($attr->[2]) : '']}">] . htescape ($attr->[0]) . '</code> = '; ## ISSUE: case?
407            $r .= '<q>' . htescape ($attr->[1]) . '</q></li>'; ## TODO: children            $r .= '<q>' . htescape ($attr->[1]) . '</q></li>'; ## TODO: children
408          }          }
409          $r .= '</ul>';          $r .= '</ul>';
# Line 411  sub print_document_tree ($) { Line 424  sub print_document_tree ($) {
424      } elsif ($nt == $child->DOCUMENT_NODE) {      } elsif ($nt == $child->DOCUMENT_NODE) {
425        $r .= qq'<li id="$node_id" class="tree-document">Document';        $r .= qq'<li id="$node_id" class="tree-document">Document';
426        $r .= qq[<ul class="attributes">];        $r .= qq[<ul class="attributes">];
427          my $cp = $child->manakai_charset;
428          if (defined $cp) {
429            $r .= qq[<li><code>charset</code> parameter = <code>];
430            $r .= htescape ($cp) . qq[</code></li>];
431          }
432          $r .= qq[<li><code>inputEncoding</code> = ];
433          my $ie = $child->input_encoding;
434          if (defined $ie) {
435            $r .= qq[<code>@{[htescape ($ie)]}</code>];
436            if ($child->manakai_has_bom) {
437              $r .= qq[ (with <code class=charname><abbr>BOM</abbr></code>)];
438            }
439          } else {
440            $r .= qq[(<code>null</code>)];
441          }
442        $r .= qq[<li>@{[scalar get_text ('manakaiIsHTML:'.($child->manakai_is_html?1:0))]}</li>];        $r .= qq[<li>@{[scalar get_text ('manakaiIsHTML:'.($child->manakai_is_html?1:0))]}</li>];
443        $r .= qq[<li>@{[scalar get_text ('manakaiCompatMode:'.$child->manakai_compat_mode)]}</li>];        $r .= qq[<li>@{[scalar get_text ('manakaiCompatMode:'.$child->manakai_compat_mode)]}</li>];
444        unless ($child->manakai_is_html) {        unless ($child->manakai_is_html) {
# Line 759  is <em>under development</em>.  The resu Line 787  is <em>under development</em>.  The resu
787    push @nav, ['#result-summary' => 'Result'];    push @nav, ['#result-summary' => 'Result'];
788  } # print_result_section  } # print_result_section
789    
790  sub print_result_unknown_type_section ($) {  sub print_result_unknown_type_section ($$) {
791    my $input = shift;    my ($input, $result) = @_;
792    
793      my $euri = htescape ($input->{uri});
794    print STDOUT qq[    print STDOUT qq[
795  <div id="result-summary" class="section">  <div id="parse-errors" class="section">
796  <p><em>Media type <code class="MIME" lang="en">@{[htescape $input->{media_type}]}</code> is not supported!</em></p>  <h2>Errors</h2>
797    
798    <dl>
799    <dt class=unsupported><code>&lt;<a href="$euri">$euri</a>&gt;</code></dt>
800        <dd class=unsupported><strong><a href="../error-description#level-u">Not
801            supported</a></strong>:
802        Media type
803        <code class="MIME" lang="en">@{[htescape $input->{media_type}]}</code>
804        is not supported.</dd>
805    </dl>
806  </div>  </div>
807  ];  ];
808    push @nav, ['#result-summary' => 'Result'];    push @nav, ['#parse-errors' => 'Errors'];
809      add_error (char => {level => 'u'} => $result);
810      add_error (syntax => {level => 'u'} => $result);
811      add_error (structure => {level => 'u'} => $result);
812  } # print_result_unknown_type_section  } # print_result_unknown_type_section
813    
814  sub print_result_input_error_section ($) {  sub print_result_input_error_section ($) {
# Line 824  sub get_error_level_label ($) { Line 865  sub get_error_level_label ($) {
865    } elsif ($err->{level} eq 'w') {    } elsif ($err->{level} eq 'w') {
866      $r = qq[<strong><a href="../error-description#level-w">Warning</a></strong>:      $r = qq[<strong><a href="../error-description#level-w">Warning</a></strong>:
867          ];          ];
868    } elsif ($err->{level} eq 'unsupported') {    } elsif ($err->{level} eq 'u' or $err->{level} eq 'unsupported') {
869      $r = qq[<strong><a href="../error-description#level-u">Not      $r = qq[<strong><a href="../error-description#level-u">Not
870          supported</a></strong>: ];          supported</a></strong>: ];
871    } else {    } else {
# Line 873  sub get_node_link ($) { Line 914  sub get_node_link ($) {
914    
915  sub load_text_catalog ($) {  sub load_text_catalog ($) {
916    my $lang = shift; # MUST be a canonical lang name    my $lang = shift; # MUST be a canonical lang name
917    open my $file, '<', "cc-msg.$lang.txt" or die "$0: cc-msg.$lang.txt: $!";    open my $file, '<:utf8', "cc-msg.$lang.txt"
918          or die "$0: cc-msg.$lang.txt: $!";
919    while (<$file>) {    while (<$file>) {
920      if (s/^([^;]+);([^;]*);//) {      if (s/^([^;]+);([^;]*);//) {
921        my ($type, $cls, $msg) = ($1, $2, $_);        my ($type, $cls, $msg) = ($1, $2, $_);
# Line 886  sub load_text_catalog ($) { Line 928  sub load_text_catalog ($) {
928  sub get_text ($) {  sub get_text ($) {
929    my ($type, $level, $node) = @_;    my ($type, $level, $node) = @_;
930    $type = $level . ':' . $type if defined $level;    $type = $level . ':' . $type if defined $level;
931      $level = 'm' unless defined $level;
932    my @arg;    my @arg;
933    {    {
934      if (defined $Msg->{$type}) {      if (defined $Msg->{$type}) {
# Line 910  sub get_text ($) { Line 953  sub get_text ($) {
953            ? htescape ($node->owner_element->manakai_local_name)            ? htescape ($node->owner_element->manakai_local_name)
954            : ''            : ''
955        }ge;        }ge;
956        return ($type, $Msg->{$type}->[0], $msg);        return ($type, 'level-' . $level . ' ' . $Msg->{$type}->[0], $msg);
957      } elsif ($type =~ s/:([^:]*)$//) {      } elsif ($type =~ s/:([^:]*)$//) {
958        unshift @arg, $1;        unshift @arg, $1;
959        redo;        redo;
960      }      }
961    }    }
962    return ($type, '', htescape ($_[0]));    return ($type, 'level-'.$level, htescape ($_[0]));
963  } # get_text  } # get_text
964    
965  }  }
# Line 972  EOH Line 1015  EOH
1015      $ua->protocols_allowed ([qw/http/]);      $ua->protocols_allowed ([qw/http/]);
1016      $ua->max_size (1000_000);      $ua->max_size (1000_000);
1017      my $req = HTTP::Request->new (GET => $request_uri);      my $req = HTTP::Request->new (GET => $request_uri);
1018        $req->header ('Accept-Encoding' => 'identity, *; q=0');
1019      my $res = $ua->request ($req);      my $res = $ua->request ($req);
1020      ## TODO: 401 sets |is_success| true.      ## TODO: 401 sets |is_success| true.
1021      if ($res->is_success or $http->get_parameter ('error-page')) {      if ($res->is_success or $http->get_parameter ('error-page')) {
# Line 981  EOH Line 1025  EOH
1025    
1026        ## TODO: More strict parsing...        ## TODO: More strict parsing...
1027        my $ct = $res->header ('Content-Type');        my $ct = $res->header ('Content-Type');
       if (defined $ct and $ct =~ m#^([0-9A-Za-z._+-]+/[0-9A-Za-z._+-]+)#) {  
         $r->{media_type} = lc $1;  
       }  
1028        if (defined $ct and $ct =~ /;\s*charset\s*=\s*"?([^\s;"]+)"?/i) {        if (defined $ct and $ct =~ /;\s*charset\s*=\s*"?([^\s;"]+)"?/i) {
1029          $r->{charset} = lc $1;          $r->{charset} = lc $1;
1030          $r->{charset} =~ tr/\\//d;          $r->{charset} =~ tr/\\//d;
1031            $r->{official_charset} = $r->{charset};
1032        }        }
1033    
1034        my $input_charset = $http->get_parameter ('charset');        my $input_charset = $http->get_parameter ('charset');
# Line 994  EOH Line 1036  EOH
1036          $r->{charset_overridden}          $r->{charset_overridden}
1037              = (not defined $r->{charset} or $r->{charset} ne $input_charset);              = (not defined $r->{charset} or $r->{charset} ne $input_charset);
1038          $r->{charset} = $input_charset;          $r->{charset} = $input_charset;
1039        }        }
1040    
1041          ## TODO: Support for HTTP Content-Encoding
1042    
1043        $r->{s} = ''.$res->content;        $r->{s} = ''.$res->content;
1044    
1045          require Whatpm::ContentType;
1046          ($r->{official_type}, $r->{media_type})
1047              = Whatpm::ContentType->get_sniffed_type
1048                  (get_file_head => sub {
1049                     return substr $r->{s}, 0, shift;
1050                   },
1051                   http_content_type_byte => $ct,
1052                   has_http_content_encoding =>
1053                       defined $res->header ('Content-Encoding'),
1054                   supported_image_types => {});
1055      } else {      } else {
1056        $r->{uri} = $res->request->uri;        $r->{uri} = $res->request->uri;
1057        $r->{request_uri} = $request_uri;        $r->{request_uri} = $request_uri;
# Line 1017  EOH Line 1072  EOH
1072      $r->{charset} = ''.$http->get_parameter ('_charset_');      $r->{charset} = ''.$http->get_parameter ('_charset_');
1073      $r->{charset} =~ s/\s+//g;      $r->{charset} =~ s/\s+//g;
1074      $r->{charset} = 'utf-8' if $r->{charset} eq '';      $r->{charset} = 'utf-8' if $r->{charset} eq '';
1075        $r->{official_charset} = $r->{charset};
1076      $r->{header_field} = [];      $r->{header_field} = [];
1077    
1078        require Whatpm::ContentType;
1079        ($r->{official_type}, $r->{media_type})
1080            = Whatpm::ContentType->get_sniffed_type
1081                (get_file_head => sub {
1082                   return substr $r->{s}, 0, shift;
1083                 },
1084                 http_content_type_byte => undef,
1085                 has_http_content_encoding => 0,
1086                 supported_image_types => {});
1087    }    }
1088    
1089    my $input_format = $http->get_parameter ('i');    my $input_format = $http->get_parameter ('i');
# Line 1034  EOH Line 1100  EOH
1100    if ($r->{media_type} eq 'text/xml') {    if ($r->{media_type} eq 'text/xml') {
1101      unless (defined $r->{charset}) {      unless (defined $r->{charset}) {
1102        $r->{charset} = 'us-ascii';        $r->{charset} = 'us-ascii';
1103          $r->{official_charset} = $r->{charset};
1104      } elsif ($r->{charset_overridden} and $r->{charset} eq 'us-ascii') {      } elsif ($r->{charset_overridden} and $r->{charset} eq 'us-ascii') {
1105        $r->{charset_overridden} = 0;        $r->{charset_overridden} = 0;
1106      }      }
Legend:
Removed from v.1.23  
changed lines
  Added in v.1.30
admin@suikawiki.org
 ViewVC Help
Powered by ViewVC 1.1.24