/[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 1.1 by wakaba, Wed Jun 27 11:08:03 2007 UTC revision 1.3 by wakaba, Wed Jun 27 13:30:15 2007 UTC
# Line 5  use lib qw[/home/httpd/html/www/markup/h Line 5  use lib qw[/home/httpd/html/www/markup/h
5             /home/wakaba/work/manakai/lib             /home/wakaba/work/manakai/lib
6             /home/wakaba/public_html/-temp/wiki/lib];             /home/wakaba/public_html/-temp/wiki/lib];
7  use CGI::Carp qw[fatalsToBrowser];  use CGI::Carp qw[fatalsToBrowser];
8  use Time::HiRes qw/time/;  use Scalar::Util qw[refaddr];
9    
10  use SuikaWiki::Input::HTTP; ## TODO: Use some better CGI module  use SuikaWiki::Input::HTTP; ## TODO: Use some better CGI module
11    
12    sub htescape ($) {
13      my $s = $_[0];
14      $s =~ s/&/&/g;
15      $s =~ s/</&lt;/g;
16      $s =~ s/>/&gt;/g;
17      $s =~ s/"/&quot;/g;
18      $s =~ s!([\x00-\x09\x0B-\x1F\x7F-\x80])!sprintf '<var>U+%04X</var>', ord $1!ge;
19      return $s;
20    } # htescape
21    
22  my $http = SuikaWiki::Input::HTTP->new;  my $http = SuikaWiki::Input::HTTP->new;
23    
24  ## TODO: _charset_  ## TODO: _charset_
25    
26  my @mode = split m#/#, scalar $http->meta_variable ('PATH_INFO'), -1;    my $input_format = $http->parameter ('i') || 'text/html';
27  shift @mode if @mode and $mode[0] == '';    my $inner_html_element = $http->parameter ('e');
28  ## TODO: decode unreserved characters    my $input_uri = 'thismessage:/';
29    
30    my $s = $http->parameter ('s');    my $s = $http->parameter ('s');
31    if (length $s > 1000_000) {    if (length $s > 1000_000) {
32      print STDOUT "Status: 400 Document Too Long\nContent-Type: text/plain; charset=us-ascii\n\nToo long";      print STDOUT "Status: 400 Document Too Long\nContent-Type: text/plain; charset=us-ascii\n\nToo long";
33      exit;      exit;
34    }    }
35    my $char_length = length $s;  
36    my %time;    my @nav;
37    my $time1;    print STDOUT qq[Content-Type: text/html; charset=utf-8
38    my $time2;  
39    <!DOCTYPE html>
40    <html lang="en">
41    <head>
42    <title>Web Document Conformance Checker (BETA)</title>
43    <link rel="stylesheet" href="../cc-style.css" type="text/css">
44    </head>
45    <body>
46    <h1>Web Document Conformance Checker (<em>beta</em>)</h1>
47    
48    <div id="document-info" section="section">
49    <dl>
50    <dt>Document URI</dt>
51        <dd><code class="URI" lang="">&lt;<a href="@{[htescape $input_uri]}">@{[htescape $input_uri]}</a>&gt;</code></dd>
52    <dt>Internet Media Type</dt>
53        <dd><code class="MIME" lang="en">@{[htescape $input_format]}</code></dd>
54    ]; # no </dl> yet
55      push @nav, ['#document-info' => 'Information'];
56    
57    require Message::DOM::DOMImplementation;    require Message::DOM::DOMImplementation;
58    my $dom = Message::DOM::DOMImplementation->____new;    my $dom = Message::DOM::DOMImplementation->____new;
 #  $| = 1;  
59    my $doc;    my $doc;
60    my $el;    my $el;
61    
62  if (@mode == 3 and $mode[0] eq 'html' and    if ($input_format eq 'text/html') {
63      ($mode[2] eq 'html' or $mode[2] eq 'test')) {      require Encode;
64    print STDOUT "Content-Type: text/plain; charset=utf-8\n\n";      require Whatpm::HTML;
65        
66    require Encode;      $s = Encode::decode ('utf-8', $s);
67    require Whatpm::HTML;  
68        print STDOUT qq[
69    $time1 = time;  <dt>Character Encoding</dt>
70    $s = Encode::decode ('utf-8', $s);      <dd>(none)</dd>
71    $time2 = time;  </dl>
72    $time{decode} = $time2 - $time1;  </div>
73      
74    <div id="source-string" class="section">
75    print STDOUT "#errors\n";  <h2>Document Source</h2>
76    ];
77        push @nav, ['#source-string' => 'Source'];
78        print_source_string (\$s);
79        print STDOUT qq[
80    </div>
81    
82    <div id="parse-errors" class="section">
83    <h2>Parse Errors</h2>
84    
85    <ul>
86    ];
87      push @nav, ['#parse-errors' => 'Parse Error'];
88    
89    my $onerror = sub {    my $onerror = sub {
90      my (%opt) = @_;      my (%opt) = @_;
91      print STDOUT "$opt{line},$opt{column},$opt{type}\n";      if ($opt{column} > 0) {
92          print STDOUT qq[<li><a href="#line-$opt{line}">Line $opt{line}</a> column $opt{column}: ];
93        } else {
94          $opt{line}--;
95          print STDOUT qq[<li><a href="#line-$opt{line}">Line $opt{line}</a>: ];
96        }
97        print STDOUT qq[@{[htescape $opt{type}]}</li>\n];
98    };    };
99    
100    $doc = $dom->create_document;    $doc = $dom->create_document;
101    $time1 = time;    if (defined $inner_html_element and length $inner_html_element) {
   if (length $mode[1]) {  
102      $el = $doc->create_element_ns      $el = $doc->create_element_ns
103          ('http://www.w3.org/1999/xhtml', [undef, $mode[1]]);          ('http://www.w3.org/1999/xhtml', [undef, $inner_html_element]);
104      Whatpm::HTML->set_inner_html ($el, $s, $onerror);      Whatpm::HTML->set_inner_html ($el, $s, $onerror);
105    } else {    } else {
106      Whatpm::HTML->parse_string ($s => $doc, $onerror);      Whatpm::HTML->parse_string ($s => $doc, $onerror);
107    }    }
   $time2 = time;  
   $time{parse} = $time2 - $time1;  
108    
109    print "#document\n";    print STDOUT qq[
110    </ul>
111    my $out;  </div>
112    if ($mode[2] eq 'html') {  ];
113      $time1 = time;    } elsif ($input_format eq 'application/xhtml+xml') {
114      $out = Whatpm::HTML->get_inner_html ($el || $doc);      require Message::DOM::XMLParserTemp;
115      $time2 = time;      require Encode;
116      $time{serialize_html} = $time2 - $time1;      
117    } else { # test      my $t = Encode::decode ('utf-8', $s);
118      $time1 = time;  
119      $out = test_serialize ($el || $doc);      print STDOUT qq[
120      $time2 = time;  <dt>Character Encoding</dt>
121      $time{serialize_test} = $time2 - $time1;      <dd>(none)</dd>
122    }  </dl>
123    print STDOUT Encode::encode ('utf-8', $$out);  </div>
124    print STDOUT "\n";  
125  } elsif (@mode == 3 and $mode[0] eq 'xhtml' and  <div id="source-string" class="section">
126           ($mode[2] eq 'html' or $mode[2] eq 'test')) {  <h2>Document Source</h2>
127    print STDOUT "Content-Type: text/plain; charset=utf-8\n\n";  ];
128        push @nav, ['#source-string' => 'Source'];
129    require Message::DOM::XMLParserTemp;      print_source_string (\$t);
130    print STDOUT "#errors\n";      print STDOUT qq[
131    </div>
132    
133    <div id="parse-errors" class="section">
134    <h2>Parse Errors</h2>
135    
136    <ul>
137    ];
138      push @nav, ['#parse-errors' => 'Parse Error'];
139    
140    my $onerror = sub {    my $onerror = sub {
141      my $err = shift;      my $err = shift;
142      print STDOUT $err->location->line_number, ",";      my $line = $err->location->line_number;
143      print STDOUT $err->location->column_number, ",";      print STDOUT qq[<li><a href="#line-$line">Line $line</a> column ];
144      print STDOUT $err->text, "\n";      print STDOUT $err->location->column_number, ": ";
145        print STDOUT htescape $err->text, "</li>\n";
146      return 1;      return 1;
147    };    };
148    
149    open my $fh, '<', \$s;    open my $fh, '<', \$s;
   my $time1 = time;  
150    $doc = Message::DOM::XMLParserTemp->parse_byte_stream    $doc = Message::DOM::XMLParserTemp->parse_byte_stream
151        ($fh => $dom, $onerror, charset => 'utf-8');        ($fh => $dom, $onerror, charset => 'utf-8');
   my $time2 = time;  
   $time{parse_xml} = $time2 - $time1;  
152    
153    print "#document\n";      print STDOUT qq[
154    </ul>
155    </div>
156    ];
157      } else {
158        print STDOUT qq[
159    </dl>
160    
161    <div id="result-summary" class="section">
162    <p><em>Media type <code class="MIME" lang="en">@{[htescape $input_format]}</code> is not supported!</em></p>
163    </div>
164    ];
165        push @nav, ['#result-summary' => 'Result'];
166      }
167    
168    
169    my $out;    if (defined $doc or defined $el) {
170    if ($mode[2] eq 'html') {      print STDOUT qq[
171      ## TODO: Use XHTML serializer  <div id="document-tree" class="section">
172      #$out = Whatpm::HTML->get_inner_html ($doc);  <h2>Document Tree</h2>
173    } else { # test  ];
174      $time1 = time;      push @nav, ['#document-tree' => 'Tree'];
175      $out = test_serialize ($doc);  
176      $time2 = time;      print_document_tree ($el || $doc);
177      $time{serialize_test} = $time2 - $time1;  
178    }      print STDOUT qq[
179    print STDOUT Encode::encode ('utf-8', $$out);  </div>
180    print STDOUT "\n";  
181  } else {  <div id="document-errors" class="section">
182    print STDOUT "Status: 404 Not Found\nContent-Type: text/plain; charset=us-ascii\n\n404";  <h2>Document Errors</h2>
183    exit;  
184  }  <ul>
185    ];
186        push @nav, ['#document-errors' => 'Document Error'];
187    
   if ($http->parameter ('dom5')) {  
188      require Whatpm::ContentChecker;      require Whatpm::ContentChecker;
189      my $onerror = sub {      my $onerror = sub {
190        my %opt = @_;        my %opt = @_;
191        print STDOUT get_node_path ($opt{node}) . ';' . $opt{type} . "\n";        print STDOUT qq[<li><a href="#node-@{[refaddr $opt{node}]}">],
192              htescape get_node_path ($opt{node}),
193              "</a>: ", htescape $opt{type}, "</li>\n";
194      };      };
195      print STDOUT "#domerrors\n";  
     $time1 = time;  
196      if ($el) {      if ($el) {
197        Whatpm::ContentChecker->check_element ($el, $onerror);        Whatpm::ContentChecker->check_element ($el, $onerror);
198      } else {      } else {
199        Whatpm::ContentChecker->check_document ($doc, $onerror);        Whatpm::ContentChecker->check_document ($doc, $onerror);
200      }      }
201      $time2 = time;  
202      $time{check} = $time2 - $time1;      print STDOUT qq[
203    </ul>
204    </div>
205    ];
206    }    }
207    
208    print STDOUT "#log\n";    ## TODO: Show result
209    for (qw/decode parse parse_xml serialize_html serialize_xml serialize_test  
210            check/) {    print STDOUT qq[
211      next unless defined $time{$_};  <ul class="navigation" id="nav-items">
212      print STDOUT {  ];
213        decode => 'bytes->chars',    for (@nav) {
214        parse => 'html5(chars)->dom5',      print STDOUT qq[<li><a href="$_->[0]">$_->[1]</a></li>];
       parse_xml => 'xml1(chars)->dom5',  
       serialize_html => 'dom5->html5(char)',  
       serialize_xml => 'dom5->xml1(char)',  
       serialize_test => 'dom5->test(char)',  
       check => 'dom5 check',  
     }->{$_};  
     print STDOUT "\t", $time{$_}, "s\n";  
     open my $file, '>>', ".manakai-$_.txt" or die ".manakai-$_.txt: $!";  
     print $file $char_length, "\t", $time{$_}, "\n";  
215    }    }
216      print STDOUT qq[
217    </ul>
218    </body>
219    </html>
220    ];
221    
222  exit;  exit;
223    
224  sub test_serialize ($) {  sub print_source_string ($) {
225      my $s = $_[0];
226      my $i = 1;
227      print STDOUT qq[<ol lang="">\n];
228      while ($$s =~ /\G([^\x0A]*?)\x0D?\x0A/gc) {
229        print STDOUT qq[<li id="line-$i">], htescape $1, "</li>\n";
230        $i++;
231      }
232      if ($$s =~ /\G([^\x0A]+)/gc) {
233        print STDOUT qq[<li id="line-$i">], htescape $1, "</li>\n";
234      }
235      print STDOUT "</ol>";
236    } # print_input_string
237    
238    sub print_document_tree ($) {
239    my $node = shift;    my $node = shift;
240    my $r = '';    my $r = '<ol class="xoxo">';
241    
242    my @node = map { [$_, ''] } @{$node->child_nodes};    my @node = ($node);
243    while (@node) {    while (@node) {
244      my $child = shift @node;      my $child = shift @node;
245      my $nt = $child->[0]->node_type;      unless (ref $child) {
246      if ($nt == $child->[0]->ELEMENT_NODE) {        $r .= $child;
247        $r .= '| ' . $child->[1] . '<' . $child->[0]->tag_name . ">\x0A"; ## ISSUE: case?        next;
248        }
249        for my $attr (sort {$a->[0] cmp $b->[0]} map { [$_->name, $_->value] }  
250                      @{$child->[0]->attributes}) {      my $node_id = 'node-'.refaddr $child;
251          $r .= '| ' . $child->[1] . '  ' . $attr->[0] . '="'; ## ISSUE: case?      my $nt = $child->node_type;
252          $r .= $attr->[1] . '"' . "\x0A";      if ($nt == $child->ELEMENT_NODE) {
253          $r .= qq'<li id="$node_id"><code>' . htescape ($child->tag_name) .
254              '</code>'; ## ISSUE: case
255    
256          if ($child->has_attributes) {
257            $r .= '<ul class="attributes">';
258            for my $attr (sort {$a->[0] cmp $b->[0]} map { [$_->name, $_->value, 'node-'.refaddr $_] }
259                          @{$child->attributes}) {
260              $r .= qq'<li id="$attr->[2]"><code>' . htescape ($attr->[0]) . '</code> = '; ## ISSUE: case?
261              $r .= '<q>' . htescape ($attr->[1]) . '</q></li>'; ## TODO: children
262            }
263            $r .= '</ul>';
264          }
265    
266          if ($node->has_child_nodes) {
267            $r .= '<ol class="children">';
268            unshift @node, @{$child->child_nodes}, '</ol>';
269          }
270        } elsif ($nt == $child->TEXT_NODE) {
271          $r .= qq'<li id="$node_id"><q>' . htescape ($child->data) . '</q></li>';
272        } elsif ($nt == $child->CDATA_SECTION_NODE) {
273          $r .= qq'<li id="$node_id"><code>&lt;[CDATA[</code><q>' . htescape ($child->data) . '</q><code>]]&gt;</code></li>';
274        } elsif ($nt == $child->COMMENT_NODE) {
275          $r .= qq'<li id="$node_id"><code>&lt;!--</code><q>' . htescape ($child->data) . '</q><code>--&gt;</code></li>';
276        } elsif ($nt == $child->DOCUMENT_NODE) {
277          $r .= qq'<li id="$node_id">Document</li>';
278          if ($child->has_child_nodes) {
279            $r .= '<ol>';
280            unshift @node, @{$child->child_nodes}, '</ol>';
281        }        }
282              } elsif ($nt == $child->DOCUMENT_TYPE_NODE) {
283        unshift @node,        $r .= qq'<li id="$node_id"><code>&lt;!DOCTYPE&gt;</code><ul>';
284          map { [$_, $child->[1] . '  '] } @{$child->[0]->child_nodes};        $r .= '<li>Name = <q>@{[htescape ($child->name)]}</q></li>';
285      } elsif ($nt == $child->[0]->TEXT_NODE) {        $r .= '<li>Public identifier = <q>@{[htescape ($child->public_id)]}</q></li>';
286        $r .= '| ' . $child->[1] . '"' . $child->[0]->data . '"' . "\x0A";        $r .= '<li>System identifier = <q>@{[htescape ($child->system_id)]}</q></li>';
287      } elsif ($nt == $child->[0]->CDATA_SECTION_NODE) {        $r .= '</ul></li>';
288        $r .= '| ' . $child->[1] . '<![CDATA[' . $child->[0]->data . "]]>\x0A";      } elsif ($nt == $child->PROCESSING_INSTRUCTION_NODE) {
289      } elsif ($nt == $child->[0]->COMMENT_NODE) {        $r .= qq'<li id="$node_id"><code>&lt;?@{[htescape ($child->target)]}?&gt;</code>';
290        $r .= '| ' . $child->[1] . '<!-- ' . $child->[0]->data . " -->\x0A";        $r .= '<ul><li>@{[htescape ($child->data)]}</li></ul></li>';
     } elsif ($nt == $child->[0]->DOCUMENT_TYPE_NODE) {  
       $r .= '| ' . $child->[1] . '<!DOCTYPE ' . $child->[0]->name . ">\x0A";  
     } elsif ($nt == $child->[0]->PROCESSING_INSTRUCTION_NODE) {  
       $r .= '| ' . $child->[1] . '<?' . $child->[0]->target . ' ' .  
           $child->[0]->data . "?>\x0A";  
291      } else {      } else {
292        $r .= '| ' . $child->[1] . $child->[0]->node_type . "\x0A"; # error        $r .= qq'<li id="$node_id">@{[$child->node_type]} @{[htescape ($child->node_name)]}</li>'; # error
293      }      }
294    }    }
295      
296    return \$r;    $r .= '</ol>';
297  } # test_serialize    print STDOUT $r;
298    } # print_document_tree
299    
300  sub get_node_path ($) {  sub get_node_path ($) {
301    my $node = shift;    my $node = shift;
Legend:
Removed from v.1.1  
changed lines
  Added in v.1.3
admin@suikawiki.org
 ViewVC Help
Powered by ViewVC 1.1.24