/[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 1.2 by wakaba, Wed Jun 27 12:35:24 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;    print STDOUT qq[Content-Type: text/html; charset=utf-8
37    my $time1;  
38    my $time2;  <!DOCTYPE html>
39    <html lang="en">
40    <head>
41    <title>Web Document Conformance Checker (BETA)</title>
42    <link rel="stylesheet" href="/www/style/html/xhtml">
43    <style>
44      q {
45        white-space: pre;
46        white-space: -moz-pre-wrap;
47        white-space: pre-wrap;
48      }
49    </style>
50    </head>
51    <body>
52    <h1>Web Document Conformance Checker (<em>beta</em>)</h1>
53    
54    <dl>
55    <dt>Document URI</dt>
56        <dd><code class="URI" lang="">&lt;<a href="@{[htescape $input_uri]}">@{[htescape $input_uri]}</a>&gt;</code></dd>
57    <dt>Internet Media Type</dt>
58        <dd><code class="MIME" lang="en">@{[htescape $input_format]}</code></dd>
59    ]; # no </dl> yet
60    
61    require Message::DOM::DOMImplementation;    require Message::DOM::DOMImplementation;
62    my $dom = Message::DOM::DOMImplementation->____new;    my $dom = Message::DOM::DOMImplementation->____new;
 #  $| = 1;  
63    my $doc;    my $doc;
64    my $el;    my $el;
65    
66  if (@mode == 3 and $mode[0] eq 'html' and    if ($input_format eq 'text/html') {
67      ($mode[2] eq 'html' or $mode[2] eq 'test')) {      require Encode;
68    print STDOUT "Content-Type: text/plain; charset=utf-8\n\n";      require Whatpm::HTML;
69        
70    require Encode;      $s = Encode::decode ('utf-8', $s);
71    require Whatpm::HTML;  
72        print STDOUT qq[
73    $time1 = time;  <dt>Character Encoding</dt>
74    $s = Encode::decode ('utf-8', $s);      <dd>(none)</dd>
75    $time2 = time;  </dl>
76    $time{decode} = $time2 - $time1;  
77      <div id="source-string" class="section">
78    ];
79        print_source_string (\$s);
80        print STDOUT qq[
81    </div>
82    
83    print STDOUT "#errors\n";  <div id="parse-errors" class="section">
84    <h2>Parse Errors</h2>
85    
86    <ul>
87    ];
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 - $time1;  
108    
109    print "#document\n";    print STDOUT qq[
110    </ul>
111    </div>
112    ];
113      } elsif ($input_format eq 'application/xhtml+xml') {
114        require Message::DOM::XMLParserTemp;
115        require Encode;
116        
117        my $t = Encode::decode ('utf-8', $s);
118    
119        print STDOUT qq[
120    <dt>Character Encoding</dt>
121        <dd>(none)</dd>
122    </dl>
123    
124    <div id="source-string" class="section">
125    ];
126        print_source_string (\$t);
127        print STDOUT qq[
128    </div>
129    
130    my $out;  <div id="parse-errors" class="section">
131    if ($mode[2] eq 'html') {  <h2>Parse Errors</h2>
     $time1 = time;  
     $out = Whatpm::HTML->get_inner_html ($el || $doc);  
     $time2 = time;  
     $time{serialize_html} = $time2 - $time1;  
   } else { # test  
     $time1 = time;  
     $out = test_serialize ($el || $doc);  
     $time2 = time;  
     $time{serialize_test} = $time2 - $time1;  
   }  
   print STDOUT Encode::encode ('utf-8', $$out);  
   print STDOUT "\n";  
 } elsif (@mode == 3 and $mode[0] eq 'xhtml' and  
          ($mode[2] eq 'html' or $mode[2] eq 'test')) {  
   print STDOUT "Content-Type: text/plain; charset=utf-8\n\n";  
132    
133    require Message::DOM::XMLParserTemp;  <ul>
134    print STDOUT "#errors\n";  ];
135    
136    my $onerror = sub {    my $onerror = sub {
137      my $err = shift;      my $err = shift;
138      print STDOUT $err->location->line_number, ",";      my $line = $err->location->line_number;
139      print STDOUT $err->location->column_number, ",";      print STDOUT qq[<li><a href="#line-$line">Line $line</a> column ];
140      print STDOUT $err->text, "\n";      print STDOUT $err->location->column_number, ": ";
141        print STDOUT htescape $err->text, "</li>\n";
142      return 1;      return 1;
143    };    };
144    
145    open my $fh, '<', \$s;    open my $fh, '<', \$s;
   my $time1 = time;  
146    $doc = Message::DOM::XMLParserTemp->parse_byte_stream    $doc = Message::DOM::XMLParserTemp->parse_byte_stream
147        ($fh => $dom, $onerror, charset => 'utf-8');        ($fh => $dom, $onerror, charset => 'utf-8');
   my $time2 = time;  
   $time{parse_xml} = $time2 - $time1;  
148    
149    print "#document\n";      print STDOUT qq[
150    </ul>
151    </div>
152    ];
153      } else {
154        print STDOUT qq[
155    </dl>
156    
157    <p><em>Media type <code class="MIME" lang="en">@{[htescape $input_format]}</code> is not supported!</em></p>
158    ];
159      }
160    
161    
162      if (defined $doc or defined $el) {
163        print STDOUT qq[
164    <div id="document-tree" class="section">
165    <h2>Document Tree</h2>
166    ];
167    
168        print_document_tree ($el || $doc);
169    
170        print STDOUT qq[
171    </div>
172    
173    my $out;  <div id="document-errors" class="section">
174    if ($mode[2] eq 'html') {  <h2>Document Errors</h2>
175      ## TODO: Use XHTML serializer  
176      #$out = Whatpm::HTML->get_inner_html ($doc);  <ul>
177    } else { # test  ];
     $time1 = time;  
     $out = test_serialize ($doc);  
     $time2 = time;  
     $time{serialize_test} = $time2 - $time1;  
   }  
   print STDOUT Encode::encode ('utf-8', $$out);  
   print STDOUT "\n";  
 } else {  
   print STDOUT "Status: 404 Not Found\nContent-Type: text/plain; charset=us-ascii\n\n404";  
   exit;  
 }  
178    
   if ($http->parameter ('dom5')) {  
179      require Whatpm::ContentChecker;      require Whatpm::ContentChecker;
180      my $onerror = sub {      my $onerror = sub {
181        my %opt = @_;        my %opt = @_;
182        print STDOUT get_node_path ($opt{node}) . ';' . $opt{type} . "\n";        print STDOUT qq[<li><a href="#node-@{[refaddr $opt{node}]}">],
183              htescape get_node_path ($opt{node}),
184              "</a>: ", htescape $opt{type}, "</li>\n";
185      };      };
186      print STDOUT "#domerrors\n";  
     $time1 = time;  
187      if ($el) {      if ($el) {
188        Whatpm::ContentChecker->check_element ($el, $onerror);        Whatpm::ContentChecker->check_element ($el, $onerror);
189      } else {      } else {
190        Whatpm::ContentChecker->check_document ($doc, $onerror);        Whatpm::ContentChecker->check_document ($doc, $onerror);
191      }      }
     $time2 = time;  
     $time{check} = $time2 - $time1;  
   }  
192    
193    print STDOUT "#log\n";      print STDOUT qq[
194    for (qw/decode parse parse_xml serialize_html serialize_xml serialize_test  </ul>
195            check/) {  </div>
196      next unless defined $time{$_};  ];
     print STDOUT {  
       decode => 'bytes->chars',  
       parse => 'html5(chars)->dom5',  
       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";  
197    }    }
198    
199      ## TODO: Show result
200      print STDOUT qq[
201    </body>
202    </html>
203    ];
204    
205  exit;  exit;
206    
207  sub test_serialize ($) {  sub print_source_string ($) {
208      my $s = $_[0];
209      my $i = 1;
210      print STDOUT qq[<ol lang="">\n];
211      while ($$s =~ /\G([^\x0A]*?)\x0D?\x0A/gc) {
212        print STDOUT qq[<li id="line-$i">], htescape $1, "</li>\n";
213        $i++;
214      }
215      if ($$s =~ /\G([^\x0A]+)/gc) {
216        print STDOUT qq[<li id="line-$i">], htescape $1, "</li>\n";
217      }
218      print STDOUT "</ol>";
219    } # print_input_string
220    
221    sub print_document_tree ($) {
222    my $node = shift;    my $node = shift;
223    my $r = '';    my $r = '<ol class="xoxo">';
224    
225    my @node = map { [$_, ''] } @{$node->child_nodes};    my @node = ($node);
226    while (@node) {    while (@node) {
227      my $child = shift @node;      my $child = shift @node;
228      my $nt = $child->[0]->node_type;      unless (ref $child) {
229      if ($nt == $child->[0]->ELEMENT_NODE) {        $r .= $child;
230        $r .= '| ' . $child->[1] . '<' . $child->[0]->tag_name . ">\x0A"; ## ISSUE: case?        next;
231        }
232        for my $attr (sort {$a->[0] cmp $b->[0]} map { [$_->name, $_->value] }  
233                      @{$child->[0]->attributes}) {      my $node_id = 'node-'.refaddr $child;
234          $r .= '| ' . $child->[1] . '  ' . $attr->[0] . '="'; ## ISSUE: case?      my $nt = $child->node_type;
235          $r .= $attr->[1] . '"' . "\x0A";      if ($nt == $child->ELEMENT_NODE) {
236          $r .= qq'<li id="$node_id"><code>' . htescape ($child->tag_name) .
237              '</code>'; ## ISSUE: case
238    
239          if ($child->has_attributes) {
240            $r .= '<ul class="attributes">';
241            for my $attr (sort {$a->[0] cmp $b->[0]} map { [$_->name, $_->value, 'node-'.refaddr $_] }
242                          @{$child->attributes}) {
243              $r .= qq'<li id="$attr->[2]"><code>' . htescape ($attr->[0]) . '</code> = '; ## ISSUE: case?
244              $r .= '<q>' . htescape ($attr->[1]) . '</q></li>'; ## TODO: children
245            }
246            $r .= '</ul>';
247          }
248    
249          if ($node->has_child_nodes) {
250            $r .= '<ol class="children">';
251            unshift @node, @{$child->child_nodes}, '</ol>';
252          }
253        } elsif ($nt == $child->TEXT_NODE) {
254          $r .= qq'<li id="$node_id"><q>' . htescape ($child->data) . '</q></li>';
255        } elsif ($nt == $child->CDATA_SECTION_NODE) {
256          $r .= qq'<li id="$node_id"><code>&lt;[CDATA[</code><q>' . htescape ($child->data) . '</q><code>]]&gt;</code></li>';
257        } elsif ($nt == $child->COMMENT_NODE) {
258          $r .= qq'<li id="$node_id"><code>&lt;!--</code><q>' . htescape ($child->data) . '</q><code>--&gt;</code></li>';
259        } elsif ($nt == $child->DOCUMENT_NODE) {
260          $r .= qq'<li id="$node_id">Document</li>';
261          if ($child->has_child_nodes) {
262            $r .= '<ol>';
263            unshift @node, @{$child->child_nodes}, '</ol>';
264        }        }
265              } elsif ($nt == $child->DOCUMENT_TYPE_NODE) {
266        unshift @node,        $r .= qq'<li id="$node_id"><code>&lt;!DOCTYPE&gt;</code><ul>';
267          map { [$_, $child->[1] . '  '] } @{$child->[0]->child_nodes};        $r .= '<li>Name = <q>@{[htescape ($child->name)]}</q></li>';
268      } elsif ($nt == $child->[0]->TEXT_NODE) {        $r .= '<li>Public identifier = <q>@{[htescape ($child->public_id)]}</q></li>';
269        $r .= '| ' . $child->[1] . '"' . $child->[0]->data . '"' . "\x0A";        $r .= '<li>System identifier = <q>@{[htescape ($child->system_id)]}</q></li>';
270      } elsif ($nt == $child->[0]->CDATA_SECTION_NODE) {        $r .= '</ul></li>';
271        $r .= '| ' . $child->[1] . '<![CDATA[' . $child->[0]->data . "]]>\x0A";      } elsif ($nt == $child->PROCESSING_INSTRUCTION_NODE) {
272      } elsif ($nt == $child->[0]->COMMENT_NODE) {        $r .= qq'<li id="$node_id"><code>&lt;?@{[htescape ($child->target)]}?&gt;</code>';
273        $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";  
274      } else {      } else {
275        $r .= '| ' . $child->[1] . $child->[0]->node_type . "\x0A"; # error        $r .= qq'<li id="$node_id">@{[$child->node_type]} @{[htescape ($child->node_name)]}</li>'; # error
276      }      }
277    }    }
278      
279    return \$r;    $r .= '</ol>';
280  } # test_serialize    print STDOUT $r;
281    } # print_document_tree
282    
283  sub get_node_path ($) {  sub get_node_path ($) {
284    my $node = shift;    my $node = shift;
Legend:
Removed from v.1.1  
changed lines
  Added in v.1.2
admin@suikawiki.org
 ViewVC Help
Powered by ViewVC 1.1.24