1 |
#!/usr/bin/perl |
#!/usr/bin/perl |
2 |
use strict; |
use strict; |
3 |
|
use utf8; |
4 |
|
|
5 |
use lib qw[/home/httpd/html/www/markup/html/whatpm |
use lib qw[/home/httpd/html/www/markup/html/whatpm |
6 |
/home/wakaba/work/manakai/lib |
/home/wakaba/work/manakai2/lib]; |
|
/home/wakaba/public_html/-temp/wiki/lib]; |
|
7 |
use CGI::Carp qw[fatalsToBrowser]; |
use CGI::Carp qw[fatalsToBrowser]; |
8 |
use Scalar::Util qw[refaddr]; |
use Scalar::Util qw[refaddr]; |
9 |
|
|
10 |
use SuikaWiki::Input::HTTP; ## TODO: Use some better CGI module |
require WebHACC::Input; |
11 |
|
require WebHACC::Result; |
12 |
|
require WebHACC::Output; |
13 |
|
|
14 |
sub htescape ($) { |
my $out; |
|
my $s = $_[0]; |
|
|
$s =~ s/&/&/g; |
|
|
$s =~ s/</</g; |
|
|
$s =~ s/>/>/g; |
|
|
$s =~ s/"/"/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 |
|
15 |
|
|
16 |
my $http = SuikaWiki::Input::HTTP->new; |
require Message::DOM::DOMImplementation; |
17 |
|
my $dom = Message::DOM::DOMImplementation->new; |
18 |
## TODO: _charset_ |
{ |
19 |
|
use Message::CGI::HTTP; |
20 |
|
my $http = Message::CGI::HTTP->new; |
21 |
|
|
22 |
if ($http->meta_variable ('PATH_INFO') ne '/') { |
if ($http->get_meta_variable ('PATH_INFO') ne '/') { |
23 |
print STDOUT "Status: 404 Not Found\nContent-Type: text/plain; charset=us-ascii\n\n400"; |
print STDOUT "Status: 404 Not Found\nContent-Type: text/plain; charset=us-ascii\n\n400"; |
24 |
exit; |
exit; |
25 |
} |
} |
26 |
|
|
|
binmode STDOUT, ':utf8'; |
|
|
$| = 1; |
|
|
|
|
|
require Message::DOM::DOMImplementation; |
|
|
my $dom = Message::DOM::DOMImplementation->new; |
|
|
|
|
27 |
load_text_catalog ('en'); ## TODO: conneg |
load_text_catalog ('en'); ## TODO: conneg |
28 |
|
|
29 |
my @nav; |
$out = WebHACC::Output->new; |
30 |
print STDOUT qq[Content-Type: text/html; charset=utf-8 |
$out->handle (*STDOUT); |
31 |
|
$out->set_utf8; |
32 |
|
$out->set_flush; |
33 |
|
$out->html (qq[Content-Type: text/html; charset=utf-8 |
34 |
|
|
35 |
<!DOCTYPE html> |
<!DOCTYPE html> |
36 |
<html lang="en"> |
<html lang="en"> |
41 |
<body> |
<body> |
42 |
<h1><a href="../cc-interface">Web Document Conformance Checker</a> |
<h1><a href="../cc-interface">Web Document Conformance Checker</a> |
43 |
(<em>beta</em>)</h1> |
(<em>beta</em>)</h1> |
44 |
]; |
]); |
45 |
|
|
|
$| = 0; |
|
46 |
my $input = get_input_document ($http, $dom); |
my $input = get_input_document ($http, $dom); |
47 |
my $inner_html_element = $http->parameter ('e'); |
$out->input ($input); |
48 |
|
$out->unset_flush; |
49 |
|
|
50 |
print qq[ |
my $char_length = 0; |
|
<div id="document-info" class="section"> |
|
|
<dl> |
|
|
<dt>Request URI</dt> |
|
|
<dd><code class="URI" lang=""><<a href="@{[htescape $input->{request_uri}]}">@{[htescape $input->{request_uri}]}</a>></code></dd> |
|
|
<dt>Document URI</dt> |
|
|
<dd><code class="URI" lang=""><<a href="@{[htescape $input->{uri}]}">@{[htescape $input->{uri}]}</a>></code></dd> |
|
|
]; # no </dl> yet |
|
|
push @nav, ['#document-info' => 'Information']; |
|
|
|
|
|
if (defined $input->{s}) { |
|
51 |
|
|
52 |
print STDOUT qq[ |
$out->start_section (id => 'document-info', title => 'Information'); |
53 |
<dt>Base URI</dt> |
$out->html (qq[<dl> |
54 |
<dd><code class="URI" lang=""><<a href="@{[htescape $input->{base_uri}]}">@{[htescape $input->{base_uri}]}</a>></code></dd> |
<dt>Request URL</dt> |
55 |
<dt>Internet Media Type</dt> |
<dd>]); |
56 |
<dd><code class="MIME" lang="en">@{[htescape $input->{media_type}]}</code> |
$out->url ($input->{request_uri}); |
57 |
@{[$input->{media_type_overridden} ? '<em>(overridden)</em>' : '']}</dd> |
$out->html (q[<dt>Document URL<!-- HTML5 document's address? --> |
58 |
<dt>Character Encoding</dt> |
<dd>]); |
59 |
<dd>@{[defined $input->{charset} ? '<code class="charset" lang="en">'.htescape ($input->{charset}).'</code>' : '(none)']} |
$out->url ($input->{uri}, id => 'anchor-document-url'); |
60 |
@{[$input->{charset_overridden} ? '<em>(overridden)</em>' : '']}</dd> |
$out->html (q[ |
61 |
|
<script> |
62 |
|
document.title = '<' |
63 |
|
+ document.getElementById ('anchor-document-url').href + '> \\u2014 ' |
64 |
|
+ document.title; |
65 |
|
</script>]); |
66 |
|
## NOTE: no </dl> yet |
67 |
|
|
68 |
|
if (defined $input->{s}) { |
69 |
|
$char_length = length $input->{s}; |
70 |
|
|
71 |
|
$out->html (qq[<dt>Base URI<dd>]); |
72 |
|
$out->url ($input->{base_uri}); |
73 |
|
$out->html (qq[<dt>Internet Media Type</dt> |
74 |
|
<dd><code class="MIME" lang="en">]); |
75 |
|
$out->text ($input->{media_type}); |
76 |
|
$out->html (qq[</code> ]); |
77 |
|
if ($input->{media_type_overridden}) { |
78 |
|
$out->html ('<em>(overridden)</em>'); |
79 |
|
} elsif (defined $input->{official_type}) { |
80 |
|
if ($input->{media_type} eq $input->{official_type}) { |
81 |
|
# |
82 |
|
} else { |
83 |
|
$out->html ('<em>(sniffed; official type is: <code class=MIME lang=en>'); |
84 |
|
$out->text ($input->{official_type}); |
85 |
|
$out->html ('</code>)'); |
86 |
|
} |
87 |
|
} else { |
88 |
|
$out->html ('<em>(sniffed)</em>'); |
89 |
|
} |
90 |
|
$out->html (q[<dt>Character Encoding<dd>]); |
91 |
|
if (defined $input->{charset}) { |
92 |
|
$out->html ('<code class="charset" lang="en">'); |
93 |
|
$out->text ($input->{charset}); |
94 |
|
$out->html ('</code>'); |
95 |
|
} else { |
96 |
|
$out->text ('(none)'); |
97 |
|
} |
98 |
|
$out->html (' <em>overridden</em>') if $input->{charset_overridden}; |
99 |
|
$out->html (qq[ |
100 |
|
<dt>Length</dt> |
101 |
|
<dd>$char_length byte@{[$char_length == 1 ? '' : 's']}</dd> |
102 |
</dl> |
</dl> |
|
</div> |
|
|
]; |
|
103 |
|
|
104 |
print_http_header_section ($input); |
<script src="../cc-script.js"></script> |
105 |
|
]); |
106 |
my $doc; |
$out->end_section; |
107 |
my $el; |
|
108 |
|
my $result = WebHACC::Result->new; |
109 |
if ($input->{media_type} eq 'text/html') { |
$result->{conforming_min} = 1; |
110 |
require Encode; |
$result->{conforming_max} = 1; |
111 |
require Whatpm::HTML; |
check_and_print ($input => $result => $out); |
112 |
|
print_result_section ($result); |
113 |
|
} else { |
114 |
|
$out->html ('</dl>'); |
115 |
|
$out->end_section; |
116 |
|
print_result_input_error_section ($input); |
117 |
|
} |
118 |
|
|
119 |
$input->{charset} ||= 'ISO-8859-1'; ## TODO: for now. |
$out->nav_list; |
|
|
|
|
my $t = Encode::decode ($input->{charset}, $input->{s}); |
|
120 |
|
|
121 |
print STDOUT qq[ |
exit; |
122 |
<div id="parse-errors" class="section"> |
} |
|
<h2>Parse Errors</h2> |
|
|
|
|
|
<dl>]; |
|
|
push @nav, ['#parse-errors' => 'Parse Error']; |
|
123 |
|
|
124 |
my $onerror = sub { |
sub add_error ($$$) { |
125 |
my (%opt) = @_; |
my ($layer, $err, $result) = @_; |
126 |
my ($type, $cls, $msg) = get_text ($opt{type}, $opt{level}); |
if (defined $err->{level}) { |
127 |
if ($opt{column} > 0) { |
if ($err->{level} eq 's') { |
128 |
print STDOUT qq[<dt class="$cls"><a href="#line-$opt{line}">Line $opt{line}</a> column $opt{column}</dt>\n]; |
$result->{$layer}->{should}++; |
129 |
|
$result->{$layer}->{score_min} -= 2; |
130 |
|
$result->{conforming_min} = 0; |
131 |
|
} elsif ($err->{level} eq 'w' or $err->{level} eq 'g') { |
132 |
|
$result->{$layer}->{warning}++; |
133 |
|
} elsif ($err->{level} eq 'u' or $err->{level} eq 'unsupported') { |
134 |
|
$result->{$layer}->{unsupported}++; |
135 |
|
$result->{unsupported} = 1; |
136 |
|
} elsif ($err->{level} eq 'i') { |
137 |
|
# |
138 |
} else { |
} else { |
139 |
$opt{line} = $opt{line} - 1 || 1; |
$result->{$layer}->{must}++; |
140 |
print STDOUT qq[<dt class="$cls"><a href="#line-$opt{line}">Line $opt{line}</a></dt>\n]; |
$result->{$layer}->{score_max} -= 2; |
141 |
|
$result->{$layer}->{score_min} -= 2; |
142 |
|
$result->{conforming_min} = 0; |
143 |
|
$result->{conforming_max} = 0; |
144 |
} |
} |
|
$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]; |
|
|
}; |
|
|
|
|
|
$doc = $dom->create_document; |
|
|
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); |
|
145 |
} else { |
} else { |
146 |
Whatpm::HTML->parse_string ($t => $doc, $onerror); |
$result->{$layer}->{must}++; |
147 |
} |
$result->{$layer}->{score_max} -= 2; |
148 |
|
$result->{$layer}->{score_min} -= 2; |
149 |
|
$result->{conforming_min} = 0; |
150 |
|
$result->{conforming_max} = 0; |
151 |
|
} |
152 |
|
} # add_error |
153 |
|
|
154 |
|
sub check_and_print ($$$) { |
155 |
|
my ($input, $result, $out) = @_; |
156 |
|
my $original_input = $out->input; |
157 |
|
$out->input ($input); |
158 |
|
|
159 |
|
print_http_header_section ($input, $result); |
160 |
|
|
161 |
|
my @subdoc; |
162 |
|
|
163 |
|
my $checker_class = { |
164 |
|
'text/cache-manifest' => 'WebHACC::Language::CacheManifest', |
165 |
|
'text/css' => 'WebHACC::Language::CSS', |
166 |
|
'text/html' => 'WebHACC::Language::HTML', |
167 |
|
'text/x-webidl' => 'WebHACC::Language::WebIDL', |
168 |
|
|
169 |
|
'text/xml' => 'WebHACC::Language::XML', |
170 |
|
'application/atom+xml' => 'WebHACC::Language::XML', |
171 |
|
'application/rss+xml' => 'WebHACC::Language::XML', |
172 |
|
'image/svg+xml' => 'WebHACC::Language::XML', |
173 |
|
'application/xhtml+xml' => 'WebHACC::Language::XML', |
174 |
|
'application/xml' => 'WebHACC::Language::XML', |
175 |
|
## TODO: Should we make all XML MIME Types fall |
176 |
|
## into this category? |
177 |
|
|
178 |
|
## NOTE: This type has different model from normal XML types. |
179 |
|
'application/rdf+xml' => 'WebHACC::Language::XML', |
180 |
|
}->{$input->{media_type}} || 'WebHACC::Language::Default'; |
181 |
|
|
182 |
|
eval qq{ require $checker_class } or die "$0: Loading $checker_class: $@"; |
183 |
|
my $checker = $checker_class->new; |
184 |
|
$checker->input ($input); |
185 |
|
$checker->output ($out); |
186 |
|
$checker->result ($result); |
187 |
|
|
188 |
|
## TODO: A cache manifest MUST be text/cache-manifest |
189 |
|
## TODO: WebIDL media type "text/x-webidl" |
190 |
|
|
191 |
|
$checker->generate_syntax_error_section; |
192 |
|
$checker->generate_source_string_section; |
193 |
|
|
194 |
|
$checker->onsubdoc (sub { |
195 |
|
push @subdoc, shift; |
196 |
|
}); |
197 |
|
|
198 |
|
$checker->generate_structure_dump_section; |
199 |
|
$checker->generate_structure_error_section; |
200 |
|
$checker->generate_additional_sections; |
201 |
|
|
202 |
print STDOUT qq[</dl> |
=pod |
|
</div> |
|
|
]; |
|
203 |
|
|
204 |
print_source_string_section (\($input->{s}), $input->{charset}); |
if (defined $doc or defined $el) { |
|
} elsif ({ |
|
|
'text/xml' => 1, |
|
|
'application/xhtml+xml' => 1, |
|
|
'application/xml' => 1, |
|
|
}->{$input->{media_type}}) { |
|
|
require Message::DOM::XMLParserTemp; |
|
205 |
|
|
206 |
|
print_table_section ($input, $elements->{table}) if @{$elements->{table}}; |
207 |
|
print_listing_section ({ |
208 |
|
id => 'identifiers', label => 'IDs', heading => 'Identifiers', |
209 |
|
}, $input, $elements->{id}) if keys %{$elements->{id}}; |
210 |
|
print_listing_section ({ |
211 |
|
id => 'terms', label => 'Terms', heading => 'Terms', |
212 |
|
}, $input, $elements->{term}) if keys %{$elements->{term}}; |
213 |
|
print_listing_section ({ |
214 |
|
id => 'classes', label => 'Classes', heading => 'Classes', |
215 |
|
}, $input, $elements->{class}) if keys %{$elements->{class}}; |
216 |
|
|
217 |
|
print_rdf_section ($input, $elements->{rdf}) if @{$elements->{rdf}}; |
218 |
|
} |
219 |
|
|
220 |
|
=cut |
221 |
|
|
222 |
|
my $id_prefix = 0; |
223 |
|
for my $_subinput (@subdoc) { |
224 |
|
my $subinput = WebHACC::Input->new; |
225 |
|
$subinput->{$_} = $_subinput->{$_} for keys %$_subinput; |
226 |
|
$subinput->id_prefix ('subdoc-' . ++$id_prefix); |
227 |
|
$subinput->nested (1); |
228 |
|
$subinput->{base_uri} = $subinput->{container_node}->base_uri |
229 |
|
unless defined $subinput->{base_uri}; |
230 |
|
my $ebaseuri = htescape ($subinput->{base_uri}); |
231 |
|
$out->start_section (id => $subinput->id_prefix, |
232 |
|
title => qq[Subdocument #$id_prefix]); |
233 |
print STDOUT qq[ |
print STDOUT qq[ |
234 |
<div id="parse-errors" class="section"> |
<dl> |
235 |
<h2>Parse Errors</h2> |
<dt>Internet Media Type</dt> |
236 |
|
<dd><code class="MIME" lang="en">@{[htescape $subinput->{media_type}]}</code> |
237 |
<dl>]; |
<dt>Container Node</dt> |
238 |
push @nav, ['#parse-errors' => 'Parse Error']; |
<dd>@{[get_node_link ($input, $subinput->{container_node})]}</dd> |
239 |
|
<dt>Base <abbr title="Uniform Resource Identifiers">URI</abbr></dt> |
240 |
my $onerror = sub { |
<dd><code class=URI><<a href="$ebaseuri">$ebaseuri</a>></code></dd> |
241 |
my $err = shift; |
</dl>]; |
242 |
my $line = $err->location->line_number; |
|
243 |
print STDOUT qq[<dt><a href="#line-$line">Line $line</a> column ]; |
$subinput->{id_prefix} .= '-'; |
244 |
print STDOUT $err->location->column_number, "</dt><dd>"; |
check_and_print ($subinput => $result => $out); |
|
print STDOUT htescape $err->text, "</dd>\n"; |
|
|
return 1; |
|
|
}; |
|
|
|
|
|
open my $fh, '<', \($input->{s}); |
|
|
$doc = Message::DOM::XMLParserTemp->parse_byte_stream |
|
|
($fh => $dom, $onerror, charset => $input->{charset}); |
|
|
|
|
|
print STDOUT qq[</dl> |
|
|
</div> |
|
245 |
|
|
246 |
]; |
$out->end_section; |
|
print_source_string_section (\($input->{s}), $doc->input_encoding); |
|
|
} else { |
|
|
## TODO: Change HTTP status code?? |
|
|
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']; |
|
247 |
} |
} |
248 |
|
|
249 |
|
$out->input ($original_input); |
250 |
|
} # check_and_print |
251 |
|
|
252 |
if (defined $doc or defined $el) { |
sub print_http_header_section ($$) { |
253 |
print STDOUT qq[ |
my ($input, $result) = @_; |
254 |
<div id="document-tree" class="section"> |
return unless defined $input->{header_status_code} or |
255 |
<h2>Document Tree</h2> |
defined $input->{header_status_text} or |
256 |
]; |
@{$input->{header_field} or []}; |
257 |
push @nav, ['#document-tree' => 'Tree']; |
|
258 |
|
$out->start_section (id => 'source-header', title => 'HTTP Header'); |
259 |
print_document_tree ($el || $doc); |
print STDOUT qq[<p><strong>Note</strong>: Due to the limitation of the |
260 |
|
network library in use, the content of this section might |
261 |
print STDOUT qq[ |
not be the real header.</p> |
|
</div> |
|
|
|
|
|
<div id="document-errors" class="section"> |
|
|
<h2>Document Errors</h2> |
|
262 |
|
|
263 |
<dl>]; |
<table><tbody> |
264 |
push @nav, ['#document-errors' => 'Document Error']; |
]; |
265 |
|
|
266 |
require Whatpm::ContentChecker; |
if (defined $input->{header_status_code}) { |
267 |
my $onerror = sub { |
print STDOUT qq[<tr><th scope="row">Status code</th>]; |
268 |
my %opt = @_; |
print STDOUT qq[<td>]; |
269 |
my ($type, $cls, $msg) = get_text ($opt{type}, $opt{level}, $opt{node}); |
$out->code ($input->{header_status_code}); |
270 |
$type =~ tr/ /-/; |
} |
271 |
$type =~ s/\|/%7C/g; |
if (defined $input->{header_status_text}) { |
272 |
$msg .= qq[ [<a href="../error-description#@{[htescape ($type)]}">Description</a>]]; |
print STDOUT qq[<tr><th scope="row">Status text</th>]; |
273 |
print STDOUT qq[<dt class="$cls">] . get_node_link ($opt{node}) . |
print STDOUT qq[<td>]; |
274 |
qq[</dt>\n<dd class="$cls">], $msg, "</dd>\n"; |
$out->code ($input->{header_status_text}); |
275 |
}; |
} |
276 |
|
|
277 |
my $elements; |
for (@{$input->{header_field}}) { |
278 |
if ($el) { |
print STDOUT qq[<tr><th scope="row">]; |
279 |
$elements = Whatpm::ContentChecker->check_element ($el, $onerror); |
$out->code ($_->[0]); |
280 |
} else { |
print STDOUT qq[<td>]; |
281 |
$elements = Whatpm::ContentChecker->check_document ($doc, $onerror); |
$out->code ($_->[1]); |
282 |
} |
} |
283 |
|
|
284 |
print STDOUT qq[</dl> |
print STDOUT qq[</tbody></table>]; |
|
</div> |
|
|
]; |
|
285 |
|
|
286 |
if (@{$elements->{table}}) { |
$out->end_section; |
287 |
require JSON; |
} # print_http_header_section |
288 |
|
|
289 |
push @nav, ['#tables' => 'Tables']; |
sub print_table_section ($$) { |
290 |
print STDOUT qq[ |
my ($input, $tables) = @_; |
291 |
<div id="tables" class="section"> |
|
292 |
|
# push @nav, [qq[#$input->{id_prefix}tables] => 'Tables'] |
293 |
|
# unless $input->{nested}; |
294 |
|
print STDOUT qq[ |
295 |
|
<div id="$input->{id_prefix}tables" class="section"> |
296 |
<h2>Tables</h2> |
<h2>Tables</h2> |
297 |
|
|
298 |
<!--[if IE]><script type="text/javascript" src="../excanvas.js"></script><![endif]--> |
<!--[if IE]><script type="text/javascript" src="../excanvas.js"></script><![endif]--> |
301 |
<p><em>Structure of tables are visualized here if scripting is enabled.</em></p> |
<p><em>Structure of tables are visualized here if scripting is enabled.</em></p> |
302 |
</noscript> |
</noscript> |
303 |
]; |
]; |
304 |
|
|
305 |
my $i = 0; |
require JSON; |
306 |
for my $table_el (@{$elements->{table}}) { |
|
307 |
$i++; |
my $i = 0; |
308 |
print STDOUT qq[<div class="section" id="table-$i"><h3>] . |
for my $table (@$tables) { |
309 |
get_node_link ($table_el) . q[</h3>]; |
$i++; |
310 |
|
print STDOUT qq[<div class="section" id="$input->{id_prefix}table-$i"><h3>] . |
311 |
## TODO: Make |ContentChecker| return |form_table| result |
get_node_link ($input, $table->{element}) . q[</h3>]; |
312 |
## so that this script don't have to run the algorithm twice. |
|
313 |
my $table = Whatpm::HTMLTable->form_table ($table_el); |
delete $table->{element}; |
314 |
|
|
315 |
for (@{$table->{column_group}}, @{$table->{column}}, $table->{caption}) { |
for (@{$table->{column_group}}, @{$table->{column}}, $table->{caption}, |
316 |
next unless $_; |
@{$table->{row}}) { |
317 |
delete $_->{element}; |
next unless $_; |
318 |
} |
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-$i'));</script>]; |
|
|
} |
|
|
|
|
|
print STDOUT qq[</div>]; |
|
|
} |
|
|
|
|
|
if (keys %{$elements->{id}}) { |
|
|
push @nav, ['#identifiers' => 'IDs']; |
|
|
print STDOUT qq[ |
|
|
<div id="identifiers" class="section"> |
|
|
<h2>Identifiers</h2> |
|
|
|
|
|
<dl> |
|
|
]; |
|
|
for my $id (sort {$a cmp $b} keys %{$elements->{id}}) { |
|
|
print STDOUT qq[<dt><code>@{[htescape $id]}</code></dt>]; |
|
|
for (@{$elements->{id}->{$id}}) { |
|
|
print STDOUT qq[<dd>].get_node_link ($_).qq[</dd>]; |
|
|
} |
|
|
} |
|
|
print STDOUT qq[</dl></div>]; |
|
319 |
} |
} |
320 |
|
|
321 |
if (keys %{$elements->{term}}) { |
for (@{$table->{row_group}}) { |
322 |
push @nav, ['#terms' => 'Terms']; |
next unless $_; |
323 |
print STDOUT qq[ |
next unless $_->{element}; |
324 |
<div id="terms" class="section"> |
$_->{type} = $_->{element}->manakai_local_name; |
325 |
<h2>Terms</h2> |
delete $_->{element}; |
|
|
|
|
<dl> |
|
|
]; |
|
|
for my $term (sort {$a cmp $b} keys %{$elements->{term}}) { |
|
|
print STDOUT qq[<dt>@{[htescape $term]}</dt>]; |
|
|
for (@{$elements->{term}->{$term}}) { |
|
|
print STDOUT qq[<dd>].get_node_link ($_).qq[</dd>]; |
|
|
} |
|
|
} |
|
|
print STDOUT qq[</dl></div>]; |
|
326 |
} |
} |
327 |
|
|
328 |
if (keys %{$elements->{class}}) { |
for (@{$table->{cell}}) { |
329 |
push @nav, ['#classes' => 'Classes']; |
next unless $_; |
330 |
print STDOUT qq[ |
for (@{$_}) { |
331 |
<div id="classes" class="section"> |
next unless $_; |
332 |
<h2>Classes</h2> |
for (@$_) { |
333 |
|
$_->{id} = refaddr $_->{element} if defined $_->{element}; |
334 |
<dl> |
delete $_->{element}; |
335 |
]; |
$_->{is_header} = $_->{is_header} ? 1 : 0; |
|
for my $class (sort {$a cmp $b} keys %{$elements->{class}}) { |
|
|
print STDOUT qq[<dt><code>@{[htescape $class]}</code></dt>]; |
|
|
for (@{$elements->{class}->{$class}}) { |
|
|
print STDOUT qq[<dd>].get_node_link ($_).qq[</dd>]; |
|
336 |
} |
} |
337 |
} |
} |
|
print STDOUT qq[</dl></div>]; |
|
338 |
} |
} |
339 |
|
|
340 |
|
print STDOUT '</div><script type="text/javascript">tableToCanvas ('; |
341 |
|
print STDOUT JSON::objToJson ($table); |
342 |
|
print STDOUT qq[, document.getElementById ('$input->{id_prefix}table-$i')]; |
343 |
|
print STDOUT qq[, '$input->{id_prefix}');</script>]; |
344 |
} |
} |
345 |
|
|
346 |
|
print STDOUT qq[</div>]; |
347 |
|
} # print_table_section |
348 |
|
|
349 |
## TODO: Show result |
sub print_listing_section ($$$) { |
350 |
} else { |
my ($opt, $input, $ids) = @_; |
351 |
|
|
352 |
|
# push @nav, ['#' . $input->{id_prefix} . $opt->{id} => $opt->{label}] |
353 |
|
# unless $input->{nested}; |
354 |
print STDOUT qq[ |
print STDOUT qq[ |
355 |
</dl> |
<div id="$input->{id_prefix}$opt->{id}" class="section"> |
356 |
</div> |
<h2>$opt->{heading}</h2> |
357 |
|
|
358 |
<div class="section" id="result-summary"> |
<dl> |
|
<p><em><strong>Input Error</strong>: @{[htescape ($input->{error_status_text})]}</em></p> |
|
|
</div> |
|
|
]; |
|
|
push @nav, ['#result-summary' => 'Result']; |
|
|
|
|
|
} |
|
|
|
|
|
print STDOUT qq[ |
|
|
<ul class="navigation" id="nav-items"> |
|
359 |
]; |
]; |
360 |
for (@nav) { |
for my $id (sort {$a cmp $b} keys %$ids) { |
361 |
print STDOUT qq[<li><a href="$_->[0]">$_->[1]</a></li>]; |
print STDOUT qq[<dt><code>@{[htescape $id]}</code></dt>]; |
362 |
|
for (@{$ids->{$id}}) { |
363 |
|
print STDOUT qq[<dd>].get_node_link ($input, $_).qq[</dd>]; |
364 |
|
} |
365 |
} |
} |
366 |
print STDOUT qq[ |
print STDOUT qq[</dl></div>]; |
367 |
</ul> |
} # print_listing_section |
|
</body> |
|
|
</html> |
|
|
]; |
|
|
|
|
|
exit; |
|
|
|
|
|
sub print_http_header_section ($) { |
|
|
my $input = shift; |
|
|
return unless defined $input->{header_status_code} or |
|
|
defined $input->{header_status_text} or |
|
|
@{$input->{header_field}}; |
|
|
|
|
|
push @nav, ['#source-header' => 'HTTP Header']; |
|
|
print STDOUT qq[<div id="source-header" class="section"> |
|
|
<h2>HTTP Header</h2> |
|
368 |
|
|
|
<p><strong>Note</strong>: Due to the limitation of the |
|
|
network library in use, the content of this section might |
|
|
not be the real header.</p> |
|
|
|
|
|
<table><tbody> |
|
|
]; |
|
369 |
|
|
370 |
if (defined $input->{header_status_code}) { |
sub print_rdf_section ($$$) { |
371 |
print STDOUT qq[<tr><th scope="row">Status code</th>]; |
my ($input, $rdfs) = @_; |
|
print STDOUT qq[<td><code>@{[htescape ($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>]; |
|
|
} |
|
372 |
|
|
373 |
for (@{$input->{header_field}}) { |
# push @nav, ['#' . $input->{id_prefix} . 'rdf' => 'RDF'] |
374 |
print STDOUT qq[<tr><th scope="row"><code>@{[htescape ($_->[0])]}</code></th>]; |
# unless $input->{nested}; |
375 |
print STDOUT qq[<td><code>@{[htescape ($_->[1])]}</code></td></tr>]; |
print STDOUT qq[ |
376 |
} |
<div id="$input->{id_prefix}rdf" class="section"> |
377 |
|
<h2>RDF Triples</h2> |
|
print STDOUT qq[</tbody></table></div>]; |
|
|
} # print_http_header_section |
|
378 |
|
|
379 |
sub print_source_string_section ($$) { |
<dl>]; |
380 |
require Encode; |
my $i = 0; |
381 |
my $enc = Encode::find_encoding ($_[1]); ## TODO: charset name -> Perl name |
for my $rdf (@$rdfs) { |
382 |
return unless $enc; |
print STDOUT qq[<dt id="$input->{id_prefix}rdf-@{[$i++]}">]; |
383 |
|
print STDOUT get_node_link ($input, $rdf->[0]); |
384 |
my $s = \($enc->decode (${$_[0]})); |
print STDOUT qq[<dd><dl>]; |
385 |
my $i = 1; |
for my $triple (@{$rdf->[1]}) { |
386 |
push @nav, ['#source-string' => 'Source']; |
print STDOUT '<dt>' . get_node_link ($input, $triple->[0]) . '<dd>'; |
387 |
print STDOUT qq[<div id="source-string" class="section"> |
print STDOUT get_rdf_resource_html ($triple->[1]); |
388 |
<h2>Document Source</h2> |
print STDOUT ' '; |
389 |
<ol lang="">\n]; |
print STDOUT get_rdf_resource_html ($triple->[2]); |
390 |
if (length $$s) { |
print STDOUT ' '; |
391 |
while ($$s =~ /\G([^\x0A]*?)\x0D?\x0A/gc) { |
print STDOUT get_rdf_resource_html ($triple->[3]); |
392 |
print STDOUT qq[<li id="line-$i">], htescape $1, "</li>\n"; |
} |
393 |
$i++; |
print STDOUT qq[</dl>]; |
394 |
} |
} |
395 |
if ($$s =~ /\G([^\x0A]+)/gc) { |
print STDOUT qq[</dl></div>]; |
396 |
print STDOUT qq[<li id="line-$i">], htescape $1, "</li>\n"; |
} # print_rdf_section |
397 |
|
|
398 |
|
sub get_rdf_resource_html ($) { |
399 |
|
my $resource = shift; |
400 |
|
if (defined $resource->{uri}) { |
401 |
|
my $euri = htescape ($resource->{uri}); |
402 |
|
return '<code class=uri><<a href="' . $euri . '">' . $euri . |
403 |
|
'</a>></code>'; |
404 |
|
} elsif (defined $resource->{bnodeid}) { |
405 |
|
return htescape ('_:' . $resource->{bnodeid}); |
406 |
|
} elsif ($resource->{nodes}) { |
407 |
|
return '(rdf:XMLLiteral)'; |
408 |
|
} elsif (defined $resource->{value}) { |
409 |
|
my $elang = htescape (defined $resource->{language} |
410 |
|
? $resource->{language} : ''); |
411 |
|
my $r = qq[<q lang="$elang">] . htescape ($resource->{value}) . '</q>'; |
412 |
|
if (defined $resource->{datatype}) { |
413 |
|
my $euri = htescape ($resource->{datatype}); |
414 |
|
$r .= '^^<code class=uri><<a href="' . $euri . '">' . $euri . |
415 |
|
'</a>></code>'; |
416 |
|
} elsif (length $resource->{language}) { |
417 |
|
$r .= '@' . htescape ($resource->{language}); |
418 |
} |
} |
419 |
|
return $r; |
420 |
} else { |
} else { |
421 |
print STDOUT q[<li id="line-1"></li>]; |
return '??'; |
422 |
} |
} |
423 |
print STDOUT "</ol></div>"; |
} # get_rdf_resource_html |
|
} # print_input_string_section |
|
424 |
|
|
425 |
sub print_document_tree ($) { |
sub print_result_section ($) { |
426 |
my $node = shift; |
my $result = 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>'; |
|
|
} |
|
427 |
|
|
428 |
if ($child->has_child_nodes) { |
$out->start_section (id => 'result-summary', |
429 |
$r .= '<ol class="children">'; |
title => 'Result'); |
430 |
unshift @node, @{$child->child_nodes}, '</ol></li>'; |
|
431 |
} else { |
if ($result->{unsupported} and $result->{conforming_max}) { |
432 |
$r .= '</li>'; |
print STDOUT qq[<p class=uncertain id=result-para>The conformance |
433 |
} |
checker cannot decide whether the document is conforming or |
434 |
} elsif ($nt == $child->TEXT_NODE) { |
not, since the document contains one or more unsupported |
435 |
$r .= qq'<li id="$node_id" class="tree-text"><q lang="">' . htescape ($child->data) . '</q></li>'; |
features. The document might or might not be conforming.</p>]; |
436 |
} elsif ($nt == $child->CDATA_SECTION_NODE) { |
} elsif ($result->{conforming_min}) { |
437 |
$r .= qq'<li id="$node_id" class="tree-cdata"><code><[CDATA[</code><q lang="">' . htescape ($child->data) . '</q><code>]]></code></li>'; |
print STDOUT qq[<p class=PASS id=result-para>No conformance-error is |
438 |
} elsif ($nt == $child->COMMENT_NODE) { |
found in this document.</p>]; |
439 |
$r .= qq'<li id="$node_id" class="tree-comment"><code><!--</code><q lang="">' . htescape ($child->data) . '</q><code>--></code></li>'; |
} elsif ($result->{conforming_max}) { |
440 |
} elsif ($nt == $child->DOCUMENT_NODE) { |
print STDOUT qq[<p class=SEE-RESULT id=result-para>This document |
441 |
$r .= qq'<li id="$node_id" class="tree-document">Document'; |
is <strong>likely <em>non</em>-conforming</strong>, but in rare case |
442 |
$r .= qq[<ul class="attributes">]; |
it might be conforming.</p>]; |
443 |
$r .= qq[<li>@{[scalar get_text ('manakaiIsHTML:'.($child->manakai_is_html?1:0))]}</li>]; |
} else { |
444 |
$r .= qq[<li>@{[scalar get_text ('manakaiCompatMode:'.$child->manakai_compat_mode)]}</li>]; |
print STDOUT qq[<p class=FAIL id=result-para>This document is |
445 |
unless ($child->manakai_is_html) { |
<strong><em>non</em>-conforming</strong>.</p>]; |
|
$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><!DOCTYPE></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><?@{[htescape ($child->target)]}</code> <q>@{[htescape ($child->data)]}</q><code>?></code></li>'; |
|
|
} else { |
|
|
$r .= qq'<li id="$node_id" class="tree-unknown">@{[$child->node_type]} @{[htescape ($child->node_name)]}</li>'; # error |
|
|
} |
|
446 |
} |
} |
447 |
|
|
448 |
$r .= '</ol>'; |
print STDOUT qq[<table> |
449 |
print STDOUT $r; |
<colgroup><col><colgroup><col><col><col><colgroup><col> |
450 |
} # print_document_tree |
<thead> |
451 |
|
<tr><th scope=col></th> |
452 |
sub get_node_path ($) { |
<th scope=col><a href="../error-description#level-m"><em class=rfc2119>MUST</em>‐level |
453 |
my $node = shift; |
Errors</a></th> |
454 |
my @r; |
<th scope=col><a href="../error-description#level-s"><em class=rfc2119>SHOULD</em>‐level |
455 |
while (defined $node) { |
Errors</a></th> |
456 |
my $rs; |
<th scope=col><a href="../error-description#level-w">Warnings</a></th> |
457 |
if ($node->node_type == 1) { |
<th scope=col>Score</th></tr></thead><tbody>]; |
458 |
$rs = $node->manakai_local_name; |
|
459 |
$node = $node->parent_node; |
my $must_error = 0; |
460 |
} elsif ($node->node_type == 2) { |
my $should_error = 0; |
461 |
$rs = '@' . $node->manakai_local_name; |
my $warning = 0; |
462 |
$node = $node->owner_element; |
my $score_min = 0; |
463 |
} elsif ($node->node_type == 3) { |
my $score_max = 0; |
464 |
$rs = '"' . $node->data . '"'; |
my $score_base = 20; |
465 |
$node = $node->parent_node; |
my $score_unit = $score_base / 100; |
466 |
} elsif ($node->node_type == 9) { |
for ( |
467 |
@r = ('') unless @r; |
[Transfer => 'transfer', ''], |
468 |
$rs = ''; |
[Character => 'char', ''], |
469 |
$node = $node->parent_node; |
[Syntax => 'syntax', '#parse-errors'], |
470 |
|
[Structure => 'structure', '#document-errors'], |
471 |
|
) { |
472 |
|
$must_error += ($result->{$_->[1]}->{must} += 0); |
473 |
|
$should_error += ($result->{$_->[1]}->{should} += 0); |
474 |
|
$warning += ($result->{$_->[1]}->{warning} += 0); |
475 |
|
$score_min += (($result->{$_->[1]}->{score_min} *= $score_unit) += $score_base); |
476 |
|
$score_max += (($result->{$_->[1]}->{score_max} *= $score_unit) += $score_base); |
477 |
|
|
478 |
|
my $uncertain = $result->{$_->[1]}->{unsupported} ? '?' : ''; |
479 |
|
my $label = $_->[0]; |
480 |
|
if ($result->{$_->[1]}->{must} or |
481 |
|
$result->{$_->[1]}->{should} or |
482 |
|
$result->{$_->[1]}->{warning} or |
483 |
|
$result->{$_->[1]}->{unsupported}) { |
484 |
|
$label = qq[<a href="$_->[2]">$label</a>]; |
485 |
|
} |
486 |
|
|
487 |
|
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>]; |
488 |
|
if ($uncertain) { |
489 |
|
print qq[<td class="@{[$result->{$_->[1]}->{must} ? 'FAIL' : $result->{$_->[1]}->{should} ? 'SEE-RESULT' : '']}">−∞..$result->{$_->[1]}->{score_max}]; |
490 |
|
} elsif ($result->{$_->[1]}->{score_min} != $result->{$_->[1]}->{score_max}) { |
491 |
|
print qq[<td class="@{[$result->{$_->[1]}->{must} ? 'FAIL' : 'SEE-RESULT']}">$result->{$_->[1]}->{score_min}..$result->{$_->[1]}->{score_max}]; |
492 |
} else { |
} else { |
493 |
$rs = '#' . $node->node_type; |
print qq[<td class="@{[$result->{$_->[1]}->{must} ? 'FAIL' : '']}">$result->{$_->[1]}->{score_min}]; |
|
$node = $node->parent_node; |
|
494 |
} |
} |
495 |
unshift @r, $rs; |
print qq[ / 20]; |
496 |
} |
} |
|
return join '/', @r; |
|
|
} # get_node_path |
|
497 |
|
|
498 |
sub get_node_link ($) { |
$score_max += $score_base; |
499 |
return qq[<a href="#node-@{[refaddr $_[0]]}">] . |
|
500 |
htescape (get_node_path ($_[0])) . qq[</a>]; |
print STDOUT qq[ |
501 |
} # get_node_link |
<tr class=uncertain><th scope=row>Semantics</th><td>0?</td><td>0?</td><td>0?</td><td>−∞..$score_base / 20 |
502 |
|
</tbody> |
503 |
|
<tfoot><tr class=uncertain><th scope=row>Total</th> |
504 |
|
<td class="@{[$must_error ? 'FAIL' : '']}">$must_error?</td> |
505 |
|
<td class="@{[$should_error ? 'SEE-RESULT' : '']}">$should_error?</td> |
506 |
|
<td>$warning?</td> |
507 |
|
<td class="@{[$must_error ? 'FAIL' : $should_error ? 'SEE-RESULT' : '']}"><strong>−∞..$score_max</strong> / 100 |
508 |
|
</table> |
509 |
|
|
510 |
|
<p><strong>Important</strong>: This conformance checking service |
511 |
|
is <em>under development</em>. The result above might be <em>wrong</em>.</p>]; |
512 |
|
$out->end_section; |
513 |
|
} # print_result_section |
514 |
|
|
515 |
|
sub print_result_input_error_section ($) { |
516 |
|
my $input = shift; |
517 |
|
$out->start_section (id => 'result-summary', title => 'Result'); |
518 |
|
print STDOUT qq[ |
519 |
|
<p><em><strong>Input Error</strong>: @{[htescape ($input->{error_status_text})]}</em></p>]; |
520 |
|
$out->end_section; |
521 |
|
} # print_result_input_error_section |
522 |
|
|
523 |
{ |
{ |
524 |
my $Msg = {}; |
my $Msg = {}; |
525 |
|
|
526 |
sub load_text_catalog ($) { |
sub load_text_catalog ($) { |
527 |
|
# my $self = shift; |
528 |
my $lang = shift; # MUST be a canonical lang name |
my $lang = shift; # MUST be a canonical lang name |
529 |
open my $file, '<', "cc-msg.$lang.txt" or die "$0: cc-msg.$lang.txt: $!"; |
open my $file, '<:utf8', "cc-msg.$lang.txt" |
530 |
|
or die "$0: cc-msg.$lang.txt: $!"; |
531 |
while (<$file>) { |
while (<$file>) { |
532 |
if (s/^([^;]+);([^;]*);//) { |
if (s/^([^;]+);([^;]*);//) { |
533 |
my ($type, $cls, $msg) = ($1, $2, $_); |
my ($type, $cls, $msg) = ($1, $2, $_); |
537 |
} |
} |
538 |
} # load_text_catalog |
} # load_text_catalog |
539 |
|
|
540 |
sub get_text ($) { |
sub get_text ($;$$) { |
541 |
|
# my $self = shift; |
542 |
my ($type, $level, $node) = @_; |
my ($type, $level, $node) = @_; |
543 |
$type = $level . ':' . $type if defined $level; |
$type = $level . ':' . $type if defined $level; |
544 |
|
$level = 'm' unless defined $level; |
545 |
my @arg; |
my @arg; |
546 |
{ |
{ |
547 |
if (defined $Msg->{$type}) { |
if (defined $Msg->{$type}) { |
548 |
my $msg = $Msg->{$type}->[1]; |
my $msg = $Msg->{$type}->[1]; |
549 |
$msg =~ s{<var>\$([0-9]+)</var>}{ |
$msg =~ s{<var>\$([0-9]+)</var>}{ |
550 |
defined $arg[$1] ? htescape ($arg[$1]) : '(undef)'; |
defined $arg[$1] ? ($arg[$1]) : '(undef)'; |
551 |
}ge; |
}ge; ##BUG: ^ must be escaped |
552 |
$msg =~ s{<var>{\@([A-Za-z0-9:_.-]+)}</var>}{ |
$msg =~ s{<var>{\@([A-Za-z0-9:_.-]+)}</var>}{ |
553 |
UNIVERSAL::can ($node, 'get_attribute_ns') |
UNIVERSAL::can ($node, 'get_attribute_ns') |
554 |
? htescape ($node->get_attribute_ns (undef, $1)) : '' |
? ($node->get_attribute_ns (undef, $1)) : '' |
555 |
|
}ge; ## BUG: ^ must be escaped |
556 |
|
$msg =~ s{<var>{\@}</var>}{ ## BUG: v must be escaped |
557 |
|
UNIVERSAL::can ($node, 'value') ? ($node->value) : '' |
558 |
}ge; |
}ge; |
559 |
$msg =~ s{<var>{\@}</var>}{ |
$msg =~ s{<var>{local-name}</var>}{ |
560 |
UNIVERSAL::can ($node, 'value') ? htescape ($node->value) : '' |
UNIVERSAL::can ($node, 'manakai_local_name') |
561 |
|
? ($node->manakai_local_name) : '' |
562 |
|
}ge; ## BUG: ^ must be escaped |
563 |
|
$msg =~ s{<var>{element-local-name}</var>}{ |
564 |
|
(UNIVERSAL::can ($node, 'owner_element') and |
565 |
|
$node->owner_element) |
566 |
|
? ($node->owner_element->manakai_local_name) |
567 |
|
: '' ## BUG: ^ must be escaped |
568 |
}ge; |
}ge; |
569 |
return ($type, $Msg->{$type}->[0], $msg); |
return ($type, 'level-' . $level . ' ' . $Msg->{$type}->[0], $msg); |
570 |
} elsif ($type =~ s/:([^:]*)$//) { |
} elsif ($type =~ s/:([^:]*)$//) { |
571 |
unshift @arg, $1; |
unshift @arg, $1; |
572 |
redo; |
redo; |
573 |
} |
} |
574 |
} |
} |
575 |
return ($type, '', htescape ($_[0])); |
return ($type, 'level-'.$level, ($_[0])); |
576 |
|
## BUG: ^ must be escaped |
577 |
} # get_text |
} # get_text |
578 |
|
|
579 |
} |
} |
581 |
sub get_input_document ($$) { |
sub get_input_document ($$) { |
582 |
my ($http, $dom) = @_; |
my ($http, $dom) = @_; |
583 |
|
|
584 |
my $request_uri = $http->parameter ('uri'); |
my $request_uri = $http->get_parameter ('uri'); |
585 |
my $r = {}; |
my $r = WebHACC::Input->new; |
586 |
if (defined $request_uri and length $request_uri) { |
if (defined $request_uri and length $request_uri) { |
587 |
my $uri = $dom->create_uri_reference ($request_uri); |
my $uri = $dom->create_uri_reference ($request_uri); |
588 |
unless ({ |
unless ({ |
629 |
$ua->protocols_allowed ([qw/http/]); |
$ua->protocols_allowed ([qw/http/]); |
630 |
$ua->max_size (1000_000); |
$ua->max_size (1000_000); |
631 |
my $req = HTTP::Request->new (GET => $request_uri); |
my $req = HTTP::Request->new (GET => $request_uri); |
632 |
|
$req->header ('Accept-Encoding' => 'identity, *; q=0'); |
633 |
my $res = $ua->request ($req); |
my $res = $ua->request ($req); |
634 |
if ($res->is_success or $http->parameter ('error-page')) { |
## TODO: 401 sets |is_success| true. |
635 |
|
if ($res->is_success or $http->get_parameter ('error-page')) { |
636 |
$r->{base_uri} = $res->base; ## NOTE: It does check |Content-Base|, |Content-Location|, and <base>. ## TODO: Use our own code! |
$r->{base_uri} = $res->base; ## NOTE: It does check |Content-Base|, |Content-Location|, and <base>. ## TODO: Use our own code! |
637 |
$r->{uri} = $res->request->uri; |
$r->{uri} = $res->request->uri; |
638 |
$r->{request_uri} = $request_uri; |
$r->{request_uri} = $request_uri; |
639 |
|
|
640 |
## TODO: More strict parsing... |
## TODO: More strict parsing... |
641 |
my $ct = $res->header ('Content-Type'); |
my $ct = $res->header ('Content-Type'); |
642 |
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) { |
|
643 |
$r->{charset} = lc $1; |
$r->{charset} = lc $1; |
644 |
$r->{charset} =~ tr/\\//d; |
$r->{charset} =~ tr/\\//d; |
645 |
|
$r->{official_charset} = $r->{charset}; |
646 |
} |
} |
647 |
|
|
648 |
my $input_charset = $http->parameter ('charset'); |
my $input_charset = $http->get_parameter ('charset'); |
649 |
if (defined $input_charset and length $input_charset) { |
if (defined $input_charset and length $input_charset) { |
650 |
$r->{charset_overridden} |
$r->{charset_overridden} |
651 |
= (not defined $r->{charset} or $r->{charset} ne $input_charset); |
= (not defined $r->{charset} or $r->{charset} ne $input_charset); |
652 |
$r->{charset} = $input_charset; |
$r->{charset} = $input_charset; |
653 |
} |
} |
654 |
|
|
655 |
|
## TODO: Support for HTTP Content-Encoding |
656 |
|
|
657 |
$r->{s} = ''.$res->content; |
$r->{s} = ''.$res->content; |
658 |
|
|
659 |
|
require Whatpm::ContentType; |
660 |
|
($r->{official_type}, $r->{media_type}) |
661 |
|
= Whatpm::ContentType->get_sniffed_type |
662 |
|
(get_file_head => sub { |
663 |
|
return substr $r->{s}, 0, shift; |
664 |
|
}, |
665 |
|
http_content_type_byte => $ct, |
666 |
|
has_http_content_encoding => |
667 |
|
defined $res->header ('Content-Encoding'), |
668 |
|
supported_image_types => {}); |
669 |
} else { |
} else { |
670 |
$r->{uri} = $res->request->uri; |
$r->{uri} = $res->request->uri; |
671 |
$r->{request_uri} = $request_uri; |
$r->{request_uri} = $request_uri; |
679 |
$r->{header_status_code} = $res->code; |
$r->{header_status_code} = $res->code; |
680 |
$r->{header_status_text} = $res->message; |
$r->{header_status_text} = $res->message; |
681 |
} else { |
} else { |
682 |
$r->{s} = ''.$http->parameter ('s'); |
$r->{s} = ''.$http->get_parameter ('s'); |
683 |
$r->{uri} = q<thismessage:/>; |
$r->{uri} = q<thismessage:/>; |
684 |
$r->{request_uri} = q<thismessage:/>; |
$r->{request_uri} = q<thismessage:/>; |
685 |
$r->{base_uri} = q<thismessage:/>; |
$r->{base_uri} = q<thismessage:/>; |
686 |
$r->{charset} = ''.$http->parameter ('_charset_'); |
$r->{charset} = ''.$http->get_parameter ('_charset_'); |
687 |
$r->{charset} =~ s/\s+//g; |
$r->{charset} =~ s/\s+//g; |
688 |
$r->{charset} = 'utf-8' if $r->{charset} eq ''; |
$r->{charset} = 'utf-8' if $r->{charset} eq ''; |
689 |
|
$r->{official_charset} = $r->{charset}; |
690 |
$r->{header_field} = []; |
$r->{header_field} = []; |
691 |
|
|
692 |
|
require Whatpm::ContentType; |
693 |
|
($r->{official_type}, $r->{media_type}) |
694 |
|
= Whatpm::ContentType->get_sniffed_type |
695 |
|
(get_file_head => sub { |
696 |
|
return substr $r->{s}, 0, shift; |
697 |
|
}, |
698 |
|
http_content_type_byte => undef, |
699 |
|
has_http_content_encoding => 0, |
700 |
|
supported_image_types => {}); |
701 |
} |
} |
702 |
|
|
703 |
my $input_format = $http->parameter ('i'); |
my $input_format = $http->get_parameter ('i'); |
704 |
if (defined $input_format and length $input_format) { |
if (defined $input_format and length $input_format) { |
705 |
$r->{media_type_overridden} |
$r->{media_type_overridden} |
706 |
= (not defined $r->{media_type} or $input_format ne $r->{media_type}); |
= (not defined $r->{media_type} or $input_format ne $r->{media_type}); |
714 |
if ($r->{media_type} eq 'text/xml') { |
if ($r->{media_type} eq 'text/xml') { |
715 |
unless (defined $r->{charset}) { |
unless (defined $r->{charset}) { |
716 |
$r->{charset} = 'us-ascii'; |
$r->{charset} = 'us-ascii'; |
717 |
|
$r->{official_charset} = $r->{charset}; |
718 |
} elsif ($r->{charset_overridden} and $r->{charset} eq 'us-ascii') { |
} elsif ($r->{charset_overridden} and $r->{charset} eq 'us-ascii') { |
719 |
$r->{charset_overridden} = 0; |
$r->{charset_overridden} = 0; |
720 |
} |
} |
726 |
return $r; |
return $r; |
727 |
} |
} |
728 |
|
|
729 |
|
$r->{inner_html_element} = $http->get_parameter ('e'); |
730 |
|
|
731 |
return $r; |
return $r; |
732 |
} # get_input_document |
} # get_input_document |
733 |
|
|
760 |
|
|
761 |
=head1 LICENSE |
=head1 LICENSE |
762 |
|
|
763 |
Copyright 2007 Wakaba <w@suika.fam.cx> |
Copyright 2007-2008 Wakaba <w@suika.fam.cx> |
764 |
|
|
765 |
This library is free software; you can redistribute it |
This library is free software; you can redistribute it |
766 |
and/or modify it under the same terms as Perl itself. |
and/or modify it under the same terms as Perl itself. |