62 |
<dt>Request URI</dt> |
<dt>Request URI</dt> |
63 |
<dd><code class="URI" lang=""><<a href="@{[htescape $input->{request_uri}]}">@{[htescape $input->{request_uri}]}</a>></code></dd> |
<dd><code class="URI" lang=""><<a href="@{[htescape $input->{request_uri}]}">@{[htescape $input->{request_uri}]}</a>></code></dd> |
64 |
<dt>Document URI</dt> |
<dt>Document URI</dt> |
65 |
<dd><code class="URI" lang=""><<a href="@{[htescape $input->{uri}]}">@{[htescape $input->{uri}]}</a>></code></dd> |
<dd><code class="URI" lang=""><<a href="@{[htescape $input->{uri}]}" id=anchor-document-uri>@{[htescape $input->{uri}]}</a>></code> |
66 |
|
<script> |
67 |
|
document.title = '<' |
68 |
|
+ document.getElementById ('anchor-document-uri').href + '> \\u2014 ' |
69 |
|
+ document.title; |
70 |
|
</script></dd> |
71 |
]; # no </dl> yet |
]; # no </dl> yet |
72 |
push @nav, ['#document-info' => 'Information']; |
push @nav, ['#document-info' => 'Information']; |
73 |
|
|
79 |
<dd><code class="URI" lang=""><<a href="@{[htescape $input->{base_uri}]}">@{[htescape $input->{base_uri}]}</a>></code></dd> |
<dd><code class="URI" lang=""><<a href="@{[htescape $input->{base_uri}]}">@{[htescape $input->{base_uri}]}</a>></code></dd> |
80 |
<dt>Internet Media Type</dt> |
<dt>Internet Media Type</dt> |
81 |
<dd><code class="MIME" lang="en">@{[htescape $input->{media_type}]}</code> |
<dd><code class="MIME" lang="en">@{[htescape $input->{media_type}]}</code> |
82 |
@{[$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> |
83 |
<dt>Character Encoding</dt> |
<dt>Character Encoding</dt> |
84 |
<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)']} |
85 |
@{[$input->{charset_overridden} ? '<em>(overridden)</em>' : '']}</dd> |
@{[$input->{charset_overridden} ? '<em>(overridden)</em>' : '']}</dd> |
98 |
|
|
99 |
if ($input->{media_type} eq 'text/html') { |
if ($input->{media_type} eq 'text/html') { |
100 |
($doc, $el) = print_syntax_error_html_section ($input, $result); |
($doc, $el) = print_syntax_error_html_section ($input, $result); |
101 |
print_source_string_section (\($input->{s}), $input->{charset}); |
print_source_string_section |
102 |
|
(\($input->{s}), $input->{charset} || $doc->input_encoding); |
103 |
} elsif ({ |
} elsif ({ |
104 |
'text/xml' => 1, |
'text/xml' => 1, |
105 |
'application/atom+xml' => 1, |
'application/atom+xml' => 1, |
116 |
print_source_string_section (\($input->{s}), 'utf-8'); |
print_source_string_section (\($input->{s}), 'utf-8'); |
117 |
} else { |
} else { |
118 |
## TODO: Change HTTP status code?? |
## TODO: Change HTTP status code?? |
119 |
print_result_unknown_type_section ($input); |
print_result_unknown_type_section ($input, $result); |
120 |
} |
} |
121 |
|
|
122 |
if (defined $doc or defined $el) { |
if (defined $doc or defined $el) { |
149 |
</html> |
</html> |
150 |
]; |
]; |
151 |
|
|
152 |
for (qw/decode parse parse_xml parse_manifest check check_manifest/) { |
for (qw/decode parse parse_html parse_xml parse_manifest |
153 |
|
check check_manifest/) { |
154 |
next unless defined $time{$_}; |
next unless defined $time{$_}; |
155 |
open my $file, '>>', ".cc-$_.txt" or die ".cc-$_.txt: $!"; |
open my $file, '>>', ".cc-$_.txt" or die ".cc-$_.txt: $!"; |
156 |
print $file $char_length, "\t", $time{$_}, "\n"; |
print $file $char_length, "\t", $time{$_}, "\n"; |
225 |
|
|
226 |
require Encode; |
require Encode; |
227 |
require Whatpm::HTML; |
require Whatpm::HTML; |
|
|
|
|
$input->{charset} ||= 'ISO-8859-1'; ## TODO: for now. |
|
228 |
|
|
|
my $time1 = time; |
|
|
my $t = Encode::decode ($input->{charset}, $input->{s}); |
|
|
$time{decode} = time - $time1; |
|
|
|
|
229 |
print STDOUT qq[ |
print STDOUT qq[ |
230 |
<div id="parse-errors" class="section"> |
<div id="parse-errors" class="section"> |
231 |
<h2>Parse Errors</h2> |
<h2>Parse Errors</h2> |
253 |
|
|
254 |
my $doc = $dom->create_document; |
my $doc = $dom->create_document; |
255 |
my $el; |
my $el; |
|
$time1 = time; |
|
256 |
if (defined $inner_html_element and length $inner_html_element) { |
if (defined $inner_html_element and length $inner_html_element) { |
257 |
|
$input->{charset} ||= 'ISO-8859-1'; ## 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 - $time1; |
|
|
|
|
274 |
print STDOUT qq[</dl></div>]; |
print STDOUT qq[</dl></div>]; |
275 |
|
|
276 |
return ($doc, $el); |
return ($doc, $el); |
768 |
push @nav, ['#result-summary' => 'Result']; |
push @nav, ['#result-summary' => 'Result']; |
769 |
} # print_result_section |
} # print_result_section |
770 |
|
|
771 |
sub print_result_unknown_type_section ($) { |
sub print_result_unknown_type_section ($$) { |
772 |
my $input = shift; |
my ($input, $result) = @_; |
773 |
|
|
774 |
|
my $euri = htescape ($input->{uri}); |
775 |
print STDOUT qq[ |
print STDOUT qq[ |
776 |
<div id="result-summary" class="section"> |
<div id="parse-errors" class="section"> |
777 |
<p><em>Media type <code class="MIME" lang="en">@{[htescape $input->{media_type}]}</code> is not supported!</em></p> |
<h2>Errors</h2> |
778 |
|
|
779 |
|
<dl> |
780 |
|
<dt class=unsupported><code><<a href="$euri">$euri</a>></code></dt> |
781 |
|
<dd class=unsupported><strong><a href="../error-description#level-u">Not |
782 |
|
supported</a></strong>: |
783 |
|
Media type |
784 |
|
<code class="MIME" lang="en">@{[htescape $input->{media_type}]}</code> |
785 |
|
is not supported.</dd> |
786 |
|
</dl> |
787 |
</div> |
</div> |
788 |
]; |
]; |
789 |
push @nav, ['#result-summary' => 'Result']; |
push @nav, ['#parse-errors' => 'Errors']; |
790 |
|
add_error (char => {level => 'unsupported'} => $result); |
791 |
|
add_error (syntax => {level => 'unsupported'} => $result); |
792 |
|
add_error (structure => {level => 'unsupported'} => $result); |
793 |
} # print_result_unknown_type_section |
} # print_result_unknown_type_section |
794 |
|
|
795 |
sub print_result_input_error_section ($) { |
sub print_result_input_error_section ($) { |
1003 |
|
|
1004 |
## TODO: More strict parsing... |
## TODO: More strict parsing... |
1005 |
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; |
|
|
} |
|
1006 |
if (defined $ct and $ct =~ /;\s*charset\s*=\s*"?([^\s;"]+)"?/i) { |
if (defined $ct and $ct =~ /;\s*charset\s*=\s*"?([^\s;"]+)"?/i) { |
1007 |
$r->{charset} = lc $1; |
$r->{charset} = lc $1; |
1008 |
$r->{charset} =~ tr/\\//d; |
$r->{charset} =~ tr/\\//d; |
1013 |
$r->{charset_overridden} |
$r->{charset_overridden} |
1014 |
= (not defined $r->{charset} or $r->{charset} ne $input_charset); |
= (not defined $r->{charset} or $r->{charset} ne $input_charset); |
1015 |
$r->{charset} = $input_charset; |
$r->{charset} = $input_charset; |
1016 |
} |
} |
1017 |
|
|
1018 |
|
## TODO: Support for HTTP Content-Encoding |
1019 |
|
|
1020 |
$r->{s} = ''.$res->content; |
$r->{s} = ''.$res->content; |
1021 |
|
|
1022 |
|
require Whatpm::ContentType; |
1023 |
|
($r->{official_type}, $r->{media_type}) |
1024 |
|
= Whatpm::ContentType->get_sniffed_type |
1025 |
|
(get_file_head => sub { |
1026 |
|
return substr $r->{s}, 0, shift; |
1027 |
|
}, |
1028 |
|
http_content_type_byte => $ct, |
1029 |
|
has_http_content_encoding => |
1030 |
|
defined $res->header ('Content-Encoding'), |
1031 |
|
supported_image_types => {}); |
1032 |
} else { |
} else { |
1033 |
$r->{uri} = $res->request->uri; |
$r->{uri} = $res->request->uri; |
1034 |
$r->{request_uri} = $request_uri; |
$r->{request_uri} = $request_uri; |
1050 |
$r->{charset} =~ s/\s+//g; |
$r->{charset} =~ s/\s+//g; |
1051 |
$r->{charset} = 'utf-8' if $r->{charset} eq ''; |
$r->{charset} = 'utf-8' if $r->{charset} eq ''; |
1052 |
$r->{header_field} = []; |
$r->{header_field} = []; |
1053 |
|
|
1054 |
|
require Whatpm::ContentType; |
1055 |
|
($r->{official_type}, $r->{media_type}) |
1056 |
|
= Whatpm::ContentType->get_sniffed_type |
1057 |
|
(get_file_head => sub { |
1058 |
|
return substr $r->{s}, 0, shift; |
1059 |
|
}, |
1060 |
|
http_content_type_byte => undef, |
1061 |
|
has_http_content_encoding => 0, |
1062 |
|
supported_image_types => {}); |
1063 |
} |
} |
1064 |
|
|
1065 |
my $input_format = $http->get_parameter ('i'); |
my $input_format = $http->get_parameter ('i'); |