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 |
|
|
61 |
<dt>Request URI</dt> |
<dt>Request URI</dt> |
62 |
<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> |
63 |
<dt>Document URI</dt> |
<dt>Document URI</dt> |
64 |
<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> |
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 |
|
|
78 |
<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> |
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> |
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, |
252 |
|
|
253 |
my $doc = $dom->create_document; |
my $doc = $dom->create_document; |
254 |
my $el; |
my $el; |
255 |
|
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} ||= 'ISO-8859-1'; ## TODO: for now. |
$input->{charset} ||= 'windows-1252'; ## TODO: for now. |
258 |
my $time1 = time; |
my $time1 = time; |
259 |
my $t = Encode::decode ($input->{charset}, $input->{s}); |
my $t = Encode::decode ($input->{charset}, $input->{s}); |
260 |
$time{decode} = time - $time1; |
$time{decode} = time - $time1; |
270 |
($input->{charset}, $input->{s} => $doc, $onerror); |
($input->{charset}, $input->{s} => $doc, $onerror); |
271 |
$time{parse_html} = time - $time1; |
$time{parse_html} = time - $time1; |
272 |
} |
} |
273 |
|
$doc->manakai_charset ($input->{official_charset}) |
274 |
|
if defined $input->{official_charset}; |
275 |
|
|
276 |
print STDOUT qq[</dl></div>]; |
print STDOUT qq[</dl></div>]; |
277 |
|
|
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 $input->{official_charset}; |
317 |
|
|
318 |
print STDOUT qq[</dl></div>]; |
print STDOUT qq[</dl></div>]; |
319 |
|
|
899 |
|
|
900 |
sub load_text_catalog ($) { |
sub load_text_catalog ($) { |
901 |
my $lang = shift; # MUST be a canonical lang name |
my $lang = shift; # MUST be a canonical lang name |
902 |
open my $file, '<', "cc-msg.$lang.txt" or die "$0: cc-msg.$lang.txt: $!"; |
open my $file, '<:utf8', "cc-msg.$lang.txt" |
903 |
|
or die "$0: cc-msg.$lang.txt: $!"; |
904 |
while (<$file>) { |
while (<$file>) { |
905 |
if (s/^([^;]+);([^;]*);//) { |
if (s/^([^;]+);([^;]*);//) { |
906 |
my ($type, $cls, $msg) = ($1, $2, $_); |
my ($type, $cls, $msg) = ($1, $2, $_); |
1008 |
|
|
1009 |
## TODO: More strict parsing... |
## TODO: More strict parsing... |
1010 |
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; |
|
|
} |
|
1011 |
if (defined $ct and $ct =~ /;\s*charset\s*=\s*"?([^\s;"]+)"?/i) { |
if (defined $ct and $ct =~ /;\s*charset\s*=\s*"?([^\s;"]+)"?/i) { |
1012 |
$r->{charset} = lc $1; |
$r->{charset} = lc $1; |
1013 |
$r->{charset} =~ tr/\\//d; |
$r->{charset} =~ tr/\\//d; |
1014 |
|
$r->{official_charset} = $r->{charset}; |
1015 |
} |
} |
1016 |
|
|
1017 |
my $input_charset = $http->get_parameter ('charset'); |
my $input_charset = $http->get_parameter ('charset'); |
1019 |
$r->{charset_overridden} |
$r->{charset_overridden} |
1020 |
= (not defined $r->{charset} or $r->{charset} ne $input_charset); |
= (not defined $r->{charset} or $r->{charset} ne $input_charset); |
1021 |
$r->{charset} = $input_charset; |
$r->{charset} = $input_charset; |
1022 |
} |
} |
1023 |
|
|
1024 |
|
## TODO: Support for HTTP Content-Encoding |
1025 |
|
|
1026 |
$r->{s} = ''.$res->content; |
$r->{s} = ''.$res->content; |
1027 |
|
|
1028 |
|
require Whatpm::ContentType; |
1029 |
|
($r->{official_type}, $r->{media_type}) |
1030 |
|
= Whatpm::ContentType->get_sniffed_type |
1031 |
|
(get_file_head => sub { |
1032 |
|
return substr $r->{s}, 0, shift; |
1033 |
|
}, |
1034 |
|
http_content_type_byte => $ct, |
1035 |
|
has_http_content_encoding => |
1036 |
|
defined $res->header ('Content-Encoding'), |
1037 |
|
supported_image_types => {}); |
1038 |
} else { |
} else { |
1039 |
$r->{uri} = $res->request->uri; |
$r->{uri} = $res->request->uri; |
1040 |
$r->{request_uri} = $request_uri; |
$r->{request_uri} = $request_uri; |
1055 |
$r->{charset} = ''.$http->get_parameter ('_charset_'); |
$r->{charset} = ''.$http->get_parameter ('_charset_'); |
1056 |
$r->{charset} =~ s/\s+//g; |
$r->{charset} =~ s/\s+//g; |
1057 |
$r->{charset} = 'utf-8' if $r->{charset} eq ''; |
$r->{charset} = 'utf-8' if $r->{charset} eq ''; |
1058 |
|
$r->{official_charset} = $r->{charset}; |
1059 |
$r->{header_field} = []; |
$r->{header_field} = []; |
1060 |
|
|
1061 |
|
require Whatpm::ContentType; |
1062 |
|
($r->{official_type}, $r->{media_type}) |
1063 |
|
= Whatpm::ContentType->get_sniffed_type |
1064 |
|
(get_file_head => sub { |
1065 |
|
return substr $r->{s}, 0, shift; |
1066 |
|
}, |
1067 |
|
http_content_type_byte => undef, |
1068 |
|
has_http_content_encoding => 0, |
1069 |
|
supported_image_types => {}); |
1070 |
} |
} |
1071 |
|
|
1072 |
my $input_format = $http->get_parameter ('i'); |
my $input_format = $http->get_parameter ('i'); |
1083 |
if ($r->{media_type} eq 'text/xml') { |
if ($r->{media_type} eq 'text/xml') { |
1084 |
unless (defined $r->{charset}) { |
unless (defined $r->{charset}) { |
1085 |
$r->{charset} = 'us-ascii'; |
$r->{charset} = 'us-ascii'; |
1086 |
|
$r->{official_charset} = $r->{charset}; |
1087 |
} elsif ($r->{charset_overridden} and $r->{charset} eq 'us-ascii') { |
} elsif ($r->{charset_overridden} and $r->{charset} eq 'us-ascii') { |
1088 |
$r->{charset_overridden} = 0; |
$r->{charset_overridden} = 0; |
1089 |
} |
} |