3 |
|
|
4 |
use lib qw[/home/httpd/html/www/markup/html/whatpm |
use lib qw[/home/httpd/html/www/markup/html/whatpm |
5 |
/home/wakaba/public_html/-temp/wiki/lib]; |
/home/wakaba/public_html/-temp/wiki/lib]; |
6 |
|
use CGI::Carp qw[fatalsToBrowser]; |
7 |
|
use Time::HiRes qw/time/; |
8 |
|
|
9 |
use SuikaWiki::Input::HTTP; ## TODO: Use some better CGI module |
use SuikaWiki::Input::HTTP; ## TODO: Use some better CGI module |
10 |
|
|
17 |
|
|
18 |
if ($mode eq '/html' or $mode eq '/test') { |
if ($mode eq '/html' or $mode eq '/test') { |
19 |
require Encode; |
require Encode; |
20 |
require What::HTML; |
require Whatpm::HTML; |
21 |
require What::NanoDOM; |
require Whatpm::NanoDOM; |
22 |
|
|
23 |
my $s = $http->parameter ('s'); |
my $s = $http->parameter ('s'); |
24 |
if (length $s > 1000_000) { |
if (length $s > 1000_000) { |
26 |
exit; |
exit; |
27 |
} |
} |
28 |
|
|
29 |
|
my $time1 = time; |
30 |
$s = Encode::decode ('utf-8', $s); |
$s = Encode::decode ('utf-8', $s); |
31 |
|
my $time2 = time; |
32 |
|
my %time = (decode => $time2 - $time1); |
33 |
|
my $char_length = length $s; |
34 |
|
|
35 |
print STDOUT "Content-Type: text/plain; charset=utf-8\n\n"; |
print STDOUT "Content-Type: text/plain; charset=utf-8\n\n"; |
36 |
|
|
37 |
print STDOUT "#errors\n"; |
print STDOUT "#errors\n"; |
38 |
|
|
39 |
my $onerror = sub { |
my $onerror = sub { |
40 |
print STDOUT "0,0,", $_[0], "\n"; |
my (%opt) = @_; |
41 |
|
print STDOUT "$opt{line},$opt{column},$opt{type}\n"; |
42 |
}; |
}; |
43 |
|
|
44 |
my $doc = What::HTML->parse_string |
$time1 = time; |
45 |
($s => What::NanoDOM::Document->new, $onerror); |
my $doc = Whatpm::HTML->parse_string |
46 |
|
($s => Whatpm::NanoDOM::Document->new, $onerror); |
47 |
|
$time2 = time; |
48 |
|
$time{parse} = $time2 - $time1; |
49 |
|
|
50 |
print "#document\n"; |
print "#document\n"; |
51 |
|
|
52 |
my $out; |
my $out; |
53 |
|
$time1 = time; |
54 |
if ($mode eq '/html') { |
if ($mode eq '/html') { |
55 |
$out = What::HTML->get_inner_html ($doc); |
$out = Whatpm::HTML->get_inner_html ($doc); |
56 |
} else { # test |
} else { # test |
57 |
$out = test_serialize ($doc); |
$out = test_serialize ($doc); |
58 |
} |
} |
59 |
|
$time2 = time; |
60 |
|
$time{serialize} = $time2 - $time1; |
61 |
print STDOUT Encode::encode ('utf-8', $$out); |
print STDOUT Encode::encode ('utf-8', $$out); |
62 |
|
print STDOUT "\n"; |
63 |
|
|
64 |
|
if ($http->parameter ('dom5')) { |
65 |
|
require Whatpm::ContentChecker; |
66 |
|
print STDOUT "#domerrors\n"; |
67 |
|
$time1 = time; |
68 |
|
Whatpm::ContentChecker->check_document ($doc, sub { |
69 |
|
my %opt = @_; |
70 |
|
print STDOUT get_node_path ($opt{node}) . ';' . $opt{type} . "\n"; |
71 |
|
}); |
72 |
|
$time2 = time; |
73 |
|
$time{check} = $time2 - $time1; |
74 |
|
} |
75 |
|
|
76 |
|
print STDOUT "#log\n"; |
77 |
|
print STDOUT "byte->char\t", $time{decode}, "s\n"; |
78 |
|
print STDOUT "html5->dom5\t", $time{parse}, "s\n"; |
79 |
|
print STDOUT "dom5->serialize\t", $time{serialize}, "s\n"; |
80 |
|
print STDOUT "dom5 check\t", $time{check}, "s\n" if defined $time{check}; |
81 |
|
for (qw/decode parse serialize check/) { |
82 |
|
next unless defined $time{$_}; |
83 |
|
open my $file, '>>', ".$_.txt" or die ".$_.txt: $!"; |
84 |
|
print $file $char_length, "\t", $time{$_}, "\n"; |
85 |
|
} |
86 |
} else { |
} else { |
87 |
print STDOUT "Status: 404 Not Found\nContent-Type: text/plain; charset=us-ascii\n\n404"; |
print STDOUT "Status: 404 Not Found\nContent-Type: text/plain; charset=us-ascii\n\n404"; |
88 |
} |
} |
121 |
|
|
122 |
return \$r; |
return \$r; |
123 |
} # test_serialize |
} # test_serialize |
124 |
|
|
125 |
|
sub get_node_path ($) { |
126 |
|
my $node = shift; |
127 |
|
my @r; |
128 |
|
while (defined $node) { |
129 |
|
my $rs; |
130 |
|
if ($node->node_type == 1) { |
131 |
|
$rs = $node->manakai_local_name; |
132 |
|
$node = $node->parent_node; |
133 |
|
} elsif ($node->node_type == 2) { |
134 |
|
$rs = '@' . $node->manakai_local_name; |
135 |
|
$node = $node->owner_element; |
136 |
|
} elsif ($node->node_type == 3) { |
137 |
|
$rs = '"' . $node->data . '"'; |
138 |
|
$node = $node->parent_node; |
139 |
|
} elsif ($node->node_type == 9) { |
140 |
|
$rs = ''; |
141 |
|
$node = $node->parent_node; |
142 |
|
} else { |
143 |
|
$rs = '#' . $node->node_type; |
144 |
|
$node = $node->parent_node; |
145 |
|
} |
146 |
|
unshift @r, $rs; |
147 |
|
} |
148 |
|
return join '/', @r; |
149 |
|
} # get_node_path |
150 |
|
|
151 |
|
=head1 AUTHOR |
152 |
|
|
153 |
|
Wakaba <w@suika.fam.cx>. |
154 |
|
|
155 |
|
=head1 LICENSE |
156 |
|
|
157 |
|
Copyright 2007 Wakaba <w@suika.fam.cx> |
158 |
|
|
159 |
|
This library is free software; you can redistribute it |
160 |
|
and/or modify it under the same terms as Perl itself. |
161 |
|
|
162 |
|
=cut |
163 |
|
|
164 |
|
## $Date$ |