| 2 |
use strict; |
use strict; |
| 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/work/manakai2/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 Message::CGI::HTTP; |
| 10 |
|
my $http = Message::CGI::HTTP->new; |
|
my $http = SuikaWiki::Input::HTTP->new; |
|
| 11 |
|
|
| 12 |
## TODO: _charset_ |
## TODO: _charset_ |
| 13 |
|
|
| 14 |
my $mode = $http->meta_variable ('PATH_INFO'); |
my $mode = $http->get_meta_variable ('PATH_INFO'); |
| 15 |
## TODO: decode unreserved characters |
## TODO: decode unreserved characters |
| 16 |
|
|
| 17 |
if ($mode eq '/html' or $mode eq '/test') { |
if ($mode eq '/html' or $mode eq '/test') { |
| 19 |
require Whatpm::HTML; |
require Whatpm::HTML; |
| 20 |
require Whatpm::NanoDOM; |
require Whatpm::NanoDOM; |
| 21 |
|
|
| 22 |
my $s = $http->parameter ('s'); |
my $s = $http->get_parameter ('s'); |
| 23 |
if (length $s > 1000_000) { |
if (length $s > 1000_000) { |
| 24 |
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"; |
| 25 |
exit; |
exit; |
| 26 |
} |
} |
| 27 |
|
|
| 28 |
|
my $time1 = time; |
| 29 |
$s = Encode::decode ('utf-8', $s); |
$s = Encode::decode ('utf-8', $s); |
| 30 |
|
my $time2 = time; |
| 31 |
|
my %time = (decode => $time2 - $time1); |
| 32 |
|
my $char_length = length $s; |
| 33 |
|
|
| 34 |
print STDOUT "Content-Type: text/plain; charset=utf-8\n\n"; |
print STDOUT "Content-Type: text/plain; charset=utf-8\n\n"; |
| 35 |
|
|
| 36 |
print STDOUT "#errors\n"; |
print STDOUT "#errors\n"; |
| 40 |
print STDOUT "$opt{line},$opt{column},$opt{type}\n"; |
print STDOUT "$opt{line},$opt{column},$opt{type}\n"; |
| 41 |
}; |
}; |
| 42 |
|
|
| 43 |
|
$time1 = time; |
| 44 |
my $doc = Whatpm::HTML->parse_string |
my $doc = Whatpm::HTML->parse_string |
| 45 |
($s => Whatpm::NanoDOM::Document->new, $onerror); |
($s => Whatpm::NanoDOM::Document->new, $onerror); |
| 46 |
|
$time2 = time; |
| 47 |
|
$time{parse} = $time2 - $time1; |
| 48 |
|
|
| 49 |
print "#document\n"; |
print "#document\n"; |
| 50 |
|
|
| 51 |
my $out; |
my $out; |
| 52 |
|
$time1 = time; |
| 53 |
if ($mode eq '/html') { |
if ($mode eq '/html') { |
| 54 |
$out = Whatpm::HTML->get_inner_html ($doc); |
require Whatpm::HTML::Serializer; |
| 55 |
|
$out = Whatpm::HTML::Serializer->get_inner_html ($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"; |
print STDOUT "\n"; |
| 63 |
|
|
| 64 |
if ($http->parameter ('dom5')) { |
if ($http->get_parameter ('dom5')) { |
| 65 |
require Whatpm::ContentChecker; |
require Whatpm::ContentChecker; |
| 66 |
print STDOUT "#domerrors\n"; |
print STDOUT "#domerrors\n"; |
| 67 |
my $docel = $doc->document_element; |
$time1 = time; |
| 68 |
my $docel_nsuri = $docel->namespace_uri; |
Whatpm::ContentChecker->check_document ($doc, sub { |
|
if (defined $docel_nsuri and |
|
|
$docel_nsuri eq q<http://www.w3.org/1999/xhtml> and |
|
|
$docel->manakai_local_name eq 'html') { |
|
|
# |
|
|
} else { |
|
|
print STDOUT get_node_path ($docel) . ";element not allowed\n"; |
|
|
} |
|
|
my $cc = Whatpm::ContentChecker->new; |
|
|
$cc->check_element ($docel, sub { |
|
| 69 |
my %opt = @_; |
my %opt = @_; |
| 70 |
print STDOUT get_node_path ($opt{node}) . ';' . $opt{type} . "\n"; |
print STDOUT get_node_path ($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"; |