view release on metacpan or  search on metacpan

lib/ApacheLog/Compressor.pm  view on Meta::CPAN

package ApacheLog::Compressor;
# ABSTRACT: Convert Apache/CLF data to binary format
use strict;
use warnings;

use Socket qw(inet_aton inet_ntoa);
use Date::Parse qw(str2time);
use List::Util qw(min);
use URI;
use URI::Escape qw(uri_unescape);
use DateTime;
use Encode qw(encode_utf8 decode_utf8 FB_DEFAULT is_utf8 FB_CROAK);
use POSIX qw{strftime};

our $VERSION = '0.005';

=head1 NAME

ApacheLog::Compressor - convert Apache / CLF log files into a binary format for transfer

lib/ApacheLog/Compressor.pm  view on Meta::CPAN

			id => 0x07,
			type => 'N1',
			regex => qr{([^ ]+)},
			process_in => sub {
				my ($self, $data) = @_;
				return $data->{url} = '' unless defined $data->{url};

				($data->{url}, $data->{query}) = split /\?/, $data->{url}, 2;
# Dodgy UTF8 handling, currently disabled - no guarantee that URLs are UTF8 anyway
#				if(length $data->{url}) {
				# URI::Escape's uri_unescape but in byte mode so we can check utf8 decoding manually
#					my $txt = $data->{url};
#					$txt = encode_utf8($txt); # turn OFF utf8
#					$txt =~ s/%([0-9A-Fa-f]{2})/pack("C1", hex($1))/ge; # expand
#					$txt = decode_utf8($txt); # turn ON utf8 where applicable
#					$data->{url} = $txt;
#				}
#				if(defined $data->{query} && length $data->{query}) {
				# URI::Escape's uri_unescape but in byte mode so we can check utf8 decoding manually
#					(my $txt = $data->{query}) =~ s/%([0-9A-Fa-f]{2})/pack("C1", hex($1))/eg;
#					$data->{query} = decode_utf8($txt, FB_DEFAULT);
#				}
			}
		},
		query		=> { id => 0x0A, type => 'N1', },
		ver		=> {
			type => 'C1',
			regex => qr{HTTP/(\d+\.\d+)"},
			process_in => sub {