#!/usr/bin/perl -wC0

use strict;
use Encode;
use Tie::File;
use PerlIO::gzip;

our $LOGDIR = "/var/log/apache-perl";
our $REPORT = "/var/www/analog/analog.html";

# 1. read input and normalize it.
# 2. pipe it off to analog
# 3. when analog finishes, fixup the silly encoding.

# 2 has to actually start before 1 :)

my $pid = open ANALOG, "| analog -" or die "can't start analog: $!";
$SIG{PIPE} = sub { die "sigpipe" };

# read logs
foreach my $file (glob $LOGDIR . "/access.log*") {
        #print "Preprocessing $file\n";
        # gzip autopop (see PerlIO::gzip) transparently handles gz or non-gz input
        open my $log, "<:gzip(autopop)", $file or die "can't read log $file: $!";
        while(<$log>) {
                # normalize URI-escaped and variously encoded data to CP1255.

                s/(?:%|\\x)([0-9A-Fa-f]{2})/chr(hex($1))/eg;

                eval { $_ = Encode::decode('utf-8', $_, 1); 1 } or
                        $_ = Encode::decode('cp1255', $_);
                $_ = Encode::encode('cp1255', $_);

                print ANALOG or die "analog: $!";
        }
}

# let analog do its stuff
close ANALOG or die "analog: $!";
waitpid $pid, 0; # let it finish

# now 3 - fixup the silly encoding.
tie my @report, 'Tie::File', $REPORT or die "Tie::File: $!";
FIXUP: foreach (@report) {
        # take care not to change the length of the line, so that the editing
        # may be done in-place.
        s{charset=ISO-8859-1"}
         {charset=CP-1255"   } && last FIXUP;
}