#!/usr/bin/perl

use strict;
use warnings;

use Data::Hash::Totals;

my %totals;
my %piggy;

my $rx_agent_ignore = qr/
    \. google \.            |
    \. yahoo  \.            |
    \b Seekbot              |
    \b MS\ Search \b        |
    \b Interarchy \b        |
    \b teoma \b
/x;

while (<DATA>) {
    chomp;
    my (undef,$naughty) = split;
    ++$piggy{ $naughty };
}

my %dl;
while (<>) {
    chomp;
    my ($who,undef,$what,$with) = split / /, $_, 4;
    next if $piggy{$who};
    next if $with =~ /$rx_agent_ignore/oi;

    $what =~ s[.+/][];
    $what =~ s/\.(tar\.gz|zip)$// or next; # Only want tarballs

    next if $what =~ /^perl-?5/;

    $what =~ s/(rc|b)\d+$//;    # Handle release candidates and betas
    $what =~ s/-[\d._]+a?$//;    # The "a" is for DateManip
    $what = "lanman" if $what =~ /lanman/;

    # Same person downloads twice, don't count it.
    ++$totals{$what} unless $dl{"$what\t$who"}++;
} # while

print as_table( \%totals );

# List of piggies follows
__END__
61016 77931
53912 70499
34716 66057
33552 10180
31884 12603
31000 12736
30056 79880
29867 15895
17420 71946
16736 18470
16652 81080
15614 26708
12607 53910
11703 37108
11265 54276
10912 44140
10406 24149
 9243 41125
 8944 20683
 8866 11474
 8836 15721
 8814 22751
 8715 59788
 8578 50934
 8313 13309
 8292 13675
 8286 78646
 8274 70561
 8271 71129
 8249 51956
 8247 56860
 8229 45259
 8200 17160
 8185 26947
 8185 29871
 8123 81511
 7938 83805
 7267 58137
 7244 53816
 6859 49585
 5560 75270
 5476 21874
 4790 27126