#!/usr/bin/perl
use warnings;
use strict;
use Data::Hash::Totals;

my @log;
while (my $line = <>) {
    next unless $line =~ m!(\S+)\s+(\S+)\s+\S*/(\S+)\s!;
    my ($ip,$date,$dist) = ($1, $2, $3);
    next unless $dist =~ s/\.(tar\.gz|tgz)$//;
    $dist =~ s/(-|_)[0-9][0-9a-z._]+$//;
    $dist =~ s/.pm$//;
    push @log, { ip => $ip, date => $date, dist => $dist };
}

# Count IP and find a cutoff for the 99%ile of downloaders
my %ip;
for my $line (@log) {
    $ip{$line->{ip}}++;
}

my $cut =  int( 0.01 * keys %ip );
my $cutoff = [ sort { $ip{$b} <=> $ip{$a} } keys %ip ]->[$cut];

# Tally distributions for everyone else
my %dist;
for my $line (@log) {
    $dist{$line->{dist}}++ if $ip{$line->{ip}} < $cutoff;
}

my %top100;
$top100{$_} = $dist{$_} 
    for splice( @{[sort { $dist{$b} <=> $dist{$a} } keys %dist ]}, 0, 100 );

print as_table(\%top100);