#!/usr/bin/perl

#
# Simple script to generate an artificial log of MAC address activity based on
# a generated list of hosts with MAC addresses.
#
# Mark Leisher <mleisher@cs.nmsu.edu>
# 07 October 2019
#

#
# Seed RNG.
#
srand(time);

#
# The number of fake hosts to generate.
#
my $host_count = 200;

#
# The amount of fake MAC address history to generate.
#
my $history_count = 100;

#
# Map to track fake unique MAC addresses and fake IP addresses.
#
my %macs;
my %ips;

#
# Chars needed to generate fake IP addresses and fake MAC addresses.
#
my @mac_chars = ('a' .. 'f', '0' .. '9');

sub fake_unique_mac {
    my ($i, $mac);

    do {
	for ($i = 0, $mac = ''; $i < 12; $i++) {
	    $mac .= "-" if ($i == 6);
	    $mac .= $mac_chars[rand(@mac_chars)];
	}
    } while ($macs{$mac});
    $macs{$mac} = 1;

    return $mac;
}

sub fake_unique_ip {
    my ($i, $ip);

    do {
	for ($i = 0, $ip = ''; $i < 4; $i++) {
	    $ip .= "." if ($i);
	    $ip .= int(rand(128));
	}
    } while ($ips{$ip});
    $ips{$ip} = 1;

    return $ip;
}

#
# Build a fake host table with randomly generated, unique MAC and IP
# addresses.
#
# The format is 11 fields separated with %, with only fields 0, 1, and 8 being
# of interest to the Rust program that will read it.
#
sub gen_fake_hosts {
    my ($num_hosts) = @_;
    my ($mac, $n) = ('', 0);

    open(OUT,">fakehosts.txt") or die "$0: unable to write 'fakehosts.txt'.\n";
    while ($n < $num_hosts) {
	$mac = fake_unique_mac();
	$ip = fake_unique_ip();
	print OUT "$ip\%host$n\%two\%three\%four\%five\%six\%seven\%$mac\%nine\%ten\n";
	$n++;
    }
    close(OUT);
}

#
# Generate a comma-separated list of MAC addresses.
#
sub some_macs {
    my @macs = keys %macs;
    my ($out, $mac, %seen);

    for (my $i = 0, $out = ''; $i < int(rand(@macs)); $i++) {
	$out .= "," if ($i);
	do {
	    $mac = $macs[rand(@macs)];
	} while ($seen{$mac});
	$seen{$mac} = 1;
	$mac =~ s/-//;
	$out .= uc($mac);
    }
    return $out;
}

#
# Build a fake MAC address history table with the specified number of lines.
#
# The format of the fake history is:
# YYYYMMDD_HHMMSS <string> <string> <string> MAC(,MAC)*
#
# where MAC(,MAC)* means a comma separated list of MAC addresses.
#
sub gen_fake_history {
    my ($history_count) = @_;
    my @mdays = (31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31);
    my ($y, $m, $d, $h, $m, $pd);

    open(OUT,">fakehistory.txt") or die "$prog: unable to write 'fakehistory.txt'.\n";

    $y = 2014;
    $m = 1;
    $d = 1;

    for (my $i = 0; $i < $history_count; $i++) {
	$date = sprintf "%d%02d%02d", $y, $m, $d;

	$h = 1;
	$s = 0;
	$pd = 46;
	for (my $j = 0; $j < $pd; $j++) {
	    print OUT sprintf("${date}_%02d%02d string string string %s\n",
			      $h, $s, some_macs());
	    if ($s == 30) {
		$h++;
		$s = 0;
	    } else {
		$s += 30;
	    }
	}
	if ($d == $mdays[$m-1]) {
	    $d = 1;
	    $m++;
	    if ($m > 12) {
		$y++;
		$m = 1;
	    }
	} else {
	    $d++;
	}
    }
    close(OUT);
}

gen_fake_hosts($host_count);
gen_fake_history($history_count);

exit 0;