#! perl -slw
use strict;
use Math::Random::MT qw[ rand ];
use Benchmark::Timer;

our $N ||= 1_000_000;

{
	## Use closures to retain info between calls or make it an object.
	my( $filename, $fh, $len ) = 'uniqints.dat';
	sub uniqPersistant {
		my( $no ) = @_;
		unless( $fh ) {
			## Open an existing (or new first time) file;
			my $mode = -e( $filename ) ? '+<:raw' : '+>:raw';
			open $fh, $mode, $filename 
				or die "$filename ($mode) : $!";
			## Remember the length.
			$len = -s $filename;
		}
		## Calculate byte offset and bit
		my( $oByte, $bit ) = ( int( $no / 8 ), ( $no % 8 ) );

		## Extend the file with nulls if writing a new highest value
		if( $len < $oByte ) {
			my $extend = ( $oByte - $len + 1 );
			sysseek $fh, 0, 2;
			syswrite $fh, chr(0) x $extend;
			$len += $extend; ## Accumulate the extension
		}

		## Read the byte
		my $byte;
		sysseek $fh, $oByte, 0;
		sysread $fh, $byte, 1;
		## All done if the bit is set
		return 1 if vec $byte, $bit, 1;
		
		## Otherwise set it, re-write teh byte and return false;
		vec( $byte, $bit, 1 ) = 1;
		sysseek $fh, $oByte, 0;
		syswrite $fh, $byte, 1;
		return;
	}
}

my @numbers = map{ int rand 1_000_000 } 1 .. $N;

my $T = new Benchmark::Timer;
for ( 1 .. 2 ) {
	my $count = 0;
	$T->start( "Pass $_" );
	uniqPersistant( $_ ) or $count++ for @numbers;
	$T->stop( "Pass $_" );
	print "During pass $_; $count numbers uniq numbers were previously unset";
}

$T->report;
__END__
P:\test>429615
During pass 1; 632091 numbers uniq numbers were previously unset
During pass 2; 0 numbers uniq numbers were previously unset
  1 trial  of Pass 1 (  11.891s total), 11.891s/trial

  1 trial  of Pass 2 (   6.469s total), 6.469s/trial


P:\test>dir uniqints.dat
 Volume in drive P has no label.
 Volume Serial Number is BCCA-B4CC

 Directory of P:\test

10/02/2005  11:17           125,000 uniqints.dat
               1 File(s)        125,000 bytes
               0 Dir(s)  58,981,855,232 bytes free