#! perl -slw 
use strict;
$|=1;

my $BSIZE ||= 1_000_000;

open my $fh, '+<:raw', $ARGV[ 0 ] or die "$ARGV[ 0 ] : $!";

my $pattern = $ARGV[ 1 ] or die "no pattern supplied";
my $overlap = int( ( length( $pattern ) + 1 ) / 8 );
my $buffer = '';
my $buffs = 0;
my $found = 0;
while( sysread( $fh, $buffer, $BSIZE, length $buffer ) ) {
    ## Convert the buffer to asciiized bits;
    my $bits = unpack 'B*', $buffer;
    
    printf "\r$buffs: [$found] ";
    
    ## Search for the pattern
    my $p = 0;
    while( $p = 1 + index( $bits, $pattern, $p ) ) {
        ## And record the hits
        $found++;

## Calculate byte/bit offsets        
#        my $byte = ( $buffs * $BSIZE ) 
#                 - ( $overap * $buffs ) 
#                 + int( ( $p - 1 ) / 8 );
#        my $bit = ( $p - 1 ) % 8;
#        printf "\rFound it at byte: $byte bit: $bit '%s'", 
#            substr( $bits, $p-1, length( $pattern ) );;
    }
    
    ## Keep track of the number of buffers process
    $buffs++;
    
    ## Move enough bytes to the front of the buffer
    ## to ensure overlap.
    $buffer = substr( $buffer, -$overlap );
}
print "Found $found occurances of '$pattern'";
__END__
[16:40:12.64] P:\test>429065 data\100millionbytes.dat 1111111111
100: [0] Found 0 occurances of '1111111111'

[16:40:46.04] P:\test>

[16:41:37.46] P:\test>429065 data\100millionbytes.dat 1100000011
100: [24999982] Found 24999990 occurances of '1100000011'

[16:41:56.28] P:\test>

[16:42:03.65] P:\test>429065 data\1000millionbytes.dat 1100000011
1000: [249999876] Found 249999900 occurances of '1100000011'

[16:45:24.09] P:\test>
[download]