use strict;
use Bio::SeqIO;
use Benchmark;
use Regexp::Assemble;
use Carp;

my $seqio = Bio::SeqIO->new( -file => "chrY.fa.masked", -format => "fasta" );
my $seq = $seqio->next_seq();
my $sequence = $seq->seq();

my @strings = (
        'CACGTG',
        'GTGCAC'
        );

my $t0 = new Benchmark;
for (1..100) {
        foreach my $string (@strings) {
                my $len = length($string);
                while ($sequence =~ /$string/g) { my $val = pos($sequence) - $len; }
                }
        }
my $t1 = new Benchmark;

my $t2 = new Benchmark;
for (1..100) {
        foreach my $string (@strings) {
                my $pos = 0;
                my $len = length($string);
                while ( ($pos = index($sequence, $string, $pos)) >= 0 ) {
                        my $val = substr($sequence, $pos, $len);
                        $pos += $len;
                        }
                }
        }
my $t3 = new Benchmark;

my $t4 = new Benchmark;
for (1..100) {
        my $ra = Regexp::Assemble->new();
        $ra->add(@strings);
        while ( $sequence =~ /$ra/g) { my $val = pos($sequence) - 6; }
        }
my $t5 = new Benchmark;

my $t6 = new Benchmark;
my $ra = Regexp::Assemble->new();
$ra->add(@strings);
for (1..100) {
        while ( $sequence =~ /$ra/g) { my $val = pos($sequence) - 6; }
        }
my $t7 = new Benchmark;

my $t8 = new Benchmark;
for (1..100) {
        study($sequence);
        foreach my $string (@strings) {
                my $len = length($string);
                while ($sequence =~ /$string/g) { my $val = pos($sequence) - $len; }
                }
        }
my $t9 = new Benchmark;


my $td1 = timediff($t1, $t0);
my $td2 = timediff($t3, $t2);
my $td3 = timediff($t5, $t4);
my $td4 = timediff($t7, $t6);
my $td5 = timediff($t9, $t8);

print 'Regexp                    : ', timestr($td1), "\n";
print 'Index                     : ', timestr($td2), "\n";
print 'Merged object inside loop : ', timestr($td3), "\n";
print 'Merged object out of loop : ', timestr($td4), "\n";
print 'Regexp with studying      : ', timestr($td5), "\n";


##</code><code>##

Regexp                    : 221 wallclock secs (221.08 usr +  0.05 sys = 221.13 CPU)
Index                     : 22 wallclock secs (21.49 usr +  0.00 sys = 21.49 CPU)
Merged object inside loop : 636 wallclock secs (636.61 usr +  0.21 sys = 636.82 CPU)
Merged object out of loop : 651 wallclock secs (651.06 usr +  0.18 sys = 651.24 CPU)
Regexp with studying      : 240 wallclock secs (239.50 usr +  0.27 sys = 239.77 CPU)