For just comparing files, it might be enough to do a CRC32 and use this along with the file size. This has the added advantage of allowing quick scans through ZIP files for dupes as well (using
Archive::Zip of course) because ZIP files already have crc32 values in them.
The CRC32 found in Compress::Zlib runs 82% faster than Digest::MD5 on my system, using the following benchmark program:
#!/usr/bin/perl -w
use strict;
use IO::File;
use Compress::Zlib ();
use Digest::MD5;
use Benchmark;
use constant BUFSIZE => 32768;
sub crc32
{
my $fh = shift;
binmode($fh);
sysseek($fh, 0, 0); # rewind
my $buffer = ' ' x BUFSIZE;
my $crc = 0;
while ($fh->sysread($buffer, BUFSIZE))
{
$crc = Compress::Zlib::crc32($buffer, $crc);
}
return $crc;
}
sub md5
{
my $fh = shift;
seek($fh, 0, 0); # rewind
my $md5 = Digest::MD5->new();
$md5->addfile($fh);
return $md5->digest;
}
foreach my $file (@ARGV)
{
my $fh = IO::File->new($file);
binmode($fh);
next if !defined($fh);
Benchmark::cmpthese(-10, {
"crc32 $file", sub { crc32($fh) },
"md5 $file", sub { md5($fh) }
});
}