Re: Optimizing performance for script to traverse on filesystem

[kejohm]

Rather than rolling your own code, you should probably use a module like File::Find. Here is an example that should do want you're trying to do (untested):

#!perl
use 5.012;

use File::Find;
use List::Util qw(min);

my $workdir = ...;

my %top_size_mailbox;
my $box_size;
my $all_mailbox_size  = 0;
my $all_mailbox_count = 0;
my $empty_mail_box    = 0;

find(
    {
        -wanted => sub {
            next if m/^\.+$/;
            next if m/\.(dat|mdb|snapshot)$/;
            if ( -d and m/^\d+\@\w/ ) {
                $all_mailbox_count++;
                $box_size = 0;
            }
            elsif ( m/\.msg$/ ) {
                my $msg_size = -s _;
                if ( $msg_size < 4096) {
                    $box_size += 4096;
                }
                else {
                    $box_size += $msg_size;
                }
            }
        },
        -postprocess => sub {
            if ( $File::Find::dir =~ m/(\d+)\@/ ) {
                my $msisdn = $1;
                $all_mailbox_size += $box_size;
                if ( $box_size == 0 ) {
                    $empty_mailbox++;
                }
                else {
                    top_size_mailbox( $msisdn, $box_size );
                }
            }
        },
    }
    $workdir,
);

sub top_size_mailbox {
    my ( $msisdn, $box_size ) = @_;

    if ( keys( %top_size_mailbox ) < $num_top_size_box ) {
        $top_size_mailbox{$box_size} = $msisdn;
    }
    else {
        my $min = min( keys %top_size_mailbox );
        if ( $box_size > $min ) {
            delete $top_size_mailbox{$min};
            $top_size_mailbox{$box_size} = $msisdn;
        }
    }
}

__END__

There are other similar modules like File::Find::Rule that you could also try.