I am new to perl (and to writing code) and I have just been in an excellent
course organized by Barcelona_pm. I have rewritten lemming code as an exercise of using Moose. To improve speed, following above suggestions, files with similar size are first identified and, afterwards, md5 value is calculated in these files. Because this is baby-code, please feell free to recomend any RTFM $manual that I sould review to improve the code. Thanks for this great language!
(I have to thank Alba from Barcelona_pm for suggestions on how to improve the code).
This is the definition of the object "FileDups"
package FileDups;
use Digest::MD5;
use Moose;
use namespace::autoclean;
has 'name' => (is => 'ro', isa => 'Str', required => 1,);
has 'pathname' => (is => 'ro', isa => 'Str', required => 1,);
has 'max_size' => (is => 'ro', isa => 'Num', required => 1,);
has 'big' => (is => 'rw', isa => 'Bool', required => 1, default =
+> 0);
has 'unread' => (is => 'rw', isa => 'Bool', required => 1, default =
+> 0);
has 'dupe' => (is => 'rw', isa => 'Bool', required => 1, default =
+> 0);
has 'md5' => (is => 'ro', isa => 'Str', lazy => 1, builder =
+> '_calculate_md5');
has 'size' => (is => 'ro', isa => 'Num', lazy => 1, builder =
+> '_calculate_size');
sub _calculate_size {
my $self = shift;
my $size = -s $self->name;
if (-s $self->name > $self->max_size) {
$size = $self->max_size;
$self->big(1);
}
return $size;
}
sub _calculate_md5 {
my $self = shift;
my $file = $self->pathname;
my $size = $self->size;
my $chksum = 0;
if ($size == $self->max_size) {
$chksum = 'a'x32;
} else {
my $fh;
unless (open $fh, "<", "$file" ) {
$self->unread(1);
return -1; #return -1 and exit from subrutine if file can
+not be opened
}
binmode($fh);
$chksum = Digest::MD5->new->addfile($fh)->hexdigest;
close($fh);
}
return $chksum;
}
;1
And this is the main package that lists duplicate files, big files and unread files.
#!/usr/bin/env perl
# References:
# http://drdobbs.com/web-development/184416070
use strict;
use warnings;
use File::Find;
use lib qw(lib);
use FileDups;
use Data::Dumper;
# Hash of => [array of [array]], [array of objects]
my (%dup, %sizes, @object, $number_files, $number_size_dups);
my $max_size = 99999999; # Size above of whitch md5 will n
+ot be calculated
my $return = "Press return to continue \n\n";
my $line = "-"x70 . "\n";
while (my $dir = shift @ARGV) { # Find and classify files
die "\"$dir\" is not a directory. Give me a directory to search\n"
+ unless (-d "$dir");
File::Find::find (\&wanted,"$dir");
}
print "\n";
foreach (@object) { # Calculates md5 for files with equ
+al size
if ($sizes{$_->size} == "1") {
$number_size_dups += 1; print "$number_size_dups Files with th
+e same size \r";
$_->dupe(1); # The object has another object with t
+he same size
$_->md5; # Calculates md5
}
}
foreach (@object) { # Creates a hash of md5 values
if ($_->dupe == 1) { # for files with the same size
if (exists $dup{$_->md5}) {
push @{$dup{$_->md5}}, [$_->size, $_->name, $_->pathname];
} else {
$dup{$_->md5} = [ [$_->size, $_->name, $_->pathname] ];
}
}
}
print "\n\nDuplicated files\n $line $return"; my $pausa4 = <>;
foreach (sort keys %dup)
{ # sort hash by md5sum
if ($#{$dup{$_}} > 0) # $_ = keys
{ # if we have more than 1 array whithin th
+e same hash
printf("\n%8s %10.10s %s\n", "Size", "Name", "Pathname");
foreach ( @{$dup{$_}} ) # $_ = keys, $dupes{keys} =
+list of references (scalars)
{ # iterate trough the first dimension of t
+he array
printf("%8d %10.10s %s\n",@{$_}); # dereference referen
+ce to array
}
}
}
my $r1 = &list_files("Big files","big",@object); # List big files
my $r2 = &list_files("Unread files","unread",@object); # List unrea
+d files
sub wanted {
return unless (-f $_);
my $file = FileDups->new(name => $_, pathname => $File::Find::name
+, max_size => $max_size);
$number_files += 1; print "$number_files Files seen\r";
if ($file->size == $max_size) { # Identifies big files
$sizes{$file->size} = "0"; # We do not check md5 for bi
+g files
} elsif (exists $sizes{$file->size}) { # There are more the
+n one file with this size
$sizes{$file->size} = "1";
} else {
$sizes{$file->size} = "0"; # This is a new size value,
+not duplicated
}
push @object, $file; # Puts the object in the @obje
+ct array
}
sub list_files { # List objects according to criter
+ia:
my ($title,$criteria,@object) = @_; # (a) big files; (b)
+unread files
print "\n \n $title \n" . $line; my $pausa = <>;
foreach (@object) {
if ($_->$criteria) {
printf(" %10.10s %s\n",$_->name,$_->pathname);
}
}
print $line;
}
-
Are you posting in the right place? Check out Where do I post X? to know for sure.
-
Posts may use any of the Perl Monks Approved HTML tags. Currently these include the following:
<code> <a> <b> <big>
<blockquote> <br /> <dd>
<dl> <dt> <em> <font>
<h1> <h2> <h3> <h4>
<h5> <h6> <hr /> <i>
<li> <nbsp> <ol> <p>
<small> <strike> <strong>
<sub> <sup> <table>
<td> <th> <tr> <tt>
<u> <ul>
-
Snippets of code should be wrapped in
<code> tags not
<pre> tags. In fact, <pre>
tags should generally be avoided. If they must
be used, extreme care should be
taken to ensure that their contents do not
have long lines (<70 chars), in order to prevent
horizontal scrolling (and possible janitor
intervention).
-
Want more info? How to link
or How to display code and escape characters
are good places to start.