in reply to Recursive search for duplicate files

Well file and folder names are sufficient. 
use warnings;
use strict;
use File::Find;
  
  
   my $directory = '/mnt/music/very-good';
  
   find (\&wanted, $directory);
  
  my %path_file;
 
  sub wanted {
    my  $path = $File::Find::dir;
    my  $filename = $File::Find::name;
 
       $path_file{$path} = $filename;
 
  my %count;
  while (my ($key , $value) = each(%path_file)) {
 
      $count{$key} +=1;
 
         }
  }

[download]

Replies are listed 'Best First'.
Re^2: Recursive search for duplicate files
by moritz (Cardinal) on Nov 27, 2007 at 14:16 UTC
    There you go: the idea is to store for each filename in which paths it occurs. 
    #!/usr/bin/perl
use warnings;
use strict;
use File::Find;
use File::Spec;
  
  
my $directory = shift @ARGV || '/mnt/music/very-good';
  
find (\&wanted, $directory);

my %path_file;

sub wanted {
    my $path = $File::Find::dir;
    my $filename = File::Spec->abs2rel($File::Find::name, $path);

    push @{$path_file{$filename}}, $path;

}

while (my ($filename, $paths) = each %path_file){
    if (scalar @$paths >= 2){
        print "$filename occurs in these paths: ", join(", ", @$paths)
+, "\n";
    }
#    else {
#        print "$filename is uniq\n";
#    }
}

    [download]
[reply]
[d/l]
      I have a question: Since %path_file is a hash why becomes an array here: 
       push @{$path_file{$filename}}, $path;

      [download]
      Dereferencing the array @path_file or the hash %path_file
[reply]
[d/l]
        The hash's values are references to arrays.

        Since push expects an array, not an array ref, it needs to be dereferenced with the @{ $array_ref } syntax.

[reply]
[d/l]

In Section Seekers of Perl Wisdom