in reply to List Duplicate Files in a given directory

When i do this i tend to be more interested in what files match so do one of these two paths 

#!/usr/bin/perl
use warnings;
use strict;
use Data::Dumper;
##############

my $md5files={}; 
my $filesmd5={}; 

while (my $line=<DATA>){ 
  chomp $line; 
  my ($fn,$md5)=split(' ',$line,2);
  push @{$md5files->{$md5}},$fn; 
  $filesmd5->{$fn}=$md5;  
  } # line 

for my $md5 (keys %$md5files){ 
  my $md5list=$md5files->{$md5}; 
  if (scalar(@$md5list) == 1 ) { print $md5."\n   ".$md5list->[0]."\n"
+;} 
  else {
    print $md5."\n";
    for my $file (sort @$md5list){ 
     print '   '.$file."\n";
      } 
    } 
  } # md5  

for my $file (sort keys %$filesmd5) { 
  my $md5list=$md5files->{$filesmd5->{$file}}; 
  if (scalar(@$md5list) == 1 ) { print $file." is unique\n";} 
  else {
    print $file." is the same as\n";
    for my $filed (sort @$md5list){ 
     print '   '.$filed."\n" unless ($file eq $filed);
      } 
    } 
  } # file 


exit; 
__DATA__ 
file2 d41d8cd98f00b204e9800998ecf8427e
file1 5bb062356cddb5d2c0ef41eb2660cb06
file3 d41d8cd98f00b204e9800998ecf8427e
file4 d41d8cd98f00b204e9800998ecf8427e
file5 5bb062356cddb5d2c0ef41eb2660cb06
file6 d617c2deabd27ff86ca9825b2e7578d4

[download]
d617c2deabd27ff86ca9825b2e7578d4
   file6
d41d8cd98f00b204e9800998ecf8427e
   file2
   file3
   file4
5bb062356cddb5d2c0ef41eb2660cb06
   file1
   file5
file1 is the same as
   file5
file2 is the same as
   file3
   file4
file3 is the same as
   file2
   file4
file4 is the same as
   file2
   file3
file5 is the same as
   file1
file6 is unique

[download]

Replies are listed 'Best First'.
Re^2: List Duplicate Files in a given directory
by pr33 (Scribe) on Jul 31, 2017 at 05:57 UTC

    Thanks Huck and Keybot . From your solution, It is clear to use md5dum's as the keys of the hash and then hash value as a reference to an array of files . I have changed my original code to create a Hash of an Array to do this. 

    #!/usr/bin/perl
use warnings;
use strict;
use Data::Dumper;
##############
my $dir = "$ARGV[0]";
my %md5sum;
opendir(my $dh, $dir) || die "Unable to Open the Directory: $!\n";
chdir $dir or die "Cannot Change directory: $!\n";
while (my $file = readdir $dh) {
    chomp $file;
    next if $file =~ /^\.{1,2}$/g;
    if (-f $file) {
        my ($md) = (split /\s+/, qx(/usr/bin/md5sum $file))[0];
    if (exists $md5sum{$md}) {
       push @{$md5sum{$md}}, $file;
    } else {
       push @{$md5sum{$md}}, $file;
    }
  }
}
   closedir($dh);

foreach my $ky (keys %md5sum) {
    if (scalar( @{$md5sum{$ky}}) == 1) {
       print "Unique File: @{$md5sum{$ky}} , Md5sum: $ky\n";
    } else {
      print "Duplicate Files:  @{$md5sum{$ky}}, Md5sum: $ky\n";
    }
}

    [download]
    -bash-3.2$ ./duplicate_files.pl directory
Duplicate Files:  file4 file2 file3, Md5sum: d41d8cd98f00b204e9800998e
+cf8427e
Unique File: file6 , Md5sum: d617c2deabd27ff86ca9825b2e7578d4
Duplicate Files:  file1 file5, Md5sum: 5bb062356cddb5d2c0ef41eb2660cb0
+6

    [download]
[reply]
[d/l]
[select]

In Section Seekers of Perl Wisdom