Re: Help with removing duplicates in array

[hdb]

Can you try with

use strict;
use warnings;

As a minimum it will tell you that in the line where you use $#filtered, the underlying array @filtered is already out of scope. Probably you will see more problems with your code.

[beanscake]

good i have done that'

 

use strict;
use warnings;

#use List::MoreUtils qw(uniq); // i have tried this to handle the dupl
+icated emails
use Data::Dumper qw(Dumper);
my $Directory = $ARGV[0]; #Directory to scan for emails
my $Filename =$ARGV[1];  # where to write out found emails note: avoid
+ forever  loop make sure it's not the same directory

my $success   = "\n [+] $0 is Scanning For E-mails \n\n";
my $tryagain    = "\n [?] perl $0 Directory fileto.txt \n\n";
if (@ARGV != 2) { print $tryagain; exit(); } else { print $success; }
sub uniq {  #and this to handle the duplicated emails
    return keys %{{ map { $_ => 1 } @_ }};
}

#sub uniq {  #with this to handle the duplicated emails
 #   my %seen;
 #   grep !$seen{$_}++, @_;
#}

my $total_filesscanned = 0;
my $total_email = 0;
my @files = grep ( -f ,<$Directory*.txt*>); #scanning directory


open(my $fh, '>>', $Filename);
 foreach my $file (@files) {
$total_filesscanned++;  # begin to count numbers of file to be scanned
open my $open, '<', $file or die $!;
    while (<$open>) {
    
    
        chomp;
        my @findemails = split(' ');
        my @filtered = uniq(@findemails);  # meant to avoid duplicates
        #my @filtered  = join(" ", uniq(@findemails)); also took this 
+aproach
        
        
        foreach my $emails (@filtered) { 
          
            if($emails =~ /^\w+\@([\da-zA-Z\-]{1,}\.){1,}[\da-zA-Z-]{2
+,6}$/) { #grab the emails
    $total_email++;   # begin to count emails
 print $fh "$emails\n"; # write the emails to file
            
            } 
            }
        
            
        }
        
             
    close $file; # close files
      print "$file\n";
        
    }
    
    close $fh; # close the file to write
    
    #my $removed = @findemails - @filtered; # am expecting it to avoid
+ duplicate emails but it's not working
     print "Files Scanned: $total_filesscanned\n";
     print "E-mail Found: $total_email\n";
     #print "Filtered Total: $removed\n";
     print "done\n";

[hdb]

And what do you get? Does it run w/o warnings? Do you still get duplicates? Are you aware that you only remove duplicates from the same $file but that there could be duplicates across? Change your printing to

print $fh "$file:$emails\n"; # write the emails to file

to check from which file your emails are retrieved from.