perl script to check duplicate files

use strict;
use warnings;
use File::Find;
 use Digest::MD5;
use Data::Dumper ;
 
my @dup = fnd_dup(@ARGV) ;
#print Dumper ([@dup]);
 foreach my $cur_cup (@dup) {
foreach my $cur_fil (@$cur_cup) {
 
print "my duplicate file is $cur_fil\n";
}
}

sub fnd_dup (@){
   my (@dir_list) = @_;
  if ( $#dir_list < 0 ) {
     return (undef) ;
  }
  my %file ;
   find( sub { -f && push @{$file{(stat($_))[7]}}, $File::Find::name }, @dir_list  );
 
#print Dumper ([\%file]);
#'2040' => [
#                          '/opt/dkim-milter-2.8.3/obj.Linux.2.6.18-92.el5.x86_64/libsm/fpurge.o',
 #                          '/opt/dkim-milter-2.8.3/obj.Linux.2.6.18-128.el5.x86_64/libsm/fpurge.o'
#                        ]
  my (@resulth);
   my %md ;
  foreach my $size ( keys %file ) {
 

    if ( $#{$file{$size}} < 1 ) {
       next ;
    }

    foreach my $curr_file ( @{$file{$size}}) {
       open (FILE, $curr_file ) or next ;
       binmode(FILE) ;
      push @{$md{Digest::MD5->new->addfile(*FILE)->hexdigest}}, $curr_file ;
       close(FILE);
    }
    foreach my $hash (keys %md ) {
       if ($#{$md{$hash}} >= 1 ) {
         push (@resulth, [@{$md{$hash}}]);
 
      }
    }
  }
return (@resulth)

 

Basic Shell scripting

shell scripting

1. How do you find out what's your shell? - echo $SHELL

1. What's the command to find out today's date? - date
2. What's the command to find out users on the system? - who
3. How do you find out the current directory you're in? - pwd
4. How do you remove a file? - rm
5. How do you remove a - rm -rf
6. How do you find out your own username? - whoami
7. How do you send a mail message to somebody? - mail somebody@techinterviews.com -s 'Your subject' -c 'cc@techinterviews.com'
8. How do you count words, lines and characters in a file? - wc
9. How do you search for a string inside a given file? - grep string filename
10. How do you search for a string inside a directory? - grep string *
11. How do you search for a string in a directory with the subdirectories recursed? - grep -r string *
12. What are PIDs? - They are process IDs given to processes. A PID can vary from 0 to 65535.
13. How do you list currently running process? - ps
14. How do you stop a process? - kill pid
15. How do you find out about all running processes? - ps -ag
16. How do you stop all the processes, except the shell window? - kill 0
17. How do you fire a process in the background? - ./process-name &
18. How do you refer to the arguments passed to a shell script? - $1, $2 and so on. $0 is your script name.
19. What's the conditional statement in shell scripting? - if {condition} then … fi
20. How do you do number comparison in shell scripts? - -eq, -ne, -lt, -le, -gt, -ge
21. How do you test for file properties in shell scripts? - -s filename tells you if the file is not empty, -f filename tells you whether the argument is a file, and not a directory, -d filename tests if the argument is a directory, and not a file, -w filename tests for writeability, -r filename tests for readability, -x filename tests for executability
22. How do you do Boolean logic operators in shell scripting? - ! tests for logical not, -a tests for logical and, and -o tests for logical or.
23. How do you find out the number of arguments passed to the shell script? - $#
24. What's a way to do multilevel if-else's in shell scripting? - if {condition} then {statement} elif {condition} {statement} fi
25. How do you write a for loop in shell? - for {variable name} in {list} do {statement} done
26. How do you write a while loop in shell? - while {condition} do {statement} done
27. How does a case statement look in shell scripts? - case {variable} in {possible-value-1}) {statement};; {possible-value-2}) {statement};; esac
28. How do you read keyboard input in shell scripts? - read {variable-name}
29. How do you define a function in a shell script? - function-name() { #some code here return }
30. How does getopts command work? - The parameters to your script can be passed as -n 15 -x 20. Inside the script, you can iterate through the getopts array as while getopts n:x option, and the variable $option contains the value of the entered option.

http://www.postfix.org/SASL_README.html#client_sasl

http://www.postfix.org/SASL_README.html#client_sasl

massive site for perl

http://ironman.enlightenedperl.org

clean up script -- difference between two files

#!/usr/bin/perl


my $totalfile = $ARGV[0];
my $suspectfile = $ARGV[1];
my $outfile = $ARGV[2];

if ($#ARGV != 2) {
print "user script.pl realfile suspectfiel goodfile\n" ;
exit;
}

local $/;
open (SUS,"<" ,$suspectfile) or die " cannot open file " ;
my @allsus = split /\n/, <SUS>;
close( SUS) ;


open (TOT,"<" ,$totalfile) or die " cannot open file " ;
my @total = split /\n/, <TOT>;
close (TOT) ;

my %allsus = map {$_ => 1 } @allsus;

my @allgood = grep {!defined $allsus{$_ } } @total ;

my @new = join "\n", @allgood;

open (OUT,">",$outfile ) or die " cannot open file ";
print OUT "@new";
close (OUT);

perlmeme.org --> good site for perl examples

good site for perl examples 

best site to download ebooks

http://www.filecrop.com --

perl guide

http://cowens.github.com/perlopquick/perlopquick.html

Perl file to find duplicate files

#!/usr/bin/perl

use strict ;
use warnings;
use File::Find;
use Data::Dumper;
use Digest::MD5;

my $pth = $ARGV[0];
unless ($pth) {
  print " perl1 path";
  exit ;
}
$\ = $/;
my %size ;
my %unopenfile ;
my %md5;
my @resuts;
my $m5 = Digest::MD5->new;

find( sub {
    return if $_ eq '.' ;
    return  if $_ eq  '..';
    $size {$File::Find::name} = -s if -f ;

    }, $pth ) ;

foreach my $file ( keys %size ){
  next if $size{$file} < 1 ;

  unless (open (f1, "$file") ) {
    $unopenfile{$file}++;
    next ;
  }
  push @{$md5{$m5->addfile(*f1)->hexdigest}}, $file;

  close (f1);
}

foreach my $files ( keys %md5){
  if ($#{$md5{$files}} >= 1){
    push (@resuts, @{$md5{$files}});
  }

}

foreach my $dup (@resuts) {
  print "the duplicate files are $dup"

auto indent

need to put in you /root/.vimrc

:set tabstop=2 softtabstop=2 shiftwidth=2 expandtab

--