#! /usr/bin/env perl

# fdupesGreatestSavings
#
# Filter which takes the output of fdupes --size and reports on which duplicated
# files clean up will result in the greatest savings.
# 
# Usage: fdupes --size --recurse / | fdupesGreatestSavings 100
#
# Copyright 2024 Daily Data, Inc.
# 
# Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following 
# conditions are met:
#
#   Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer.
#   Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer 
#   in the documentation and/or other materials provided with the distribution.
#   Neither the name of the copyright holder nor the names of its contributors may be used to endorse or promote products derived
#   from this software without specific prior written permission.
# 
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT
# NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL
# THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
# (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
# OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

use strict;
use warnings;
use Data::Dumper;

# takes a path and returns an array of the path for each subdirectory
sub parseDirectory {
   use File::Basename;
   my $separator = '/';
   my @result;
   my @temp = split( $separator, dirname( shift ) );
   my $curpath = '';
   for ( my $i = 0; $i < scalar( @temp ); $i++ ) {
      $curpath .= ($curpath ? $separator : '' ) . $temp[$i];
      push @result, $curpath;
   }
   return \@result;
}

my $maxCount = shift;
die "Enter maximum entries to show\n" unless $maxCount;

my $entry = 0; # just a simple index into our data
my %data; # hash for all our data
my $files = (); # temporary array for our file list
while ( my $line = <> ) {
   chomp $line;
   if ( $line =~ m/^(\d+) bytes each:$/ ) { # new entry
      $data{++$entry}{'size'} = $1;
      $data{$entry}{'files'} = [];
   } elsif ( $line =~ m/^\s*$/ ) { # blank line, so get summary
      $data{$entry}{'total'} = $data{$entry}{'size'} * scalar( @{$data{$entry}{'files'}} );
   } else { # this should be a file name
      push @{ $data{$entry}{'files'} }, $line;
   }
}

#print Dumper( \%data ) . "\n"; die;

foreach my $thisEntry ( sort{ $data{$b}{'total'} <=> $data{$a}{'total'} } keys %data ) {
   last unless $maxCount--;
   my $numCopies = scalar( @{$data{$thisEntry}{'files'}} );
   print "$data{$thisEntry}{total} bytes wasted in following " . $numCopies . " files of $data{$thisEntry}{size} bytes\n";
   print "\t" . join( "\n\t", @{$data{$thisEntry}{'files'}} ) . "\n\n";
}

exit 1;

my %directories;

foreach my $thisEntry ( keys %data ) {
   foreach my $file ( @{$data{$thisEntry}{'files'}} ) {
      my $parsedDir = &parseDirectory( $file );
      foreach my $thisDir( @$parsedDir ) {
         $directories{$thisDir}{'size'} += $data{$thisEntry}{'size'} * 1;
         push @{ $directories{$thisDir}{'files'} }, $file;
      }
   }
}
  
foreach my $thisEntry ( sort{ $data{$b}{'size'} <=> $data{$a}{'size'} } keys %directories ) {
   last unless $maxCount--;
   print "$directories{$thisEntry}{size}\t$thisEntry\n\t";
   print join( "\n\t", @{ $directories{$thisEntry}{'files'} } ) . "\n\n";
}

 
1;