| 158 |
rodolico |
1 |
#! /usr/bin/env perl
|
|
|
2 |
|
|
|
3 |
use strict;
|
|
|
4 |
use warnings;
|
|
|
5 |
use Data::Dumper;
|
|
|
6 |
|
|
|
7 |
# takes a path and returns an array of the path for each subdirectory
|
|
|
8 |
sub parseDirectory {
|
|
|
9 |
use File::Basename;
|
|
|
10 |
my $separator = '/';
|
|
|
11 |
my @result;
|
|
|
12 |
my @temp = split( $separator, dirname( shift ) );
|
|
|
13 |
my $curpath = '';
|
|
|
14 |
for ( my $i = 0; $i < scalar( @temp ); $i++ ) {
|
|
|
15 |
$curpath .= ($curpath ? $separator : '' ) . $temp[$i];
|
|
|
16 |
push @result, $curpath;
|
|
|
17 |
}
|
|
|
18 |
return \@result;
|
|
|
19 |
}
|
|
|
20 |
|
|
|
21 |
my $maxCount = shift;
|
|
|
22 |
die "Enter maximum entries to show\n" unless $maxCount;
|
|
|
23 |
|
|
|
24 |
my $entry = 0; # just a simple index into our data
|
|
|
25 |
my %data; # hash for all our data
|
|
|
26 |
my $files = (); # temporary array for our file list
|
|
|
27 |
while ( my $line = <> ) {
|
|
|
28 |
chomp $line;
|
|
|
29 |
if ( $line =~ m/^(\d+) bytes each:$/ ) { # new entry
|
|
|
30 |
$data{++$entry}{'size'} = $1;
|
|
|
31 |
$data{$entry}{'files'} = [];
|
|
|
32 |
} elsif ( $line =~ m/^\s*$/ ) { # blank line, so get summary
|
|
|
33 |
$data{$entry}{'total'} = $data{$entry}{'size'} * scalar( @{$data{$entry}{'files'}} );
|
|
|
34 |
} else { # this should be a file name
|
|
|
35 |
push @{ $data{$entry}{'files'} }, $line;
|
|
|
36 |
}
|
|
|
37 |
}
|
|
|
38 |
|
|
|
39 |
#print Dumper( \%data ) . "\n"; die;
|
|
|
40 |
|
|
|
41 |
foreach my $thisEntry ( sort{ $data{$b}{'total'} <=> $data{$a}{'total'} } keys %data ) {
|
|
|
42 |
last unless $maxCount--;
|
|
|
43 |
my $numCopies = scalar( @{$data{$entry}{'files'}} );
|
|
|
44 |
print "$data{$thisEntry}{total} bytes wasted in following " . $numCopies . " files of $data{$thisEntry}{size} bytes\n";
|
|
|
45 |
print "\t" . join( "\n\t", @{$data{$thisEntry}{'files'}} ) . "\n\n";
|
|
|
46 |
}
|
|
|
47 |
|
|
|
48 |
exit 1;
|
|
|
49 |
|
|
|
50 |
my %directories;
|
|
|
51 |
|
|
|
52 |
foreach my $thisEntry ( keys %data ) {
|
|
|
53 |
foreach my $file ( @{$data{$thisEntry}{'files'}} ) {
|
|
|
54 |
my $parsedDir = &parseDirectory( $file );
|
|
|
55 |
foreach my $thisDir( @$parsedDir ) {
|
|
|
56 |
$directories{$thisDir}{'size'} += $data{$thisEntry}{'size'} * 1;
|
|
|
57 |
push @{ $directories{$thisDir}{'files'} }, $file;
|
|
|
58 |
}
|
|
|
59 |
}
|
|
|
60 |
}
|
|
|
61 |
|
|
|
62 |
foreach my $thisEntry ( sort{ $data{$b}{'size'} <=> $data{$a}{'size'} } keys %directories ) {
|
|
|
63 |
last unless $maxCount--;
|
|
|
64 |
print "$directories{$thisEntry}{size}\t$thisEntry\n\t";
|
|
|
65 |
print join( "\n\t", @{ $directories{$thisEntry}{'files'} } ) . "\n\n";
|
|
|
66 |
}
|
|
|
67 |
|
|
|
68 |
|
|
|
69 |
1;
|