in reply to Find the n biggest files

#!/usr/bin/perl --
use strict; use warnings;
use File::Find::Rule;
use Number::Bytes::Human qw(format_bytes);

my $nBiggest = 20;
my $progress = 1;

Main( @ARGV );
exit( 0 );

sub Main {
    my @dirs = @_;
    push @dirs, '.' unless @dirs; # cwd
    my $rule = File::Find::Rule->file->readable;
    
    $rule->exec(\&progress) if $progress;
    
    my @files = $rule->in( @dirs );
    
    @files = sort { $$b[0] <=> $$a[0] } map { [ -s $_ , $_ ] } @files;
    @files = @files[ 0 .. $nBiggest ];
    print "\rBiggest $nBiggest\n";
    for my $file ( @files ){
        printf " %10s  %s\n", format_bytes( $$file[0] ), $$file[1];
    }
}

BEGIN {
    my $n = 0;
    my @s = qw[ * - \ | / ];
    sub progress {
        local $|=1;
        print "\r", $s[ $n++ % 4 ];
        1;
    }
}
__END__
Biggest 20
       282K  blort.1.0.1.0.zip
       104K  blort.615.dll
       104K  blib/arch/auto/win32/blort/blort.dll
       103K  blort.cpp
       100K  blort.316.pll
       100K  blort.522.dll
        54K  win32-blort.tar.gz
        49K  x86/win32-blort.tar.gz
        45K  main.cpp
        22K  list.cpp
        21K  blort.pm
        21K  blib/lib/win32/blort.pm
        20K  fort.h
        15K  blib/html/lib/site/blort/blort.html
        13K  plfort.h
        13K  plfort.cpp
        12K  makefile
       5.9K  fort.cpp
       4.6K  rambo.diff
       4.1K  list.h
       3.2K  flap.cpp

[download]

Replies are listed 'Best First'.
Re^2: Find the n biggest files
by salva (Canon) on Feb 10, 2012 at 08:57 UTC
    A derived version that doesn't load the full file list in memory: 
    use strict;
use warnings;
use File::Find::Rule;

my ($n, @dirs) = @ARGV;
$n ||= 20;
@dirs = '.' unless @dirs;

sub top {
    my $file_sizes = shift;
    my @big = (sort { $file_sizes->{$b} <=> $file_sizes->{$a} } keys %
+$file_sizes)[0..$n-1];
    my %big = map { $_ => $file_sizes->{$_} } @big;
    return \%big
}

my $rule = File::Find::Rule->file->readable;
my $file_sizes = {};

$rule->start(@dirs);
while (defined (my $image = $rule->match) ) {
    my $size = (stat $image)[7];
    $file_sizes->{$image} = $size if defined $size;
    $file_sizes = top($file_sizes) if keys %$file_sizes > ($n + 10000)
+;
}
$file_sizes = top($file_sizes);

print "Biggest $n\n";
for my $file ( sort { $file_sizes->{$b} <=> $file_sizes->{$a} } keys %
+$file_sizes ){
    printf " %8dK  %s\n", $file_sizes->{$file} / 1024, $file;
}

    [download]
[reply]
[d/l]

In Section Seekers of Perl Wisdom