Initial commit

1 files changed, 56 insertions, 0 deletions

diff --git a/dups b/dups
new file mode 100755
index 0000000..bbf357e
--- /dev/null
+++ b/dups
@@ -0,0 +1,56 @@
+#!/usr/bin/env perl
+
+use strict;
+use warnings;
+
+use File::Find qw<find>;
+use IPC::System::Simple qw<capture>;
+
+@ARGV ge 1 || die "Usage: $0 <dir1> [<dir2> ...]\n";
+
+my %sizes;
+my %md5s;
+
+sub fill_sizes {
+    return if -d "$_"; # Skip directories
+
+    my $size = capture("stat", "--printf=%s", $_);
+    $sizes{$size} ||= [];
+    push @{$sizes{$size}}, $File::Find::name;
+}
+
+print STDERR "Collecting file sizes...\n";
+find(\&fill_sizes, $_) foreach (@ARGV);
+
+print STDERR "Computing md5s of files with same size...\n";
+my @progress = (0, 0, scalar(keys(%sizes)));
+foreach my $size (keys(%sizes)) {
+    $progress[0]++;
+    $progress[1] = 0;
+    my @same_size_files = @{$sizes{$size}};
+    next unless @same_size_files gt 1; # Discard unique sizes
+
+
+    foreach my $file (@same_size_files) {
+        $progress[1]++;
+        print STDERR "$progress[0].$progress[1] / $progress[2]\r";
+        STDERR->flush();
+
+        my ($md5) = capture("md5sum", "-z", $file) =~ m/^([^ ]+)/;
+        $md5s{$md5} ||= [];
+        push @{$md5s{$md5}}, $file;
+    }
+}
+
+foreach my $md5 (keys(%md5s)) {
+    my @same_md5_files = @{$md5s{$md5}};
+    next unless @same_md5_files gt 1; # Discard unique hashes
+
+    print "Found duplicate files:\n";
+    foreach my $file (@same_md5_files) {
+        print "\t$file\n";
+    }
+    printf "\n";
+}
+
+printf STDERR "Done!\n";