#!/usr/bin/perl -w # usesage: dupDisplay.pl fileMD5.txt [remove] # input file has the following form: # 8e773d2546655b84dd1fdd31c735113e 304048 /media/PICTURES-1/mymedia/pictures/pics/20041004-kids-camera/im001020.jpg im001020.jpg # e01d4d804d454dd1fb6150fc74a0912d 296663 /media/PICTURES-1/mymedia/pictures/pics/20041004-kids-camera/im001021.jpg im001021.jpg use strict; use warnings; my %seen; my $fileCNT = 0; my $origCNT = 0; my $delCNT = 0; my $failCNT = 0; my $remove = 'remove' if $ARGV[1]; $remove = '' if !$ARGV[1]; print "\n\n ... running in NON removal mode.\n\n" if !$remove; open IN,"< $ARGV[0]" or die ".. we don't see a file to read: $ARGV[0]"; open OUT,"> $ARGV[0]_new.temp" or die ".. we can't write the file: $ARGV[0]_new.temp"; open OUTdel,"> $ARGV[0]_deleted" or die ".. we can't write the file: $ARGV[0]_deleted"; open OUTfail,"> $ARGV[0]_failed" or die ".. we can't write the file: $ARGV[0]_failed"; print "\n ... starting to read find duplicats in: $ARGV[0]\n"; if(! -d './trash/'){mkdir './trash/' or die " !! couldn't make trash directory.\n $! \n";} while(){ my $line = $_; chomp $line; $fileCNT++; my ($md5,$filesize,$pathfile,$file) = split /\t+/,$line,4; if(exists $seen{"$md5:$filesize"}){ my $timenow = time; my $trashFile = './trash/' . $file . "_" . $timenow; # moves duplicate file to trash with timestamp extension. #if( ! unlink($pathfile){print OUTfail "$pathfile\n"; $failCNT++;} if($remove){if( ! rename $pathfile,$trashFile){print OUTfail "$pathfile\n"; $failCNT++;}} $seen{"$md5:$filesize"} .= "\n $pathfile"; $delCNT++; print " files: $fileCNT originals: $origCNT files to delete: $delCNT failed: $failCNT \r"; }else{ $seen{"$md5:$filesize"} = "$pathfile"; printf OUT ("%32s\t%8d\t%s\t%s\n", $md5,$filesize,$pathfile,$file); $origCNT++; print " files: $fileCNT originals: $origCNT files to delete: $delCNT failed: $failCNT \r"; } } foreach my $key (keys %seen){ print OUTdel " $seen{$key}\n"; } print " files: $fileCNT originals: $origCNT files to delete: $delCNT failed: $failCNT \n\n";