simple/dup/removeduplicatemails

53 lines
1.2 KiB
Plaintext
Raw Normal View History

2005-06-20 11:24:27 +02:00
#!/usr/bin/perl
use warnings;
use strict;
use File::Find;
use MIME::Parser;
my $parser = new MIME::Parser;
$parser->output_to_core(1);
$parser->tmp_to_core(1);
my %files;
my %messages;
sub check_file {
unless (-f) {
return;
}
my ($dev,$ino,$mode,$nlink,$uid,$gid,$rdev,$size,
$atime,$mtime,$ctime,$blksize,$blocks) = stat(_);
if ($files{"$dev.$ino"}) {
# we already looked at this file - skip
return;
}
my $entity = $parser->parse_open($_);
unless ($entity) {
print STDERR "$File::Find::name cannot be parsed: skipping\n";
return;
}
my $mid = $entity->head->get('Message-Id');
unless ($mid) {
print STDERR "$File::Find::name contains no message id: skipping\n";
return;
}
if ($messages{$mid}) {
# duplicate!
print STDERR "$File::Find::name is a duplicate of ",
$files{$messages{$mid}},
"\n";
my $ft = $File::Find::name;
$ft =~ s|(.*/)(.*)|$1|;
$ft .= "removedups.$$." . rand;
link ($files{$messages{$mid}}, $ft) && rename ($ft, $File::Find::name) || do {
print STDERR "\terror: $!\n";
};
return;
}
$messages{$mid} = "$dev.$ino";
$files{"$dev.$ino"} = $File::Find::name;
}
find(\&check_file, @ARGV);