watch: remove {mdir} array

Since we store all watched directory names as keys in %mdmap,
there should be no need to keep an array of those directories
around.

t/watch_maildir*.t required changes to remove trained spam.
Once we've trained something as spam, there shouldn't be
a need to rescan it.

diff --git a/lib/PublicInbox/WatchMaildir.pm b/lib/PublicInbox/WatchMaildir.pm
index 621d41bd81d40e2166bbd64a6d2f200671323fc2..8d2dc43268466efc38bea13924171f4e79973c9c 100644 (file)
--- a/lib/PublicInbox/WatchMaildir.pm
+++ b/lib/PublicInbox/WatchMaildir.pm
@@ -40,8 +40,7 @@ sub compile_watchheaders ($) {
 
 sub new {
        my ($class, $config) = @_;
-       my (%mdmap, @mdir, $spamc);
-       my %uniq; # directory => count
+       my (%mdmap, $spamc);
        my %imap; # url => [inbox objects] or 'watchspam'
 
        # "publicinboxwatch" is the documented namespace
@@ -54,10 +53,7 @@ sub new {
                for my $dir (@$dirs) {
                        if (is_maildir($dir)) {
                                # skip "new", no MUA has seen it, yet.
-                               my $cur = "$dir/cur";
-                               push @mdir, $cur;
-                               $uniq{$cur}++;
-                               $mdmap{$cur} = 'watchspam';
+                               $mdmap{"$dir/cur"} = 'watchspam';
                        } elsif (my $url = imap_url($dir)) {
                                $imap{$url} = 'watchspam';
                        } else {
@@ -83,8 +79,6 @@ sub new {
                                my ($new, $cur) = ("$watch/new", "$watch/cur");
                                my $cur_dst = $mdmap{$cur} //= [];
                                return if is_watchspam($cur, $cur_dst, $ibx);
-                               push @mdir, $new unless $uniq{$new}++;
-                               push @mdir, $cur unless $uniq{$cur}++;
                                push @{$mdmap{$new} //= []}, $ibx;
                                push @$cur_dst, $ibx;
                        } elsif (my $url = imap_url($watch)) {
@@ -96,17 +90,16 @@ sub new {
                        }
                }
        });
-       return unless scalar(@mdir) || scalar(keys %imap);
 
        my $mdre;
-       if (@mdir) {
-               $mdre = join('|', map { quotemeta($_) } @mdir);
+       if (scalar keys %mdmap) {
+               $mdre = join('|', map { quotemeta($_) } keys %mdmap);
                $mdre = qr!\A($mdre)/!;
        }
+       return unless $mdre || scalar(keys %imap);
        bless {
                spamcheck => $spamcheck,
                mdmap => \%mdmap,
-               mdir => \@mdir,
                mdre => $mdre,
                config => $config,
                imap => scalar keys %imap ? \%imap : undef,
@@ -231,7 +224,8 @@ sub watch_fs_init ($) {
                $self->{done_timer} //= PublicInbox::DS::requeue($done);
        };
        require PublicInbox::DirIdle;
-       PublicInbox::DirIdle->new($self->{mdir}, $cb); # EPOLL_CTL_ADD
+       # inotify_create + EPOLL_CTL_ADD
+       PublicInbox::DirIdle->new([keys %{$self->{mdmap}}], $cb);
 }
 
 # returns the git config section name, e.g [imap "imaps://user@example.com"]
@@ -688,7 +682,7 @@ sub fs_scan_step {
                $opendirs->{$dir} = $dh if $n < 0;
        }
        if ($op && $op eq 'full') {
-               foreach my $dir (@{$self->{mdir}}) {
+               foreach my $dir (keys %{$self->{mdmap}}) {
                        next if $opendirs->{$dir}; # already in progress
                        my $ok = opendir(my $dh, $dir);
                        unless ($ok) {

diff --git a/t/watch_maildir.t b/t/watch_maildir.t
index c8658140cf2de1ed6d97c2816f54cfcbd4e49617..c44273f051902afe94694832ca4f6a5f3652c3bc 100644 (file)
--- a/t/watch_maildir.t
+++ b/t/watch_maildir.t
@@ -84,6 +84,7 @@ PublicInbox::WatchMaildir->new($config)->scan('full');
 is(scalar @list, 2, 'two revisions in rev-list');
 @list = $git->qx(qw(ls-tree -r --name-only refs/heads/master));
 is(scalar @list, 0, 'tree is empty');
+is(unlink(glob("$spamdir/cur/*")), 1, 'unlinked trained spam');
 
 # check with scrubbing
 {
@@ -105,6 +106,7 @@ More majordomo info at  http://vger.kernel.org/majordomo-info.html\n);
        is(scalar @list, 0, 'tree is empty');
        @list = $git->qx(qw(rev-list refs/heads/master));
        is(scalar @list, 4, 'four revisions in rev-list');
+       is(unlink(glob("$spamdir/cur/*")), 1, 'unlinked trained spam');
 }
 
 {

diff --git a/t/watch_maildir_v2.t b/t/watch_maildir_v2.t
index 6cc8b6ff0e9a1c62baeaadc8d4943dad43a34f94..f5b8e932985076c5e413b77f3a1d0870ffdb997e 100644 (file)
--- a/t/watch_maildir_v2.t
+++ b/t/watch_maildir_v2.t
@@ -71,6 +71,7 @@ $write_spam->();
 is(unlink(glob("$maildir/new/*")), 1, 'unlinked old spam');
 PublicInbox::WatchMaildir->new($config)->scan('full');
 is(($srch->reopen->query(''))[0], 0, 'deleted file');
+is(unlink(glob("$spamdir/cur/*")), 1, 'unlinked trained spam');
 
 # check with scrubbing
 {
@@ -90,6 +91,7 @@ More majordomo info at  http://vger.kernel.org/majordomo-info.html\n);
        PublicInbox::WatchMaildir->new($config)->scan('full');
        ($nr, $msgs) = $srch->reopen->query('');
        is($nr, 0, 'inbox is empty again');
+       is(unlink(glob("$spamdir/cur/*")), 1, 'unlinked trained spam');
 }
 
 {