X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FWatchMaildir.pm;h=02e4b32f254a8933e81e60b2001b8cc5ebce63c8;hb=e5a139171c3d9bfa23c4da009839cd6eafe3dae1;hp=cb64f899fb27e277b8a6032100f18683c35ff5e3;hpb=d983e59299602acac5d700093ac76c87dbaad10c;p=public-inbox.git

diff --git a/lib/PublicInbox/WatchMaildir.pm b/lib/PublicInbox/WatchMaildir.pm
index cb64f899..02e4b32f 100644
--- a/lib/PublicInbox/WatchMaildir.pm
+++ b/lib/PublicInbox/WatchMaildir.pm
@@ -1,211 +1,294 @@
-# Copyright (C) 2016 all contributors <meta@public-inbox.org>
+# Copyright (C) 2016-2020 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
+#
+# ref: https://cr.yp.to/proto/maildir.html
+#	http://wiki2.dovecot.org/MailboxFormat/Maildir
 package PublicInbox::WatchMaildir;
 use strict;
 use warnings;
-use Email::MIME;
-use Email::MIME::ContentType;
-$Email::MIME::ContentType::STRICT_PARAMS = 0; # user input is imperfect
-use PublicInbox::Git;
-use PublicInbox::Import;
-use PublicInbox::MDA;
-use PublicInbox::Spawn qw(spawn);
+use PublicInbox::MIME;
+use PublicInbox::InboxWritable;
+use File::Temp 0.19 (); # 0.19 for ->newdir
+use PublicInbox::Filter::Base qw(REJECT);
+use PublicInbox::Spamcheck;
+*mime_from_path = \&PublicInbox::InboxWritable::mime_from_path;
 
 sub new {
 	my ($class, $config) = @_;
-	my (%mdmap, @mdir);
-	my $k = 'publicinboxlearn.watchspam';
-	if (my $spamdir = $config->{$k}) {
-		if ($spamdir =~ s/\Amaildir://) {
-			$spamdir =~ s!/+\z!!;
-			# skip "new", no MUA has seen it, yet.
-			my $cur = "$spamdir/cur";
-			push @mdir, $cur;
-			$mdmap{$cur} = 'watchspam';
-		} else {
-			warn "unsupported $k=$spamdir\n";
+	my (%mdmap, @mdir, $spamc);
+	my %uniq;
+
+	# "publicinboxwatch" is the documented namespace
+	# "publicinboxlearn" is legacy but may be supported
+	# indefinitely...
+	foreach my $pfx (qw(publicinboxwatch publicinboxlearn)) {
+		my $k = "$pfx.watchspam";
+		defined(my $dirs = $config->{$k}) or next;
+		$dirs = [ $dirs ] if !ref($dirs);
+		for my $dir (@$dirs) {
+			if (is_maildir($dir)) {
+				# skip "new", no MUA has seen it, yet.
+				my $cur = "$dir/cur";
+				my $old = $mdmap{$cur};
+				if (ref($old)) {
+					foreach my $ibx (@$old) {
+						warn <<"";
+"$cur already watched for `$ibx->{name}'
+
+					}
+					die;
+				}
+				push @mdir, $cur;
+				$uniq{$cur}++;
+				$mdmap{$cur} = 'watchspam';
+			} else {
+				warn "unsupported $k=$dir\n";
+			}
 		}
 	}
-	foreach $k (keys %$config) {
-		$k =~ /\Apublicinbox\.([^\.]+)\.watch\z/ or next;
-		my $name = $1;
-		my $watch = $config->{$k};
-		if ($watch =~ s/\Amaildir://) {
-			$watch =~ s!/+\z!!;
-			my $inbox = $config->lookup_name($name);
-			if (my $wm = $inbox->{watchheader}) {
-				my ($k, $v) = split(/:/, $wm, 2);
-				$inbox->{-watchheader} = [ $k, qr/\Q$v\E/ ];
+
+	my $k = 'publicinboxwatch.spamcheck';
+	my $default = undef;
+	my $spamcheck = PublicInbox::Spamcheck::get($config, $k, $default);
+	$spamcheck = _spamcheck_cb($spamcheck) if $spamcheck;
+
+	$config->each_inbox(sub {
+		# need to make all inboxes writable for spam removal:
+		my $ibx = $_[0] = PublicInbox::InboxWritable->new($_[0]);
+
+		my $watch = $ibx->{watch} or return;
+		if (is_maildir($watch)) {
+			my $watch_hdrs = [];
+			if (my $whs = $ibx->{watchheader}) {
+				for (@$whs) {
+					my ($k, $v) = split(/:/, $_, 2);
+					push @$watch_hdrs, [ $k, qr/\Q$v\E/ ];
+				}
+			}
+			if (my $list_ids = $ibx->{listid}) {
+				for (@$list_ids) {
+					my $re = qr/<[ \t]*\Q$_\E[ \t]*>/;
+					push @$watch_hdrs, ['List-Id', $re ];
+				}
+			}
+			if (scalar @$watch_hdrs) {
+				$ibx->{-watchheaders} = $watch_hdrs;
 			}
 			my $new = "$watch/new";
 			my $cur = "$watch/cur";
-			push @mdir, $new, $cur;
-			die "$new already in use\n" if $mdmap{$new};
-			die "$cur already in use\n" if $mdmap{$cur};
-			$mdmap{$new} = $mdmap{$cur} = $inbox;
+			push @mdir, $new unless $uniq{$new}++;
+			push @mdir, $cur unless $uniq{$cur}++;
+
+			push @{$mdmap{$new} ||= []}, $ibx;
+			push @{$mdmap{$cur} ||= []}, $ibx;
 		} else {
 			warn "watch unsupported: $k=$watch\n";
 		}
-	}
+	});
 	return unless @mdir;
 
 	my $mdre = join('|', map { quotemeta($_) } @mdir);
 	$mdre = qr!\A($mdre)/!;
 	bless {
+		spamcheck => $spamcheck,
 		mdmap => \%mdmap,
 		mdir => \@mdir,
 		mdre => $mdre,
+		config => $config,
 		importers => {},
+		opendirs => {}, # dirname => dirhandle (in progress scans)
 	}, $class;
 }
 
 sub _done_for_now {
-	$_->done foreach values %{$_[0]->{importers}};
+	my ($self) = @_;
+	my $importers = $self->{importers};
+	foreach my $im (values %$importers) {
+		$im->done;
+	}
 }
 
 sub _try_fsn_paths {
-	my ($self, $paths) = @_;
-	_try_path($self, $_->{path}) foreach @$paths;
+	my ($self, $scan_re, $paths) = @_;
+	foreach (@$paths) {
+		my $path = $_->{path};
+		if ($path =~ $scan_re) {
+			scan($self, $path);
+		} else {
+			_try_path($self, $path);
+		}
+	}
 	_done_for_now($self);
 }
 
-sub _check_spam {
+sub _remove_spam {
 	my ($self, $path) = @_;
-	my $mime = _path_to_mime($path) or return;
-	_force_mid($mime);
-	foreach my $inbox (values %{$self->{mdmap}}) {
-		next unless ref $inbox;
-		my $im = _importer_for($self, $inbox);
-		$im->remove($mime);
-		if (my $scrub = _scrubber_for($inbox)) {
-			my $scrubbed = $scrub->scrub($mime) or next;
-			$im->remove($scrubbed);
+	# path must be marked as (S)een
+	$path =~ /:2,[A-R]*S[T-Za-z]*\z/ or return;
+	my $mime = mime_from_path($path) or return;
+	$self->{config}->each_inbox(sub {
+		my ($ibx) = @_;
+		eval {
+			my $im = _importer_for($self, $ibx);
+			$im->remove($mime, 'spam');
+			if (my $scrub = $ibx->filter($im)) {
+				my $scrubbed = $scrub->scrub($mime, 1);
+				$scrubbed or return;
+				$scrubbed == REJECT() and return;
+				$im->remove($scrubbed, 'spam');
+			}
+		};
+		if ($@) {
+			warn "error removing spam at: ", $path,
+				" from ", $ibx->{name}, ': ', $@, "\n";
 		}
-	}
-}
-
-# used to hash the relevant portions of a message when there are conflicts
-sub _hash_mime2 {
-	my ($mime) = @_;
-	require Digest::SHA;
-	my $dig = Digest::SHA->new('SHA-1');
-	$dig->add($mime->header_obj->header_raw('Subject'));
-	$dig->add($mime->body_raw);
-	$dig->hexdigest;
-}
-
-sub _force_mid {
-	my ($mime) = @_;
-	# probably a bad idea, but we inject a Message-Id if
-	# one is missing, here..
-	my $mid = $mime->header_obj->header_raw('Message-Id');
-	if (!defined $mid || $mid =~ /\A\s*\z/) {
-		$mid = '<' . _hash_mime2($mime) . '@generated>';
-		$mime->header_set('Message-Id', $mid);
-	}
+	})
 }
 
 sub _try_path {
 	my ($self, $path) = @_;
+	return unless PublicInbox::InboxWritable::is_maildir_path($path);
 	if ($path !~ $self->{mdre}) {
 		warn "unrecognized path: $path\n";
 		return;
 	}
-	my $inbox = $self->{mdmap}->{$1};
-	unless ($inbox) {
+	my $inboxes = $self->{mdmap}->{$1};
+	unless ($inboxes) {
 		warn "unmappable dir: $1\n";
 		return;
 	}
-	if (!ref($inbox) && $inbox eq 'watchspam') {
-		return _check_spam($self, $path);
-	}
-	my $im = _importer_for($self, $inbox);
-	my $mime = _path_to_mime($path) or return;
-	$mime->header_set($_) foreach @PublicInbox::MDA::BAD_HEADERS;
-	my $wm = $inbox->{-watchheader};
-	if ($wm) {
-		my $v = $mime->header_obj->header_raw($wm->[0]);
-		return unless ($v && $v =~ $wm->[1]);
-	}
-	if (my $scrub = _scrubber_for($inbox)) {
-		$mime = $scrub->scrub($mime) or return;
+	if (!ref($inboxes) && $inboxes eq 'watchspam') {
+		return _remove_spam($self, $path);
 	}
 
-	_force_mid($mime);
-	$im->add($mime);
+	my $warn_cb = $SIG{__WARN__} || sub { print STDERR @_ };
+	local $SIG{__WARN__} = sub {
+		$warn_cb->("path: $path\n");
+		$warn_cb->(@_);
+	};
+	foreach my $ibx (@$inboxes) {
+		my $mime = mime_from_path($path) or next;
+		my $im = _importer_for($self, $ibx);
+
+		# any header match means it's eligible for the inbox:
+		if (my $watch_hdrs = $ibx->{-watchheaders}) {
+			my $ok;
+			my $hdr = $mime->header_obj;
+			for my $wh (@$watch_hdrs) {
+				my @v = $hdr->header_raw($wh->[0]);
+				$ok = grep(/$wh->[1]/, @v) and last;
+			}
+			next unless $ok;
+		}
+
+		if (my $scrub = $ibx->filter($im)) {
+			my $ret = $scrub->scrub($mime) or next;
+			$ret == REJECT() and next;
+			$mime = $ret;
+		}
+		$im->add($mime, $self->{spamcheck});
+	}
 }
 
+sub quit { trigger_scan($_[0], 'quit') }
+
 sub watch {
 	my ($self) = @_;
-	my $cb = sub { _try_fsn_paths($self, \@_) };
-	my $mdir = $self->{mdir};
+	my $scan = File::Temp->newdir("public-inbox-watch.$$.scan.XXXXXX",
+					TMPDIR => 1);
+	my $scandir = $self->{scandir} = $scan->dirname;
+	my $re = qr!\A$scandir/!;
+	my $cb = sub { _try_fsn_paths($self, $re, \@_) };
 
-	require Filesys::Notify::Simple;
-	my $watcher = Filesys::Notify::Simple->new($mdir);
-	$watcher->wait($cb) while (1);
+	# lazy load here, we may support watching via IMAP IDLE
+	# in the future...
+	eval { require Filesys::Notify::Simple } or
+		die "Filesys::Notify::Simple is currently required for $0\n";
+	my $fsn = Filesys::Notify::Simple->new([@{$self->{mdir}}, $scandir]);
+	$fsn->wait($cb) until $self->{quit};
+}
+
+sub trigger_scan {
+	my ($self, $base) = @_;
+	my $dir = $self->{scandir} or return;
+	open my $fh, '>', "$dir/$base" or die "open $dir/$base failed: $!\n";
+	close $fh or die "close $dir/$base failed: $!\n";
 }
 
 sub scan {
-	my ($self) = @_;
-	my $mdir = $self->{mdir};
-	foreach my $dir (@$mdir) {
-		my $ok = opendir(my $dh, $dir);
-		unless ($ok) {
-			warn "failed to open $dir: $!\n";
-			next;
-		}
+	my ($self, $path) = @_;
+	if ($path =~ /quit\z/) {
+		%{$self->{opendirs}} = ();
+		_done_for_now($self);
+		delete $self->{scandir};
+		$self->{quit} = 1;
+		return;
+	}
+	# else: $path =~ /(cont|full)\z/
+	return if $self->{quit};
+	my $max = 10;
+	my $opendirs = $self->{opendirs};
+	my @dirnames = keys %$opendirs;
+	foreach my $dir (@dirnames) {
+		my $dh = delete $opendirs->{$dir};
+		my $n = $max;
 		while (my $fn = readdir($dh)) {
-			next unless $fn =~ /\A[a-zA-Z0-9][\w:,=\.]+\z/;
-			$fn = "$dir/$fn";
-			if (-f $fn) {
-				_try_path($self, $fn);
-			} else {
-				warn "not a file: $fn\n";
+			_try_path($self, "$dir/$fn");
+			last if --$n < 0;
+		}
+		$opendirs->{$dir} = $dh if $n < 0;
+	}
+	if ($path =~ /full\z/) {
+		foreach my $dir (@{$self->{mdir}}) {
+			next if $opendirs->{$dir}; # already in progress
+			my $ok = opendir(my $dh, $dir);
+			unless ($ok) {
+				warn "failed to open $dir: $!\n";
+				next;
+			}
+			my $n = $max;
+			while (my $fn = readdir($dh)) {
+				_try_path($self, "$dir/$fn");
+				last if --$n < 0;
 			}
+			$opendirs->{$dir} = $dh if $n < 0;
 		}
-		closedir $dh;
 	}
 	_done_for_now($self);
+	# do we have more work to do?
+	trigger_scan($self, 'cont') if keys %$opendirs;
 }
 
-sub _path_to_mime {
-	my ($path) = @_;
-	if (open my $fh, '<', $path) {
-		local $/;
-		my $str = <$fh>;
-		$str or return;
-		return Email::MIME->new(\$str);
-	} elsif ($!{ENOENT}) {
-		return;
-	} else {
-		warn "failed to open $path: $!\n";
-		return;
+sub _importer_for {
+	my ($self, $ibx) = @_;
+	my $importers = $self->{importers};
+	my $im = $importers->{"$ibx"} ||= $ibx->importer(0);
+	if (scalar(keys(%$importers)) > 2) {
+		delete $importers->{"$ibx"};
+		_done_for_now($self);
 	}
-}
 
-sub _importer_for {
-	my ($self, $inbox) = @_;
-	my $im = $inbox->{-import} ||= eval {
-		my $git = $inbox->git;
-		my $name = $inbox->{name};
-		my $addr = $inbox->{-primary_address};
-		PublicInbox::Import->new($git, $name, $addr);
-	};
-	$self->{importers}->{"$im"} = $im;
+	$importers->{"$ibx"} = $im;
 }
 
-sub _scrubber_for {
-	my ($inbox) = @_;
-	my $f = $inbox->{filter};
-	if ($f && $f =~ /::/) {
-		eval "require $f";
-		if ($@) {
-			warn $@;
-		} else {
-			return $f->new;
+sub _spamcheck_cb {
+	my ($sc) = @_;
+	sub {
+		my ($mime) = @_;
+		my $tmp = '';
+		if ($sc->spamcheck($mime, \$tmp)) {
+			return PublicInbox::MIME->new(\$tmp);
 		}
+		warn $mime->header('Message-ID')." failed spam check\n";
+		undef;
 	}
-	undef;
+}
+
+sub is_maildir {
+	$_[0] =~ s!\Amaildir:!! or return;
+	$_[0] =~ tr!/!/!s;
+	$_[0] =~ s!/\z!!;
+	$_[0];
 }
 
 1;