X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FWatchMaildir.pm;h=78aec8a25d5f4b6cfd3103917ecc93aed6ba2a7b;hb=b1054300d1e33cb7b2279922c8f73628551fbf8f;hp=fea7d5ef9ee54cd13d6a906dbb4339afaafdb511;hpb=1d2cc9c8ebf7916616c947837854a4a01d76d447;p=public-inbox.git

diff --git a/lib/PublicInbox/WatchMaildir.pm b/lib/PublicInbox/WatchMaildir.pm
index fea7d5ef..78aec8a2 100644
--- a/lib/PublicInbox/WatchMaildir.pm
+++ b/lib/PublicInbox/WatchMaildir.pm
@@ -7,13 +7,14 @@ package PublicInbox::WatchMaildir;
 use strict;
 use warnings;
 use PublicInbox::Eml;
-use PublicInbox::InboxWritable;
-use File::Temp 0.19 (); # 0.19 for ->newdir
+use PublicInbox::InboxWritable qw(eml_from_path warn_ignore_cb);
 use PublicInbox::Filter::Base qw(REJECT);
 use PublicInbox::Spamcheck;
+use PublicInbox::Sigfd;
 use PublicInbox::DS qw(now);
-use POSIX qw(_exit WNOHANG);
-*mime_from_path = \&PublicInbox::InboxWritable::mime_from_path;
+use PublicInbox::MID qw(mids);
+use PublicInbox::ContentHash qw(content_hash);
+use POSIX qw(_exit);
 
 sub compile_watchheaders ($) {
 	my ($ibx) = @_;
@@ -40,9 +41,8 @@ sub compile_watchheaders ($) {
 
 sub new {
 	my ($class, $config) = @_;
-	my (%mdmap, @mdir, $spamc);
-	my %uniq; # directory => count
-	my %imap; # url => [inbox objects] or 'watchspam'
+	my (%mdmap, $spamc);
+	my (%imap, %nntp); # url => [inbox objects] or 'watchspam'
 
 	# "publicinboxwatch" is the documented namespace
 	# "publicinboxlearn" is legacy but may be supported
@@ -50,16 +50,16 @@ sub new {
 	foreach my $pfx (qw(publicinboxwatch publicinboxlearn)) {
 		my $k = "$pfx.watchspam";
 		defined(my $dirs = $config->{$k}) or next;
-		$dirs = [ $dirs ] if !ref($dirs);
+		$dirs = PublicInbox::Config::_array($dirs);
 		for my $dir (@$dirs) {
+			my $url;
 			if (is_maildir($dir)) {
 				# skip "new", no MUA has seen it, yet.
-				my $cur = "$dir/cur";
-				push @mdir, $cur;
-				$uniq{$cur}++;
-				$mdmap{$cur} = 'watchspam';
-			} elsif (my $url = imap_url($dir)) {
+				$mdmap{"$dir/cur"} = 'watchspam';
+			} elsif ($url = imap_url($dir)) {
 				$imap{$url} = 'watchspam';
+			} elsif ($url = nntp_url($dir)) {
+				$nntp{$url} = 'watchspam';
 			} else {
 				warn "unsupported $k=$dir\n";
 			}
@@ -75,61 +75,59 @@ sub new {
 		# 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)) {
-			compile_watchheaders($ibx);
-			my ($new, $cur) = ("$watch/new", "$watch/cur");
-			return if is_watchspam($cur, $mdmap{$cur}, $ibx);
-			push @mdir, $new unless $uniq{$new}++;
-			push @mdir, $cur unless $uniq{$cur}++;
-			push @{$mdmap{$new} ||= []}, $ibx;
-			push @{$mdmap{$cur} ||= []}, $ibx;
-		} elsif (my $url = imap_url($watch)) {
-			return if is_watchspam($url, $imap{$url}, $ibx);
-			compile_watchheaders($ibx);
-			push @{$imap{$url} ||= []}, $ibx;
-		} else {
-			warn "watch unsupported: $k=$watch\n";
+		my $watches = $ibx->{watch} or return;
+		$watches = PublicInbox::Config::_array($watches);
+		for my $watch (@$watches) {
+			my $url;
+			if (is_maildir($watch)) {
+				compile_watchheaders($ibx);
+				my ($new, $cur) = ("$watch/new", "$watch/cur");
+				my $cur_dst = $mdmap{$cur} //= [];
+				return if is_watchspam($cur, $cur_dst, $ibx);
+				push @{$mdmap{$new} //= []}, $ibx;
+				push @$cur_dst, $ibx;
+			} elsif ($url = imap_url($watch)) {
+				return if is_watchspam($url, $imap{$url}, $ibx);
+				compile_watchheaders($ibx);
+				push @{$imap{$url} ||= []}, $ibx;
+			} elsif ($url = nntp_url($watch)) {
+				return if is_watchspam($url, $nntp{$url}, $ibx);
+				compile_watchheaders($ibx);
+				push @{$nntp{$url} ||= []}, $ibx;
+			} else {
+				warn "watch unsupported: $k=$watch\n";
+			}
 		}
 	});
-	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) || scalar(keys %nntp);
+
 	bless {
 		spamcheck => $spamcheck,
 		mdmap => \%mdmap,
-		mdir => \@mdir,
 		mdre => $mdre,
 		config => $config,
 		imap => scalar keys %imap ? \%imap : undef,
+		nntp => scalar keys %nntp? \%nntp : undef,
 		importers => {},
 		opendirs => {}, # dirname => dirhandle (in progress scans)
+		ops => [], # 'quit', 'full'
 	}, $class;
 }
 
 sub _done_for_now {
 	my ($self) = @_;
-	my $importers = $self->{importers};
-	foreach my $im (values %$importers) {
-		$im->done;
-	}
-}
-
-sub _try_fsn_paths {
-	my ($self, $scan_re, $paths) = @_;
-	foreach (@$paths) {
-		my $path = $_->{path};
-		if ($path =~ $scan_re) {
-			scan($self, $path);
-		} else {
-			_try_path($self, $path);
-		}
+	local $PublicInbox::DS::in_loop = 0; # waitpid() synchronously
+	for my $im (values %{$self->{importers}}) {
+		next if !$im; # $im may be undef during cleanup
+		eval { $im->done };
+		warn "$im->{ibx}->{name} ->done: $@\n" if $@;
 	}
-	_done_for_now($self);
 }
 
 sub remove_eml_i { # each_inbox callback
@@ -140,43 +138,51 @@ sub remove_eml_i { # each_inbox callback
 		$im->remove($eml, 'spam');
 		if (my $scrub = $ibx->filter($im)) {
 			my $scrubbed = $scrub->scrub($eml, 1);
-			$scrubbed or return;
-			$scrubbed == REJECT() and return;
-			$im->remove($scrubbed, 'spam');
+			if ($scrubbed && $scrubbed != REJECT) {
+				$im->remove($scrubbed, 'spam');
+			}
 		}
 	};
-	warn "error removing spam at: $loc from $ibx->{name}: $@\n" if $@;
+	if ($@) {
+		warn "error removing spam at: $loc from $ibx->{name}: $@\n";
+		_done_for_now($self);
+	}
 }
 
 sub _remove_spam {
 	my ($self, $path) = @_;
 	# path must be marked as (S)een
 	$path =~ /:2,[A-R]*S[T-Za-z]*\z/ or return;
-	my $eml = mime_from_path($path) or return;
+	my $eml = eml_from_path($path) or return;
+	local $SIG{__WARN__} = warn_ignore_cb();
 	$self->{config}->each_inbox(\&remove_eml_i, [ $self, $eml, $path ]);
 }
 
 sub import_eml ($$$) {
 	my ($self, $ibx, $eml) = @_;
-	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 = $eml->header_obj;
 		for my $wh (@$watch_hdrs) {
-			my @v = $hdr->header_raw($wh->[0]);
+			my @v = $eml->header_raw($wh->[0]);
 			$ok = grep(/$wh->[1]/, @v) and last;
 		}
 		return unless $ok;
 	}
-
-	if (my $scrub = $ibx->filter($im)) {
-		my $ret = $scrub->scrub($eml) or return;
-		$ret == REJECT() and return;
-		$eml = $ret;
+	eval {
+		my $im = _importer_for($self, $ibx);
+		if (my $scrub = $ibx->filter($im)) {
+			my $scrubbed = $scrub->scrub($eml) or return;
+			$scrubbed == REJECT and return;
+			$eml = $scrubbed;
+		}
+		$im->add($eml, $self->{spamcheck});
+	};
+	if ($@) {
+		warn "$ibx->{name} add failed: $@\n";
+		_done_for_now($self);
 	}
-	$im->add($eml, $self->{spamcheck});
 }
 
 sub _try_path {
@@ -191,71 +197,102 @@ sub _try_path {
 		warn "unmappable dir: $1\n";
 		return;
 	}
-	if (!ref($inboxes) && $inboxes eq 'watchspam') {
-		return _remove_spam($self, $path);
-	}
-
 	my $warn_cb = $SIG{__WARN__} || sub { print STDERR @_ };
 	local $SIG{__WARN__} = sub {
-		$warn_cb->("path: $path\n");
-		$warn_cb->(@_);
+		my $pfx = ($_[0] // '') =~ /^([A-Z]: )/g ? $1 : '';
+		$warn_cb->($pfx, "path: $path\n", @_);
 	};
+	if (!ref($inboxes) && $inboxes eq 'watchspam') {
+		return _remove_spam($self, $path);
+	}
 	foreach my $ibx (@$inboxes) {
-		my $eml = mime_from_path($path) or next;
+		my $eml = eml_from_path($path) or next;
 		import_eml($self, $ibx, $eml);
 	}
 }
 
-sub quit {
+sub quit_done ($) {
 	my ($self) = @_;
-	trigger_scan($self, 'quit') or $self->{quit} = 1;
-	if (my $imap_pid = $self->{-imap_pid}) {
-		kill('QUIT', $imap_pid);
-	}
-	if (my $idle_pids = $self->{idle_pids}) {
-		kill('QUIT', $_) for (keys %$idle_pids);
+	return unless $self->{quit};
+
+	# don't have reliable wakeups, keep signalling
+	my $done = 1;
+	for (qw(idle_pids poll_pids)) {
+		my $pids = $self->{$_} or next;
+		for (keys %$pids) {
+			$done = undef if kill('QUIT', $_);
+		}
 	}
+	$done;
+}
+
+sub quit {
+	my ($self) = @_;
+	$self->{quit} = 1;
+	%{$self->{opendirs}} = ();
+	_done_for_now($self);
+	quit_done($self);
 	if (my $idle_mic = $self->{idle_mic}) {
 		eval { $idle_mic->done };
-		warn "IDLE DONE error: $@\n" if $@;
-		eval { $idle_mic->disconnect };
-		warn "IDLE LOGOUT error: $@\n" if $@;
+		if ($@) {
+			warn "IDLE DONE error: $@\n";
+			eval { $idle_mic->disconnect };
+			warn "IDLE LOGOUT error: $@\n" if $@;
+		}
 	}
 }
 
-sub watch_fs {
+sub watch_fs_init ($) {
 	my ($self) = @_;
-	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, \@_) };
+	my $done = sub {
+		delete $self->{done_timer};
+		_done_for_now($self);
+	};
+	my $cb = sub {
+		_try_path($self, $_[0]->fullname);
+		$self->{done_timer} //= PublicInbox::DS::requeue($done);
+	};
+	require PublicInbox::DirIdle;
+	# inotify_create + EPOLL_CTL_ADD
+	PublicInbox::DirIdle->new([keys %{$self->{mdmap}}], $cb);
+}
+
+# avoid exposing deprecated "snews" to users.
+my %SCHEME_MAP = ('snews' => 'nntps');
 
-	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 $self->{quit};
+sub uri_scheme ($) {
+	my ($uri) = @_;
+	my $scheme = $uri->scheme;
+	$SCHEME_MAP{$scheme} // $scheme;
 }
 
 # returns the git config section name, e.g [imap "imaps://user@example.com"]
 # without the mailbox, so we can share connections between different inboxes
-sub imap_section ($) {
+sub uri_section ($) {
 	my ($uri) = @_;
-	$uri->scheme . '://' . $uri->authority;
+	uri_scheme($uri) . '://' . $uri->authority;
 }
 
-sub cfg_intvl ($$) {
-	my ($cfg, $key) = @_;
-	defined(my $v = $cfg->{lc($key)}) or return;
-	$v =~ /\A[0-9]+\z/s and return $v + 0;
+sub cfg_intvl ($$$) {
+	my ($cfg, $key, $url) = @_;
+	my $v = $cfg->urlmatch($key, $url) // return;
+	$v =~ /\A[0-9]+(?:\.[0-9]+)?\z/s and return $v + 0;
 	if (ref($v) eq 'ARRAY') {
 		$v = join(', ', @$v);
 		warn "W: $key has multiple values: $v\nW: $key ignored\n";
 	} else {
-		warn "W: $key=$v is not an integer value in seconds\n";
+		warn "W: $key=$v is not a numeric value in seconds\n";
 	}
 }
 
+sub cfg_bool ($$$) {
+	my ($cfg, $key, $url) = @_;
+	my $orig = $cfg->urlmatch($key, $url) // return;
+	my $bool = $cfg->git_bool($orig);
+	warn "W: $key=$orig for $url is not boolean\n" unless defined($bool);
+	$bool;
+}
+
 # flesh out common IMAP-specific data structures
 sub imap_common_init ($) {
 	my ($self) = @_;
@@ -263,23 +300,24 @@ sub imap_common_init ($) {
 	my $mic_args = {}; # scheme://authority => Mail:IMAPClient arg
 	for my $url (sort keys %{$self->{imap}}) {
 		my $uri = PublicInbox::URIimap->new($url);
-		my $sec = imap_section($uri);
+		my $sec = uri_section($uri);
 		for my $k (qw(Starttls Debug Compress)) {
-			my $key = lc("imap.$sec.$k");
-			defined(my $orig = $cfg->{$key}) or next;
-			my $v = PublicInbox::Config::_git_config_bool($orig);
-			if (defined($v)) {
-				$mic_args->{$sec}->{$k} = $v;
-			} else {
-				warn "W: $key=$orig is not boolean\n";
-			}
+			my $bool = cfg_bool($cfg, "imap.$k", $url) // next;
+			$mic_args->{$sec}->{$k} = $bool;
 		}
-		my $to = cfg_intvl($cfg, "imap.$sec.Timeout");
+		my $to = cfg_intvl($cfg, 'imap.timeout', $url);
 		$mic_args->{$sec}->{Timeout} = $to if $to;
-		$to = cfg_intvl($cfg, "imap.$sec.PollInterval");
-		$self->{imap_opt}->{$sec}->{poll_intvl} = $to if $to;
-		$to = cfg_intvl($cfg, "imap.$sec.IdleInterval");
-		$self->{imap_opt}->{$sec}->{idle_intvl} = $to if $to;
+		for my $k (qw(pollInterval idleInterval)) {
+			$to = cfg_intvl($cfg, "imap.$k", $url) // next;
+			$self->{imap_opt}->{$sec}->{$k} = $to;
+		}
+		my $k = 'imap.fetchBatchSize';
+		my $bs = $cfg->urlmatch($k, $url) // next;
+		if ($bs =~ /\A([0-9]+)\z/) {
+			$self->{imap_opt}->{$sec}->{batch_size} = $bs;
+		} else {
+			warn "$k=$bs is not an integer\n";
+		}
 	}
 	$mic_args;
 }
@@ -287,21 +325,23 @@ sub imap_common_init ($) {
 sub auth_anon_cb { '' }; # for Mail::IMAPClient::Authcallback
 
 sub mic_for ($$$) { # mic = Mail::IMAPClient
-	my ($self, $uri, $mic_args) = @_;
-	my $url = $uri->as_string;
-	my $cred = {
+	my ($self, $url, $mic_args) = @_;
+	my $uri = PublicInbox::URIimap->new($url);
+	require PublicInbox::GitCredential;
+	my $cred = bless {
 		url => $url,
 		protocol => $uri->scheme,
 		host => $uri->host,
 		username => $uri->user,
 		password => $uri->password,
-	};
-	my $common = $mic_args->{imap_section($uri)} // {};
+	}, 'PublicInbox::GitCredential';
+	my $common = $mic_args->{uri_section($uri)} // {};
+	# IMAPClient and Net::Netrc both mishandles `0', so we pass `127.0.0.1'
 	my $host = $cred->{host};
+	$host = '127.0.0.1' if $host eq '0';
 	my $mic_arg = {
 		Port => $uri->port,
-		# IMAPClient mishandles `0', so we pass `127.0.0.1'
-		Server => $host eq '0' ? '127.0.0.1' : $host,
+		Server => $host,
 		Ssl => $uri->scheme eq 'imaps',
 		Keepalive => 1, # SO_KEEPALIVE
 		%$common, # may set Starttls, Compress, Debug ....
@@ -323,7 +363,8 @@ sub mic_for ($$$) { # mic = Mail::IMAPClient
 		$cred = undef;
 	}
 	if ($cred) {
-		Git::credential($cred, 'fill'); # may prompt user here
+		$cred->check_netrc unless defined $cred->{password};
+		$cred->fill; # may prompt user here
 		$mic->User($mic_arg->{User} = $cred->{username});
 		$mic->Password($mic_arg->{Password} = $cred->{password});
 	} else { # AUTH=ANONYMOUS
@@ -332,39 +373,44 @@ sub mic_for ($$$) { # mic = Mail::IMAPClient
 	}
 	if ($mic->login && $mic->IsAuthenticated) {
 		# success! keep IMAPClient->new arg in case we get disconnected
-		$self->{mic_arg}->{imap_section($uri)} = $mic_arg;
+		$self->{mic_arg}->{uri_section($uri)} = $mic_arg;
 	} else {
 		warn "E: <$url> LOGIN: $@\n";
 		$mic = undef;
 	}
-	Git::credential($cred, $mic ? 'approve' : 'reject') if $cred;
+	$cred->run($mic ? 'approve' : 'reject') if $cred;
 	$mic;
 }
 
-sub imap_start ($) {
-	my ($self) = @_;
-	eval { require PublicInbox::IMAPClient } or
-		die "Mail::IMAPClient is required for IMAP:\n$@\n";
-	eval { require Git } or
-		die "Git (Perl module) is required for IMAP:\n$@\n";
-	eval { require PublicInbox::IMAPTracker } or
-		die "DBD::SQLite is required for IMAP\n:$@\n";
+sub imap_import_msg ($$$$$) {
+	my ($self, $url, $uid, $raw, $flags) = @_;
+	# our target audience expects LF-only, save storage
+	$$raw =~ s/\r\n/\n/sg;
 
-	my $mic_args = imap_common_init($self);
-	# make sure we can connect and cache the credentials in memory
-	$self->{mic_arg} = {}; # schema://authority => IMAPClient->new args
-	my $mics = $self->{mics} = {}; # schema://authority => IMAPClient obj
-	for my $url (sort keys %{$self->{imap}}) {
-		my $uri = PublicInbox::URIimap->new($url);
-		$mics->{imap_section($uri)} //= mic_for($self, $uri, $mic_args);
+	my $inboxes = $self->{imap}->{$url};
+	if (ref($inboxes)) {
+		for my $ibx (@$inboxes) {
+			my $eml = PublicInbox::Eml->new($$raw);
+			my $x = import_eml($self, $ibx, $eml);
+		}
+	} elsif ($inboxes eq 'watchspam') {
+		# we don't remove unseen messages
+		if ($flags =~ /\\Seen\b/) {
+			local $SIG{__WARN__} = warn_ignore_cb();
+			my $eml = PublicInbox::Eml->new($raw);
+			my $arg = [ $self, $eml, "$url UID:$uid" ];
+			$self->{config}->each_inbox(\&remove_eml_i, $arg);
+		}
+	} else {
+		die "BUG: destination unknown $inboxes";
 	}
 }
 
 sub imap_fetch_all ($$$) {
-	my ($self, $mic, $uri) = @_;
-	my $sec = imap_section($uri);
+	my ($self, $mic, $url) = @_;
+	my $uri = PublicInbox::URIimap->new($url);
+	my $sec = uri_section($uri);
 	my $mbx = $uri->mailbox;
-	my $url = $uri->as_string;
 	$mic->Clear(1); # trim results history
 	$mic->examine($mbx) or return "E: EXAMINE $mbx ($sec) failed: $!";
 	my ($r_uidval, $r_uidnext);
@@ -377,8 +423,8 @@ sub imap_fetch_all ($$$) {
 		return "E: $url cannot get UIDVALIDITY";
 	$r_uidnext //= $mic->uidnext($mbx) //
 		return "E: $url cannot get UIDNEXT";
-	my $itrk = PublicInbox::IMAPTracker->new;
-	my ($l_uidval, $l_uid) = $itrk->get_last($url);
+	my $itrk = PublicInbox::IMAPTracker->new($url);
+	my ($l_uidval, $l_uid) = $itrk->get_last;
 	$l_uidval //= $r_uidval; # first time
 	$l_uid //= 1;
 	if ($l_uidval != $r_uidval) {
@@ -392,52 +438,64 @@ sub imap_fetch_all ($$$) {
 	}
 	return if $l_uid >= $r_uid; # nothing to do
 
+	warn "I: $url fetching UID $l_uid:$r_uid\n";
 	$mic->Uid(1); # the default, we hope
+	my $bs = $self->{imap_opt}->{$sec}->{batch_size} // 1;
 	my $req = $mic->imap4rev1 ? 'BODY.PEEK[]' : 'RFC822.PEEK';
+
+	# TODO: FLAGS may be useful for personal use
 	my $key = $req;
 	$key =~ s/\.PEEK//;
-	my $inboxes = $self->{imap}->{$url};
-	warn "I: $url fetching $l_uid..$r_uid\n";
-	my $uid = -1;
+	my ($uids, $batch);
 	my $warn_cb = $SIG{__WARN__} || sub { print STDERR @_ };
 	local $SIG{__WARN__} = sub {
-		$warn_cb->("$url UID:$uid\n");
-		$warn_cb->(@_);
+		my $pfx = ($_[0] // '') =~ /^([A-Z]: )/g ? $1 : '';
+		$batch //= '?';
+		$warn_cb->("$pfx$url UID:$batch\n", @_);
 	};
 	my $err;
-	$itrk->{dbh}->begin_work;
-	for my $u ($l_uid..$r_uid) {
-		$uid = $u;
-		local $0 = "UID:$uid $mbx $sec";
-		my $r = $mic->fetch_hash($uid, $req);
-		unless ($r) { # network error?
-			$err = "E: $url UID FETCH $uid error: $!\n";
-			last;
-		}
+	do {
+		# I wish "UID FETCH $START:*" could work, but:
+		# 1) servers do not need to return results in any order
+		# 2) Mail::IMAPClient doesn't offer a streaming API
+		$uids = $mic->search("UID $l_uid:*") or
+			return "E: $url UID SEARCH $l_uid:* error: $!";
+		return if scalar(@$uids) == 0;
 
-		# messages get deleted, so holes appear
-		defined(my $raw = delete $r->{$uid}->{$key}) or next;
+		# RFC 3501 doesn't seem to indicate order of UID SEARCH
+		# responses, so sort it ourselves.  Order matters so
+		# IMAPTracker can store the newest UID.
+		@$uids = sort { $a <=> $b } @$uids;
 
-		# our target audience expects LF-only, save storage
-		$raw =~ s/\r\n/\n/sg;
+		# Did we actually get new messages?
+		return if $uids->[0] < $l_uid;
 
-		if (ref($inboxes)) {
-			for my $ibx (@$inboxes) {
-				my $eml = PublicInbox::Eml->new($raw);
-				my $x = import_eml($self, $ibx, $eml);
+		$l_uid = $uids->[-1] + 1; # for next search
+		my $last_uid;
+
+		while (scalar @$uids) {
+			my @batch = splice(@$uids, 0, $bs);
+			$batch = join(',', @batch);
+			local $0 = "UID:$batch $mbx $sec";
+			my $r = $mic->fetch_hash($batch, $req, 'FLAGS');
+			unless ($r) { # network error?
+				$err = "E: $url UID FETCH $batch error: $!";
+				last;
 			}
-		} elsif ($inboxes eq 'watchspam') {
-			my $eml = PublicInbox::Eml->new($raw);
-			my $arg = [ $self, $eml, "$uri UID:$uid" ];
-			$self->{config}->each_inbox(\&remove_eml_i, $arg);
-		} else {
-			die "BUG: destination unknown $inboxes";
+			for my $uid (@batch) {
+				# messages get deleted, so holes appear
+				my $per_uid = delete $r->{$uid} // next;
+				my $raw = delete($per_uid->{$key}) // next;
+				my $fl = $per_uid->{FLAGS} // '';
+				imap_import_msg($self, $url, $uid, \$raw, $fl);
+				$last_uid = $uid;
+				last if $self->{quit};
+			}
+			last if $self->{quit};
 		}
-		$itrk->update_last($url, $r_uidval, $uid);
-		last if $self->{quit};
-	}
-	_done_for_now($self);
-	$itrk->{dbh}->commit;
+		_done_for_now($self);
+		$itrk->update_last($r_uidval, $last_uid) if defined $last_uid;
+	} until ($err || $self->{quit});
 	$err;
 }
 
@@ -453,7 +511,8 @@ sub imap_idle_once ($$$$) {
 	}
 	$self->{idle_mic} = $mic; # for ->quit
 	my @res;
-	until ($self->{quit} || grep(/^\* [0-9]+ EXISTS/, @res) || $i <= 0) {
+	until ($self->{quit} || !$mic->IsConnected ||
+			grep(/^\* [0-9]+ EXISTS/, @res) || $i <= 0) {
 		@res = $mic->idle_data($i);
 		$i = $end - now();
 	}
@@ -467,17 +526,22 @@ sub imap_idle_once ($$$$) {
 
 # idles on a single URI
 sub watch_imap_idle_1 ($$$) {
-	my ($self, $uri, $intvl) = @_;
-	my $sec = imap_section($uri);
+	my ($self, $url, $intvl) = @_;
+	my $uri = PublicInbox::URIimap->new($url);
+	my $sec = uri_section($uri);
 	my $mic_arg = $self->{mic_arg}->{$sec} or
 			die "BUG: no Mail::IMAPClient->new arg for $sec";
 	my $mic;
 	local $0 = $uri->mailbox." $sec";
 	until ($self->{quit}) {
-		$mic //= delete($self->{mics}->{$sec}) //
-				PublicInbox::IMAPClient->new(%$mic_arg);
-		my $err = imap_fetch_all($self, $mic, $uri);
-		$err //= imap_idle_once($self, $mic, $intvl, $uri->as_string);
+		$mic //= PublicInbox::IMAPClient->new(%$mic_arg);
+		my $err;
+		if ($mic && $mic->IsConnected) {
+			$err = imap_fetch_all($self, $mic, $url);
+			$err //= imap_idle_once($self, $mic, $intvl, $url);
+		} else {
+			$err = "not connected: $!";
+		}
 		if ($err && !$self->{quit}) {
 			warn $err, "\n";
 			$mic = undef;
@@ -486,118 +550,432 @@ sub watch_imap_idle_1 ($$$) {
 	}
 }
 
-sub watch_imap_idle_all ($$) {
-	my ($self, $idle) = @_; # $idle = [[ uri1, intvl1 ], [ uri2, intvl2 ]]
-	$self->{mics} = {}; # going to be forking, so disconnect
-	my $idle_pids = $self->{idle_pids} = {};
-	until ($self->{quit}) {
-		while (my $uri_intvl = shift @$idle) {
-			my ($uri, $intvl) = @$uri_intvl;
-			defined(my $pid = fork) or die "fork: $!";
-			if ($pid == 0) {
-				delete $self->{idle_pids};
-				watch_imap_idle_1($self, $uri, $intvl);
-				_exit(0);
-			}
-			$idle_pids->{$pid} = $uri_intvl;
+sub watch_atfork_child ($) {
+	my ($self) = @_;
+	delete $self->{idle_pids};
+	delete $self->{poll_pids};
+	delete $self->{opendirs};
+	PublicInbox::DS->Reset;
+	%SIG = (%SIG, %{$self->{sig}}, CHLD => 'DEFAULT');
+	PublicInbox::Sigfd::sig_setmask($self->{oldset});
+}
+
+sub watch_atfork_parent ($) {
+	my ($self) = @_;
+	_done_for_now($self);
+}
+
+sub imap_idle_requeue ($) { # DS::add_timer callback
+	my ($self, $url_intvl) = @{$_[0]};
+	return if $self->{quit};
+	push @{$self->{idle_todo}}, $url_intvl;
+	event_step($self);
+}
+
+sub imap_idle_reap { # PublicInbox::DS::dwaitpid callback
+	my ($self, $pid) = @_;
+	my $url_intvl = delete $self->{idle_pids}->{$pid} or
+		die "BUG: PID=$pid (unknown) reaped: \$?=$?\n";
+
+	my ($url, $intvl) = @$url_intvl;
+	return if $self->{quit};
+	warn "W: PID=$pid on $url died: \$?=$?\n" if $?;
+	PublicInbox::DS::add_timer(60,
+				\&imap_idle_requeue, [ $self, $url_intvl ]);
+}
+
+sub imap_idle_fork ($$) {
+	my ($self, $url_intvl) = @_;
+	my ($url, $intvl) = @$url_intvl;
+	defined(my $pid = fork) or die "fork: $!";
+	if ($pid == 0) {
+		watch_atfork_child($self);
+		watch_imap_idle_1($self, $url, $intvl);
+		_exit(0);
+	}
+	$self->{idle_pids}->{$pid} = $url_intvl;
+	PublicInbox::DS::dwaitpid($pid, \&imap_idle_reap, $self);
+}
+
+sub event_step {
+	my ($self) = @_;
+	return if $self->{quit};
+	my $idle_todo = $self->{idle_todo};
+	if ($idle_todo && @$idle_todo) {
+		watch_atfork_parent($self);
+		while (my $url_intvl = shift(@$idle_todo)) {
+			imap_idle_fork($self, $url_intvl);
 		}
-		my $pid = waitpid(-1, 0) or next;
-		if ($pid < 0) {
-			warn "W: no idling children: $!";
-			if (@$idle) {
-				sleep 60;
-			} else {
-				warn "W: nothing to respawn, quitting IDLE\n";
+	}
+	goto(&fs_scan_step) if $self->{mdre};
+}
+
+sub watch_imap_fetch_all ($$) {
+	my ($self, $urls) = @_;
+	for my $url (@$urls) {
+		my $uri = PublicInbox::URIimap->new($url);
+		my $sec = uri_section($uri);
+		my $mic_arg = $self->{mic_arg}->{$sec} or
+			die "BUG: no Mail::IMAPClient->new arg for $sec";
+		my $mic = PublicInbox::IMAPClient->new(%$mic_arg) or next;
+		my $err = imap_fetch_all($self, $mic, $url);
+		last if $self->{quit};
+		warn $err, "\n" if $err;
+	}
+}
+
+sub watch_nntp_fetch_all ($$) {
+	my ($self, $urls) = @_;
+	for my $url (@$urls) {
+		my $uri = uri_new($url);
+		my $sec = uri_section($uri);
+		my $nn_arg = $self->{nn_arg}->{$sec} or
+			die "BUG: no Net::NNTP->new arg for $sec";
+		my $nntp_opt = $self->{nntp_opt}->{$sec};
+		my $nn = nn_new($nn_arg, $nntp_opt, $url);
+		unless ($nn) {
+			warn "E: $url: \$!=$!\n";
+			next;
+		}
+		last if $self->{quit};
+		if (my $postconn = $nntp_opt->{-postconn}) {
+			for my $m_arg (@$postconn) {
+				my ($method, @args) = @$m_arg;
+				$nn->$method(@args) and next;
+				warn "E: <$url> $method failed\n";
+				$nn = undef;
 				last;
 			}
 		}
-		if (my $uri_intvl = delete $idle_pids->{$pid}) {
-			my ($uri, $intvl) = @$uri_intvl;
-			my $url = $uri->as_string;
-			if ($? || !$self->{quit}) {
-				warn "W: PID=$pid on $url died: \$?=$?\n";
-			}
-			push @$idle, $uri_intvl;
-		} else {
-			warn "W: PID=$pid (unknown) reaped: \$?=$?\n";
+		last if $self->{quit};
+		if ($nn) {
+			my $err = nntp_fetch_all($self, $nn, $url);
+			warn $err, "\n" if $err;
 		}
 	}
+}
 
-	# tear it all down
-	kill('QUIT', $_) for (keys %$idle_pids);
-	while (scalar keys %$idle_pids) {
-		if (my $pid = waitpid(-1, WNOHANG)) {
-			if ($pid < 0) {
-				warn "E: no children? $! (PIDs: ",
-					join(', ', keys %$idle_pids),")\n";
-				last;
-			} else {
-				delete $idle_pids->{$pid};
-			}
-		} else { # signals aren't that reliable w/o signalfd/kevent
-			sleep 1;
-			kill('QUIT', $_) for (keys %$idle_pids);
+sub poll_fetch_fork ($) { # DS::add_timer callback
+	my ($self, $intvl, $urls) = @{$_[0]};
+	return if $self->{quit};
+	watch_atfork_parent($self);
+	defined(my $pid = fork) or die "fork: $!";
+	if ($pid == 0) {
+		watch_atfork_child($self);
+		if ($urls->[0] =~ m!\Aimaps?://!i) {
+			watch_imap_fetch_all($self, $urls);
+		} else {
+			watch_nntp_fetch_all($self, $urls);
 		}
+		_exit(0);
 	}
+	$self->{poll_pids}->{$pid} = [ $intvl, $urls ];
+	PublicInbox::DS::dwaitpid($pid, \&poll_fetch_reap, $self);
 }
 
-sub watch_imap ($) {
-	my ($self) = @_;
-	my $idle = []; # [ [ uri1, intvl1 ], [uri2, intvl2] ];
-	my $poll = {}; # intvl_seconds => [ uri1, uri2 ]
+sub poll_fetch_reap { # PublicInbox::DS::dwaitpid callback
+	my ($self, $pid) = @_;
+	my $intvl_urls = delete $self->{poll_pids}->{$pid} or
+		die "BUG: PID=$pid (unknown) reaped: \$?=$?\n";
+	return if $self->{quit};
+	my ($intvl, $urls) = @$intvl_urls;
+	if ($?) {
+		warn "W: PID=$pid died: \$?=$?\n", map { "$_\n" } @$urls;
+	}
+	warn("I: will check $_ in ${intvl}s\n") for @$urls;
+	PublicInbox::DS::add_timer($intvl, \&poll_fetch_fork,
+					[$self, $intvl, $urls]);
+}
+
+sub watch_imap_init ($$) {
+	my ($self, $poll) = @_;
+	eval { require PublicInbox::IMAPClient } or
+		die "Mail::IMAPClient is required for IMAP:\n$@\n";
+	eval { require PublicInbox::IMAPTracker } or
+		die "DBD::SQLite is required for IMAP\n:$@\n";
+
+	my $mic_args = imap_common_init($self); # read args from config
+
+	# make sure we can connect and cache the credentials in memory
+	$self->{mic_arg} = {}; # schema://authority => IMAPClient->new args
+	my $mics = {}; # schema://authority => IMAPClient obj
+	for my $url (sort keys %{$self->{imap}}) {
+		my $uri = PublicInbox::URIimap->new($url);
+		$mics->{uri_section($uri)} //= mic_for($self, $url, $mic_args);
+	}
+
+	my $idle = []; # [ [ url1, intvl1 ], [url2, intvl2] ]
 	for my $url (keys %{$self->{imap}}) {
 		my $uri = PublicInbox::URIimap->new($url);
-		my $sec = imap_section($uri);
-		my $mic = $self->{mics}->{$sec};
-		my $intvl = $self->{imap_opt}->{$sec}->{poll_intvl};
+		my $sec = uri_section($uri);
+		my $mic = $mics->{$sec};
+		my $intvl = $self->{imap_opt}->{$sec}->{pollInterval};
 		if ($mic->has_capability('IDLE') && !$intvl) {
-			$intvl = $self->{imap_opt}->{$sec}->{idle_intvl};
-			push @$idle, [ $uri, $intvl // () ];
+			$intvl = $self->{imap_opt}->{$sec}->{idleInterval};
+			push @$idle, [ $url, $intvl // () ];
 		} else {
-			push @{$poll->{$intvl || 120}}, $uri;
+			push @{$poll->{$intvl || 120}}, $url;
 		}
 	}
-	my $nr_poll = scalar keys %$poll;
-	if (scalar @$idle && !$nr_poll) { # multiple idlers, need fork
-		watch_imap_idle_all($self, $idle);
+	if (scalar @$idle) {
+		$self->{idle_todo} = $idle;
+		PublicInbox::DS::requeue($self); # ->event_step to fork
 	}
-	# TODO: polling
 }
 
-sub watch {
+# flesh out common NNTP-specific data structures
+sub nntp_common_init ($) {
 	my ($self) = @_;
-	if ($self->{mdre} && $self->{imap}) {
-		defined(my $pid = fork) or die "fork: $!";
-		if ($pid == 0) {
-			imap_start($self);
-			goto &watch_imap;
+	my $cfg = $self->{config};
+	my $nn_args = {}; # scheme://authority => Net::NNTP->new arg
+	for my $url (sort keys %{$self->{nntp}}) {
+		my $sec = uri_section(uri_new($url));
+
+		# Debug and Timeout are passed to Net::NNTP->new
+		my $v = cfg_bool($cfg, 'nntp.Debug', $url);
+		$nn_args->{$sec}->{Debug} = $v if defined $v;
+		my $to = cfg_intvl($cfg, 'nntp.Timeout', $url);
+		$nn_args->{$sec}->{Timeout} = $to if $to;
+
+		# Net::NNTP post-connect commands
+		for my $k (qw(starttls compress)) {
+			$v = cfg_bool($cfg, "nntp.$k", $url) // next;
+			$self->{nntp_opt}->{$sec}->{$k} = $v;
+		}
+
+		# internal option
+		for my $k (qw(pollInterval)) {
+			$to = cfg_intvl($cfg, "nntp.$k", $url) // next;
+			$self->{nntp_opt}->{$sec}->{$k} = $to;
 		}
-		$self->{-imap_pid} = $pid;
-	} elsif ($self->{imap}) {
-		imap_start($self);
-		goto &watch_imap;
 	}
-	goto &watch_fs;
+	$nn_args;
 }
 
-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: $!\n";
+# Net::NNTP doesn't support CAPABILITIES, yet
+sub try_starttls ($) {
+	my ($host) = @_;
+	return if $host =~ /\.onion\z/s;
+	return if $host =~ /\A127\.[0-9]+\.[0-9]+\.[0-9]+\z/s;
+	return if $host eq '::1';
+	1;
 }
 
-sub scan {
-	my ($self, $path) = @_;
-	if ($path =~ /quit\z/) {
-		%{$self->{opendirs}} = ();
-		_done_for_now($self);
-		delete $self->{scandir};
-		$self->{quit} = 1;
-		return;
+sub nn_new ($$$) {
+	my ($nn_arg, $nntp_opt, $url) = @_;
+	my $nn = Net::NNTP->new(%$nn_arg) or die "E: <$url> new: $!\n";
+
+	# default to using STARTTLS if it's available, but allow
+	# it to be disabled for localhost/VPN users
+	if (!$nn_arg->{SSL} && $nn->can('starttls')) {
+		if (!defined($nntp_opt->{starttls}) &&
+				try_starttls($nn_arg->{Host})) {
+			# soft fail by default
+			$nn->starttls or warn <<"";
+W: <$url> STARTTLS tried and failed (not requested)
+
+		} elsif ($nntp_opt->{starttls}) {
+			# hard fail if explicitly configured
+			$nn->starttls or die <<"";
+E: <$url> STARTTLS requested and failed
+
+		}
+	} elsif ($nntp_opt->{starttls}) {
+		$nn->can('starttls') or
+			die "E: <$url> Net::NNTP too old for STARTTLS\n";
+		$nn->starttls or die <<"";
+E: <$url> STARTTLS requested and failed
+
 	}
-	# else: $path =~ /(cont|full)\z/
+	$nn;
+}
+
+sub nn_for ($$$) { # nn = Net::NNTP
+	my ($self, $url, $nn_args) = @_;
+	my $uri = uri_new($url);
+	my $sec = uri_section($uri);
+	my $nntp_opt = $self->{nntp_opt}->{$sec} //= {};
+	my $host = $uri->host;
+	# Net::NNTP and Net::Netrc both mishandle `0', so we pass `127.0.0.1'
+	$host = '127.0.0.1' if $host eq '0';
+	my $cred;
+	my ($u, $p);
+	if (defined(my $ui = $uri->userinfo)) {
+		require PublicInbox::GitCredential;
+		$cred = bless {
+			url => $sec,
+			protocol => uri_scheme($uri),
+			host => $host,
+		}, 'PublicInbox::GitCredential';
+		($u, $p) = split(/:/, $ui, 2);
+		($cred->{username}, $cred->{password}) = ($u, $p);
+		$cred->check_netrc unless defined $p;
+	}
+	my $common = $nn_args->{$sec} // {};
+	my $nn_arg = {
+		Port => $uri->port,
+		Host => $host,
+		SSL => $uri->secure, # snews == nntps
+		%$common, # may Debug ....
+	};
+	my $nn = nn_new($nn_arg, $nntp_opt, $url);
+
+	if ($cred) {
+		$cred->fill; # may prompt user here
+		if ($nn->authinfo($u, $p)) {
+			push @{$nntp_opt->{-postconn}}, [ 'authinfo', $u, $p ];
+		} else {
+			warn "E: <$url> AUTHINFO $u XXXX failed\n";
+			$nn = undef;
+		}
+	}
+
+	if ($nntp_opt->{compress}) {
+		# https://rt.cpan.org/Ticket/Display.html?id=129967
+		if ($nn->can('compress')) {
+			if ($nn->compress) {
+				push @{$nntp_opt->{-postconn}}, [ 'compress' ];
+			} else {
+				warn "W: <$url> COMPRESS failed\n";
+			}
+		} else {
+			delete $nntp_opt->{compress};
+			warn <<"";
+W: <$url> COMPRESS not supported by Net::NNTP
+W: see https://rt.cpan.org/Ticket/Display.html?id=129967 for updates
+
+		}
+	}
+
+	$self->{nn_arg}->{$sec} = $nn_arg;
+	$cred->run($nn ? 'approve' : 'reject') if $cred;
+	$nn;
+}
+
+sub nntp_fetch_all ($$$) {
+	my ($self, $nn, $url) = @_;
+	my $uri = uri_new($url);
+	my ($group, $num_a, $num_b) = $uri->group;
+	my $sec = uri_section($uri);
+	my ($nr, $beg, $end) = $nn->group($group);
+	unless (defined($nr)) {
+		chomp(my $msg = $nn->message);
+		return "E: GROUP $group <$sec> $msg";
+	}
+
+	# IMAPTracker is also used for tracking NNTP, UID == article number
+	# LIST.ACTIVE can get the equivalent of UIDVALIDITY, but that's
+	# expensive.  So we assume newsgroups don't change:
+	my $itrk = PublicInbox::IMAPTracker->new($url);
+	my (undef, $l_art) = $itrk->get_last;
+	$l_art //= $beg; # initial import
+
+	# allow users to specify articles to refetch
+	# cf. https://tools.ietf.org/id/draft-gilman-news-url-01.txt
+	# nntp://example.com/inbox.foo/$num_a-$num_b
+	$l_art = $num_a if defined($num_a) && $num_a < $l_art;
+	$end = $num_b if defined($num_b) && $num_b < $end;
+
+	return if $l_art >= $end; # nothing to do
+	$beg = $l_art + 1;
+
+	warn "I: $url fetching ARTICLE $beg..$end\n";
+	my $warn_cb = $SIG{__WARN__} || sub { print STDERR @_ };
+	my ($err, $art);
+	local $SIG{__WARN__} = sub {
+		my $pfx = ($_[0] // '') =~ /^([A-Z]: )/g ? $1 : '';
+		$warn_cb->("$pfx$url ", $art ? ("ARTICLE $art") : (), "\n", @_);
+	};
+	my $inboxes = $self->{nntp}->{$url};
+	my $last_art;
+	for ($beg..$end) {
+		last if $self->{quit};
+		$art = $_;
+		my $raw = $nn->article($art);
+		unless (defined($raw)) {
+			my $msg = $nn->message;
+			if ($nn->code == 421) { # pseudo response from Net::Cmd
+				$err = "E: $msg";
+				last;
+			} else { # probably just a deleted message (spam)
+				warn "W: $msg";
+				next;
+			}
+		}
+		s/\r\n/\n/ for @$raw;
+		$raw = join('', @$raw);
+		if (ref($inboxes)) {
+			for my $ibx (@$inboxes) {
+				my $eml = PublicInbox::Eml->new($raw);
+				import_eml($self, $ibx, $eml);
+			}
+		} elsif ($inboxes eq 'watchspam') {
+			my $eml = PublicInbox::Eml->new(\$raw);
+			my $arg = [ $self, $eml, "$url ARTICLE $art" ];
+			$self->{config}->each_inbox(\&remove_eml_i, $arg);
+		} else {
+			die "BUG: destination unknown $inboxes";
+		}
+		$last_art = $art;
+	}
+	_done_for_now($self);
+	$itrk->update_last(0, $last_art) if defined $last_art;
+	$err;
+}
+
+sub watch_nntp_init ($$) {
+	my ($self, $poll) = @_;
+	eval { require Net::NNTP } or
+		die "Net::NNTP is required for NNTP:\n$@\n";
+	eval { require PublicInbox::IMAPTracker } or
+		die "DBD::SQLite is required for NNTP\n:$@\n";
+
+	my $nn_args = nntp_common_init($self); # read args from config
+
+	# make sure we can connect and cache the credentials in memory
+	$self->{nn_arg} = {}; # schema://authority => Net::NNTP->new args
+	for my $url (sort keys %{$self->{nntp}}) {
+		nn_for($self, $url, $nn_args);
+	}
+	for my $url (keys %{$self->{nntp}}) {
+		my $uri = uri_new($url);
+		my $sec = uri_section($uri);
+		my $intvl = $self->{nntp_opt}->{$sec}->{pollInterval};
+		push @{$poll->{$intvl || 120}}, $url;
+	}
+}
+
+sub watch {
+	my ($self, $sig, $oldset) = @_;
+	$self->{oldset} = $oldset;
+	$self->{sig} = $sig;
+	my $poll = {}; # intvl_seconds => [ url1, url2 ]
+	watch_imap_init($self, $poll) if $self->{imap};
+	watch_nntp_init($self, $poll) if $self->{nntp};
+	while (my ($intvl, $urls) = each %$poll) {
+		# poll all URLs for a given interval sequentially
+		PublicInbox::DS::add_timer(0, \&poll_fetch_fork,
+						[$self, $intvl, $urls]);
+	}
+	watch_fs_init($self) if $self->{mdre};
+	PublicInbox::DS->SetPostLoopCallback(sub { !$self->quit_done });
+	PublicInbox::DS->EventLoop;
+	_done_for_now($self);
+}
+
+sub trigger_scan {
+	my ($self, $op) = @_;
+	push @{$self->{ops}}, $op;
+	PublicInbox::DS::requeue($self);
+}
+
+sub fs_scan_step {
+	my ($self) = @_;
 	return if $self->{quit};
+	my $op = shift @{$self->{ops}};
+	local $PublicInbox::DS::in_loop = 0; # waitpid() synchronously
+
+	# continue existing scan
 	my $max = 10;
 	my $opendirs = $self->{opendirs};
 	my @dirnames = keys %$opendirs;
@@ -610,8 +988,8 @@ sub scan {
 		}
 		$opendirs->{$dir} = $dh if $n < 0;
 	}
-	if ($path =~ /full\z/) {
-		foreach my $dir (@{$self->{mdir}}) {
+	if ($op && $op eq 'full') {
+		foreach my $dir (keys %{$self->{mdmap}}) {
 			next if $opendirs->{$dir}; # already in progress
 			my $ok = opendir(my $dh, $dir);
 			unless ($ok) {
@@ -628,7 +1006,13 @@ sub scan {
 	}
 	_done_for_now($self);
 	# do we have more work to do?
-	trigger_scan($self, 'cont') if keys %$opendirs;
+	PublicInbox::DS::requeue($self) if keys %$opendirs;
+}
+
+sub scan {
+	my ($self, $op) = @_;
+	push @{$self->{ops}}, $op;
+	goto &fs_scan_step;
 }
 
 sub _importer_for {
@@ -643,10 +1027,27 @@ sub _importer_for {
 	$importers->{"$ibx"} = $im;
 }
 
+# XXX consider sharing with V2Writable, this only requires read-only access
+sub content_exists ($$) {
+	my ($ibx, $eml) = @_;
+	my $over = $ibx->over or return;
+	my $mids = mids($eml);
+	my $chash = content_hash($eml);
+	my ($id, $prev);
+	for my $mid (@$mids) {
+		while (my $smsg = $over->next_by_mid($mid, \$id, \$prev)) {
+			my $cmp = $ibx->smsg_eml($smsg) or return;
+			return 1 if $chash eq content_hash($cmp);
+		}
+	}
+	undef;
+}
+
 sub _spamcheck_cb {
 	my ($sc) = @_;
 	sub {
-		my ($mime) = @_;
+		my ($mime, $ibx) = @_;
+		return if content_exists($ibx, $mime);
 		my $tmp = '';
 		if ($sc->spamcheck($mime, \$tmp)) {
 			return PublicInbox::Eml->new(\$tmp);
@@ -674,6 +1075,14 @@ EOF
 	undef;
 }
 
+sub uri_new {
+	my ($url) = @_;
+
+	# URI::snews exists, URI::nntps does not, so use URI::snews
+	$url =~ s!\Anntps://!snews://!i;
+	URI->new($url);
+}
+
 sub imap_url {
 	my ($url) = @_;
 	require PublicInbox::URIimap;
@@ -681,4 +1090,16 @@ sub imap_url {
 	$uri ? $uri->canonical->as_string : undef;
 }
 
+my %IS_NNTP = (news => 1, snews => 1, nntp => 1);
+sub nntp_url {
+	my ($url) = @_;
+	require URI;
+	my $uri = uri_new($url);
+	return unless $uri && $IS_NNTP{$uri->scheme} && $uri->group;
+	$url = $uri->canonical->as_string;
+	# nntps is IANA registered, snews is deprecated
+	$url =~ s!\Asnews://!nntps://!;
+	$url;
+}
+
 1;