use strict;
use warnings;
use PublicInbox::Eml;
-use PublicInbox::InboxWritable;
+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 PublicInbox::MID qw(mids);
+use PublicInbox::ContentHash qw(content_hash);
use POSIX qw(_exit);
-*mime_from_path = \&PublicInbox::InboxWritable::mime_from_path;
sub compile_watchheaders ($) {
my ($ibx) = @_;
return unless $mdre || scalar(keys %imap) || scalar(keys %nntp);
bless {
+ max_batch => 10, # avoid hogging locks for too long
spamcheck => $spamcheck,
mdmap => \%mdmap,
mdre => $mdre,
sub _done_for_now {
my ($self) = @_;
- my $importers = $self->{importers};
- foreach my $im (values %$importers) {
- $im->done;
+ 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 $@;
}
}
$im->remove($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 {
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_done ($) {
+ my ($self) = @_;
+ 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);
- if (my $imap_pid = $self->{-imap_pid}) {
- kill('QUIT', $imap_pid);
- }
- for (qw(idle_pids poll_pids)) {
- my $pids = $self->{$_} or next;
- kill('QUIT', $_) for (keys %$pids);
- }
+ quit_done($self);
if (my $idle_mic = $self->{idle_mic}) {
eval { $idle_mic->done };
if ($@) {
sub cfg_bool ($$$) {
my ($cfg, $key, $url) = @_;
my $orig = $cfg->urlmatch($key, $url) // return;
- my $bool = PublicInbox::Config::_git_config_bool($orig);
+ my $bool = $cfg->git_bool($orig);
warn "W: $key=$orig for $url is not boolean\n" unless defined($bool);
$bool;
}
password => $uri->password,
}, '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 ....
$cred = undef;
}
if ($cred) {
+ $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});
$mic;
}
-sub imap_import_msg ($$$$) {
- my ($self, $url, $uid, $raw) = @_;
+sub imap_import_msg ($$$$$) {
+ my ($self, $url, $uid, $raw, $flags) = @_;
# our target audience expects LF-only, save storage
$$raw =~ s/\r\n/\n/sg;
my $x = import_eml($self, $ibx, $eml);
}
} elsif ($inboxes eq 'watchspam') {
- my $eml = PublicInbox::Eml->new($raw);
- my $arg = [ $self, $eml, "$url UID:$uid" ];
- $self->{config}->each_inbox(\&remove_eml_i, $arg);
+ # we don't remove unseen messages
+ if ($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 $inboxes";
}
my ($uids, $batch);
my $warn_cb = $SIG{__WARN__} || sub { print STDERR @_ };
local $SIG{__WARN__} = sub {
+ my $pfx = ($_[0] // '') =~ /^([A-Z]: )/g ? $1 : '';
$batch //= '?';
- $warn_cb->("$url UID:$batch\n");
- $warn_cb->(@_);
+ $warn_cb->("$pfx$url UID:$batch\n", @_);
};
my $err;
do {
$l_uid = $uids->[-1] + 1; # for next search
my $last_uid;
+ my $n = $self->{max_batch};
while (scalar @$uids) {
+ if (--$n < 0) {
+ _done_for_now($self);
+ $itrk->update_last($r_uidval, $last_uid);
+ $n = $self->{max_batch};
+ }
my @batch = splice(@$uids, 0, $bs);
$batch = join(',', @batch);
local $0 = "UID:$batch $mbx $sec";
- my $r = $mic->fetch_hash($batch, $req);
+ my $r = $mic->fetch_hash($batch, $req, 'FLAGS');
unless ($r) { # network error?
$err = "E: $url UID FETCH $batch error: $!";
last;
# messages get deleted, so holes appear
my $per_uid = delete $r->{$uid} // next;
my $raw = delete($per_uid->{$key}) // next;
- imap_import_msg($self, $url, $uid, \$raw);
+ my $fl = $per_uid->{FLAGS} // '';
+ imap_import_msg($self, $url, $uid, \$raw, $fl);
$last_uid = $uid;
last if $self->{quit};
}
last if $self->{quit};
}
_done_for_now($self);
- $itrk->update_last($r_uidval, $last_uid) if defined $last_uid;
+ $itrk->update_last($r_uidval, $last_uid);
} until ($err || $self->{quit});
$err;
}
}
$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();
}
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, $url);
- $err //= imap_idle_once($self, $mic, $intvl, $url);
+ $mic //= PublicInbox::IMAPClient->new(%$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;
delete $self->{poll_pids};
delete $self->{opendirs};
PublicInbox::DS->Reset;
+ %SIG = (%SIG, %{$self->{sig}}, CHLD => 'DEFAULT');
PublicInbox::Sigfd::sig_setmask($self->{oldset});
- %SIG = (%SIG, %{$self->{sig}});
}
sub watch_atfork_parent ($) {
my ($self) = @_;
_done_for_now($self);
- $self->{mics} = {}; # going to be forking, so disconnect
+}
+
+sub imap_idle_requeue ($) { # 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 ($url, $intvl) = @$url_intvl;
return if $self->{quit};
warn "W: PID=$pid on $url died: \$?=$?\n" if $?;
- push @{$self->{idle_todo}}, $url_intvl;
- PubicInbox::DS::requeue($self); # call ->event_step to respawn
+ PublicInbox::DS::add_timer(60,
+ \&imap_idle_requeue, [ $self, $url_intvl ]);
}
sub imap_idle_fork ($$) {
[$self, $intvl, $urls]);
}
-sub watch_imap_init ($) {
- my ($self) = @_;
+sub watch_imap_init ($$) {
+ my ($self, $poll) = @_;
eval { require PublicInbox::IMAPClient } or
die "Mail::IMAPClient is required for IMAP:\n$@\n";
eval { require PublicInbox::IMAPTracker } or
# 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
+ 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] ]
- my $poll = {}; # intvl_seconds => [ url1, url2 ]
for my $url (keys %{$self->{imap}}) {
my $uri = PublicInbox::URIimap->new($url);
my $sec = uri_section($uri);
}
}
if (scalar @$idle) {
- $self->{idle_pids} = {};
$self->{idle_todo} = $idle;
PublicInbox::DS::requeue($self); # ->event_step to fork
}
- return unless scalar keys %$poll;
- $self->{poll_pids} //= {};
-
- # poll all URLs for a given interval sequentially
- while (my ($intvl, $urls) = each %$poll) {
- PublicInbox::DS::add_timer(0, \&poll_fetch_fork,
- [$self, $intvl, $urls]);
- }
}
# flesh out common NNTP-specific data structures
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)) {
$cred = bless {
url => $sec,
protocol => uri_scheme($uri),
- host => $uri->host,
+ 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,
- # Net::NNTP mishandles `0', so we pass `127.0.0.1'
- Host => $uri->host eq '0' ? '127.0.0.1' : $uri->host,
+ Host => $host,
SSL => $uri->secure, # snews == nntps
%$common, # may Debug ....
};
my $warn_cb = $SIG{__WARN__} || sub { print STDERR @_ };
my ($err, $art);
local $SIG{__WARN__} = sub {
- $warn_cb->("$url ", $art ? ("ARTICLE $art") : (), "\n", @_);
+ my $pfx = ($_[0] // '') =~ /^([A-Z]: )/g ? $1 : '';
+ $warn_cb->("$pfx$url ", $art ? ("ARTICLE $art") : (), "\n", @_);
};
my $inboxes = $self->{nntp}->{$url};
my $last_art;
+ my $n = $self->{max_batch};
for ($beg..$end) {
last if $self->{quit};
$art = $_;
+ if (--$n < 0) {
+ _done_for_now($self);
+ $itrk->update_last(0, $last_art);
+ $n = $self->{max_batch};
+ }
my $raw = $nn->article($art);
unless (defined($raw)) {
my $msg = $nn->message;
}
$last_art = $art;
}
- $itrk->update_last(0, $last_art) if defined $last_art;
_done_for_now($self);
+ $itrk->update_last(0, $last_art);
$err;
}
-sub watch_nntp_init ($) {
- my ($self) = @_;
+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
for my $url (sort keys %{$self->{nntp}}) {
nn_for($self, $url, $nn_args);
}
- my $poll = {}; # intvl_seconds => [ url1, url2 ]
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;
}
- $self->{poll_pids} //= {};
-
- # poll all URLs for a given interval sequentially
- while (my ($intvl, $urls) = each %$poll) {
- PublicInbox::DS::add_timer(0, \&poll_fetch_fork,
- [$self, $intvl, $urls]);
- }
}
sub watch {
my ($self, $sig, $oldset) = @_;
$self->{oldset} = $oldset;
$self->{sig} = $sig;
- watch_imap_init($self) if $self->{imap};
- watch_nntp_init($self) if $self->{nntp};
+ 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 {});
- PublicInbox::DS->EventLoop until $self->{quit};
+ PublicInbox::DS->SetPostLoopCallback(sub { !$self->quit_done });
+ PublicInbox::DS->EventLoop;
_done_for_now($self);
}
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;
foreach my $dir (@dirnames) {
my $dh = delete $opendirs->{$dir};
- my $n = $max;
+ my $n = $self->{max_batch};
while (my $fn = readdir($dh)) {
_try_path($self, "$dir/$fn");
last if --$n < 0;
warn "failed to open $dir: $!\n";
next;
}
- my $n = $max;
+ my $n = $self->{max_batch};
while (my $fn = readdir($dh)) {
_try_path($self, "$dir/$fn");
last if --$n < 0;
$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);