use warnings;
use PublicInbox::Eml;
use PublicInbox::InboxWritable;
-use File::Temp 0.19 (); # 0.19 for ->newdir
use PublicInbox::Filter::Base qw(REJECT);
use PublicInbox::Spamcheck;
+use PublicInbox::Sigfd;
use PublicInbox::DS qw(now);
-use POSIX qw(_exit WNOHANG);
+use POSIX qw(_exit);
*mime_from_path = \&PublicInbox::InboxWritable::mime_from_path;
sub compile_watchheaders ($) {
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) {
if (is_maildir($dir)) {
# skip "new", no MUA has seen it, yet.
# 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) {
+ 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 @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)) {
+ return if is_watchspam($url, $imap{$url}, $ibx);
+ compile_watchheaders($ibx);
+ push @{$imap{$url} ||= []}, $ibx;
+ } else {
+ warn "watch unsupported: $k=$watch\n";
+ }
}
});
return unless scalar(@mdir) || scalar(keys %imap);
imap => scalar keys %imap ? \%imap : undef,
importers => {},
opendirs => {}, # dirname => dirhandle (in progress scans)
+ ops => [], # 'quit', 'full'
}, $class;
}
}
}
-sub _try_fsn_paths {
- my ($self, $scan_re, $paths) = @_;
- foreach (@$paths) {
- my $path = $_->{path};
- if ($path =~ $scan_re) {
- scan($self, $path);
- } else {
- _try_path($self, $path);
- }
- }
- _done_for_now($self);
-}
-
sub remove_eml_i { # each_inbox callback
my ($ibx, $arg) = @_;
my ($self, $eml, $loc) = @$arg;
sub quit {
my ($self) = @_;
- trigger_scan($self, 'quit') or $self->{quit} = 1;
+ $self->{quit} = 1;
+ %{$self->{opendirs}} = ();
+ _done_for_now($self);
if (my $imap_pid = $self->{-imap_pid}) {
kill('QUIT', $imap_pid);
}
- if (my $idle_pids = $self->{idle_pids}) {
- kill('QUIT', $_) for (keys %$idle_pids);
+ for (qw(idle_pids poll_pids)) {
+ my $pids = $self->{$_} or next;
+ kill('QUIT', $_) for (keys %$pids);
}
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.$$.scan.XXXXXX",
- TMPDIR => 1);
- my $scandir = $self->{scandir} = $scan->dirname;
- my $re = qr!\A$scandir/!;
- my $cb = sub { _try_fsn_paths($self, $re, \@_) };
-
- eval { require Filesys::Notify::Simple } or
- die "Filesys::Notify::Simple is currently required for $0\n";
- my $fsn = Filesys::Notify::Simple->new([@{$self->{mdir}}, $scandir]);
- $fsn->wait($cb) until $self->{quit};
+ my $done = sub {
+ delete $self->{done_timer};
+ _done_for_now($self);
+ };
+ my $cb = sub {
+ _try_path($self, $_[0]->fullname);
+ $self->{done_timer} //= PublicInbox::DS::requeue($done);
+ };
+ require PublicInbox::DirIdle;
+ PublicInbox::DirIdle->new($self->{mdir}, $cb); # EPOLL_CTL_ADD
}
# returns the git config section name, e.g [imap "imaps://user@example.com"]
$uri->scheme . '://' . $uri->authority;
}
-sub cfg_intvl ($$) {
- my ($cfg, $key) = @_;
- defined(my $v = $cfg->{lc($key)}) or return;
- $v =~ /\A[0-9]+\z/s and return $v + 0;
+sub cfg_intvl ($$$$$) {
+ my ($cfg, $cfg_section, $cfg_key, $imap_section, $url) = @_;
+ my $key = "$cfg_section.$imap_section.$cfg_key";
+ my $v = $cfg->{lc($key)} //
+ $cfg->urlmatch("$cfg_section.$cfg_key", $url) // return;
+ $v =~ /\A[0-9]+(?:\.[0-9]+)?\z/s and return $v + 0;
if (ref($v) eq 'ARRAY') {
$v = join(', ', @$v);
warn "W: $key has multiple values: $v\nW: $key ignored\n";
} else {
- warn "W: $key=$v is not an integer value in seconds\n";
+ warn "W: $key=$v is not a numeric value in seconds\n";
}
}
my $sec = imap_section($uri);
for my $k (qw(Starttls Debug Compress)) {
my $key = lc("imap.$sec.$k");
- defined(my $orig = $cfg->{$key}) or next;
+ my $orig = $cfg->{$key} //
+ $cfg->urlmatch("imap.$k", $url) // next;
my $v = PublicInbox::Config::_git_config_bool($orig);
if (defined($v)) {
$mic_args->{$sec}->{$k} = $v;
warn "W: $key=$orig is not boolean\n";
}
}
- my $to = cfg_intvl($cfg, "imap.$sec.Timeout");
+ my $to = cfg_intvl($cfg, 'imap', 'Timeout', $sec, $url);
$mic_args->{$sec}->{Timeout} = $to if $to;
- $to = cfg_intvl($cfg, "imap.$sec.PollInterval");
+ $to = cfg_intvl($cfg, 'imap', 'PollInterval', $sec, $url);
$self->{imap_opt}->{$sec}->{poll_intvl} = $to if $to;
- $to = cfg_intvl($cfg, "imap.$sec.IdleInterval");
+ $to = cfg_intvl($cfg, 'imap', 'IdleInterval', $sec, $url);
$self->{imap_opt}->{$sec}->{idle_intvl} = $to if $to;
+
+ my $key = lc("imap.$sec.fetchBatchSize");
+ my $bs = $cfg->{lc($key)} //
+ $cfg->urlmatch('imap.fetchBatchSize', $url) // next;
+ if ($bs =~ /\A([0-9]+)\z/) {
+ $self->{imap_opt}->{$sec}->{batch_size} = $bs;
+ } else {
+ warn "W: $key=$bs is not an integer\n";
+ }
}
$mic_args;
}
$mic;
}
-sub imap_start ($) {
- my ($self) = @_;
- eval { require PublicInbox::IMAPClient } or
- die "Mail::IMAPClient is required for IMAP:\n$@\n";
- eval { require Git } or
- die "Git (Perl module) is required for IMAP:\n$@\n";
- eval { require PublicInbox::IMAPTracker } or
- die "DBD::SQLite is required for IMAP\n:$@\n";
+sub imap_import_msg ($$$$) {
+ my ($self, $url, $uid, $raw) = @_;
+ # our target audience expects LF-only, save storage
+ $$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') {
+ 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";
}
}
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) {
}
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");
+ $batch //= '?';
+ $warn_cb->("$url UID:$batch\n");
$warn_cb->(@_);
};
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;
- }
-
- # messages get deleted, so holes appear
- defined(my $raw = delete $r->{$uid}->{$key}) or next;
-
- # our target audience expects LF-only, save storage
- $raw =~ s/\r\n/\n/sg;
-
- if (ref($inboxes)) {
- for my $ibx (@$inboxes) {
- my $eml = PublicInbox::Eml->new($raw);
- my $x = import_eml($self, $ibx, $eml);
+ 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;
+
+ # 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;
+
+ # Did we actually get new messages?
+ return if $uids->[0] < $l_uid;
+
+ $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);
+ 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;
+ imap_import_msg($self, $url, $uid, \$raw);
+ $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;
}
}
}
-sub watch_imap_idle_all ($$) {
- my ($self, $idle) = @_; # $idle = [[ uri1, intvl1 ], [ uri2, intvl2 ]]
+sub watch_atfork_child ($) {
+ my ($self) = @_;
+ delete $self->{idle_pids};
+ delete $self->{poll_pids};
+ delete $self->{opendirs};
+ PublicInbox::DS->Reset;
+ PublicInbox::Sigfd::sig_setmask($self->{oldset});
+ %SIG = (%SIG, %{$self->{sig}});
+}
+
+sub watch_atfork_parent ($) {
+ my ($self) = @_;
+ _done_for_now($self);
$self->{mics} = {}; # going to be forking, so disconnect
- 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;
- }
- 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";
- 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: \$?=$?\n";
+}
+
+sub imap_idle_reap { # PublicInbox::DS::dwaitpid callback
+ my ($self, $pid) = @_;
+ my $uri_intvl = delete $self->{idle_pids}->{$pid} or
+ die "BUG: PID=$pid (unknown) reaped: \$?=$?\n";
+
+ my ($uri, $intvl) = @$uri_intvl;
+ my $url = $uri->as_string;
+ return if $self->{quit};
+ warn "W: PID=$pid on $url died: \$?=$?\n" if $?;
+ push @{$self->{idle_todo}}, $uri_intvl;
+ PubicInbox::DS::requeue($self); # call ->event_step to respawn
+}
+
+sub imap_idle_fork ($$) {
+ my ($self, $uri_intvl) = @_;
+ my ($uri, $intvl) = @$uri_intvl;
+ defined(my $pid = fork) or die "fork: $!";
+ if ($pid == 0) {
+ watch_atfork_child($self);
+ watch_imap_idle_1($self, $uri, $intvl);
+ _exit(0);
+ }
+ $self->{idle_pids}->{$pid} = $uri_intvl;
+ PublicInbox::DS::dwaitpid($pid, \&imap_idle_reap, $self);
+}
+
+sub event_step {
+ my ($self) = @_;
+ return if $self->{quit};
+ my $idle_todo = $self->{idle_todo};
+ if ($idle_todo && @$idle_todo) {
+ watch_atfork_parent($self);
+ while (my $uri_intvl = shift(@$idle_todo)) {
+ imap_idle_fork($self, $uri_intvl);
}
}
+ goto(&fs_scan_step) if $self->{mdre};
+}
- # tear it all down
- kill('QUIT', $_) for (keys %$idle_pids);
- while (scalar keys %$idle_pids) {
- if (my $pid = waitpid(-1, WNOHANG)) {
- if ($pid < 0) {
- warn "E: no children? $! (PIDs: ",
- join(', ', keys %$idle_pids),")\n";
- last;
- } else {
- delete $idle_pids->{$pid};
- }
- } else { # signals aren't that reliable w/o signalfd/kevent
- sleep 1;
- kill('QUIT', $_) for (keys %$idle_pids);
- }
+sub watch_imap_fetch_all ($$) {
+ my ($self, $uris) = @_;
+ for my $uri (@$uris) {
+ my $sec = imap_section($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, $uri);
+ last if $self->{quit};
+ warn $err, "\n" if $err;
}
}
-sub watch_imap ($) {
+sub imap_fetch_fork ($) { # DS::add_timer callback
+ my ($self, $intvl, $uris) = @{$_[0]};
+ return if $self->{quit};
+ watch_atfork_parent($self);
+ defined(my $pid = fork) or die "fork: $!";
+ if ($pid == 0) {
+ watch_atfork_child($self);
+ watch_imap_fetch_all($self, $uris);
+ _exit(0);
+ }
+ $self->{poll_pids}->{$pid} = [ $intvl, $uris ];
+ PublicInbox::DS::dwaitpid($pid, \&imap_fetch_reap, $self);
+}
+
+sub imap_fetch_reap { # PublicInbox::DS::dwaitpid callback
+ my ($self, $pid) = @_;
+ my $intvl_uris = delete $self->{poll_pids}->{$pid} or
+ die "BUG: PID=$pid (unknown) reaped: \$?=$?\n";
+ return if $self->{quit};
+ my ($intvl, $uris) = @$intvl_uris;
+ if ($?) {
+ warn "W: PID=$pid died: \$?=$?\n",
+ map { $_->as_string."\n" } @$uris;
+ }
+ warn('I: will check ', $_->as_string, " in ${intvl}s\n") for @$uris;
+ PublicInbox::DS::add_timer($intvl, \&imap_fetch_fork,
+ [$self, $intvl, $uris]);
+}
+
+sub watch_imap_init ($) {
my ($self) = @_;
- my $idle = []; # [ [ uri1, intvl1 ], [uri2, intvl2] ];
+ eval { require PublicInbox::IMAPClient } or
+ die "Mail::IMAPClient is required for IMAP:\n$@\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";
+
+ 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 = $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 $idle = []; # [ [ uri1, intvl1 ], [uri2, intvl2] ]
my $poll = {}; # intvl_seconds => [ uri1, uri2 ]
for my $url (keys %{$self->{imap}}) {
my $uri = PublicInbox::URIimap->new($url);
my $sec = imap_section($uri);
- my $mic = $self->{mics}->{$sec};
+ my $mic = $mics->{$sec};
my $intvl = $self->{imap_opt}->{$sec}->{poll_intvl};
if ($mic->has_capability('IDLE') && !$intvl) {
$intvl = $self->{imap_opt}->{$sec}->{idle_intvl};
push @{$poll->{$intvl || 120}}, $uri;
}
}
- 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_pids} = {};
+ $self->{idle_todo} = $idle;
+ PublicInbox::DS::requeue($self); # ->event_step to fork
+ }
+ return unless scalar keys %$poll;
+ $self->{poll_pids} = {};
+
+ # poll all URIs for a given interval sequentially
+ while (my ($intvl, $uris) = each %$poll) {
+ PublicInbox::DS::add_timer(0, \&imap_fetch_fork,
+ [$self, $intvl, $uris]);
}
- # TODO: polling
}
sub watch {
- my ($self) = @_;
- if ($self->{mdre} && $self->{imap}) {
- defined(my $pid = fork) or die "fork: $!";
- if ($pid == 0) {
- imap_start($self);
- goto &watch_imap;
- }
- $self->{-imap_pid} = $pid;
- } elsif ($self->{imap}) {
- imap_start($self);
- goto &watch_imap;
- }
- goto &watch_fs;
+ my ($self, $sig, $oldset) = @_;
+ $self->{oldset} = $oldset;
+ $self->{sig} = $sig;
+ watch_imap_init($self) if $self->{imap};
+ watch_fs_init($self) if $self->{mdre};
+ PublicInbox::DS->SetPostLoopCallback(sub {});
+ PublicInbox::DS->EventLoop until $self->{quit};
+ _done_for_now($self);
}
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: $!\n";
+ my ($self, $op) = @_;
+ push @{$self->{ops}}, $op;
+ PublicInbox::DS::requeue($self);
}
-sub scan {
- my ($self, $path) = @_;
- if ($path =~ /quit\z/) {
- %{$self->{opendirs}} = ();
- _done_for_now($self);
- delete $self->{scandir};
- $self->{quit} = 1;
- return;
- }
- # else: $path =~ /(cont|full)\z/
+sub fs_scan_step {
+ my ($self) = @_;
return if $self->{quit};
+ my $op = shift @{$self->{ops}};
+
+ # continue existing scan
my $max = 10;
my $opendirs = $self->{opendirs};
my @dirnames = keys %$opendirs;
}
$opendirs->{$dir} = $dh if $n < 0;
}
- if ($path =~ /full\z/) {
+ if ($op && $op eq 'full') {
foreach my $dir (@{$self->{mdir}}) {
next if $opendirs->{$dir}; # already in progress
my $ok = opendir(my $dh, $dir);
}
_done_for_now($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 {