use strict;
use v5.10.1;
use parent qw(PublicInbox::LeiSearch PublicInbox::IPC);
-use Sys::Syslog qw(syslog);
+use PublicInbox::DS qw(dwaitpid);
+use PublicInbox::OpPipe;
+use PublicInbox::Import;
+use File::Temp 0.19 (); # 0.19 for ->newdir
+use File::Spec ();
sub new {
my ($class) = @_;
sub query_thread_mset { # for --thread
my ($self, $lei, $ibxish) = @_;
- local %SIG = (%SIG, $lei->atfork_child_wq($self));
+ my %sig = $lei->atfork_child_wq($self);
+ local @SIG{keys %sig} = values %sig;
+
my ($srch, $over) = ($ibxish->search, $ibxish->over);
unless ($srch && $over) {
my $desc = $ibxish->{inboxdir} // $ibxish->{topdir};
}
my $mo = { %{$lei->{mset_opt}} };
my $mset;
- my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei);
+ my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei, $ibxish);
+ my $dedupe = $lei->{dedupe} // die 'BUG: {dedupe} missing';
+ $dedupe->prepare_dedupe;
do {
$mset = $srch->mset($mo->{qstr}, $mo);
my $ids = $srch->mset_to_artnums($mset, $mo);
while ($over->expand_thread($ctx)) {
for my $n (@{$ctx->{xids}}) {
my $smsg = $over->get_art($n) or next;
- # next if $dd->is_smsg_dup($smsg); TODO
+ next if $dedupe->is_smsg_dup($smsg);
my $mitem = delete $n2item{$smsg->{num}};
$each_smsg->($smsg, $mitem);
- # $self->out($buf .= $ORS);
- # $emit_cb->($smsg);
}
@{$ctx->{xids}} = ();
}
} while (_mset_more($mset, $mo));
+ undef $each_smsg; # drops @io for l2m->{each_smsg_done}
$lei->{ovv}->ovv_atexit_child($lei);
}
sub query_mset { # non-parallel for non-"--thread" users
my ($self, $lei, $srcs) = @_;
+ my %sig = $lei->atfork_child_wq($self);
+ local @SIG{keys %sig} = values %sig;
my $mo = { %{$lei->{mset_opt}} };
my $mset;
- local %SIG = (%SIG, $lei->atfork_child_wq($self));
$self->attach_external($_) for @$srcs;
- my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei);
+ my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei, $self);
+ my $dedupe = $lei->{dedupe} // die 'BUG: {dedupe} missing';
+ $dedupe->prepare_dedupe;
do {
$mset = $self->mset($mo->{qstr}, $mo);
for my $it ($mset->items) {
my $smsg = smsg_for($self, $it) or next;
- # next if $dd->is_smsg_dup($smsg);
+ next if $dedupe->is_smsg_dup($smsg);
$each_smsg->($smsg, $it);
- # $self->out($buf .= $ORS) if defined $buf;
- #$emit_cb->($smsg);
}
} while (_mset_more($mset, $mo));
+ undef $each_smsg; # drops @io for l2m->{each_smsg_done}
$lei->{ovv}->ovv_atexit_child($lei);
}
-sub do_query {
- my ($self, $lei_orig, $qry_done, $srcs) = @_;
- my ($lei, @io) = $lei_orig->atfork_parent_wq($self);
- $io[0] = $qry_done; # don't need stdin
- $io[1]->autoflush(1);
- $io[2]->autoflush(1);
+sub git {
+ my ($self) = @_;
+ my (%seen, @dirs);
+ my $tmp = File::Temp->newdir('lei_xsrch_git-XXXXXXXX', TMPDIR => 1);
+ for my $ibx (@{$self->{shard2ibx} // []}) {
+ my $d = File::Spec->canonpath($ibx->git->{git_dir});
+ $seen{$d} //= push @dirs, "$d/objects\n"
+ }
+ my $git_dir = $tmp->dirname;
+ PublicInbox::Import::init_bare($git_dir);
+ my $f = "$git_dir/objects/info/alternates";
+ open my $alt, '>', $f or die "open($f): $!";
+ print $alt @dirs or die "print $f: $!";
+ close $alt or die "close $f: $!";
+ my $git = PublicInbox::Git->new($git_dir);
+ $git->{-tmp} = $tmp;
+ $git;
+}
+
+sub query_done { # EOF callback
+ my ($self, $lei) = @_;
+ my $l2m = delete $lei->{l2m};
+ if (my $pids = delete $self->{l2m_pids}) {
+ my $ipc_worker_reap = $self->can('ipc_worker_reap');
+ dwaitpid($_, $ipc_worker_reap, $l2m) for @$pids;
+ }
+ $lei->{ovv}->ovv_end($lei);
+ $lei->start_mua if $l2m && !$l2m->lock_free;
+ $lei->dclose;
+}
+
+sub start_query { # always runs in main (lei-daemon) process
+ my ($self, $io, $lei, $srcs) = @_;
+ if (my $l2m = $lei->{l2m}) {
+ $lei->{1} = $io->[1];
+ $l2m->post_augment($lei);
+ $io->[1] = delete $lei->{1};
+ $lei->start_mua($io->[3]) if $l2m->lock_free;
+ }
+ my $remotes = $self->{remotes} // [];
if ($lei->{opt}->{thread}) {
for my $ibxish (@$srcs) {
- $self->wq_do('query_thread_mset', \@io, $lei, $ibxish);
+ $self->wq_do('query_thread_mset', $io, $lei, $ibxish);
}
} else {
- $self->wq_do('query_mset', \@io, $lei, $srcs);
+ $self->wq_do('query_mset', $io, $lei, $srcs);
}
# TODO
- for my $rmt (@{$self->{remotes} // []}) {
- $self->wq_do('query_thread_mbox', \@io, $lei, $rmt);
+ for my $rmt (@$remotes) {
+ $self->wq_do('query_thread_mbox', $io, $lei, $rmt);
}
+ close $io->[0]; # qry_status_wr
+ @$io = ();
+}
- # sent off to children, they will drop remaining references to it
- close $qry_done;
+sub query_prepare { # wq_do
+ my ($self, $lei) = @_;
+ my %sig = $lei->atfork_child_wq($self);
+ local @SIG{keys %sig} = values %sig;
+ if (my $l2m = $lei->{l2m}) {
+ eval { $l2m->do_augment($lei) };
+ return $lei->fail($@) if $@;
+ }
+ # trigger PublicInbox::OpPipe->event_step
+ my $qry_status_wr = $lei->{0} or
+ return $lei->fail('BUG: qry_status_wr missing');
+ $qry_status_wr->autoflush(1);
+ print $qry_status_wr '.' or # this should never fail...
+ return $lei->fail("BUG? print qry_status_wr: $!");
}
-sub ipc_atfork_child {
- my ($self) = @_;
- $SIG{__WARN__} = sub { syslog('warning', "@_") };
- $self->SUPER::ipc_atfork_child; # PublicInbox::IPC
+sub do_query {
+ my ($self, $lei_orig, $srcs) = @_;
+ my ($lei, @io) = $lei_orig->atfork_parent_wq($self);
+ $io[0] = undef;
+ pipe(my $qry_status_rd, $io[0]) or die "pipe $!";
+
+ $lei_orig->event_step_init; # wait for shutdowns
+ my $op_map = { '' => [ \&query_done, $self, $lei_orig ] };
+ my $in_loop = exists $lei_orig->{sock};
+ my $opp = PublicInbox::OpPipe->new($qry_status_rd, $op_map, $in_loop);
+ my $l2m = $lei->{l2m};
+ if ($l2m) {
+ $l2m->pre_augment($lei_orig); # may redirect $lei->{1} for mbox
+ $io[1] = $lei_orig->{1};
+ $op_map->{'.'} = [ \&start_query, $self, \@io, $lei, $srcs ];
+ $self->wq_do('query_prepare', \@io, $lei);
+ $opp->event_step if !$in_loop;
+ } else {
+ start_query($self, \@io, $lei, $srcs);
+ }
+ unless ($in_loop) {
+ my @pids = $self->wq_close;
+ # for the $lei->atfork_child_wq PIPE handler:
+ $op_map->{'!'} = [ \&CORE::kill, 'TERM', @pids ];
+ $opp->event_step;
+ my $ipc_worker_reap = $self->can('ipc_worker_reap');
+ if (my $l2m_pids = delete $self->{l2m_pids}) {
+ dwaitpid($_, $ipc_worker_reap, $l2m) for @$l2m_pids;
+ }
+ dwaitpid($_, $ipc_worker_reap, $self) for @pids;
+ }
}
sub ipc_atfork_prepare {
my ($self) = @_;
- $self->wq_set_recv_modes(qw[+<&= >&= >&= +<&=]);
+ # (qry_status_wr, stdout|mbox, stderr, 3: sock, 4: $l2m->{-wq_s1})
+ $self->wq_set_recv_modes(qw[+<&= >&= >&= +<&= +<&=]);
$self->SUPER::ipc_atfork_prepare; # PublicInbox::IPC
}