use v5.10.1;
use parent qw(PublicInbox::LeiSearch PublicInbox::IPC);
use PublicInbox::DS qw(dwaitpid);
+use PublicInbox::OpPipe;
+use PublicInbox::Import;
+use File::Temp 0.19 (); # 0.19 for ->newdir
+use File::Spec ();
+use PublicInbox::Search qw(xap_terms);
sub new {
my ($class) = @_;
sub attach_external {
my ($self, $ibxish) = @_; # ibxish = ExtSearch or Inbox
-
- if (!$ibxish->can('over') || !$ibxish->over) {
- return push(@{$self->{remotes}}, $ibxish)
- }
my $desc = $ibxish->{inboxdir} // $ibxish->{topdir};
my $srch = $ibxish->search or
return warn("$desc not indexed for Xapian\n");
}
# returns a list of local inboxes (or count in scalar context)
-sub locals {
- my %uniq = map {; "$_" => $_ } @{$_[0]->{shard2ibx} // []};
- values %uniq;
-}
+sub locals { @{$_[0]->{locals} // []} }
+
+sub remotes { @{$_[0]->{remotes} // []} }
# called by PublicInbox::Search::xdb
sub xdb_shards_flat { @{$_[0]->{shards_flat} // []} }
my $docid = $mitem->get_docid;
my $shard = ($docid - 1) % $nshard;
my $num = int(($docid - 1) / $nshard) + 1;
- my $smsg = $self->{shard2ibx}->[$shard]->over->get_art($num);
+ my $ibx = $self->{shard2ibx}->[$shard];
+ my $smsg = $ibx->over->get_art($num);
+ if (ref($ibx->can('msg_keywords'))) {
+ my $kw = xap_terms('K', $mitem->get_document);
+ $smsg->{kw} = [ sort keys %$kw ];
+ }
$smsg->{docid} = $docid;
$smsg;
}
$size && (($mo->{offset} += $size) < ($mo->{limit} // 10000));
}
+# $startq will EOF when query_prepare is done augmenting and allow
+# query_mset and query_thread_mset to proceed.
+sub wait_startq ($) {
+ my ($startq) = @_;
+ $_[0] = undef;
+ read($startq, my $query_prepare_done, 1);
+}
+
sub query_thread_mset { # for --thread
my ($self, $lei, $ibxish) = @_;
+ local $0 = "$0 query_thread_mset";
+ my $startq = delete $self->{5};
my %sig = $lei->atfork_child_wq($self);
local @SIG{keys %sig} = values %sig;
}
my $mo = { %{$lei->{mset_opt}} };
my $mset;
- my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei);
- my $dd = $lei->{dd};
- $dd->prepare_dedupe;
+ 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);
+ wait_startq($startq) if $startq;
+ next if $dedupe->is_smsg_dup($smsg);
my $mitem = delete $n2item{$smsg->{num}};
$each_smsg->($smsg, $mitem);
}
@{$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, $srcs) = @_;
+ my ($self, $lei) = @_;
+ local $0 = "$0 query_mset";
+ my $startq = delete $self->{5};
my %sig = $lei->atfork_child_wq($self);
local @SIG{keys %sig} = values %sig;
my $mo = { %{$lei->{mset_opt}} };
my $mset;
- $self->attach_external($_) for @$srcs;
- my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei);
- my $dd = $lei->{dd};
- $dd->prepare_dedupe;
+ for my $loc (locals($self)) {
+ attach_external($self, $loc);
+ }
+ 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);
- $each_smsg->($smsg, $it);
+ for my $mitem ($mset->items) {
+ my $smsg = smsg_for($self, $mitem) or next;
+ wait_startq($startq) if $startq;
+ next if $dedupe->is_smsg_dup($smsg);
+ $each_smsg->($smsg, $mitem);
}
} while (_mset_more($mset, $mo));
+ undef $each_smsg; # drops @io for l2m->{each_smsg_done}
$lei->{ovv}->ovv_atexit_child($lei);
}
-sub query_done { # PublicInbox::EOFpipe callback
+sub query_remote_mboxrd {
+ my ($self, $lei, $uri) = @_;
+}
+
+sub git {
+ my ($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;
+ $git;
+}
+
+sub query_done { # EOF callback
my ($lei) = @_;
+ my $has_l2m = exists $lei->{l2m};
+ for my $f (qw(lxs l2m)) {
+ my $wq = delete $lei->{$f} or next;
+ $wq->wq_wait_old;
+ }
$lei->{ovv}->ovv_end($lei);
+ if ($has_l2m) { # close() calls LeiToMail reap_compress
+ close(delete($lei->{1})) if $lei->{1};
+ $lei->start_mua;
+ }
$lei->dclose;
}
-sub do_query {
- my ($self, $lei_orig, $srcs) = @_;
- my ($lei, @io) = $lei_orig->atfork_parent_wq($self);
- my $remotes = $self->{remotes} // [];
- pipe(my ($eof_wait, $qry_done)) or die "pipe $!";
- $io[0] = $qry_done; # don't need stdin
+sub do_post_augment {
+ my ($lei, $zpipe, $au_done) = @_;
+ my $l2m = $lei->{l2m} or die 'BUG: no {l2m}';
+ eval { $l2m->post_augment($lei, $zpipe) };
+ if (my $err = $@) {
+ if (my $lxs = delete $lei->{lxs}) {
+ $lxs->wq_kill;
+ $lxs->wq_close;
+ }
+ $lei->fail("$err");
+ }
+ close $au_done; # triggers wait_startq
+}
+sub start_query { # always runs in main (lei-daemon) process
+ my ($self, $io, $lei) = @_;
if ($lei->{opt}->{thread}) {
- $lei->{-parallel} = scalar(@$remotes) + scalar(@$srcs) - 1;
- for my $ibxish (@$srcs) {
- $self->wq_do('query_thread_mset', \@io, $lei, $ibxish);
+ for my $ibxish (locals($self)) {
+ $self->wq_do('query_thread_mset', $io, $lei, $ibxish);
}
} else {
- $lei->{-parallel} = scalar(@$remotes);
- $self->wq_do('query_mset', \@io, $lei, $srcs);
+ $self->wq_do('query_mset', $io, $lei);
}
# TODO
- for my $rmt (@$remotes) {
- $self->wq_do('query_thread_mbox', \@io, $lei, $rmt);
+ for my $uri (remotes($self)) {
+ $self->wq_do('query_remote_mboxrd', $io, $lei, $uri);
}
- @io = ();
- close $qry_done; # fully closed when children are done
-
- # query_done will run when query_*mset close $qry_done
- if ($lei_orig->{sock}) { # watch for client premature exit
- require PublicInbox::EOFpipe;
- PublicInbox::EOFpipe->new($eof_wait, \&query_done, $lei_orig);
- $lei_orig->{lxs} = $self;
- $lei_orig->event_step_init;
- } else {
- my @pids = $self->wq_close;
- # wait for close($lei->{0})
- if (read($eof_wait, my $buf, 1)) {
- # if we get a SIGPIPE from one, kill the rest
- kill('TERM', @pids) if $buf eq '!';
- }
- my $ipc_worker_reap = $self->can('ipc_worker_reap');
- dwaitpid($_, $ipc_worker_reap, $self) for @pids;
- query_done($lei_orig); # may SIGPIPE
+ @$io = ();
+}
+
+sub query_prepare { # called by wq_do
+ my ($self, $lei) = @_;
+ local $0 = "$0 query_prepare";
+ my %sig = $lei->atfork_child_wq($self);
+ -p $lei->{0} or die "BUG: \$done pipe expected";
+ local @SIG{keys %sig} = values %sig;
+ eval { $lei->{l2m}->do_augment($lei) };
+ $lei->fail($@) if $@;
+ syswrite($lei->{0}, '.') == 1 or die "do_post_augment trigger: $!";
+}
+
+sub sigpipe_handler { # handles SIGPIPE from l2m/lxs workers
+ my ($lei) = @_;
+ my $lxs = delete $lei->{lxs};
+ if ($lxs && $lxs->wq_kill_old) {
+ kill 'PIPE', $$;
+ $lxs->wq_wait_old;
+ }
+ close(delete $lei->{1}) if $lei->{1};
+}
+
+sub do_query {
+ my ($self, $lei_orig) = @_;
+ my ($lei, @io) = $lei_orig->atfork_parent_wq($self);
+ $io[0] = undef;
+ pipe(my $done, $io[0]) or die "pipe $!";
+
+ $lei_orig->event_step_init; # wait for shutdowns
+ my $done_op = {
+ '' => [ \&query_done, $lei_orig ],
+ '!' => [ \&sigpipe_handler, $lei_orig ]
+ };
+ my $in_loop = exists $lei_orig->{sock};
+ $done = PublicInbox::OpPipe->new($done, $done_op, $in_loop);
+ my $l2m = $lei->{l2m};
+ if ($l2m) {
+ # may redirect $lei->{1} for mbox
+ my $zpipe = $l2m->pre_augment($lei_orig);
+ $io[1] = $lei_orig->{1};
+ pipe(my ($startq, $au_done)) or die "pipe: $!";
+ $done_op->{'.'} = [ \&do_post_augment, $lei_orig,
+ $zpipe, $au_done ];
+ local $io[4] = *STDERR{GLOB}; # don't send l2m->{-wq_s1}
+ die "BUG: unexpected \$io[5]: $io[5]" if $io[5];
+ $self->wq_do('query_prepare', \@io, $lei);
+ fcntl($startq, 1031, 4096) if $^O eq 'linux'; # F_SETPIPE_SZ
+ $io[5] = $startq;
+ $io[1] = $zpipe->[1] if $zpipe;
+ }
+ start_query($self, \@io, $lei);
+ $self->wq_close(1);
+ unless ($in_loop) {
+ # for the $lei->atfork_child_wq PIPE handler:
+ while ($done->{sock}) { $done->event_step }
}
}
sub ipc_atfork_prepare {
my ($self) = @_;
- $self->wq_set_recv_modes(qw[+<&= >&= >&= +<&=]);
+ # (0: done_wr, 1: stdout|mbox, 2: stderr,
+ # 3: sock, 4: $l2m->{-wq_s1}, 5: $startq)
+ $self->wq_set_recv_modes(qw[+<&= >&= >&= +<&= +<&= <&=]);
$self->SUPER::ipc_atfork_prepare; # PublicInbox::IPC
}
+sub prepare_external {
+ my ($self, $loc, $boost) = @_; # n.b. already ordered by boost
+ if (ref $loc) { # already a URI, or PublicInbox::Inbox-like object
+ return push(@{$self->{remotes}}, $loc) if $loc->can('scheme');
+ } elsif ($loc =~ m!\Ahttps?://!) {
+ require URI;
+ return push(@{$self->{remotes}}, URI->new($loc));
+ } elsif (-f "$loc/ei.lock") {
+ require PublicInbox::ExtSearch;
+ $loc = PublicInbox::ExtSearch->new($loc);
+ } elsif (-f "$loc/inbox.lock" || -d "$loc/public-inbox") {
+ require PublicInbox::Inbox; # v2, v1
+ $loc = bless { inboxdir => $loc }, 'PublicInbox::Inbox';
+ } else {
+ warn "W: ignoring $loc, unable to determine type\n";
+ return;
+ }
+ push @{$self->{locals}}, $loc;
+}
+
+
1;