use File::Temp 0.19 (); # 0.19 for ->newdir
use File::Spec ();
use PublicInbox::Search qw(xap_terms);
+use PublicInbox::Spawn qw(popen_rd);
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 { @{$_[0]->{shards_flat} // []} }
sub query_thread_mset { # for --thread
my ($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;
}
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;
+ 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;
$lei->{ovv}->ovv_atexit_child($lei);
}
+sub each_eml { # callback for MboxReader->mboxrd
+ my ($eml, $self, $lei, $each_smsg) = @_;
+ my $smsg = bless {}, 'PublicInbox::Smsg';
+ $smsg->populate($eml);
+ $smsg->{$_} //= '' for qw(from to cc ds subject references mid);
+ delete @$smsg{qw(From Subject -ds -ts)};
+ if (my $startq = delete($self->{5})) { wait_startq($startq) }
+ return if !$lei->{l2m} && $lei->{dedupe}->is_smsg_dup($smsg);
+ $each_smsg->($smsg, undef, $eml);
+}
+
+sub query_remote_mboxrd {
+ my ($self, $lei, $uris) = @_;
+ local $0 = "$0 query_remote_mboxrd";
+ my %sig = $lei->atfork_child_wq($self); # keep $self->{5} startq
+ local @SIG{keys %sig} = values %sig;
+ my ($opt, $env) = @$lei{qw(opt env)};
+ my @qform = (q => $lei->{mset_opt}->{qstr}, x => 'm');
+ push(@qform, t => 1) if $opt->{thread};
+ my $dedupe = $lei->{dedupe} // die 'BUG: {dedupe} missing';
+ $dedupe->prepare_dedupe;
+ my @cmd = qw(curl -XPOST -sSf);
+ my $verbose = $opt->{verbose};
+ push @cmd, '-v' if $verbose;
+ for my $o ($lei->curl_opt) {
+ $o =~ s/\|[a-z0-9]\b//i; # remove single char short option
+ if ($o =~ s/=[is]@\z//) {
+ my $ary = $opt->{$o} or next;
+ push @cmd, map { ("--$o", $_) } @$ary;
+ } elsif ($o =~ s/=[is]\z//) {
+ my $val = $opt->{$o} // next;
+ push @cmd, "--$o", $val;
+ } elsif ($opt->{$o}) {
+ push @cmd, "--$o";
+ }
+ }
+ $opt->{torsocks} = 'false' if $opt->{'no-torsocks'};
+ my $tor = $opt->{torsocks} //= 'auto';
+ for my $uri (@$uris) {
+ $uri->query_form(@qform);
+ my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei, $uri);
+ my $cmd = [ @cmd, $uri->as_string ];
+ if ($tor eq 'auto' && substr($uri->host, -6) eq '.onion' &&
+ (($env->{LD_PRELOAD}//'') !~ /torsocks/)) {
+ unshift @$cmd, 'torsocks';
+ } elsif (PublicInbox::Config::git_bool($tor)) {
+ unshift @$cmd, 'torsocks';
+ }
+ $lei->err("# @$cmd") if $verbose;
+ $? = 0;
+ my $fh = popen_rd($cmd, $env, { 2 => $lei->{2} });
+ $fh = IO::Uncompress::Gunzip->new($fh);
+ eval {
+ PublicInbox::MboxReader->mboxrd($fh, \&each_eml, $self,
+ $lei, $each_smsg);
+ };
+ return $lei->fail("E: @$cmd: $@") if $@;
+ if (($? >> 8) == 22) { # HTTP 404 from curl(1)
+ $uri->query_form(q => $lei->{mset_opt}->{qstr});
+ $lei->err('# no results from '.$uri->as_string);
+ } elsif ($?) {
+ $uri->query_form(q => $lei->{mset_opt}->{qstr});
+ $lei->err('E: '.$uri->as_string);
+ $lei->child_error($?);
+ }
+ }
+ $lei->{ovv}->ovv_atexit_child($lei);
+}
+
sub git {
my ($self) = @_;
my (%seen, @dirs);
}
sub query_done { # EOF callback
- my ($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;
+ 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 ($l2m) { # calls LeiToMail reap_compress
- close(delete($lei->{1})) if $lei->{1};
+ if ($has_l2m) { # close() calls LeiToMail reap_compress
+ if (my $out = delete $lei->{old_1}) {
+ if (my $mbout = $lei->{1}) {
+ close($mbout) or return $lei->fail(<<"");
+Error closing $lei->{ovv}->{dst}: $!
+
+ }
+ $lei->{1} = $out;
+ }
$lei->start_mua;
}
$lei->dclose;
close $au_done; # triggers wait_startq
}
+my $MAX_PER_HOST = 4;
+sub MAX_PER_HOST { $MAX_PER_HOST }
+
+sub concurrency {
+ my ($self, $opt) = @_;
+ my $nl = $opt->{thread} ? locals($self) : 1;
+ my $nr = remotes($self);
+ $nr = $MAX_PER_HOST if $nr > $MAX_PER_HOST;
+ $nl + $nr;
+}
+
sub start_query { # always runs in main (lei-daemon) process
- my ($self, $io, $lei, $srcs) = @_;
- my $remotes = $self->{remotes} // [];
+ my ($self, $io, $lei) = @_;
if ($lei->{opt}->{thread}) {
- for my $ibxish (@$srcs) {
+ for my $ibxish (locals($self)) {
$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);
+ }
+ my $i = 0;
+ my $q = [];
+ for my $uri (remotes($self)) {
+ push @{$q->[$i++ % $MAX_PER_HOST]}, $uri;
}
- # TODO
- for my $rmt (@$remotes) {
- $self->wq_do('query_thread_mbox', $io, $lei, $rmt);
+ for my $uris (@$q) {
+ $self->wq_do('query_remote_mboxrd', $io, $lei, $uris);
}
- close $io->[0]; # qry_status_wr
@$io = ();
}
sub query_prepare { # called by wq_do
my ($self, $lei) = @_;
+ local $0 = "$0 query_prepare";
my %sig = $lei->atfork_child_wq($self);
-p $lei->{0} or die "BUG: \$done pipe expected";
local @SIG{keys %sig} = values %sig;
syswrite($lei->{0}, '.') == 1 or die "do_post_augment trigger: $!";
}
-sub sigpipe_handler {
- my ($self, $lei_orig, $pids) = @_;
- if ($pids) { # one-shot (no event loop)
- kill 'TERM', @$pids;
+sub sigpipe_handler { # handles SIGPIPE from l2m/lxs workers
+ my ($lei) = @_;
+ my $lxs = delete $lei->{lxs};
+ if ($lxs && $lxs->wq_kill_old) {
kill 'PIPE', $$;
- } else {
- $self->wq_kill;
- $self->wq_close;
+ $lxs->wq_wait_old;
}
- close(delete $lei_orig->{1}) if $lei_orig->{1};
+ close(delete $lei->{1}) if $lei->{1};
}
sub do_query {
- my ($self, $lei_orig, $srcs) = @_;
+ my ($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->{1}->autoflush(1);
$lei_orig->event_step_init; # wait for shutdowns
my $done_op = {
- '' => [ \&query_done, $self, $lei_orig ],
- '!' => [ \&sigpipe_handler, $self, $lei_orig ]
+ '' => [ \&query_done, $lei_orig ],
+ '!' => [ \&sigpipe_handler, $lei_orig ]
};
my $in_loop = exists $lei_orig->{sock};
$done = PublicInbox::OpPipe->new($done, $done_op, $in_loop);
$io[5] = $startq;
$io[1] = $zpipe->[1] if $zpipe;
}
- start_query($self, \@io, $lei, $srcs);
+ start_query($self, \@io, $lei);
+ $self->wq_close(1);
unless ($in_loop) {
- my @pids = $self->wq_close;
# for the $lei->atfork_child_wq PIPE handler:
- $done_op->{'!'}->[3] = \@pids;
- # $done->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;
- # }
while ($done->{sock}) { $done->event_step }
- my $ipc_worker_reap = $self->can('ipc_worker_reap');
- dwaitpid($_, $ipc_worker_reap, $self) for @pids;
}
}
sub ipc_atfork_prepare {
my ($self) = @_;
- # (0: qry_status_wr, 1: stdout|mbox, 2: stderr,
- # 3: sock, 4: $l2m->{-wq_s1}, 5: $startq)
- $self->wq_set_recv_modes(qw[+<&= >&= >&= +<&= +<&= <&=]);
+ if (exists $self->{remotes}) {
+ require PublicInbox::MboxReader;
+ require IO::Uncompress::Gunzip;
+ }
+ # FDS: (0: done_wr, 1: stdout|mbox, 2: stderr,
+ # 3: sock, 4: $l2m->{-wq_s1}, 5: $startq)
$self->SUPER::ipc_atfork_prepare; # PublicInbox::IPC
}
+sub prepare_external {
+ my ($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;