use strict;
use v5.10.1;
use parent qw(PublicInbox::LeiSearch PublicInbox::IPC);
-use PublicInbox::Search qw(get_pct);
-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 ();
+use PublicInbox::Search qw(xap_terms);
+use PublicInbox::Spawn qw(popen_rd spawn which);
+use PublicInbox::MID qw(mids);
+use PublicInbox::Smsg;
+use Fcntl qw(SEEK_SET F_SETFL O_APPEND O_RDWR);
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");
my @shards = $srch->xdb_shards_flat or
- return warn("$desc has no Xapian shardsXapian\n");
+ return warn("$desc has no Xapian shards\n");
if (delete $self->{xdb}) { # XXX: do we need this?
# clobber existing {xdb} if amending
}
# returns a list of local inboxes (or count in scalar context)
-sub locals {
- my %uniq = map {; "$_" => $_ } @{$_[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 %SIG = (%SIG, $lei->atfork_child_wq($self));
+ local $0 = "$0 query_thread_mset";
+ $lei->atfork_child_wq($self);
+ my $startq = delete $lei->{startq};
+
my ($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, $ibxish);
do {
$mset = $srch->mset($mo->{qstr}, $mo);
my $ids = $srch->mset_to_artnums($mset, $mo);
my $ctx = { ids => $ids };
my $i = 0;
- my %n2p = map { ($ids->[$i++], get_pct($_)) } $mset->items;
+ my %n2item = map { ($ids->[$i++], $_) } $mset->items;
while ($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
- if (my $p = delete $n2p{$smsg->{num}}) {
- $smsg->{relevance} = $p;
- }
- print { $self->{1} } Dumper($smsg);
- # $self->out($buf .= $ORS);
- # $emit_cb->($smsg);
+ wait_startq($startq) if $startq;
+ 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";
+ $lei->atfork_child_wq($self);
+ my $startq = delete $lei->{startq};
my $mo = { %{$lei->{mset_opt}} };
my $mset;
- local %SIG = (%SIG, $lei->atfork_child_wq($self));
- $self->attach_external($_) for @$srcs;
+ for my $loc (locals($self)) {
+ attach_external($self, $loc);
+ }
+ my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei, $self);
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);
- $smsg->{relevance} = get_pct($it);
- use Data::Dumper;
- print { $self->{1} } Dumper($smsg);
- # $self->out($buf .= $ORS) if defined $buf;
- #$emit_cb->($smsg);
+ for my $mitem ($mset->items) {
+ my $smsg = smsg_for($self, $mitem) or next;
+ wait_startq($startq) if $startq;
+ $each_smsg->($smsg, $mitem);
}
} while (_mset_more($mset, $mo));
+ undef $each_smsg; # drops @io for l2m->{each_smsg_done}
+ $lei->{ovv}->ovv_atexit_child($lei);
}
-sub do_query {
- my ($self, $lei_orig, $srcs) = @_;
- my ($lei, @io) = $lei_orig->atfork_parent_wq($self);
- $io[1]->autoflush(1);
- $io[2]->autoflush(1);
- if ($lei->{opt}->{thread}) {
- for my $ibxish (@$srcs) {
- $self->wq_do('query_thread_mset', \@io, $lei, $ibxish);
+sub each_eml { # callback for MboxReader->mboxrd
+ my ($eml, $self, $lei, $each_smsg) = @_;
+ my $smsg = bless {}, 'PublicInbox::Smsg';
+ $smsg->populate($eml);
+ $smsg->parse_references($eml, mids($eml));
+ $smsg->{$_} //= '' for qw(from to cc ds subject references mid);
+ delete @$smsg{qw(From Subject -ds -ts)};
+ if (my $startq = delete($lei->{startq})) { wait_startq($startq) }
+ $each_smsg->($smsg, undef, $eml);
+}
+
+# PublicInbox::OnDestroy callback
+sub kill_reap {
+ my ($pid) = @_;
+ kill('KILL', $pid); # spawn() blocks other signals
+ waitpid($pid, 0);
+}
+
+sub query_remote_mboxrd {
+ my ($self, $lei, $uris) = @_;
+ local $0 = "$0 query_remote_mboxrd";
+ $lei->atfork_child_wq($self);
+ my ($opt, $env) = @$lei{qw(opt env)};
+ my @qform = (q => $lei->{mset_opt}->{qstr}, x => 'm');
+ push(@qform, t => 1) if $opt->{thread};
+ my @cmd = ($self->{curl}, qw(-sSf -d), '');
+ my $verbose = $opt->{verbose};
+ my $reap;
+ my $cerr = File::Temp->new(TEMPLATE => 'curl.err-XXXX', TMPDIR => 1);
+ fcntl($cerr, F_SETFL, O_APPEND|O_RDWR) or warn "set O_APPEND: $!";
+ my $rdr = { 2 => $cerr };
+ my $coff = 0;
+ if ($verbose) {
+ # spawn a process to force line-buffering, otherwise curl
+ # will write 1 character at-a-time and parallel outputs
+ # mmmaaayyy llloookkk llliiikkkeee ttthhhiiisss
+ push @cmd, '-v';
+ my $o = { 1 => $lei->{2}, 2 => $lei->{2} };
+ my $pid = spawn(['tail', '-f', $cerr->filename], undef, $o);
+ $reap = PublicInbox::OnDestroy->new(\&kill_reap, $pid);
+ }
+ 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";
}
- } else {
- $self->wq_do('query_mset', \@io, $lei, $srcs);
}
- # TODO
- for my $rmt (@{$self->{remotes} // []}) {
- $self->wq_do('query_thread_mbox', \@io, $lei, $rmt);
+ $opt->{torsocks} = 'false' if $opt->{'no-torsocks'};
+ my $tor = $opt->{torsocks} //= 'auto';
+ my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei);
+ for my $uri (@$uris) {
+ $uri->query_form(@qform);
+ my $cmd = [ @cmd, $uri->as_string ];
+ if ($tor eq 'auto' && substr($uri->host, -6) eq '.onion' &&
+ (($env->{LD_PRELOAD}//'') !~ /torsocks/)) {
+ unshift @$cmd, which('torsocks');
+ } elsif (PublicInbox::Config::git_bool($tor)) {
+ unshift @$cmd, which('torsocks');
+ }
+
+ # continue anyways if torsocks is missing; a proxy may be
+ # specified via CLI, curlrc, environment variable, or even
+ # firewall rule
+ shift(@$cmd) if !$cmd->[0];
+
+ $lei->err("# @$cmd") if $verbose;
+ $? = 0;
+ my $fh = popen_rd($cmd, $env, $rdr);
+ $fh = IO::Uncompress::Gunzip->new($fh);
+ eval {
+ PublicInbox::MboxReader->mboxrd($fh, \&each_eml, $self,
+ $lei, $each_smsg);
+ };
+ return $lei->fail("E: @$cmd: $@") if $@;
+ next unless $?;
+ seek($cerr, $coff, SEEK_SET) or warn "seek(curl stderr): $!\n";
+ my $e = do { local $/; <$cerr> } //
+ die "read(curl stderr): $!\n";
+ $coff += length($e);
+ next if (($? >> 8) == 22 && $e =~ /\b404\b/);
+ $lei->child_error($?);
+ $uri->query_form(q => $lei->{mset_opt}->{qstr});
+ # --verbose already showed the error via tail(1)
+ $lei->err("E: $uri \$?=$?\n", $verbose ? () : $e);
}
+ undef $each_smsg;
+ $lei->{ovv}->ovv_atexit_child($lei);
}
-sub ipc_atfork_child {
+sub git {
my ($self) = @_;
- $SIG{__WARN__} = sub { syslog('warning', "@_") };
- $self->SUPER::ipc_atfork_child; # PublicInbox::IPC
+ 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;
+ $git;
}
-sub ipc_atfork_prepare {
- my ($self) = @_;
- $self->wq_set_recv_modes(qw[<&= >&= >&= +<&=]);
- $self->SUPER::ipc_atfork_prepare; # PublicInbox::IPC
+sub query_done { # EOF callback
+ my ($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);
+ }
+ $lei->{ovv}->ovv_end($lei);
+ 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;
+ }
+ $lei->dclose;
+}
+
+sub do_post_augment {
+ my ($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
}
+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, $lei) = @_;
+ if ($lei->{opt}->{thread}) {
+ for my $ibxish (locals($self)) {
+ $self->wq_do('query_thread_mset', $io, $lei, $ibxish);
+ }
+ } elsif (locals($self)) {
+ $self->wq_do('query_mset', $io, $lei);
+ }
+ my $i = 0;
+ my $q = [];
+ for my $uri (remotes($self)) {
+ push @{$q->[$i++ % $MAX_PER_HOST]}, $uri;
+ }
+ for my $uris (@$q) {
+ $self->wq_do('query_remote_mboxrd', $io, $lei, $uris);
+ }
+ @$io = ();
+}
+
+sub query_prepare { # called by wq_do
+ my ($self, $lei) = @_;
+ local $0 = "$0 query_prepare";
+ $lei->atfork_child_wq($self);
+ delete $lei->{l2m}->{-wq_s1};
+ eval { $lei->{l2m}->do_augment($lei) };
+ $lei->fail($@) if $@;
+ syswrite($lei->{op_pipe}, '.') == 1 or die "do_post_augment trigger: $!"
+}
+
+sub fail_handler ($;$$) {
+ my ($lei, $code, $io) = @_;
+ if (my $lxs = delete $lei->{lxs}) {
+ $lxs->wq_wait_old($lei) if $lxs->wq_kill_old; # lei-daemon
+ }
+ close($io) if $io; # needed to avoid warnings on SIGPIPE
+ $lei->x_it($code // (1 >> 8));
+}
+
+sub sigpipe_handler { # handles SIGPIPE from l2m/lxs workers
+ fail_handler($_[0], 13, delete $_[0]->{1});
+}
+
+sub do_query {
+ my ($self, $lei) = @_;
+ $lei->{1}->autoflush(1);
+ my ($au_done, $zpipe);
+ my $l2m = $lei->{l2m};
+ if ($l2m) {
+ pipe($lei->{startq}, $au_done) or die "pipe: $!";
+ # 1031: F_SETPIPE_SZ
+ fcntl($lei->{startq}, 1031, 4096) if $^O eq 'linux';
+ $zpipe = $l2m->pre_augment($lei);
+ }
+ pipe(my $done, $lei->{op_pipe}) or die "pipe $!";
+ my ($lei_ipc, @io) = $lei->atfork_parent_wq($self);
+ delete($lei->{op_pipe});
+
+ $lei->event_step_init; # wait for shutdowns
+ my $done_op = {
+ '' => [ \&query_done, $lei ],
+ '|' => [ \&sigpipe_handler, $lei ],
+ '!' => [ \&fail_handler, $lei ]
+ };
+ my $in_loop = exists $lei->{sock};
+ $done = PublicInbox::OpPipe->new($done, $done_op, $in_loop);
+ if ($l2m) {
+ $done_op->{'.'} = [ \&do_post_augment, $lei, $zpipe, $au_done ];
+ $self->wq_do('query_prepare', \@io, $lei_ipc);
+ $io[1] = $zpipe->[1] if $zpipe;
+ }
+ start_query($self, \@io, $lei_ipc);
+ $self->wq_close(1);
+ unless ($in_loop) {
+ # for the $lei_ipc->atfork_child_wq PIPE handler:
+ while ($done->{sock}) { $done->event_step }
+ }
+}
+
+sub add_uri {
+ my ($self, $uri) = @_;
+ if (my $curl = $self->{curl} //= which('curl') // 0) {
+ require PublicInbox::MboxReader;
+ require IO::Uncompress::Gunzip;
+ push @{$self->{remotes}}, $uri;
+ } else {
+ warn "curl missing, ignoring $uri\n";
+ }
+}
+
+sub prepare_external {
+ my ($self, $loc, $boost) = @_; # n.b. already ordered by boost
+ if (ref $loc) { # already a URI, or PublicInbox::Inbox-like object
+ return add_uri($self, $loc) if $loc->can('scheme');
+ } elsif ($loc =~ m!\Ahttps?://!) {
+ require URI;
+ return add_uri($self, URI->new($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;