use strict;
use v5.10.1;
use parent qw(PublicInbox::LeiSearch PublicInbox::IPC);
-use PublicInbox::DS qw(dwaitpid);
-use PublicInbox::OpPipe;
+use PublicInbox::DS qw(dwaitpid now);
+use PublicInbox::PktOp qw(pkt_do);
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 {
sub _mset_more ($$) {
my ($mset, $mo) = @_;
my $size = $mset->size;
- $size && (($mo->{offset} += $size) < ($mo->{limit} // 10000));
+ $size >= $mo->{limit} && (($mo->{offset} += $size) < $mo->{limit});
}
# $startq will EOF when query_prepare is done augmenting and allow
read($startq, my $query_prepare_done, 1);
}
+sub mset_progress {
+ my $lei = shift;
+ return unless $lei->{-progress};
+ if ($lei->{pkt_op}) { # called via pkt_op/pkt_do from workers
+ pkt_do($lei->{pkt_op}, 'mset_progress', @_);
+ } else { # single lei-daemon consumer
+ my ($desc, $mset_size, $mset_total_est) = @_;
+ $lei->{-mset_total} += $mset_size;
+ $lei->err("# $desc $mset_size/$mset_total_est");
+ }
+}
+
sub query_thread_mset { # for --thread
my ($self, $lei, $ibxish) = @_;
local $0 = "$0 query_thread_mset";
- my %sig = $lei->atfork_child_wq($self);
- local @SIG{keys %sig} = values %sig;
+ $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};
- warn "$desc not indexed by Xapian\n";
- return;
- }
+ my $desc = $ibxish->{inboxdir} // $ibxish->{topdir};
+ return warn("$desc not indexed by Xapian\n") unless ($srch && $over);
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);
+ mset_progress($lei, $desc, $mset->size,
+ $mset->get_matches_estimated);
my $ids = $srch->mset_to_artnums($mset, $mo);
my $ctx = { ids => $ids };
my $i = 0;
sub query_mset { # non-parallel for non-"--thread" users
my ($self, $lei) = @_;
local $0 = "$0 query_mset";
- my %sig = $lei->atfork_child_wq($self);
- local @SIG{keys %sig} = values %sig;
+ $lei->atfork_child_wq($self);
my $startq = delete $lei->{startq};
my $mo = { %{$lei->{mset_opt}} };
my $mset;
my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei, $self);
do {
$mset = $self->mset($mo->{qstr}, $mo);
+ mset_progress($lei, 'xsearch', $mset->size,
+ $mset->size, $mset->get_matches_estimated);
for my $mitem ($mset->items) {
my $smsg = smsg_for($self, $mitem) or next;
wait_startq($startq) if $startq;
$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) }
+ if ($lei->{-progress}) {
+ ++$lei->{-nr_remote_eml};
+ my $now = now();
+ my $next = $lei->{-next_progress} //= ($now + 1);
+ if ($now > $next) {
+ $lei->{-next_progress} = $now + 1;
+ my $nr = $lei->{-nr_remote_eml};
+ $lei->err("# $lei->{-current_url} $nr/?");
+ }
+ }
$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;
+ $lei->atfork_child_wq($self);
+ local $SIG{TERM} = sub { exit(0) }; # for DESTROY (File::Temp, $reap)
my ($opt, $env) = @$lei{qw(opt env)};
my @qform = (q => $lei->{mset_opt}->{qstr}, x => 'm');
push(@qform, t => 1) if $opt->{thread};
my $tor = $opt->{torsocks} //= 'auto';
my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei);
for my $uri (@$uris) {
+ $lei->{-current_url} = $uri->as_string;
+ $lei->{-nr_remote_eml} = 0;
$uri->query_form(@qform);
my $cmd = [ @cmd, $uri->as_string ];
if ($tor eq 'auto' && substr($uri->host, -6) eq '.onion' &&
shift(@$cmd) if !$cmd->[0];
$lei->err("# @$cmd") if $verbose;
- $? = 0;
- my $fh = popen_rd($cmd, $env, $rdr);
+ my ($fh, $pid) = 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 $?;
+ PublicInbox::MboxReader->mboxrd($fh, \&each_eml, $self,
+ $lei, $each_smsg);
+ waitpid($pid, 0) == $pid or die "BUG: waitpid (curl): $!";
+ if ($? == 0) {
+ my $nr = $lei->{-nr_remote_eml};
+ mset_progress($lei, $lei->{-current_url}, $nr, $nr);
+ next;
+ }
seek($cerr, $coff, SEEK_SET) or warn "seek(curl stderr): $!\n";
my $e = do { local $/; <$cerr> } //
die "read(curl stderr): $!\n";
$coff += length($e);
+ truncate($cerr, 0);
next if (($? >> 8) == 22 && $e =~ /\b404\b/);
$lei->child_error($?);
$uri->query_form(q => $lei->{mset_opt}->{qstr});
my $has_l2m = exists $lei->{l2m};
for my $f (qw(lxs l2m)) {
my $wq = delete $lei->{$f} or next;
- $wq->wq_wait_old;
+ $wq->wq_wait_old($lei);
}
$lei->{ovv}->ovv_end($lei);
if ($has_l2m) { # close() calls LeiToMail reap_compress
}
$lei->start_mua;
}
+ $lei->{-progress} and
+ $lei->err('# ', $lei->{-mset_total} // 0, " matches");
$lei->dclose;
}
}
my $MAX_PER_HOST = 4;
-sub MAX_PER_HOST { $MAX_PER_HOST }
sub concurrency {
my ($self, $opt) = @_;
sub query_prepare { # called by wq_do
my ($self, $lei) = @_;
local $0 = "$0 query_prepare";
- my %sig = $lei->atfork_child_wq($self);
- -p $lei->{op_pipe} or die "BUG: \$done pipe expected";
- local @SIG{keys %sig} = values %sig;
+ $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: $!"
+ pkt_do($lei->{pkt_op}, '.') == 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', $$;
- $lxs->wq_wait_old;
+sub fail_handler ($;$$) {
+ my ($lei, $code, $io) = @_;
+ for my $f (qw(lxs l2m)) {
+ my $wq = delete $lei->{$f} or next;
+ $wq->wq_wait_old($lei) if $wq->wq_kill_old; # lei-daemon
}
- close(delete $lei->{1}) if $lei->{1};
+ close($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 $_[0]->{1});
}
sub do_query {
fcntl($lei->{startq}, 1031, 4096) if $^O eq 'linux';
$zpipe = $l2m->pre_augment($lei);
}
- pipe(my $done, $lei->{op_pipe}) or die "pipe $!";
+ my $ops = {
+ '|' => [ \&sigpipe_handler, $lei ],
+ '!' => [ \&fail_handler, $lei ],
+ '.' => [ \&do_post_augment, $lei, $zpipe, $au_done ],
+ '' => [ \&query_done, $lei ],
+ 'mset_progress' => [ \&mset_progress, $lei ],
+ 'x_it' => [ $lei->can('x_it'), $lei ],
+ 'child_error' => [ $lei->can('child_error'), $lei ],
+ };
+ (my $op, $lei->{pkt_op}) = PublicInbox::PktOp->pair($ops);
my ($lei_ipc, @io) = $lei->atfork_parent_wq($self);
- delete($lei->{op_pipe});
+ delete($lei->{pkt_op});
$lei->event_step_init; # wait for shutdowns
- my $done_op = {
- '' => [ \&query_done, $lei ],
- '!' => [ \&sigpipe_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) {
+ if ($lei->{oneshot}) {
# for the $lei_ipc->atfork_child_wq PIPE handler:
- while ($done->{sock}) { $done->event_step }
+ while ($op->{sock}) { $op->event_step }
}
}