use strict;
use v5.10.1;
use parent qw(PublicInbox::LeiSearch PublicInbox::IPC);
-use PublicInbox::DS qw(dwaitpid);
-use PublicInbox::OpPipe;
-use PublicInbox::Import;
+use PublicInbox::DS qw(now);
use File::Temp 0.19 (); # 0.19 for ->newdir
use File::Spec ();
use PublicInbox::Search qw(xap_terms);
-use PublicInbox::Spawn qw(popen_rd);
+use PublicInbox::Spawn qw(popen_rd spawn which);
+use PublicInbox::MID qw(mids);
+use PublicInbox::Smsg;
+use PublicInbox::Eml;
+use Fcntl qw(SEEK_SET F_SETFL O_APPEND O_RDWR);
+use PublicInbox::ContentHash qw(git_sha);
sub new {
my ($class) = @_;
my ($self, $ibxish) = @_; # ibxish = ExtSearch or Inbox
my $desc = $ibxish->{inboxdir} // $ibxish->{topdir};
my $srch = $ibxish->search or
- return warn("$desc not indexed for Xapian\n");
+ 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 $self->{xdb}) { # XXX: do we need this?
# clobber existing {xdb} if amending
sub remotes { @{$_[0]->{remotes} // []} }
-# called by PublicInbox::Search::xdb
+# called by PublicInbox::Search::xdb (usually via ->mset)
sub xdb_shards_flat { @{$_[0]->{shards_flat} // []} }
+sub _mitem_kw { # retry_reopen callback
+ my ($srch, $smsg, $mitem, $flagged) = @_;
+ my $doc = $mitem->get_document;
+ my $kw = xap_terms('K', $doc);
+ $kw->{flagged} = 1 if $flagged;
+ my @L = xap_terms('L', $doc);
+ # we keep the empty {kw} array here to prevent expensive work in
+ # ->xsmsg_vmd, _unbless_smsg will clobber it iff it's empty
+ $smsg->{kw} = [ sort keys %$kw ];
+ $smsg->{L} = \@L if scalar(@L);
+}
+
+sub mitem_kw ($$$;$) {
+ my ($srch, $smsg, $mitem, $flagged) = @_;
+ $srch->retry_reopen(\&_mitem_kw, $smsg, $mitem, $flagged);
+}
+
# like over->get_art
sub smsg_for {
my ($self, $mitem) = @_;
my $num = int(($docid - 1) / $nshard) + 1;
my $ibx = $self->{shard2ibx}->[$shard];
my $smsg = $ibx->over->get_art($num);
- if (ref($ibx->can('msg_keywords'))) {
- my $kw = xap_terms('K', $mitem->get_document);
- $smsg->{kw} = [ sort keys %$kw ];
+ return if $smsg->{bytes} == 0; # external message
+ if ($ibx->can('msg_keywords')) {
+ mitem_kw($self, $smsg, $mitem);
}
- $smsg->{docid} = $docid;
$smsg;
}
my ($self, $qstr, $opt) = @_;
$opt //= {};
$opt->{relevance} //= -2;
- $self->mset($qstr //= 'bytes:1..', $opt);
+ $self->mset($qstr //= 'z:1..', $opt);
}
sub over {}
sub _mset_more ($$) {
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
-# query_mset and query_thread_mset to proceed.
+# $startq will EOF when do_augment is done augmenting and allow
+# query_combined_mset and query_thread_mset to proceed.
sub wait_startq ($) {
- my ($startq) = @_;
- $_[0] = undef;
- read($startq, my $query_prepare_done, 1);
+ my ($lei) = @_;
+ my $startq = delete $lei->{startq} or return;
+ while (1) {
+ my $n = sysread($startq, my $do_augment_done, 1);
+ if (defined $n) {
+ return if $n == 0; # no MUA
+ if ($do_augment_done eq 'q') {
+ $lei->{opt}->{quiet} = 1;
+ delete $lei->{opt}->{verbose};
+ delete $lei->{-progress};
+ } else {
+ $lei->fail("$$ WTF `$do_augment_done'");
+ }
+ return;
+ }
+ return $lei->fail("$$ wait_startq: $!") unless $!{EINTR};
+ }
}
-sub query_thread_mset { # for --thread
- my ($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 mset_progress {
+ my $lei = shift;
+ return if $lei->{early_mua} || !$lei->{-progress};
+ if ($lei->{pkt_op_p}) {
+ $lei->{pkt_op_p}->pkt_do('mset_progress', @_);
+ } else { # single lei-daemon consumer
+ my ($desc, $mset_size, $mset_total_est) = @_;
+ $lei->{-mset_total} += $mset_size if $mset_total_est ne '?';
+ $lei->qerr("# $desc $mset_size/$mset_total_est");
+ }
+}
+sub l2m_progress {
+ my ($lei, $nr) = @_;
+ $lei->{-nr_write} += $nr;
+}
+
+sub query_one_mset { # for --threads and l2m w/o sort
+ my ($self, $ibxish) = @_;
+ local $0 = "$0 query_one_mset";
+ my $lei = $self->{lei};
my ($srch, $over) = ($ibxish->search, $ibxish->over);
- unless ($srch && $over) {
- my $desc = $ibxish->{inboxdir} // $ibxish->{topdir};
- warn "$desc not indexed by Xapian\n";
- return;
- }
- my $mo = { %{$lei->{mset_opt}} };
+ my $dir = $ibxish->{inboxdir} // $ibxish->{topdir};
+ return warn("$dir not indexed by Xapian\n") unless ($srch && $over);
+ bless $srch, 'PublicInbox::LeiSearch'; # for ->qparse_new
+ my $mo = { %{$lei->{mset_opt}} }; # copy
my $mset;
- my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei, $ibxish);
- my $dedupe = $lei->{dedupe} // die 'BUG: {dedupe} missing';
- $dedupe->prepare_dedupe;
+ my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei);
+ my $can_kw = !!$ibxish->can('msg_keywords');
+ my $threads = $lei->{opt}->{threads} // 0;
+ my $fl = $threads > 1 ? 1 : undef;
+ my $lss = $lei->{dedupe};
+ $lss = undef unless $lss && $lss->can('cfg_set'); # saved search
+ my $maxk = "external.$dir.maxuid";
+ my $stop_at = $lss ? $lss->{-cfg}->{$maxk} : undef;
+ if (defined $stop_at) {
+ die "$maxk=$stop_at has multiple values" if ref $stop_at;
+ my @e;
+ local $SIG{__WARN__} = sub { push @e, @_ };
+ $stop_at += 0;
+ return warn("$maxk=$stop_at: @e") if @e;
+ }
+ my $first_ids;
do {
$mset = $srch->mset($mo->{qstr}, $mo);
+ mset_progress($lei, $dir, $mset->size,
+ $mset->get_matches_estimated);
+ wait_startq($lei); # wait for keyword updates
my $ids = $srch->mset_to_artnums($mset, $mo);
- my $ctx = { ids => $ids };
+ @$ids = grep { $_ > $stop_at } @$ids if defined($stop_at);
my $i = 0;
- my %n2item = map { ($ids->[$i++], $_) } $mset->items;
- while ($over->expand_thread($ctx)) {
- for my $n (@{$ctx->{xids}}) {
+ if ($threads) {
+ # copy $ids if $lss since over->expand_thread
+ # shifts @{$ctx->{ids}}
+ $first_ids = [ @$ids ] if $lss;
+ my $ctx = { ids => $ids };
+ my %n2item = map { ($ids->[$i++], $_) } $mset->items;
+ while ($over->expand_thread($ctx)) {
+ for my $n (@{$ctx->{xids}}) {
+ my $smsg = $over->get_art($n) or next;
+ my $mitem = delete $n2item{$n};
+ next if $smsg->{bytes} == 0;
+ if ($mitem && $can_kw) {
+ mitem_kw($srch, $smsg, $mitem,
+ $fl);
+ } elsif ($mitem && $fl) {
+ # call ->xsmsg_vmd, later
+ $smsg->{lei_q_tt_flagged} = 1;
+ }
+ $each_smsg->($smsg, $mitem);
+ }
+ @{$ctx->{xids}} = ();
+ }
+ } else {
+ $first_ids = $ids;
+ my @items = $mset->items;
+ for my $n (@$ids) {
+ my $mitem = $items[$i++];
my $smsg = $over->get_art($n) or next;
- wait_startq($startq) if $startq;
- next if $dedupe->is_smsg_dup($smsg);
- my $mitem = delete $n2item{$smsg->{num}};
+ next if $smsg->{bytes} == 0;
+ mitem_kw($srch, $smsg, $mitem, $fl) if $can_kw;
$each_smsg->($smsg, $mitem);
}
- @{$ctx->{xids}} = ();
}
} while (_mset_more($mset, $mo));
- undef $each_smsg; # drops @io for l2m->{each_smsg_done}
+ if ($lss && scalar(@$first_ids)) {
+ undef $stop_at;
+ my $max = $first_ids->[0];
+ $lss->cfg_set($maxk, $max);
+ undef $lss;
+ }
+ undef $each_smsg; # may commit
$lei->{ovv}->ovv_atexit_child($lei);
}
-sub query_mset { # non-parallel for non-"--thread" users
- 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;
+sub query_combined_mset { # non-parallel for non-"--threads" users
+ my ($self) = @_;
+ local $0 = "$0 query_combined_mset";
+ my $lei = $self->{lei};
my $mo = { %{$lei->{mset_opt}} };
my $mset;
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;
+ my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei);
do {
$mset = $self->mset($mo->{qstr}, $mo);
+ mset_progress($lei, 'xsearch', $mset->size,
+ $mset->get_matches_estimated);
+ wait_startq($lei); # wait for keyword updates
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}
+ undef $each_smsg; # may commit
$lei->{ovv}->ovv_atexit_child($lei);
}
-sub each_eml { # callback for MboxReader->mboxrd
- my ($eml, $self, $lei, $each_smsg) = @_;
- my $smsg = bless {}, 'PublicInbox::Smsg';
+sub _smsg_fill ($$) {
+ my ($smsg, $eml) = @_;
$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($self->{5})) { wait_startq($startq) }
- return if !$lei->{l2m} && $lei->{dedupe}->is_smsg_dup($smsg);
+}
+
+sub each_remote_eml { # callback for MboxReader->mboxrd
+ my ($eml, $self, $lei, $each_smsg) = @_;
+ my $xoids = $lei->{ale}->xoids_for($eml, 1);
+ my $smsg = bless {}, 'PublicInbox::Smsg';
+ if ($self->{import_sto} && !$xoids) {
+ my $res = $self->{import_sto}->ipc_do('add_eml', $eml);
+ if (ref($res) eq ref($smsg)) { # totally new message
+ $smsg = $res;
+ $smsg->{kw} = []; # short-circuit xsmsg_vmd
+ }
+ }
+ $smsg->{blob} //= $xoids ? (keys(%$xoids))[0] : $lei->git_blob_id($eml);
+ _smsg_fill($smsg, $eml);
+ wait_startq($lei);
+ 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};
+ mset_progress($lei, $lei->{-current_url}, $nr, '?');
+ }
+ }
$each_smsg->($smsg, undef, $eml);
}
sub query_remote_mboxrd {
- my ($self, $lei, $uri) = @_;
+ my ($self, $uris) = @_;
local $0 = "$0 query_remote_mboxrd";
- my %sig = $lei->atfork_child_wq($self); # keep $self->{5} startq
- local @SIG{keys %sig} = values %sig;
+ local $SIG{TERM} = sub { exit(0) }; # for DESTROY (File::Temp, $reap)
+ my $lei = $self->{lei};
my $opt = $lei->{opt};
- $uri->query_form(q => $lei->{mset_opt}->{qstr}, x => 'm',
- $opt->{thread} ? (t => 1) : ());
- my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei, $uri);
- my $dedupe = $lei->{dedupe} // die 'BUG: {dedupe} missing';
- $dedupe->prepare_dedupe;
- my @cmd = qw(curl -XPOST -sSf);
- $opt->{torsocks} = 'false' if $opt->{'no-torsocks'};
- my $tor = $opt->{torsocks} //= 'auto';
- if ($tor eq 'auto' && substr($uri->host, -6) eq '.onion' &&
- (($lei->{env}->{LD_PRELOAD}//'') !~ /torsocks/)) {
- unshift @cmd, 'torsocks';
- } elsif (PublicInbox::Config::git_bool($tor)) {
- unshift @cmd, 'torsocks';
- }
+ my $qstr = $lei->{mset_opt}->{qstr};
+ $qstr =~ s/[ \n\t]+/ /sg; # make URLs less ugly
+ my @qform = (q => $qstr, x => 'm');
+ push(@qform, t => 1) if $opt->{threads};
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";
- }
+ my ($reap_tail, $reap_curl);
+ 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, pgid => 0 };
+ my $sigint_reap = $lei->can('sigint_reap');
+ 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
+ my $o = { 1 => $lei->{2}, 2 => $lei->{2}, pgid => 0 };
+ my $pid = spawn(['tail', '-f', $cerr->filename], undef, $o);
+ $reap_tail = PublicInbox::OnDestroy->new($sigint_reap, $pid);
}
- push @cmd, $uri->as_string;
- $lei->err("# @cmd") if $verbose;
- $? = 0;
- my $fh = popen_rd(\@cmd, $lei->{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 ($?) {
+ my $curl = PublicInbox::LeiCurl->new($lei, $self->{curl}) or return;
+ push @$curl, '-s', '-d', '';
+ my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei);
+ $self->{import_sto} = $lei->{sto} if $lei->{opt}->{'import-remote'};
+ for my $uri (@$uris) {
+ $lei->{-current_url} = $uri->as_string;
+ $lei->{-nr_remote_eml} = 0;
+ $uri->query_form(@qform);
+ my $cmd = $curl->for_uri($lei, $uri);
+ $lei->qerr("# $cmd");
+ my ($fh, $pid) = popen_rd($cmd, undef, $rdr);
+ $reap_curl = PublicInbox::OnDestroy->new($sigint_reap, $pid);
+ $fh = IO::Uncompress::Gunzip->new($fh, MultiStream => 1);
+ PublicInbox::MboxReader->mboxrd($fh, \&each_remote_eml, $self,
+ $lei, $each_smsg);
+ my $err = waitpid($pid, 0) == $pid ? undef
+ : "BUG: waitpid($cmd): $!";
+ @$reap_curl = (); # cancel OnDestroy
+ die $err if $err;
+ my $nr = $lei->{-nr_remote_eml};
+ if ($nr && $lei->{sto}) {
+ my $wait = $lei->{sto}->ipc_do('done');
+ }
+ if ($? == 0) {
+ mset_progress($lei, $lei->{-current_url}, $nr, $nr);
+ next;
+ }
+ $err = '';
+ if (-s $cerr) {
+ seek($cerr, 0, SEEK_SET) or
+ $lei->err("seek($cmd stderr): $!");
+ $err = do { local $/; <$cerr> } //
+ "read($cmd stderr): $!";
+ truncate($cerr, 0) or
+ $lei->err("truncate($cmd stderr): $!");
+ }
+ next if (($? >> 8) == 22 && $err =~ /\b404\b/);
$uri->query_form(q => $lei->{mset_opt}->{qstr});
- $lei->err('E: '.$uri->as_string);
- $lei->child_error($?);
+ $lei->child_error($?, "E: <$uri> $err");
}
undef $each_smsg;
$lei->{ovv}->ovv_atexit_child($lei);
}
-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 git { $_[0]->{git} // die 'BUG: git uninitialized' }
+
+sub xsearch_done_wait { # dwaitpid callback
+ my ($arg, $pid) = @_;
+ my ($wq, $lei) = @$arg;
+ $lei->child_error($?, 'non-fatal error from '.ref($wq)) if $?;
}
-sub query_done { # EOF callback
+sub query_done { # EOF callback for main daemon
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;
+ my $l2m = delete $lei->{l2m};
+ $l2m->wq_wait_old(\&xsearch_done_wait, $lei) if $l2m;
+ if (my $lxs = delete $lei->{lxs}) {
+ $lxs->wq_wait_old(\&xsearch_done_wait, $lei);
+ }
+ if ($lei->{opt}->{'mail-sync'} && !$lei->{sto}) {
+ warn "BUG: {sto} missing with --mail-sync";
}
+ $lei->sto_done_request if $lei->{sto};
+ my $wait = $lei->{v2w} ? $lei->{v2w}->ipc_do('done') : undef;
$lei->{ovv}->ovv_end($lei);
- if ($has_l2m) { # close() calls LeiToMail reap_compress
+ my $start_mua;
+ if ($l2m) { # close() calls LeiToMail reap_compress
if (my $out = delete $lei->{old_1}) {
if (my $mbout = $lei->{1}) {
close($mbout) or return $lei->fail(<<"");
}
$lei->{1} = $out;
}
- $lei->start_mua;
+ if ($l2m->lock_free) {
+ $l2m->poke_dst;
+ $lei->poke_mua;
+ } else { # mbox users
+ delete $l2m->{mbl}; # drop dotlock
+ $start_mua = 1;
+ }
+ }
+ if ($lei->{-progress}) {
+ my $tot = $lei->{-mset_total} // 0;
+ my $nr = $lei->{-nr_write} // 0;
+ if ($l2m) {
+ my $m = "# $nr written to " .
+ "$lei->{ovv}->{dst} ($tot matches)";
+ $nr ? $lei->qfin($m) : $lei->qerr($m);
+ } else {
+ $lei->qerr("# $tot matches");
+ }
}
+ $lei->start_mua if $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 = $@) {
+ my ($lei) = @_;
+ my $l2m = $lei->{l2m} or return; # client disconnected
+ $lei->fchdir or return;
+ my $err;
+ eval { $l2m->post_augment($lei) };
+ $err = $@;
+ if ($err) {
if (my $lxs = delete $lei->{lxs}) {
$lxs->wq_kill;
- $lxs->wq_close;
+ $lxs->wq_close(0, undef, $lei);
}
$lei->fail("$err");
}
- close $au_done; # triggers wait_startq
+ if (!$err && delete $lei->{early_mua}) { # non-augment case
+ $lei->start_mua;
+ }
+ close(delete $lei->{au_done}); # triggers wait_startq in lei_xsearch
}
-sub start_query { # always runs in main (lei-daemon) process
- my ($self, $io, $lei) = @_;
- if ($lei->{opt}->{thread}) {
+sub incr_post_augment { # called whenever an l2m shard finishes augment
+ my ($lei) = @_;
+ my $l2m = $lei->{l2m} or return; # client disconnected
+ return if ++$lei->{nr_post_augment} != $l2m->{-wq_nr_workers};
+ do_post_augment($lei);
+}
+
+my $MAX_PER_HOST = 4;
+
+sub concurrency {
+ my ($self, $opt) = @_;
+ my $nl = $opt->{threads} ? 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, $l2m) = @_;
+ if ($self->{opt_threads} || ($l2m && !$self->{opt_sort})) {
for my $ibxish (locals($self)) {
- $self->wq_do('query_thread_mset', $io, $lei, $ibxish);
+ $self->wq_io_do('query_one_mset', [], $ibxish);
}
- } else {
- $self->wq_do('query_mset', $io, $lei);
+ } elsif (locals($self)) {
+ $self->wq_io_do('query_combined_mset', []);
}
+ my $i = 0;
+ my $q = [];
for my $uri (remotes($self)) {
- $self->wq_do('query_remote_mboxrd', $io, $lei, $uri);
+ push @{$q->[$i++ % $MAX_PER_HOST]}, $uri;
+ }
+ for my $uris (@$q) {
+ $self->wq_io_do('query_remote_mboxrd', [], $uris);
+ }
+ if ($self->{-do_lcat}) {
+ $self->wq_io_do('lcat_dump', []);
}
- @$io = ();
+ $self->wq_close(1); # lei_xsearch workers stop when done
}
-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 incr_start_query { # called whenever an l2m shard starts do_post_auth
+ my ($self, $l2m) = @_;
+ return if ++$self->{nr_start_query} != $l2m->{-wq_nr_workers};
+ start_query($self, $l2m);
}
-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 $lei->{1};
+sub ipc_atfork_child {
+ my ($self) = @_;
+ $self->{lei}->_lei_atfork_child;
+ $self->SUPER::ipc_atfork_child;
}
sub do_query {
- my ($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->{1}->autoflush(1);
-
- $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, $in_loop);
+ my ($self, $lei) = @_;
my $l2m = $lei->{l2m};
+ my $ops = {
+ '|' => [ $lei->can('sigpipe_handler'), $lei ],
+ '!' => [ $lei->can('fail_handler'), $lei ],
+ '.' => [ \&do_post_augment, $lei ],
+ '+' => [ \&incr_post_augment, $lei ],
+ '' => [ \&query_done, $lei ],
+ 'mset_progress' => [ \&mset_progress, $lei ],
+ 'l2m_progress' => [ \&l2m_progress, $lei ],
+ 'x_it' => [ $lei->can('x_it'), $lei ],
+ 'child_error' => [ $lei->can('child_error'), $lei ],
+ 'incr_start_query' => [ \&incr_start_query, $self, $l2m ],
+ };
+ $lei->{auth}->op_merge($ops, $l2m) if $l2m && $lei->{auth};
+ my $end = $lei->pkt_op_pair;
+ $lei->{1}->autoflush(1);
+ $lei->start_pager if delete $lei->{need_pager};
+ $lei->{ovv}->ovv_begin($lei);
+ die 'BUG: xdb|over open' if $lei->{lse}->{xdb} || $lei->{lse}->{over};
if ($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;
+ $l2m->pre_augment($lei);
+ if ($lei->{opt}->{augment} && delete $lei->{early_mua}) {
+ $lei->start_mua;
+ }
+ my $F_SETPIPE_SZ = $^O eq 'linux' ? 1031 : undef;
+ if ($l2m->{-wq_nr_workers} > 1 &&
+ $l2m->{base_type} =~ /\A(?:maildir|mbox)\z/) {
+ # setup two barriers to coordinate ->has_entries
+ # between l2m workers
+ pipe(my ($a_r, $a_w)) or die "pipe: $!";
+ fcntl($a_r, $F_SETPIPE_SZ, 4096) if $F_SETPIPE_SZ;
+ pipe(my ($b_r, $b_w)) or die "pipe: $!";
+ fcntl($b_r, $F_SETPIPE_SZ, 4096) if $F_SETPIPE_SZ;
+ $l2m->{au_peers} = [ $a_r, $a_w, $b_r, $b_w ];
+ }
+ $l2m->wq_workers_start('lei2mail', undef,
+ $lei->oldset, { lei => $lei });
+ pipe($lei->{startq}, $lei->{au_done}) or die "pipe: $!";
+ fcntl($lei->{startq}, $F_SETPIPE_SZ, 4096) if $F_SETPIPE_SZ;
+ delete $l2m->{au_peers};
}
- start_query($self, \@io, $lei);
- $self->wq_close(1);
- unless ($in_loop) {
- # for the $lei->atfork_child_wq PIPE handler:
- while ($done->{sock}) { $done->event_step }
+ $self->wq_workers_start('lei_xsearch', undef,
+ $lei->oldset, { lei => $lei });
+ my $op_c = delete $lei->{pkt_op_c};
+ delete $lei->{pkt_op_p};
+ @$end = ();
+ $self->{opt_threads} = $lei->{opt}->{threads};
+ $self->{opt_sort} = $lei->{opt}->{'sort'};
+ $self->{-do_lcat} = $lei->{lcat_blob} // $lei->{lcat_fid};
+ if ($l2m) {
+ $l2m->net_merge_all_done unless $lei->{auth};
+ } else {
+ start_query($self);
}
+ $lei->event_step_init; # wait for shutdowns
+ $lei->wait_wq_events($op_c, $ops);
}
-sub ipc_atfork_prepare {
- my ($self) = @_;
- if (exists $self->{remotes}) {
+sub add_uri {
+ my ($self, $uri) = @_;
+ if (my $curl = $self->{curl} //= which('curl') // 0) {
require PublicInbox::MboxReader;
require IO::Uncompress::Gunzip;
+ require PublicInbox::LeiCurl;
+ push @{$self->{remotes}}, $uri;
+ } else {
+ warn "curl missing, ignoring $uri\n";
}
- # (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 $loc->can('scheme');
+ return add_uri($self, $loc) if $loc->can('scheme');
} elsif ($loc =~ m!\Ahttps?://!) {
require URI;
- return push(@{$self->{remotes}}, URI->new($loc));
+ return add_uri($self, URI->new($loc));
} elsif (-f "$loc/ei.lock") {
require PublicInbox::ExtSearch;
+ die "`\\n' not allowed in `$loc'\n" if index($loc, "\n") >= 0;
$loc = PublicInbox::ExtSearch->new($loc);
} elsif (-f "$loc/inbox.lock" || -d "$loc/public-inbox") {
+ die "`\\n' not allowed in `$loc'\n" if index($loc, "\n") >= 0;
require PublicInbox::Inbox; # v2, v1
$loc = bless { inboxdir => $loc }, 'PublicInbox::Inbox';
} else {
push @{$self->{locals}}, $loc;
}
+sub _lcat_i { # LeiMailSync->each_src iterator callback
+ my ($oidbin, $id, $each_smsg) = @_;
+ $each_smsg->({blob => unpack('H*', $oidbin), pct => 100});
+}
+
+sub _lcat2smsg { # git->cat_async callback
+ my ($bref, $oid, $type, $size, $smsg) = @_;
+ if ($bref) {
+ my $eml = PublicInbox::Eml->new($bref);
+ my $json_dump = delete $smsg->{-json_dump};
+ bless $smsg, 'PublicInbox::Smsg';
+ _smsg_fill($smsg, $eml);
+ $json_dump->($smsg, undef, $eml);
+ }
+}
+
+sub lcat_dump {
+ my ($self) = @_;
+ my $lei = $self->{lei};
+ my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei);
+ my $git = $lei->{ale}->git;
+ if (!$lei->{l2m}) {
+ my $json_dump = $each_smsg;
+ $each_smsg = sub {
+ my ($smsg) = @_;
+ use Data::Dumper;
+ $smsg->{-json_dump} = $json_dump;
+ $git->cat_async($smsg->{blob}, \&_lcat2smsg, $smsg);
+ };
+ }
+ for my $oid (@{$lei->{lcat_blob} // []}) {
+ $each_smsg->({ blob => $oid, pct => 100 });
+ }
+ if (my $fids = delete $lei->{lcat_fid}) {
+ my $lms = $lei->{lse}->lms;
+ for my $fid (@$fids) {
+ $lms->each_src({fid => $fid}, \&_lcat_i, $each_smsg);
+ }
+ }
+ $git->async_wait_all;
+ undef $each_smsg; # may commit
+ $lei->{ovv}->ovv_atexit_child($lei);
+}
1;