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) = @_;
sub mitem_kw ($$;$) {
my ($smsg, $mitem, $flagged) = @_;
- my $kw = xap_terms('K', $mitem->get_document);
+ my $kw = xap_terms('K', my $doc = $mitem->get_document);
$kw->{flagged} = 1 if $flagged;
+ # we keep the empty {kw} array here to prevent expensive work in
+ # ->xsmsg_vmd, _unbless_smsg will clobber it iff it's empty
$smsg->{kw} = [ sort keys %$kw ];
+ my $L = xap_terms('L', $doc);
+ $smsg->{L} = [ sort keys %$L ] if scalar(keys %$L);
}
# like over->get_art
my $num = int(($docid - 1) / $nshard) + 1;
my $ibx = $self->{shard2ibx}->[$shard];
my $smsg = $ibx->over->get_art($num);
- mitem_kw($smsg, $mitem) if $ibx->can('msg_keywords');
- $smsg->{docid} = $docid;
+ return if $smsg->{bytes} == 0; # external message
+ if ($ibx->can('msg_keywords')) {
+ mitem_kw($smsg, $mitem);
+ }
$smsg;
}
sub over {}
-sub overs_all { # for xids_for
- my ($self) = @_;
- grep(defined, map { $_->over } locals($self))
-}
-
sub _mset_more ($$) {
my ($mset, $mo) = @_;
my $size = $mset->size;
}
# $startq will EOF when do_augment is done augmenting and allow
-# query_mset and query_thread_mset to proceed.
+# query_combined_mset and query_thread_mset to proceed.
sub wait_startq ($) {
my ($lei) = @_;
my $startq = delete $lei->{startq} or return;
}
}
-sub query_thread_mset { # for --threads
+sub query_one_mset { # for --threads and l2m w/o sort
my ($self, $ibxish) = @_;
- local $0 = "$0 query_thread_mset";
+ local $0 = "$0 query_one_mset";
my $lei = $self->{lei};
my ($srch, $over) = ($ibxish->search, $ibxish->over);
- my $desc = $ibxish->{inboxdir} // $ibxish->{topdir};
- return warn("$desc not indexed by Xapian\n") unless ($srch && $over);
- my $mo = { %{$lei->{mset_opt}} };
+ my $dir = $ibxish->{inboxdir} // $ibxish->{topdir};
+ return warn("$dir not indexed by Xapian\n") unless ($srch && $over);
+ my $mo = { %{$lei->{mset_opt}} }; # copy
my $mset;
- my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei, $ibxish);
+ my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei);
my $can_kw = !!$ibxish->can('msg_keywords');
- my $fl = $lei->{opt}->{threads} > 1 ? [ 'flagged' ] : undef;
+ 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, $desc, $mset->size,
+ mset_progress($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}}) {
- my $smsg = $over->get_art($n) or next;
- wait_startq($lei);
- my $mitem = delete $n2item{$smsg->{num}};
- if ($mitem) {
- if ($can_kw) {
+ 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 && $can_kw) {
mitem_kw($smsg, $mitem, $fl);
- } elsif ($fl) {
- $smsg->{kw} = $fl;
+ } elsif ($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;
+ next if $smsg->{bytes} == 0;
+ mitem_kw($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-"--threads" users
+sub query_combined_mset { # non-parallel for non-"--threads" users
my ($self) = @_;
- local $0 = "$0 query_mset";
+ 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 $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei);
do {
$mset = $self->mset($mo->{qstr}, $mo);
mset_progress($lei, 'xsearch', $mset->size,
$mset->size, $mset->get_matches_estimated);
+ wait_startq($lei); # wait for keyword updates
for my $mitem ($mset->items) {
my $smsg = smsg_for($self, $mitem) or next;
- wait_startq($lei);
$each_smsg->($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_remote_eml { # callback for MboxReader->mboxrd
my ($eml, $self, $lei, $each_smsg) = @_;
- if (my $sto = $self->{import_sto}) {
- $sto->ipc_do('add_eml_maybe', $eml);
+ my $xoids = $lei->{ale}->xoids_for($eml, 1);
+ if ($self->{import_sto} && !$xoids) {
+ $self->{import_sto}->ipc_do('add_eml', $eml);
}
my $smsg = bless {}, 'PublicInbox::Smsg';
+ $smsg->{blob} = $xoids ? (keys(%$xoids))[0]
+ : git_sha(1, $eml)->hexdigest;
$smsg->populate($eml);
$smsg->parse_references($eml, mids($eml));
$smsg->{$_} //= '' for qw(from to cc ds subject references mid);
if ($now > $next) {
$lei->{-next_progress} = $now + 1;
my $nr = $lei->{-nr_remote_eml};
- $lei->err("# $lei->{-current_url} $nr/?");
+ mset_progress($lei, $lei->{-current_url}, $nr, '?');
}
}
$each_smsg->($smsg, undef, $eml);
$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);
+ $fh = IO::Uncompress::Gunzip->new($fh, MultiStream => 1);
PublicInbox::MboxReader->mboxrd($fh, \&each_remote_eml, $self,
$lei, $each_smsg);
my $err = waitpid($pid, 0) == $pid ? undef
$lei->{ovv}->ovv_atexit_child($lei);
}
-# called by LeiOverview::each_smsg_cb
-sub git { $_[0]->{git_tmp} // die 'BUG: caller did not set {git_tmp}' }
-
-sub git_tmp ($) {
- my ($self) = @_;
- my (%seen, @dirs);
- my $tmp = File::Temp->newdir("lei_xsearch_git.$$-XXXX", TMPDIR => 1);
- for my $ibxish (locals($self)) {
- my $d = File::Spec->canonpath($ibxish->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) = @_;
if (my $lxs = delete $lei->{lxs}) {
$lxs->wq_wait_old(\&xsearch_done_wait, $lei);
}
+ my $wait = $lei->{sto} ? $lei->{sto}->ipc_do('done') : undef;
$lei->{ovv}->ovv_end($lei);
if ($l2m) { # close() calls LeiToMail reap_compress
if (my $out = delete $lei->{old_1}) {
$nl + $nr;
}
-sub start_query { # always runs in main (lei-daemon) process
- my ($self) = @_;
- if ($self->{threads}) {
+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_io_do('query_thread_mset', [], $ibxish);
+ $self->wq_io_do('query_one_mset', [], $ibxish);
}
} elsif (locals($self)) {
- $self->wq_io_do('query_mset', []);
+ $self->wq_io_do('query_combined_mset', []);
}
my $i = 0;
my $q = [];
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);
+ start_query($self, $l2m);
}
sub ipc_atfork_child {
my ($self) = @_;
- $self->{lei}->lei_atfork_child;
+ $self->{lei}->_lei_atfork_child;
$SIG{__WARN__} = PublicInbox::Eml::warn_ignore_cb();
$self->SUPER::ipc_atfork_child;
}
-sub delete_pkt_op { # OnDestroy callback
- my $unclosed_after_die = delete($_[0])->{pkt_op_p} or return;
- close $unclosed_after_die;
-}
-
sub do_query {
my ($self, $lei) = @_;
my $l2m = $lei->{l2m};
'incr_start_query' => [ \&incr_start_query, $self, $l2m ],
};
$lei->{auth}->op_merge($ops, $l2m) if $l2m && $lei->{auth};
- my $od = PublicInbox::OnDestroy->new($$, \&delete_pkt_op, $lei);
- ($lei->{pkt_op_c}, $lei->{pkt_op_p}) = PublicInbox::PktOp->pair($ops);
+ 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) {
$l2m->pre_augment($lei);
if ($lei->{opt}->{augment} && delete $lei->{early_mua}) {
# 1031: F_SETPIPE_SZ
fcntl($lei->{startq}, 1031, 4096) if $^O eq 'linux';
}
- if (!$lei->{opt}->{threads} && locals($self)) { # for query_mset
- # lei->{git_tmp} is set for wq_wait_old so we don't
- # delete until all lei2mail + lei_xsearch workers are reaped
- $lei->{git_tmp} = $self->{git_tmp} = git_tmp($self);
- }
$self->wq_workers_start('lei_xsearch', undef,
$lei->oldset, { lei => $lei });
- my $op = delete $lei->{pkt_op_c};
+ my $op_c = delete $lei->{pkt_op_c};
delete $lei->{pkt_op_p};
- $self->{threads} = $lei->{opt}->{threads};
+ @$end = ();
+ $self->{opt_threads} = $lei->{opt}->{threads};
+ $self->{opt_sort} = $lei->{opt}->{'sort'};
if ($l2m) {
$l2m->net_merge_complete unless $lei->{auth};
} else {
start_query($self);
}
$lei->event_step_init; # wait for shutdowns
- if ($lei->{oneshot}) {
- while ($op->{sock}) { $op->event_step }
- }
+ $op_c->op_wait_event($ops);
}
sub add_uri {