use v5.10.1;
use parent qw(PublicInbox::LeiSearch PublicInbox::IPC);
use PublicInbox::DS qw(now);
-use PublicInbox::PktOp qw(pkt_do);
use File::Temp 0.19 (); # 0.19 for ->newdir
use File::Spec ();
use PublicInbox::Search qw(xap_terms);
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 shards\n");
# called by PublicInbox::Search::xdb (usually via ->mset)
sub xdb_shards_flat { @{$_[0]->{shards_flat} // []} }
-sub mitem_kw ($$;$) {
- my ($smsg, $mitem, $flagged) = @_;
- my $kw = xap_terms('K', $mitem->get_document);
+sub _mitem_kw { # retry_reopen callback
+ my ($srch, $smsg, $mitem, $flagged) = @_;
+ my $doc = $mitem->get_document;
+ my $kw = xap_terms('K', $doc);
$kw->{flagged} = 1 if $flagged;
+ my @L = xap_terms('L', $doc);
+ # we keep the empty {kw} array here to prevent expensive work in
+ # ->xsmsg_vmd, _unbless_smsg will clobber it iff it's empty
$smsg->{kw} = [ sort keys %$kw ];
+ $smsg->{L} = \@L if scalar(@L);
+}
+
+sub mitem_kw ($$$;$) {
+ my ($srch, $smsg, $mitem, $flagged) = @_;
+ $srch->retry_reopen(\&_mitem_kw, $smsg, $mitem, $flagged);
}
# like over->get_art
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($self, $smsg, $mitem);
+ }
$smsg;
}
my ($self, $qstr, $opt) = @_;
$opt //= {};
$opt->{relevance} //= -2;
- $self->mset($qstr //= 'bytes:1..', $opt);
+ $self->mset($qstr //= 'z:1..', $opt);
}
sub over {}
}
# $startq will EOF when do_augment is done augmenting and allow
-# query_mset and query_thread_mset to proceed.
+# query_combined_mset and query_thread_mset to proceed.
sub wait_startq ($) {
my ($lei) = @_;
my $startq = delete $lei->{startq} or return;
my $lei = shift;
return if $lei->{early_mua} || !$lei->{-progress};
if ($lei->{pkt_op_p}) {
- pkt_do($lei->{pkt_op_p}, 'mset_progress', @_);
+ $lei->{pkt_op_p}->pkt_do('mset_progress', @_);
} else { # single lei-daemon consumer
my ($desc, $mset_size, $mset_total_est) = @_;
- $lei->{-mset_total} += $mset_size;
+ $lei->{-mset_total} += $mset_size if $mset_total_est ne '?';
$lei->qerr("# $desc $mset_size/$mset_total_est");
}
}
-sub query_thread_mset { # for --threads
+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_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);
+ 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 $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei);
my $can_kw = !!$ibxish->can('msg_keywords');
- my $fl = $lei->{opt}->{threads} > 1;
+ 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) {
- mitem_kw($smsg, $mitem, $fl);
- } else {
- $smsg->{kw} = [ 'flagged' ];
+ if ($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;
+ 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-"--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);
+ $mset->get_matches_estimated);
+ wait_startq($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) = @_;
- $lei->{sto}->ipc_do('add_eml', $eml) if $lei->{opt}->{'import-remote'};
- 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)};
+}
+
+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};
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);
local $SIG{TERM} = sub { exit(0) }; # for DESTROY (File::Temp, $reap)
my $lei = $self->{lei};
my $opt = $lei->{opt};
- my @qform = (q => $lei->{mset_opt}->{qstr}, x => 'm');
+ 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};
my ($reap_tail, $reap_curl);
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;
$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, $lei);
}
+ if ($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);
+ my $start_mua;
if ($l2m) { # close() calls LeiToMail reap_compress
if (my $out = delete $lei->{old_1}) {
if (my $mbout = $lei->{1}) {
$lei->poke_mua;
} else { # mbox users
delete $l2m->{mbl}; # drop dotlock
- $lei->start_mua;
+ $start_mua = 1;
+ }
+ }
+ if ($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->{-progress} and
- $lei->err('# ', $lei->{-mset_total} // 0, " matches");
+ $lei->start_mua if $start_mua;
$lei->dclose;
}
sub do_post_augment {
my ($lei) = @_;
my $l2m = $lei->{l2m} or return; # client disconnected
+ $lei->fchdir or return;
my $err;
eval { $l2m->post_augment($lei) };
$err = $@;
$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 = [];
for my $uris (@$q) {
$self->wq_io_do('query_remote_mboxrd', [], $uris);
}
+ if ($self->{-do_lcat}) {
+ $self->wq_io_do('lcat_dump', []);
+ }
$self->wq_close(1); # lei_xsearch workers stop when done
}
sub incr_start_query { # called whenever an l2m shard starts do_post_auth
my ($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;
- $SIG{__WARN__} = PublicInbox::Eml::warn_ignore_cb();
+ $self->{lei}->_lei_atfork_child;
$self->SUPER::ipc_atfork_child;
}
'+' => [ \&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 && $lei->{auth};
- ($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}) {
$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: $!";
- # 1031: F_SETPIPE_SZ
- fcntl($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);
+ fcntl($lei->{startq}, $F_SETPIPE_SZ, 4096) if $F_SETPIPE_SZ;
+ delete $l2m->{au_peers};
}
$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'};
+ $self->{-do_lcat} = $lei->{lcat_blob} // $lei->{lcat_fid};
if ($l2m) {
- $l2m->net_merge_complete unless $lei->{auth};
+ $l2m->net_merge_all_done unless $lei->{auth};
} else {
start_query($self);
}
$lei->event_step_init; # wait for shutdowns
- if ($lei->{oneshot}) {
- while ($op->{sock}) { $op->event_step }
- }
+ $lei->wait_wq_events($op_c, $ops);
}
sub add_uri {
return add_uri($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;