use PublicInbox::Spawn qw(popen_rd spawn which);
use PublicInbox::MID qw(mids);
use PublicInbox::Smsg;
+use PublicInbox::AutoReap;
use PublicInbox::Eml;
+use PublicInbox::LEI;
use Fcntl qw(SEEK_SET F_SETFL O_APPEND O_RDWR);
use PublicInbox::ContentHash qw(git_sha);
+use POSIX qw(strftime);
sub new {
my ($class) = @_;
sub attach_external {
my ($self, $ibxish) = @_; # ibxish = ExtSearch or Inbox
my $desc = $ibxish->{inboxdir} // $ibxish->{topdir};
- my $srch = $ibxish->search or
+ my $srch = $ibxish->search //
return warn("$desc not indexed for Xapian ($@ $!)\n");
my @shards = $srch->xdb_shards_flat or
return warn("$desc has no Xapian shards\n");
sub over {}
+sub _check_mset_limit ($$$) {
+ my ($lei, $desc, $mset) = @_;
+ return if defined($lei->{opt}->{limit}); # user requested limit
+ my $est = $mset->get_matches_estimated;
+ my $tot = $lei->{mset_opt}->{total};
+ $est > $tot and $lei->qerr(<<"");
+# $desc estimated matches ($est) exceeds default --limit=$tot
+
+}
+
sub _mset_more ($$) {
my ($mset, $mo) = @_;
my $size = $mset->size;
- $size >= $mo->{limit} && (($mo->{offset} += $size) < $mo->{limit});
+ $size >= $mo->{limit} && (($mo->{offset} += $size) < $mo->{total});
}
# $startq will EOF when do_augment is done augmenting and allow
my ($srch, $over) = ($ibxish->search, $ibxish->over);
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);
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 $lss = $lei->{lss};
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=$stop_at: @e") if @e;
+ ref($stop_at) and
+ return warn("$maxk=$stop_at has multiple values\n");
+ ($stop_at =~ /[^0-9]/) and
+ return warn("$maxk=$stop_at not numeric\n");
}
my $first_ids;
do {
$mset = $srch->mset($mo->{qstr}, $mo);
- mset_progress($lei, $dir, $mset->size,
+ mset_progress($lei, $dir, $mo->{offset} + $mset->size,
$mset->get_matches_estimated);
wait_startq($lei); # wait for keyword updates
my $ids = $srch->mset_to_artnums($mset, $mo);
}
}
} while (_mset_more($mset, $mo));
+ _check_mset_limit($lei, $dir, $mset);
if ($lss && scalar(@$first_ids)) {
undef $stop_at;
my $max = $first_ids->[0];
my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei);
do {
$mset = $self->mset($mo->{qstr}, $mo);
- mset_progress($lei, 'xsearch', $mset->size,
+ mset_progress($lei, 'xsearch', $mo->{offset} + $mset->size,
$mset->get_matches_estimated);
wait_startq($lei); # wait for keyword updates
for my $mitem ($mset->items) {
$each_smsg->($smsg, $mitem);
}
} while (_mset_more($mset, $mo));
+ _check_mset_limit($lei, 'xsearch', $mset);
undef $each_smsg; # may commit
$lei->{ovv}->ovv_atexit_child($lei);
}
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;
- $smsg->{kw} = []; # short-circuit xsmsg_vmd
- }
+ my ($res, $kw) = $self->{import_sto}->wq_do('add_eml', $eml);
+ $smsg = $res if ref($res) eq ref($smsg); # totally new message
+ $smsg->{kw} = $kw; # short-circuit xsmsg_vmd
}
- $smsg->{blob} //= $xoids ? (keys(%$xoids))[0] : $lei->git_blob_id($eml);
+ $smsg->{blob} //= $xoids ? (keys(%$xoids))[0]
+ : $lei->git_oid($eml)->hexdigest;
_smsg_fill($smsg, $eml);
wait_startq($lei);
if ($lei->{-progress}) {
$each_smsg->($smsg, undef, $eml);
}
+sub fudge_qstr_time ($$$) {
+ my ($lei, $uri, $qstr) = @_;
+ return ($qstr, undef) unless $lei->{lss};
+ my $cfg = $lei->{lss}->{-cfg} // die 'BUG: no lss->{-cfg}';
+ my $cfg_key = "external.$uri.lastresult";
+ my $lr = $cfg->{$cfg_key} or return ($qstr, $cfg_key);
+ if ($lr !~ /\A\-?[0-9]+\z/) {
+ $lei->child_error(0,
+ "$cfg->{-f}: $cfg_key=$lr not an integer, ignoring");
+ return ($qstr, $cfg_key);
+ }
+ my $rft = $lei->{opt}->{'remote-fudge-time'};
+ if ($rft && $rft !~ /\A-?[0-9]+\z/) {
+ my @t = $lei->{lss}->git->date_parse($rft);
+ my $diff = time - $t[0];
+ $lei->qerr("# $rft => $diff seconds");
+ $rft = $diff;
+ }
+ $lr -= ($rft || (48 * 60 * 60));
+ $lei->qerr("# $uri limiting to ".
+ strftime('%Y-%m-%d %k:%M %z', localtime($lr)). ' and newer');
+ # this should really be rt: (received-time), but no stable
+ # public-inbox releases support it, yet.
+ my $dt = 'dt:'.strftime('%Y%m%d%H%M%S', gmtime($lr)).'..';
+ if ($qstr =~ /\S/) {
+ substr($qstr, 0, 0, '(');
+ $qstr .= ') AND ';
+ }
+ ($qstr .= $dt, $cfg_key);
+}
+
sub query_remote_mboxrd {
my ($self, $uris) = @_;
local $0 = "$0 query_remote_mboxrd";
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 = (x => 'm');
push(@qform, t => 1) if $opt->{threads};
my $verbose = $opt->{verbose};
- my ($reap_tail, $reap_curl);
+ my $reap_tail;
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');
+ my $rdr = { 2 => $cerr };
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 $o = { 1 => $lei->{2}, 2 => $lei->{2} };
my $pid = spawn(['tail', '-f', $cerr->filename], undef, $o);
- $reap_tail = PublicInbox::OnDestroy->new($sigint_reap, $pid);
+ $reap_tail = PublicInbox::AutoReap->new($pid);
}
my $curl = PublicInbox::LeiCurl->new($lei, $self->{curl}) or return;
push @$curl, '-s', '-d', '';
for my $uri (@$uris) {
$lei->{-current_url} = $uri->as_string;
$lei->{-nr_remote_eml} = 0;
- $uri->query_form(@qform);
+ my $start = time;
+ my ($q, $key) = fudge_qstr_time($lei, $uri, $qstr);
+ $uri->query_form(@qform, q => $q);
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);
+ my $reap_curl = PublicInbox::AutoReap->new($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');
- }
+ my $wait = $lei->{sto}->wq_do('done') if $nr && $lei->{sto};
+ $reap_curl->join;
if ($? == 0) {
+ # don't update if no results, maybe MTA is down
+ $key && $nr and
+ $lei->{lss}->cfg_set($key, $start);
mset_progress($lei, $lei->{-current_url}, $nr, $nr);
next;
}
- $err = '';
+ my $err;
if (-s $cerr) {
- seek($cerr, 0, SEEK_SET) or
- $lei->err("seek($cmd stderr): $!");
+ seek($cerr, 0, SEEK_SET) //
+ warn "seek($cmd stderr): $!";
$err = do { local $/; <$cerr> } //
- "read($cmd stderr): $!";
- truncate($cerr, 0) or
- $lei->err("truncate($cmd stderr): $!");
+ warn "read($cmd stderr): $!";
+ truncate($cerr, 0) // warn "truncate($cmd stderr): $!";
}
+ $err //= '';
next if (($? >> 8) == 22 && $err =~ /\b404\b/);
- $uri->query_form(q => $lei->{mset_opt}->{qstr});
+ $uri->query_form(q => $qstr);
$lei->child_error($?, "E: <$uri> $err");
}
undef $each_smsg;
sub query_done { # EOF callback for main daemon
my ($lei) = @_;
+ local $PublicInbox::LEI::current_lei = $lei;
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}) {
+ ($lei->{opt}->{'mail-sync'} && !$lei->{sto}) and
warn "BUG: {sto} missing with --mail-sync";
- }
$lei->sto_done_request if $lei->{sto};
- my $wait = $lei->{v2w} ? $lei->{v2w}->ipc_do('done') : undef;
+ my $wait = $lei->{v2w} ? $lei->{v2w}->wq_do('done') : undef;
$lei->{ovv}->ovv_end($lei);
my $start_mua;
if ($l2m) { # close() calls LeiToMail reap_compress
if ($lei->{-progress}) {
my $tot = $lei->{-mset_total} // 0;
my $nr = $lei->{-nr_write} // 0;
- $lei->qerr($l2m ?
- "# $nr written to $lei->{ovv}->{dst} ($tot matches)" :
- "# $tot matches");
+ 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) = @_;
+ local $PublicInbox::LEI::current_lei = $lei;
my $l2m = $lei->{l2m} or return; # client disconnected
$lei->fchdir or return;
my $err;
$err = $@;
if ($err) {
if (my $lxs = delete $lei->{lxs}) {
- $lxs->wq_kill;
+ $lxs->wq_kill('-TERM');
$lxs->wq_close(0, undef, $lei);
}
$lei->fail("$err");
$nl + $nr;
}
-sub start_query ($;$) { # always runs in main (lei-daemon) process
- my ($self, $l2m) = @_;
- if ($self->{opt_threads} || ($l2m && !$self->{opt_sort})) {
+sub start_query ($$) { # always runs in main (lei-daemon) process
+ my ($self, $lei) = @_;
+ local $PublicInbox::LEI::current_lei = $lei;
+ if ($self->{opt_threads} || ($lei->{l2m} && !$self->{opt_sort})) {
for my $ibxish (locals($self)) {
$self->wq_io_do('query_one_mset', [], $ibxish);
}
}
sub incr_start_query { # called whenever an l2m shard starts do_post_auth
- my ($self, $l2m) = @_;
+ my ($self, $lei) = @_;
+ my $l2m = $lei->{l2m};
return if ++$self->{nr_start_query} != $l2m->{-wq_nr_workers};
- start_query($self, $l2m);
+ start_query($self, $lei);
}
sub ipc_atfork_child {
my ($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 ],
+ 'sigpipe_handler' => [ $lei ],
+ 'fail_handler' => [ $lei ],
+ 'do_post_augment' => [ \&do_post_augment, $lei ],
+ 'incr_post_augment' => [ \&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 ],
+ 'x_it' => [ $lei ],
+ 'child_error' => [ $lei ],
+ 'incr_start_query' => [ $self, $lei ],
};
$lei->{auth}->op_merge($ops, $l2m) if $l2m && $lei->{auth};
my $end = $lei->pkt_op_pair;
@$end = ();
$self->{opt_threads} = $lei->{opt}->{threads};
$self->{opt_sort} = $lei->{opt}->{'sort'};
- $self->{-do_lcat} = $lei->{lcat_blob} // $lei->{lcat_fid};
+ $self->{-do_lcat} = !!(delete $lei->{lcat_todo});
if ($l2m) {
- $l2m->net_merge_all_done unless $lei->{auth};
+ $l2m->net_merge_all_done($lei) unless $lei->{auth};
} else {
- start_query($self);
+ start_query($self, $lei);
}
$lei->event_step_init; # wait for shutdowns
$lei->wait_wq_events($op_c, $ops);
die "`\\n' not allowed in `$loc'\n" if index($loc, "\n") >= 0;
require PublicInbox::Inbox; # v2, v1
$loc = bless { inboxdir => $loc }, 'PublicInbox::Inbox';
+ } elsif (!-e $loc) {
+ warn "W: $loc gone, perhaps run: lei forget-external $loc\n";
+ return;
} else {
- warn "W: ignoring $loc, unable to determine type\n";
+ warn "W: $loc ignored, unable to determine external type\n";
return;
}
push @{$self->{locals}}, $loc;
}
}
-sub lcat_dump {
+sub lcat_dump { # via wq_io_do
my ($self) = @_;
my $lei = $self->{lei};
my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei);
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);
+ my $lms;
+ for my $ent (@{$lei->{lcat_todo}}) {
+ if (ref $ent eq 'HASH') { # { fid => $fid ,.. }
+ $lms //= $lei->{lse}->lms;
+ $lms->each_src($ent, \&_lcat_i, $each_smsg);
+ } else { # oidhex
+ $each_smsg->({ blob => $ent, pct => 100 });
}
}
$git->async_wait_all;