use PublicInbox::Eml;
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 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 $can_kw = !!$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) {
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);
+ my $res = $self->{import_sto}->wq_do('add_eml', $eml);
if (ref($res) eq ref($smsg)) { # totally new message
$smsg = $res;
$smsg->{kw} = []; # short-circuit xsmsg_vmd
$each_smsg->($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("# $uri limiting to ".
+ strftime('%Y-%m-%d %k:%M', gmtime($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";
my $opt = $lei->{opt};
my $qstr = $lei->{mset_opt}->{qstr};
$qstr =~ s/[ \n\t]+/ /sg; # make URLs less ugly
- my @qform = (q => $qstr, x => 'm');
+ my @qform = (x => 'm');
push(@qform, t => 1) if $opt->{threads};
my $verbose = $opt->{verbose};
my ($reap_tail, $reap_curl);
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 = (); # 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 && $lei->{sto};
if ($? == 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;
}
$lei->err("truncate($cmd stderr): $!");
}
next if (($? >> 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;
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
@$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);
}
}
}
-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;