use PublicInbox::Spawn qw(spawn nodatacow_dir);
use PublicInbox::Git qw(git_unquote);
use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp);
-our @EXPORT_OK = qw(crlf_adjust log2stack is_ancestor check_size prepare_stack);
+our @EXPORT_OK = qw(crlf_adjust log2stack is_ancestor check_size prepare_stack
+ index_text term_generator add_val);
my $X = \%PublicInbox::Search::X;
-my ($DB_CREATE_OR_OPEN, $DB_OPEN);
+our ($DB_CREATE_OR_OPEN, $DB_OPEN);
our $DB_NO_SYNC = 0;
our $BATCH_BYTES = $ENV{XAPIAN_FLUSH_THRESHOLD} ? 0x7fffffff : 1_000_000;
use constant DEBUG => !!$ENV{DEBUG};
$self->{term_generator} //= do {
my $tg = $X->{TermGenerator}->new;
- $tg->set_stemmer($self->stemmer);
+ $tg->set_stemmer(PublicInbox::Search::stemmer($self));
$tg;
}
}
if (defined(my $eidx_key = $smsg->{eidx_key})) {
$doc->add_boolean_term('O'.$eidx_key);
- $doc->add_boolean_term('P'.
- "$eidx_key:$smsg->{num}:$smsg->{blob}");
}
msg_iter($eml, \&index_xapian, [ $self, $doc ]);
index_ids($self, $doc, $eml, $mids);
}
}
-sub add_xref3 {
- my ($self, $docid, $xnum, $oid, $eidx_key, $eml) = @_;
+sub add_eidx_info {
+ my ($self, $docid, $oid, $eidx_key, $eml) = @_;
begin_txn_lazy($self);
my $doc = _get_doc($self, $docid, $oid) or return;
term_generator($self)->set_document($doc);
$doc->add_boolean_term('O'.$eidx_key);
- $doc->add_boolean_term('P'."$eidx_key:$xnum:$oid");
index_list_id($self, $doc, $eml);
$self->{xdb}->replace_document($docid, $doc);
}
-sub remove_xref3 {
+sub remove_eidx_info {
my ($self, $docid, $oid, $eidx_key, $eml) = @_;
begin_txn_lazy($self);
my $doc = _get_doc($self, $docid, $oid) or return;
- my $xref3 = PublicInbox::Smsg::xref3(undef, $doc);
- my %x3 = map { $_ => undef } @$xref3;
- for (grep(/\A\Q$eidx_key\E:[0-9]+:\Q$oid\E\z/, @$xref3)) {
- delete $x3{$_};
- $doc->remove_term('P' . $_);
- }
- if (scalar(keys(%x3)) == 0) {
- $self->{xdb}->delete_document($docid);
- if (my $del_fh = $self->{del_fh}) { # TODO
- print $del_fh $docid, "\n" or die "E: print $!";
- }
- } else {
- if (!grep(/\A\Q$eidx_key\E:/, keys %x3)) {
- $doc->remove_term('O'.$eidx_key);
- }
- for my $l ($eml->header_raw('List-Id')) {
- $l =~ /<([^>]+)>/ or next;
- my $lid = lc $1;
- $doc->remove_term('G' . $lid);
-
- # nb: we don't remove the XL probabilistic terms
- # since terms may overlap if cross-posted.
- #
- # IOW, a message which has both <foo.example.com>
- # and <bar.example.com> would have overlapping
- # "XLexample" and "XLcom" as terms and which we
- # wouldn't know if they're safe to remove if we just
- # unindex <foo.example.com> while preserving
- # <bar.example.com>.
- #
- # In any case, this entire sub is will likely never
- # be needed and users using the "l:" prefix are probably
- # rarer.
- }
- $self->{xdb}->replace_document($docid, $doc);
+ eval { $doc->remove_term('O'.$eidx_key) };
+ warn "W: ->remove_term O$eidx_key: $@\n" if $@;
+ for my $l ($eml->header_raw('List-Id')) {
+ $l =~ /<([^>]+)>/ or next;
+ my $lid = lc $1;
+ eval { $doc->remove_term('G' . $lid) };
+ warn "W: ->remove_term G$lid: $@\n" if $@;
+
+ # nb: we don't remove the XL probabilistic terms
+ # since terms may overlap if cross-posted.
+ #
+ # IOW, a message which has both <foo.example.com>
+ # and <bar.example.com> would have overlapping
+ # "XLexample" and "XLcom" as terms and which we
+ # wouldn't know if they're safe to remove if we just
+ # unindex <foo.example.com> while preserving
+ # <bar.example.com>.
+ #
+ # In any case, this entire sub is will likely never
+ # be needed and users using the "l:" prefix are probably
+ # rarer.
}
+ $self->{xdb}->replace_document($docid, $doc);
}
sub get_val ($$) {
$tmp{$_}++ for @removed;
}
if (!$nr) {
- $mids = join('> <', @$mids);
- warn "W: <$mids> missing for removal from overview\n";
+ my $m = join('> <', @$mids);
+ warn "W: <$m> missing for removal from overview\n";
}
while (my ($num, $nr) = each %tmp) {
warn "BUG: $num appears >1 times ($nr) for $oid\n" if $nr != 1;
$smsg->{num} = index_mm($self, $eml, $oid, $sync) or
die "E: could not generate NNTP article number for $oid";
add_message($self, $eml, $smsg, $sync);
+ my $cur_cmt = $sync->{cur_cmt} // die 'BUG: {cur_cmt} missing';
+ ${$sync->{latest_cmt}} = $cur_cmt;
}
sub unindex_both { # git->cat_async callback
- my ($bref, $oid, $type, $size, $self) = @_;
- unindex_eml($self, $oid, PublicInbox::Eml->new($bref));
+ my ($bref, $oid, $type, $size, $sync) = @_;
+ unindex_eml($sync->{sidx}, $oid, PublicInbox::Eml->new($bref));
+ # may be undef if leftover
+ if (defined(my $cur_cmt = $sync->{cur_cmt})) {
+ ${$sync->{latest_cmt}} = $cur_cmt;
+ }
}
sub with_umask {
my ($self, $sync, $stk) = @_;
$self->{ibx}->git->async_wait_all;
- # latest_cmt may be undef
- my $newest = $stk ? $stk->{latest_cmt} : undef;
- if ($newest) {
+ # $newest may be undef
+ my $newest = $stk ? $stk->{latest_cmt} : ${$sync->{latest_cmt}};
+ if (defined($newest)) {
my $cur = $self->{mm}->last_commit || '';
if (need_update($self, $cur, $newest)) {
$self->{mm}->last_commit($newest);
}
- } else {
- ${$sync->{max}} = $self->{batch_bytes};
}
+ ${$sync->{max}} = $self->{batch_bytes};
$self->{mm}->{dbh}->commit;
- if ($newest && need_xapian($self)) {
- my $xdb = $self->{xdb};
+ my $xdb = need_xapian($self) ? $self->{xdb} : undef;
+ if ($newest && $xdb) {
my $cur = $xdb->get_metadata('last_commit');
if (need_update($self, $cur, $newest)) {
$xdb->set_metadata('last_commit', $newest);
}
-
+ }
+ if ($stk) { # all done if $stk is passed
# let SearchView know a full --reindex was done so it can
# generate ->has_threadid-dependent links
- if ($sync->{reindex} && !ref($sync->{reindex})) {
+ if ($xdb && $sync->{reindex} && !ref($sync->{reindex})) {
my $n = $xdb->get_metadata('has_threadid');
$xdb->set_metadata('has_threadid', '1') if $n ne '1';
}
+ $self->{oidx}->rethread_done($sync->{-opt}); # all done
}
-
- $self->{oidx}->rethread_done($sync->{-opt}) if $newest; # all done
commit_txn_lazy($self);
$sync->{ibx}->git->cleanup;
my $nr = ${$sync->{nr}};
$sync->{nr} = \$nr;
$sync->{max} = \$max;
$sync->{sidx} = $self;
+ $sync->{latest_cmt} = \(my $latest_cmt);
$self->{mm}->{dbh}->begin_work;
if (my @leftovers = keys %{delete($sync->{D}) // {}}) {
warn('W: unindexing '.scalar(@leftovers)." leftovers\n");
for my $oid (@leftovers) {
$oid = unpack('H*', $oid);
- $git->cat_async($oid, \&unindex_both, $self);
+ $git->cat_async($oid, \&unindex_both, $sync);
}
}
if ($sync->{max_size} = $sync->{-opt}->{max_size}) {
$sync->{index_oid} = \&index_both;
}
- while (my ($f, $at, $ct, $oid) = $stk->pop_rec) {
+ while (my ($f, $at, $ct, $oid, $cur_cmt) = $stk->pop_rec) {
+ my $arg = { %$sync, cur_cmt => $cur_cmt };
if ($f eq 'm') {
- my $arg = { %$sync, autime => $at, cotime => $ct };
+ $arg->{autime} = $at;
+ $arg->{cotime} = $ct;
if ($sync->{max_size}) {
$git->check_async($oid, \&check_size, $arg);
} else {
}
v1_checkpoint($self, $sync) if $max <= 0;
} elsif ($f eq 'd') {
- $git->cat_async($oid, \&unindex_both, $self);
+ $git->cat_async($oid, \&unindex_both, $arg);
}
}
v1_checkpoint($self, $sync, $stk);
my $fh = $git->popen(qw(log --raw -r --pretty=tformat:%at-%ct-%H
--no-notes --no-color --no-renames --no-abbrev),
$range);
- my ($at, $ct, $stk);
+ my ($at, $ct, $stk, $cmt);
while (<$fh>) {
+ return if $sync->{quit};
if (/\A([0-9]+)-([0-9]+)-($OID)$/o) {
- ($at, $ct) = ($1 + 0, $2 + 0);
- $stk //= PublicInbox::IdxStack->new($3);
+ ($at, $ct, $cmt) = ($1 + 0, $2 + 0, $3);
+ $stk //= PublicInbox::IdxStack->new($cmt);
} elsif (/$del/) {
my $oid = $1;
if ($D) { # reindex case
$D->{pack('H*', $oid)}++;
} else { # non-reindex case:
- $stk->push_rec('d', $at, $ct, $oid);
+ $stk->push_rec('d', $at, $ct, $oid, $cmt);
}
} elsif (/$add/) {
my $oid = $1;
my $oid_bin = pack('H*', $oid);
my $nr = --$D->{$oid_bin};
delete($D->{$oid_bin}) if $nr <= 0;
-
# nr < 0 (-1) means it never existed
- $stk->push_rec('m', $at, $ct, $oid) if $nr < 0;
- } else {
- $stk->push_rec('m', $at, $ct, $oid);
+ next if $nr >= 0;
}
+ $stk->push_rec('m', $at, $ct, $oid, $cmt);
}
}
close $fh or die "git log failed: \$?=$?";