X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FV2Writable.pm;h=edb8ba570f0ae2e9a6a127d2e778160a8b68a255;hb=0c8106d44f317175e122744b43407bf067183175;hp=2b849ddffb0d1221a1d20a2829823174f7cb0d4a;hpb=e8d6c34c749d1b0fd1dc1278cd4a2a310b31a9ac;p=public-inbox.git

diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
index 2b849ddf..edb8ba57 100644
--- a/lib/PublicInbox/V2Writable.pm
+++ b/lib/PublicInbox/V2Writable.pm
@@ -24,7 +24,7 @@ use File::Temp ();
 
 my $OID = qr/[a-f0-9]{40,}/;
 # an estimate of the post-packed size to the raw uncompressed size
-my $PACKING_FACTOR = 0.4;
+our $PACKING_FACTOR = 0.4;
 
 # SATA storage lags behind what CPUs are capable of, so relying on
 # nproc(1) can be misleading and having extra Xapian shards is a
@@ -73,13 +73,7 @@ sub count_shards ($) {
 		delete $ibx->{search};
 		$srch->{nshard} // 0
 	} else { # ExtSearchIdx
-		$self->{nshard} // do {
-			if ($self->xdb_sharded) {
-				$self->{nshard} // die 'BUG: {nshard} unset';
-			} else {
-				0;
-			}
-		}
+		$self->{nshard} ||= scalar($self->xdb_shards_flat);
 	}
 }
 
@@ -879,7 +873,7 @@ sub reindex_checkpoint ($$) {
 		$self->done; # release lock
 	}
 
-	if (my $pr = $sync->{-opt}->{-progress}) {
+	if (my $pr = $sync->{-regen_fmt} ? $sync->{-opt}->{-progress} : undef) {
 		$pr->(sprintf($sync->{-regen_fmt}, ${$sync->{nr}}));
 	}
 
@@ -891,12 +885,22 @@ sub reindex_checkpoint ($$) {
 	$mm_tmp->atfork_parent if $mm_tmp;
 }
 
+sub index_finalize ($$) {
+	my ($arg, $index) = @_;
+	++$arg->{self}->{nidx};
+	if (defined(my $cur = $arg->{cur_cmt})) {
+		${$arg->{latest_cmt}} = $cur;
+	} elsif ($index) {
+		die 'BUG: {cur_cmt} missing';
+	} # else { unindexing @leftovers doesn't set {cur_cmt}
+}
+
 sub index_oid { # cat_async callback
 	my ($bref, $oid, $type, $size, $arg) = @_;
-	return if is_bad_blob($oid, $type, $size, $arg->{oid});
+	is_bad_blob($oid, $type, $size, $arg->{oid}) and
+		return index_finalize($arg, 1); # size == 0 purged returns here
 	my $self = $arg->{self};
 	local $self->{current_info} = "$self->{current_info} $oid";
-	return if $size == 0; # purged
 	my ($num, $mid0);
 	my $eml = PublicInbox::Eml->new($$bref);
 	my $mids = mids($eml);
@@ -967,7 +971,7 @@ sub index_oid { # cat_async callback
 	if (do_idx($self, $bref, $eml, $smsg)) {
 		${$arg->{need_checkpoint}} = 1;
 	}
-	${$arg->{latest_cmt}} = $arg->{cur_cmt} // die 'BUG: {cur_cmt} missing';
+	index_finalize($arg, 1);
 }
 
 # only update last_commit for $i on reindex iff newer than current
@@ -1094,12 +1098,14 @@ sub sync_prepare ($$) {
 		-d $git_dir or next; # missing epochs are fine
 		my $git = PublicInbox::Git->new($git_dir);
 		my $unit = { git => $git, epoch => $i };
+		my $tip;
 		if ($reindex_heads) {
-			$head = $reindex_heads->[$i] or next;
+			$tip = $head = $reindex_heads->[$i] or next;
+		} else {
+			$tip = $git->qx(qw(rev-parse -q --verify), $head);
+			next if $?; # new repo
+			chomp $tip;
 		}
-		chomp(my $tip = $git->qx(qw(rev-parse -q --verify), $head));
-		next if $?; # new repo
-
 		my $range = log_range($sync, $unit, $tip) or next;
 		# can't use 'rev-list --count' if we use --diff-filter
 		$pr->("$pfx $i.git counting $range ... ") if $pr;
@@ -1157,11 +1163,12 @@ sub unindex_oid_aux ($$$) {
 }
 
 sub unindex_oid ($$;$) { # git->cat_async callback
-	my ($bref, $oid, $type, $size, $sync) = @_;
-	return if is_bad_blob($oid, $type, $size, $sync->{oid});
-	my $self = $sync->{self};
+	my ($bref, $oid, $type, $size, $arg) = @_;
+	is_bad_blob($oid, $type, $size, $arg->{oid}) and
+		return index_finalize($arg, 0);
+	my $self = $arg->{self};
 	local $self->{current_info} = "$self->{current_info} $oid";
-	my $unindexed = $sync->{in_unindex} ? $sync->{unindexed} : undef;
+	my $unindexed = $arg->{in_unindex} ? $arg->{unindexed} : undef;
 	my $mm = $self->{mm};
 	my $mids = mids(PublicInbox::Eml->new($bref));
 	undef $$bref;
@@ -1186,6 +1193,7 @@ sub unindex_oid ($$;$) { # git->cat_async callback
 		}
 		unindex_oid_aux($self, $oid, $mid);
 	}
+	index_finalize($arg, 0);
 }
 
 sub git { $_[0]->{ibx}->git }