From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <e@80x24.org>
X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net
X-Spam-Level: 
X-Spam-Status: No, score=-4.0 required=3.0 tests=ALL_TRUSTED,AWL,BAYES_00
	shortcircuit=no autolearn=ham autolearn_force=no version=3.4.2
Received: from localhost (dcvr.yhbt.net [127.0.0.1])
	by dcvr.yhbt.net (Postfix) with ESMTP id F102F20083
	for <meta@public-inbox.org>; Tue, 27 Oct 2020 07:54:56 +0000 (UTC)
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 21/52] searchidx: xref3 delete support
Date: Tue, 27 Oct 2020 07:54:22 +0000
Message-Id: <20201027075453.19163-22-e@80x24.org>
In-Reply-To: <20201027075453.19163-1-e@80x24.org>
References: <20201027075453.19163-1-e@80x24.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
List-Id: <meta.public-inbox.org>

Not yet tested, but Perl compiles it!
---
 lib/PublicInbox/SearchIdx.pm | 50 ++++++++++++++++++++++--------------
 1 file changed, 31 insertions(+), 19 deletions(-)

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 5171c610..0458d9c3 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -472,29 +472,41 @@ sub remove_xref3 {
 	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' . $_);
 	}
-	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.
+	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);
 	}
-	$self->{xdb}->replace_document($docid, $doc);
 }
 
 sub get_val ($$) {