From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <e@80x24.org>
X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on dcvr.yhbt.net
X-Spam-Level: 
X-Spam-ASN:  
X-Spam-Status: No, score=-4.2 required=3.0 tests=ALL_TRUSTED,AWL,BAYES_00,
	DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,
	T_SCC_BODY_TEXT_LINE shortcircuit=no autolearn=ham autolearn_force=no
	version=3.4.6
Received: from localhost (dcvr.yhbt.net [127.0.0.1])
	by dcvr.yhbt.net (Postfix) with ESMTP id 370D61F452
	for <meta@public-inbox.org>; Wed,  3 May 2023 11:42:15 +0000 (UTC)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=80x24.org;
	s=selector1; t=1683114135;
	bh=JVvTTdZGNmRNZGiGuoILlZDhvnNfMKJcau6fBzVhLok=;
	h=From:To:Subject:Date:From;
	b=2EktpaVGJJVCp2X/f+5RehqLM2WyYXtwuMmeselbFqm9ZlWobNhehSGeXa51bNwVa
	 jYZLeDmED6yYF9l1oFTYKakXT0Mro7RgFblYRC0EUlymiqK8kc23YV7QXujxLSZcS9
	 jxneRQGFKj6Xvy8QwuifnnJMtYkzcFIyLTsJ9hzw=
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH] cindex: --prune + --exclude= drops repo information
Date: Wed,  3 May 2023 11:42:15 +0000
Message-Id: <20230503114215.3414226-1-e@80x24.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
List-Id: <meta.public-inbox.org>

--exclude= alone only prevents a coderepo from being indexed in
a particular invocation, but --prune will purge all traces of it
to ensure --update doesn't pick it up again w/o --exclude=
(unless --project-list= includes it).
---
 lib/PublicInbox/CodeSearchIdx.pm | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/lib/PublicInbox/CodeSearchIdx.pm b/lib/PublicInbox/CodeSearchIdx.pm
index 671134bf..d92d87fc 100644
--- a/lib/PublicInbox/CodeSearchIdx.pm
+++ b/lib/PublicInbox/CodeSearchIdx.pm
@@ -648,9 +648,7 @@ sub prune_do { # via wq_io_do in IDX_SHARDS
 	local $/ = "\0";
 	while (my $p = <$gone>) { # Q$cmt or P$git_dir
 		chomp $p;
-		my @docids = docids_by_postlist($self, $p) or warn <<EOM;
-W: no docids for `$p' [$self->{shard}]
-EOM
+		my @docids = docids_by_postlist($self, $p);
 		for (@docids) {
 			$TXN_BYTES -= $xdb->get_doclength($_) * 42;
 			$xdb->delete_document($_);
@@ -914,9 +912,13 @@ sub cidx_run { # main entry point
 		my $re = '(?:'.join('\\z|', map {
 				glob2re($_) // qr/\A\Q$_\E/
 			} @$excl).'\\z)';
+		my @excl;
 		@{$self->{git_dirs}} = grep {
-			$_ =~ /$re/ ? (warn("# excluding $_\n"), 0) : 1;
+			$_ =~ /$re/ ? (push(@excl, $_), 0) : 1;
 		} @{$self->{git_dirs}};
+		warn("# excluding $_\n") for @excl;
+		my %uniq; # List::Util::uniq requires Perl 5.26+
+		@GIT_DIR_GONE = grep { !$uniq{$_}++ } (@GIT_DIR_GONE, @excl);
 	}
 	local $NCHANGE = 0;
 	local $LIVE_JOBS = $self->{-opt}->{jobs} ||