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 89AF51F87D
	for <meta@public-inbox.org>; Thu, 30 Nov 2023 11:41:11 +0000 (UTC)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=80x24.org;
	s=selector1; t=1701344471;
	bh=GZUJCgl5bykYVTchZhzLoFGMC/FRtDZRU5qiAq+0e/I=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=1VLZggQGOWHnPpjtkYrDClTc4S2Dv/Hk5WVEDh+JU9HX4Fmpwhe3x23q5E1pGSi0S
	 0F3BtFMMZ0Zksdy6yBaiXrYCgyknTkwPYehS9kX/avHKygv+4CQ2ojgzmvyWNd4na6
	 0PoSbe5lGjJ+sMS3Brw757GaPbCOyc3v1vaUAdhI=
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 15/15] codesearch: use retry_reopen for WWW
Date: Thu, 30 Nov 2023 11:41:08 +0000
Message-ID: <20231130114109.2577708-16-e@80x24.org>
In-Reply-To: <20231130114109.2577708-1-e@80x24.org>
References: <20231130114109.2577708-1-e@80x24.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
List-Id: <meta.public-inbox.org>

As with mail search, a cindex may be updated while WWW is
serving requests.  Thus we must reopen the Xapian DB when
the revision we're using becomes stale.
---
 lib/PublicInbox/CodeSearch.pm | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/lib/PublicInbox/CodeSearch.pm b/lib/PublicInbox/CodeSearch.pm
index f4694686..a2f4bae8 100644
--- a/lib/PublicInbox/CodeSearch.pm
+++ b/lib/PublicInbox/CodeSearch.pm
@@ -256,17 +256,22 @@ sub load_ct { # retry_reopen cb
 	}
 }
 
+sub load_ct { # retry_reopen cb
+	my ($self, $git_dir) = @_;
+	my @ids = docids_of_git_dir $self, $git_dir or return;
+	for (@ids) {
+		my $doc = $self->get_doc($_) // next;
+		return int_val($doc, CT);
+	}
+}
+
 sub load_commit_times { # each_cindex callback
 	my ($self, $todo) = @_; # todo = [ [ time, git ], [ time, git ] ...]
-	my (@pending, $rec, $dir, @ids, $doc);
+	my (@pending, $rec, $ct);
 	while ($rec = shift @$todo) {
-		@ids = docids_of_git_dir $self, $rec->[1]->{git_dir};
-		if (@ids) {
-			for (@ids) {
-				$doc = $self->get_doc($_) // next;
-				$rec->[0] = int_val($doc, CT);
-				last;
-			}
+		$ct = $self->retry_reopen(\&load_ct, $rec->[1]->{git_dir});
+		if (defined $ct) {
+			$rec->[0] = $ct;
 		} else { # may be in another cindex:
 			push @pending, $rec;
 		}
@@ -295,7 +300,7 @@ EOM
 			$git;
 		};
 	}
-	my $jd = join_data($self) or return warn <<EOM;
+	my $jd = $self->retry_reopen(\&join_data, $self) or return warn <<EOM;
 W: cindex.$name.topdir=$self->{topdir} has no usable join data for $cfg_f
 EOM
 	my ($ekeys, $roots, $ibx2root) = @$jd{qw(ekeys roots ibx2root)};
@@ -366,7 +371,7 @@ sub repos_sorted {
 	my @recs = map { [ 0, $_ ] } @_; # PublicInbox::Git objects
 	my @todo = @recs;
 	$pi_cfg->each_cindex(\&load_commit_times, \@todo);
-	@recs = sort { $b->[0] <=> $a->[0] } @recs;
+	@recs = sort { $b->[0] <=> $a->[0] } @recs; # sort by commit time
 }
 
 1;