From: Eric Wong <e@yhbt.net>
Date: Thu, 23 Jan 2020 23:05:59 +0000 (+0000)
Subject: contentid: ignore duplicate References: headers
X-Git-Tag: v1.3.0~83
X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=commitdiff_plain;h=2a56039ff6a6a8d0b04437b5463c172ecab002c5

contentid: ignore duplicate References: headers

OverIdx::parse_references already skips duplicate
References (which we use in SearchThread for rendering).
So there's no reason for our content deduplication logic
to care if a Message-Id in the Reference header is mentioned
twice.
---

diff --git a/lib/PublicInbox/ContentId.pm b/lib/PublicInbox/ContentId.pm
index 0c4a8678..65691593 100644
--- a/lib/PublicInbox/ContentId.pm
+++ b/lib/PublicInbox/ContentId.pm
@@ -64,8 +64,7 @@ sub content_digest ($) {
 	# if we got here, we've already got Message-ID reuse
 	my %seen = map { $_ => 1 } @{mids($hdr)};
 	foreach my $mid (@{references($hdr)}) {
-		next if $seen{$mid};
-		$dig->add("ref\0$mid\0");
+		$dig->add("ref\0$mid\0") unless $seen{$mid}++;
 	}
 
 	# Only use Sender: if From is not present
diff --git a/lib/PublicInbox/OverIdx.pm b/lib/PublicInbox/OverIdx.pm
index 189bd21d..5f1007aa 100644
--- a/lib/PublicInbox/OverIdx.pm
+++ b/lib/PublicInbox/OverIdx.pm
@@ -230,8 +230,7 @@ sub parse_references ($$$) {
 			warn "References: <$ref> too long, ignoring\n";
 			next;
 		}
-		next if $seen{$ref}++;
-		push @keep, $ref;
+		push(@keep, $ref) unless $seen{$ref}++;
 	}
 	$smsg->{references} = '<'.join('> <', @keep).'>' if @keep;
 	\@keep;