From: Eric Wong <e@80x24.org>
Date: Sat, 10 Dec 2016 01:09:46 +0000 (+0000)
Subject: search: favor In-Reply-To over last References iff IRT exists
X-Git-Tag: v1.0.0~150
X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=commitdiff_plain;h=86c018672f6bf9739a76489c8870c151d338fc15

search: favor In-Reply-To over last References iff IRT exists

Some email clients set the References headers backwards, so
trust the In-Reply-To header if (and only if) it exists and
is parseable as direct parent of the current message.

For affected repos, this will require reindexing (via
"public-inbox-index --reindex"), but there will be no
version bump for this bugfix.
---

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 4aac0281..832d1cbf 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -293,10 +293,10 @@ sub link_message {
 	my $hdr = $mime->header_obj;
 	my $refs = $hdr->header_raw('References');
 	my @refs = $refs ? ($refs =~ /<([^>]+)>/g) : ();
-	if (my $irt = $hdr->header_raw('In-Reply-To')) {
-		# last References should be $irt
-		# we will de-dupe later
-		push @refs, mid_clean($irt);
+	my $irt = $hdr->header_raw('In-Reply-To');
+	if (defined $irt) {
+		$irt = mid_clean($irt);
+		$irt = undef if $mid eq $irt;
 	}
 
 	my $tid;
@@ -305,6 +305,15 @@ sub link_message {
 		my @orig_refs = @refs;
 		@refs = ();
 
+		if (defined $irt) {
+			# to check MAX_MID_SIZE
+			push @orig_refs, $irt;
+
+			# below, we will ensure IRT (if specified)
+			# is the last References
+			$uniq{$irt} = 1;
+		}
+
 		# prevent circular references via References: here:
 		foreach my $ref (@orig_refs) {
 			if (length($ref) > MAX_MID_SIZE) {
@@ -315,6 +324,11 @@ sub link_message {
 			push @refs, $ref;
 		}
 	}
+
+	# last References should be IRT, but some mail clients do things
+	# out of order, so trust IRT over References iff IRT exists
+	push @refs, $irt if defined $irt;
+
 	if (@refs) {
 		$smsg->{references} = '<'.join('> <', @refs).'>';