From: Eric Wong <e@80x24.org>
Date: Mon, 2 Oct 2017 22:19:16 +0000 (+0000)
Subject: threading: deal with improperly-terminated References headers
X-Git-Tag: v1.0.0~24
X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=commitdiff_plain;h=2aa29ee6a35f5be2d76c39ccc50bf7a34075e2bd

threading: deal with improperly-terminated References headers

We should not blindly join References and In-Reply-To headers
as a single string, because some messages can have an open
angle brace '<' in References: without a corresponding '>'.
---

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 0824db03..cfb9a088 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -414,9 +414,8 @@ sub link_message {
 
 	# last References should be IRT, but some mail clients do things
 	# out of order, so trust IRT over References iff IRT exists
-	my @refs = ($hdr->header_raw('References'),
-			$hdr->header_raw('In-Reply-To'));
-	@refs = ((join(' ', @refs)) =~ /<([^>]+)>/g);
+	my @refs = (($hdr->header_raw('References') || '') =~ /<([^>]+)>/g);
+	push(@refs, (($hdr->header_raw('In-Reply-To') || '') =~ /<([^>]+)>/g));
 
 	my $tid;
 	if (@refs) {
diff --git a/lib/PublicInbox/View.pm b/lib/PublicInbox/View.pm
index 7454acbb..b39c8203 100644
--- a/lib/PublicInbox/View.pm
+++ b/lib/PublicInbox/View.pm
@@ -104,9 +104,8 @@ EOF
 sub in_reply_to {
 	my ($hdr) = @_;
 	my %mid = map { $_ => 1 } $hdr->header_raw('Message-ID');
-	my @refs = ($hdr->header_raw('References'),
-			$hdr->header_raw('In-Reply-To'));
-	@refs = ((join(' ', @refs)) =~ /<([^>]+)>/g);
+	my @refs = (($hdr->header_raw('References') || '') =~ /<([^>]+)>/g);
+	push(@refs, (($hdr->header_raw('In-Reply-To') || '') =~ /<([^>]+)>/g));
 	while (defined(my $irt = pop @refs)) {
 		next if $mid{"<$irt>"};
 		return $irt;