From 1cb230c4d47c8ef5d03f0b8de2f8ad93c303d816 Mon Sep 17 00:00:00 2001
From: "Eric Wong (Contractor, The Linux Foundation)" <e@80x24.org>
Date: Sun, 1 Apr 2018 23:23:44 +0000
Subject: truncate Message-IDs and References consistently

We need to stop ghost messages from generating longer
Message-IDs than Xapian can handle with terms.
---
 lib/PublicInbox/MID.pm | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

(limited to 'lib/PublicInbox')

diff --git a/lib/PublicInbox/MID.pm b/lib/PublicInbox/MID.pm
index 117d3c42..c82e8401 100644
--- a/lib/PublicInbox/MID.pm
+++ b/lib/PublicInbox/MID.pm
@@ -65,12 +65,6 @@ sub mids ($) {
 			push(@mids, $v);
 		}
 	}
-	foreach my $i (0..$#mids) {
-		next if length($mids[$i]) <= MAX_MID_SIZE;
-		warn "Message-ID: <$mids[$i]> too long, truncating\n";
-		$mids[$i] = substr($mids[$i], 0, MAX_MID_SIZE);
-	}
-
 	uniq_mids(\@mids);
 }
 
@@ -92,10 +86,14 @@ sub uniq_mids ($) {
 	my ($mids) = @_;
 	my @ret;
 	my %seen;
-	foreach (@$mids) {
-		next if $seen{$_};
-		push @ret, $_;
-		$seen{$_} = 1;
+	foreach my $mid (@$mids) {
+		if (length($mid) > MAX_MID_SIZE) {
+			warn "Message-ID: <$mid> too long, truncating\n";
+			$mid = substr($mid, 0, MAX_MID_SIZE);
+		}
+		next if $seen{$mid};
+		push @ret, $mid;
+		$seen{$mid} = 1;
 	}
 	\@ret;
 }
-- 
cgit v1.2.3-24-ge0c7