From: Eric Wong <e@80x24.org>
Date: Sat, 2 Oct 2021 11:18:34 +0000 (+0000)
Subject: content_hash: normalize whitespace before hashing addresses
X-Git-Tag: v1.7.0~226
X-Git-Url: http://www.git.stargrave.org/?a=commitdiff_plain;h=f28fdcd6d8d6ac36c7b6adf6670238426f3cc067;p=public-inbox.git

content_hash: normalize whitespace before hashing addresses

This should prevent some false duplicates.  I noticed this
while implementing "lei mail-diff", and only noticed it when
I implemented the ContentDigestDbg wrapper for mail-diff.
---

diff --git a/lib/PublicInbox/ContentHash.pm b/lib/PublicInbox/ContentHash.pm
index f6ae9011..bacc9cdd 100644
--- a/lib/PublicInbox/ContentHash.pm
+++ b/lib/PublicInbox/ContentHash.pm
@@ -20,6 +20,7 @@ use Digest::SHA;
 sub digest_addr ($$$) {
 	my ($dig, $h, $v) = @_;
 	$v =~ tr/"//d;
+	$v =~ tr/\r\n\t / /s;
 	$v =~ s/@([a-z0-9\_\.\-\(\)]*([A-Z])\S*)/'@'.lc($1)/ge;
 	utf8::encode($v);
 	$dig->add("$h\0$v\0");