From f46019039da6ac1596a4aef64b7bf394c743c1b1 Mon Sep 17 00:00:00 2001
From: "Eric Wong (Contractor, The Linux Foundation)" <e@80x24.org>
Date: Thu, 15 Feb 2018 00:25:53 +0000
Subject: address: extract more characters from email addresses

There's a lot of weird characters which show up in LKML archives
which we did not support before.  Furthermore, allow spaces
before the '>' in the From: line as at least some non-spam
poster used it.
---
 lib/PublicInbox/Address.pm | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'lib/PublicInbox/Address.pm')

diff --git a/lib/PublicInbox/Address.pm b/lib/PublicInbox/Address.pm
index f334adea..548f417c 100644
--- a/lib/PublicInbox/Address.pm
+++ b/lib/PublicInbox/Address.pm
@@ -8,7 +8,8 @@ use warnings;
 # just enough to make thing sanely displayable and pass to git
 
 sub emails {
-	($_[0] =~ /([\w\.\+=\-]+\@[\w\.\-]+)>?\s*(?:\(.*?\))?(?:,\s*|\z)/g)
+	($_[0] =~ /([\w\.\+=\?"\(\)\-!#\$%&'\*\/\^\`\|\{\}~]+\@[\w\.\-\(\)]+)
+		(?:\s[^>]*)?>?\s*(?:\(.*?\))?(?:,\s*|\z)/gx)
 }
 
 sub names {
-- 
cgit v1.2.3-24-ge0c7