From dfe55f5ee5bd6e3a12d933a6570eb94f294d1c54 Mon Sep 17 00:00:00 2001
From: Eric Wong <e@80x24.org>
Date: Thu, 18 Aug 2016 02:02:50 +0000
Subject: linkify: be stricter about matching RFC 3986

We're not to-the-letter about percent-encoding, but
we should allow all the characters.  This is mainly
so we can effectively use the link to some Wikipedia
pages with parentheses in them:

	https://en.wikipedia.org/wiki/Atom_(standard)
	https://en.wikipedia.org/wiki/Git_(software)
---
 lib/PublicInbox/Linkify.pm | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'lib/PublicInbox')

diff --git a/lib/PublicInbox/Linkify.pm b/lib/PublicInbox/Linkify.pm
index d4df689e..ea7fd71f 100644
--- a/lib/PublicInbox/Linkify.pm
+++ b/lib/PublicInbox/Linkify.pm
@@ -17,7 +17,10 @@ use Digest::SHA qw/sha1_hex/;
 my $SALT = rand;
 my $LINK_RE = qr{\b((?:ftps?|https?|nntps?|gopher)://
 		 [\@:\w\.-]+/
-		 ?[!,:~\$\@\w\+\&\?\.\%\;/#=-]*)}x;
+		 (?:[a-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@/%]*)
+		 (?:\?[a-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@/%]+)?
+		 (?:\#[a-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@/%\?]+)?
+		 )}xi;
 
 sub new { bless {}, shift }
 
-- 
cgit v1.2.3-24-ge0c7