From 472d39de46603b180ab6e739e0b31ab7ef559870 Mon Sep 17 00:00:00 2001
From: Eric Wong <e@80x24.org>
Date: Tue, 1 Mar 2016 03:44:04 +0000
Subject: linkify: do not capture trailing '.' or ';' in URLs

It seems common for users to end statements with URLs,
while it is rare for a URL itself to end with a '.' or ';'.
So make a guess and assume the URL was intended to not
include the trailing '.' or ';'
---
 MANIFEST                   |  1 +
 lib/PublicInbox/Linkify.pm | 10 +++++++++-
 t/linkify.t                | 26 ++++++++++++++++++++++++++
 3 files changed, 36 insertions(+), 1 deletion(-)
 create mode 100644 t/linkify.t

diff --git a/MANIFEST b/MANIFEST
index 5d790f9c..259f42ce 100644
--- a/MANIFEST
+++ b/MANIFEST
@@ -80,6 +80,7 @@ t/httpd-corner.psgi
 t/httpd-corner.t
 t/httpd.t
 t/init.t
+t/linkify.t
 t/main-bin/spamc
 t/mda.t
 t/msgmap.t
diff --git a/lib/PublicInbox/Linkify.pm b/lib/PublicInbox/Linkify.pm
index 8f634f48..4eddedd0 100644
--- a/lib/PublicInbox/Linkify.pm
+++ b/lib/PublicInbox/Linkify.pm
@@ -25,6 +25,14 @@ sub linkify_1 {
 	my ($self, $s) = @_;
 	$s =~ s!$LINK_RE!
 		my $url = $1;
+		my $end = '';
+
+		# it's fairly common to end URLs in messages with
+		# '.' or ';' to denote the end of a statement.
+		if ($url =~ s/(\.)\z// || $url =~ s/(;)\z//) {
+			$end = $1;
+		}
+
 		# salt this, as this could be exploited to show
 		# links in the HTML which don't show up in the raw mail.
 		my $key = sha1_hex($url . $SALT);
@@ -32,7 +40,7 @@ sub linkify_1 {
 		# only escape ampersands, others do not match LINK_RE
 		$url =~ s/&/&#38;/g;
 		$self->{$key} = $url;
-		'PI-LINK-'. $key;
+		'PI-LINK-'. $key . $end;
 	!ge;
 	$s;
 }
diff --git a/t/linkify.t b/t/linkify.t
new file mode 100644
index 00000000..586691ae
--- /dev/null
+++ b/t/linkify.t
@@ -0,0 +1,26 @@
+# Copyright (C) 2016 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
+use strict;
+use warnings;
+use Test::More;
+use PublicInbox::Linkify;
+
+{
+	my $l = PublicInbox::Linkify->new;
+	my $u = 'http://example.com/url-with-trailing-period';
+	my $s = $u . '.';
+	$s = $l->linkify_1($s);
+	$s = $l->linkify_2($s);
+	is($s, qq(<a\nhref="$u">$u</a>.), 'trailing period not in URL');
+}
+
+{
+	my $l = PublicInbox::Linkify->new;
+	my $u = 'http://example.com/url-with-trailing-semicolon';
+	my $s = $u . ';';
+	$s = $l->linkify_1($s);
+	$s = $l->linkify_2($s);
+	is($s, qq(<a\nhref="$u">$u</a>;), 'trailing semicolon not in URL');
+}
+
+done_testing();
-- 
cgit v1.2.3-24-ge0c7