linkify: support Internationalized Domain Names in URLs

The "\w" character class in Perl matches any word characters
in the Unicode database, not just ASCII characters.  So we
must be prepared for that and generate links to IDNs.

1 files changed, 12 insertions, 0 deletions

diff --git a/t/linkify.t b/t/linkify.t
index fe218b91..c4923582 100644
--- a/t/linkify.t
+++ b/t/linkify.t
@@ -132,4 +132,16 @@ use PublicInbox::Linkify;
                 'punctuation with unpaired ) OK')
 }
 
+if ('IDN example: <ACDB98F4-178C-43C3-99C4-A1D03DD6A8F5@sb.org>') {
+        my $hc = '&#26376;';
+        my $u = "http://www.\x{6708}.example.com/";
+        my $s = $u;
+        my $l = PublicInbox::Linkify->new;
+        $s = $l->linkify_1($s);
+        $s = $l->linkify_2($s);
+        my $expect = qq{<a
+href="http://www.$hc.example.com/">http://www.$hc.example.com/</a>};
+        is($s, $expect, 'IDN message escaped properly');
+}
+
 done_testing();