Merge remote-tracking branch 'origin/newspeak' into xcpdb

[public-inbox.git] / lib / PublicInbox / Linkify.pm

diff --git a/lib/PublicInbox/Linkify.pm b/lib/PublicInbox/Linkify.pm
index 71193bc28732f28ca715323b04d31e53467ab189..84960a98889fd4c53cc68aa5fce72eac1094084f 100644 (file)
--- a/lib/PublicInbox/Linkify.pm
+++ b/lib/PublicInbox/Linkify.pm
@@ -13,6 +13,7 @@ package PublicInbox::Linkify;
 use strict;
 use warnings;
 use Digest::SHA qw/sha1_hex/;
+use PublicInbox::Hval qw(ascii_html);
 
 my $SALT = rand;
 my $LINK_RE = qr{([\('!])?\b((?:ftps?|https?|nntps?|gopher)://
@@ -47,18 +48,26 @@ sub linkify_1 {
                        if ($url =~ s/$re//) {
                                $end = $1;
                        }
-               } elsif ($url =~ s/([\.,;])\z//) {
-                       $end = $1;
+               } elsif ($url =~ s/(\))?([\.,;])\z//) {
+                       $end = $2;
+                       # require ')' to be paired with '('
+                       if (defined $1) { # ')'
+                               if (index($url, '(') < 0) {
+                                       $end = ")$end";
+                               } else {
+                                       $url .= ')';
+                               }
+                       }
                } elsif ($url !~ /\(/ && $url =~ s/\)\z//) {
                        $end = ')';
                }
 
+               $url = ascii_html($url); # for IDN
+
                # 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);
 
-               # only escape ampersands, others do not match LINK_RE
-               $url =~ s/&/&#38;/g;
                $_[0]->{$key} = $url;
                $beg . 'PI-LINK-'. $key . $end;
        ^ge;