run update-copyrights from gnulib for 2019

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

diff --git a/lib/PublicInbox/Linkify.pm b/lib/PublicInbox/Linkify.pm
index 93c468fe74839c6d2a0e818996e8a00680a70464..175f8d724dbb25e2d8e04f89a2a1792373d83b3c 100644 (file)
--- a/lib/PublicInbox/Linkify.pm
+++ b/lib/PublicInbox/Linkify.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2014-2016 all contributors <meta@public-inbox.org>
+# Copyright (C) 2014-2019 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
 # two-step linkification.
@@ -13,17 +13,27 @@ 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)://
-                [\@:\w\.-]+/
+my $LINK_RE = qr{([\('!])?\b((?:ftps?|https?|nntps?|gopher)://
+                [\@:\w\.-]+(?:/
                 (?:[a-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@/%]*)
                 (?:\?[a-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@/%]+)?
                 (?:\#[a-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@/%\?]+)?
-                )}xi;
+                )?
+               )}xi;
 
 sub new { bless {}, $_[0] }
 
+# try to distinguish paired punctuation chars from the URL itself
+# Maybe other languages/formats can be supported here, too...
+my %pairs = (
+       "(" => qr/(\)[\.,;\+]?)\z/, # Markdown (,), Ruby (+) (, for arrays)
+       "'" => qr/('[\.,;\+]?)\z/, # Perl / Ruby
+       "!" => qr/(![\.,;\+]?)\z/, # Perl / Ruby
+);
+
 sub linkify_1 {
        $_[1] =~ s^$LINK_RE^
                my $beg = $1 || '';
@@ -34,23 +44,30 @@ sub linkify_1 {
                # '.', ',' or ';' to denote the end of a statement;
                # assume the intent was to end the statement/sentence
                # in English
-               # Markdown compatibility:
-               if ($beg eq '(') {
-                       if ($url =~ s/(\)[\.,;]?)\z//) {
+               if (defined(my $re = $pairs{$beg})) {
+                       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;