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)://
+my $LINK_RE = qr{([\('!])?\b((?:ftps?|https?|nntps?|gopher)://
[\@:\w\.-]+(?:/
(?:[a-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@/%]*)
(?:\?[a-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@/%]+)?
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 = $1 || '';
# '.', ',' or ';' to denote the end of a statement;
# assume the intent was to end the statement/sentence
# in English
- # Markdown compatibility:
- if ($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/&/&/g;
$_[0]->{$key} = $url;
$beg . 'PI-LINK-'. $key . $end;
^ge;