-# Copyright (C) 2014-2016 all contributors <meta@public-inbox.org>
+# Copyright (C) 2014-2018 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
# two-step linkification.
use Digest::SHA qw/sha1_hex/;
my $SALT = rand;
-my $LINK_RE = qr!\b((?:ftp|https?|nntp)://
+my $LINK_RE = qr{(\()?\b((?:ftps?|https?|nntps?|gopher)://
[\@:\w\.-]+/
- ?[~\@\w\+\&\?\.\%\;/#=-]*)!x;
+ (?:[a-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@/%]*)
+ (?:\?[a-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@/%]+)?
+ (?:\#[a-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@/%\?]+)?
+ )}xi;
-sub new { bless {}, shift }
+sub new { bless {}, $_[0] }
sub linkify_1 {
- my ($self, $s) = @_;
- $s =~ s!$LINK_RE!
- my $url = $1;
+ $_[1] =~ s^$LINK_RE^
+ my $beg = $1 || '';
+ my $url = $2;
my $end = '';
# it's fairly common to end URLs in messages with
- # '.' or ';' to denote the end of a statement.
- if ($url =~ s/(\.)\z// || $url =~ s/(;)\z//) {
+ # '.', ',' or ';' to denote the end of a statement;
+ # assume the intent was to end the statement/sentence
+ # in English
+ # Markdown compatibility:
+ if ($beg eq '(') {
+ if ($url =~ s/(\)[\.,;]?)\z//) {
+ $end = $1;
+ }
+ } elsif ($url =~ s/([\.,;])\z//) {
$end = $1;
+ } elsif ($url !~ /\(/ && $url =~ s/\)\z//) {
+ $end = ')';
}
# salt this, as this could be exploited to show
# only escape ampersands, others do not match LINK_RE
$url =~ s/&/&/g;
- $self->{$key} = $url;
- 'PI-LINK-'. $key . $end;
- !ge;
- $s;
+ $_[0]->{$key} = $url;
+ $beg . 'PI-LINK-'. $key . $end;
+ ^ge;
+ $_[1];
}
sub linkify_2 {
- my ($self, $s) = @_;
-
# Added "PI-LINK-" prefix to avoid false-positives on git commits
- $s =~ s!\bPI-LINK-([a-f0-9]{40})\b!
+ $_[1] =~ s!\bPI-LINK-([a-f0-9]{40})\b!
my $key = $1;
- my $url = $self->{$key};
+ my $url = $_[0]->{$key};
if (defined $url) {
"<a\nhref=\"$url\">$url</a>";
} else {
$key;
}
!ge;
- $s;
+ $_[1];
}
1;