linkify: implement Markdown link compatibility

Although unescaped parentheses in URLs are technically allowed,
they are uncommon.  However, Markdown-like syntaxes are
unfortunately common for URLs, so we might as well support them.

diff --git a/lib/PublicInbox/Linkify.pm b/lib/PublicInbox/Linkify.pm
index ea7fd71f13ca6d7f8a0909b271be95a03be1b2aa..cc0f7e3a5a3a775d3744100a0e67e3f71a11a3db 100644 (file)
--- a/lib/PublicInbox/Linkify.pm
+++ b/lib/PublicInbox/Linkify.pm
@@ -15,7 +15,7 @@ use warnings;
 use Digest::SHA qw/sha1_hex/;
 
 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\-\._~!\$\&\';\(\)\*\+,;=:@/%]+)?
@@ -27,15 +27,22 @@ sub new { bless {}, shift }
 sub linkify_1 {
        my ($self, $s) = @_;
        $s =~ s!$LINK_RE!
-               my $url = $1;
+               my $beg = $1 || '';
+               my $url = $2;
                my $end = '';
 
+               # Markdown compatibility:
+               if ($beg eq '(') {
+                       $url =~ s/\)\z//;
+                       $end = ')';
+               }
+
                # it's fairly common to end URLs in messages with
                # '.', ',' or ';' to denote the end of a statement;
                # assume the intent was to end the statement/sentence
                # in English
                if ($url =~ s/([\.,;])\z//) {
-                       $end = $1;
+                       $end = $1 . $end;
                }
 
                # salt this, as this could be exploited to show
@@ -45,7 +52,7 @@ sub linkify_1 {
                # only escape ampersands, others do not match LINK_RE
                $url =~ s/&/&/g;
                $self->{$key} = $url;
-               'PI-LINK-'. $key . $end;
+               $beg . 'PI-LINK-'. $key . $end;
        !ge;
        $s;
 }

diff --git a/t/linkify.t b/t/linkify.t
index 49cbbd64edf5d18ca1892f91abd111afed88407e..a794c785221e3349790528b8e3c69f706cf9d757 100644 (file)
--- a/t/linkify.t
+++ b/t/linkify.t
@@ -57,4 +57,13 @@ use PublicInbox::Linkify;
        is($s, qq(hello <a\nhref="$u">$u</a> world), "root + fragment");
 }
 
+{
+       my $l = PublicInbox::Linkify->new;
+       my $u = 'http://example.com/';
+       my $s = "[markdown]($u)";
+       $s = $l->linkify_1($s);
+       $s = $l->linkify_2($s);
+       is($s, qq![markdown](<a\nhref="$u">$u</a>)!, 'markdown compatible');
+}
+
 done_testing();