linkify: modify argument in place

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

diff --git a/lib/PublicInbox/Linkify.pm b/lib/PublicInbox/Linkify.pm
index 8f634f482828f64896ee7795e60f0267ee21ee02..8e1728c71136c78de06af4d53603e54116496edb 100644 (file)
--- a/lib/PublicInbox/Linkify.pm
+++ b/lib/PublicInbox/Linkify.pm
@@ -15,35 +15,51 @@ use warnings;
 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 $end = '';
+
+               # it's fairly common to end URLs in messages with
+               # '.', ',' or ';' to denote the end of a statement;
+               # assume the intent was to end the statement/sentence
+               # in English
+               # Markdown compatibility:
+               if ($beg eq '(') {
+                       if ($url =~ s/(\)[\.,;]?)\z//) {
+                               $end = $1;
+                       }
+               } elsif ($url =~ s/([\.,;])\z//) {
+                       $end = $1;
+               }
+
                # 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;
-               $self->{$key} = $url;
-               'PI-LINK-'. $key;
+               $_[0]->{$key} = $url;
+               $beg . 'PI-LINK-'. $key . $end;
        !ge;
-       $s;
+       $_[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 {
@@ -51,7 +67,7 @@ sub linkify_2 {
                        $key;
                }
        !ge;
-       $s;
+       $_[1];
 }
 
 1;