update copyrights for 2021

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

diff --git a/lib/PublicInbox/Linkify.pm b/lib/PublicInbox/Linkify.pm
index 5b83742c14b36ace1e62790b20d417e0971dbc87..2ac74e2a98bc1c1c666d674fcb4591976801845a 100644 (file)
--- a/lib/PublicInbox/Linkify.pm
+++ b/lib/PublicInbox/Linkify.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2014-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2014-2021 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
 # two-step linkification.
@@ -13,10 +13,11 @@ package PublicInbox::Linkify;
 use strict;
 use warnings;
 use Digest::SHA qw/sha1_hex/;
-use PublicInbox::Hval qw(ascii_html);
+use PublicInbox::Hval qw(ascii_html mid_href);
+use PublicInbox::MID qw($MID_EXTRACT);
 
 my $SALT = rand;
-my $LINK_RE = qr{([\('!])?\b((?:ftps?|https?|nntps?|gopher)://
+my $LINK_RE = qr{([\('!])?\b((?:ftps?|https?|nntps?|imaps?|s?news|gopher)://
                 [\@:\w\.-]+(?:/
                 (?:[a-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@/%]*)
                 (?:\?[a-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@/%]+)?
@@ -70,7 +71,7 @@ sub linkify_1 {
 
                $_[0]->{$key} = $url;
                $beg . 'PI-LINK-'. $key . $end;
-       ^ge;
+       ^geo;
        $_[1];
 }
 
@@ -92,25 +93,26 @@ sub linkify_2 {
 # single pass linkification of <Message-ID@example.com> within $str
 # with $pfx being the URL prefix
 sub linkify_mids {
-       my ($self, $pfx, $str) = @_;
-       $$str =~ s!<([^>]+)>!
-               my $msgid = PublicInbox::Hval->new_msgid($1);
-               my $html = $msgid->as_html;
-               my $href = $msgid->{href};
-               $href = ascii_html($href); # for IDN
+       my ($self, $pfx, $str, $raw) = @_;
+       $$str =~ s!$MID_EXTRACT!
+               my $mid = $1;
+               my $html = ascii_html($mid);
+               my $href = mid_href($mid);
 
                # salt this, as this could be exploited to show
                # links in the HTML which don't show up in the raw mail.
                my $key = sha1_hex($html . $SALT);
-               $self->{$key} = [ $href, $html ];
-               '<PI-LINK-'. $key . '>';
+               my $repl = qq(&lt;<a\nhref="$pfx/$href/">$html</a>&gt;);
+               $repl .= qq{ (<a\nhref="$pfx/$href/raw">raw</a>)} if $raw;
+               $self->{$key} = $repl;
+               'PI-LINK-'. $key;
                !ge;
        $$str = ascii_html($$str);
        $$str =~ s!\bPI-LINK-([a-f0-9]{40})\b!
                my $key = $1;
                my $repl = $_[0]->{$key};
                if (defined $repl) {
-                       "<a\nhref=\"$pfx/$repl->[0]/\">$repl->[1]</a>";
+                       $repl;
                } else {
                        # false positive or somebody tried to mess with us
                        $key;
@@ -118,4 +120,6 @@ sub linkify_mids {
        !ge;
 }
 
+sub to_html { linkify_2($_[0], ascii_html(linkify_1(@_))) }
+
 1;