newswww: add /$MESSAGE_ID global redirector endpoint

This is the fallback for the normal WWW endpoint.

Adding this to the top-level seems to be alright, since lynx and
w3m both understand nntp://<HOSTNAME>/<Message-ID> anyways.

If newsgroup and inbox names conflict, then consider it the
fault of the original sender.

Since NewsWWW is intended to support buggy linkifiers in mail clients,
they can interpret nntp:// URLs as http://<HOSTNAME>/<Message-ID>

Inbox ordering from the config file is preserved since
commit cfa8ff7c256e20f3240aed5f98d155c019788e3b
("config: each_inbox iteration preserves config order"),
so admins can rely on that to configure how scanning
works.

Requested-by: Konstantin Ryabitsev <konstantin@linuxfoundation.org>
cf. https://public-inbox.org/meta/20190107190719.GE9442@pure.paranoia.local/
    nntp://news.public-inbox.org/20190107190719.GE9442@pure.paranoia.local

1 files changed, 41 insertions, 9 deletions

diff --git a/lib/PublicInbox/NewsWWW.pm b/lib/PublicInbox/NewsWWW.pm
index 01e34d7b..d7fcb0da 100644
--- a/lib/PublicInbox/NewsWWW.pm
+++ b/lib/PublicInbox/NewsWWW.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2016-2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2016-2019 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 #
 # Plack app redirector for mapping /$NEWSGROUP requests to
@@ -17,16 +17,34 @@ sub new {
         bless { pi_config => $pi_config }, $class;
 }
 
+sub redirect ($$) {
+        my ($code, $url) = @_;
+        [ $code,
+          [ Location => $url, 'Content-Type' => 'text/plain' ],
+          [ "Redirecting to $url\n" ] ]
+}
+
+sub try_inbox ($$) {
+        my ($ibx, $mid) = @_;
+        # do not pass $env since HTTP_HOST may differ
+        my $url = $ibx->base_url or return;
+
+        eval { $ibx->mm->num_for($mid) } or return;
+
+        # 302 since the same message may show up on
+        # multiple inboxes and inboxes can be added/reordered
+        redirect(302, $url .= mid_escape($mid) . '/');
+}
+
 sub call {
         my ($self, $env) = @_;
-        my $path = $env->{PATH_INFO};
-        $path =~ s!\A/+!!;
-        $path =~ s!/+\z!!;
 
         # some links may have the article number in them:
         # /inbox.foo.bar/123456
-        my ($ng, $article) = split(m!/+!, $path, 2);
-        if (my $inbox = $self->{pi_config}->lookup_newsgroup($ng)) {
+        my (undef, @parts) = split(m!/!, $env->{PATH_INFO});
+        my ($ng, $article) = @parts;
+        my $pi_config = $self->{pi_config};
+        if (my $inbox = $pi_config->lookup_newsgroup($ng)) {
                 my $url = PublicInbox::Hval::prurl($env, $inbox->{url});
                 my $code = 301;
                 if (defined $article && $article =~ /\A\d+\z/) {
@@ -38,12 +56,26 @@ sub call {
                                 $url .= mid_escape($mid) . '/';
                         }
                 }
+                return redirect($code, $url);
+        }
 
-                my $h = [ Location => $url, 'Content-Type' => 'text/plain' ];
+        my $res;
+        my @try = (join('/', @parts));
+
+        # trailing slash is in the rest of our WWW, so maybe some users
+        # will assume it:
+        if ($parts[-1] eq '') {
+                pop @parts;
+                push @try, join('/', @parts);
+        }
 
-                return [ $code, $h, [ "Redirecting to $url\n" ] ]
+        foreach my $mid (@try) {
+                $pi_config->each_inbox(sub {
+                        $res ||= try_inbox($_[0], $mid);
+                });
+                last if defined $res;
         }
-        [ 404, [ 'Content-Type' => 'text/plain' ], [ "404 Not Found\n" ] ];
+        $res || [ 404, [qw(Content-Type text/plain)], ["404 Not Found\n"] ];
 }
 
 1;