X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FNewsWWW.pm;h=61d9ae7cacecbbc4facaeb05d119acdfaf433e95;hb=0d38f65c490466837ae091afa7a7b6f59d04ce7c;hp=01e34d7b136b9d87e1931f4bac43b635c048de95;hpb=3d41aa23f35501ca92aab8aa42980fa73f7fa74f;p=public-inbox.git

diff --git a/lib/PublicInbox/NewsWWW.pm b/lib/PublicInbox/NewsWWW.pm
index 01e34d7b..61d9ae7c 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) 2016-2020 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
@@ -10,27 +10,48 @@ use strict;
 use warnings;
 use PublicInbox::Config;
 use PublicInbox::MID qw(mid_escape);
+use PublicInbox::Hval qw(prurl);
 
 sub new {
-	my ($class, $pi_config) = @_;
-	$pi_config ||= PublicInbox::Config->new;
-	bless { pi_config => $pi_config }, $class;
+	my ($class, $pi_cfg) = @_;
+	bless { pi_cfg => $pi_cfg // PublicInbox::Config->new }, $class;
+}
+
+sub redirect ($$) {
+	my ($code, $url) = @_;
+	[ $code,
+	  [ Location => $url, 'Content-Type' => 'text/plain' ],
+	  [ "Redirecting to $url\n" ] ]
+}
+
+sub try_inbox {
+	my ($ibx, $arg) = @_;
+	return if scalar(@$arg) > 1;
+
+	# do not pass $env since HTTP_HOST may differ
+	my $url = $ibx->base_url or return;
+
+	my ($mid) = @$arg;
+	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
+	$arg->[1] = 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 $url = PublicInbox::Hval::prurl($env, $inbox->{url});
+	my (undef, @parts) = split(m!/!, $env->{PATH_INFO});
+	my ($ng, $article) = @parts;
+	my $pi_cfg = $self->{pi_cfg};
+	if (my $ibx = $pi_cfg->lookup_newsgroup($ng)) {
+		my $url = prurl($env, $ibx->{url});
 		my $code = 301;
-		if (defined $article && $article =~ /\A\d+\z/) {
-			my $mid = eval { $inbox->mm->mid_for($article) };
+		if (defined $article && $article =~ /\A[0-9]+\z/) {
+			my $mid = eval { $ibx->mm->mid_for($article) };
 			if (defined $mid) {
 				# article IDs are not stable across clones,
 				# do not encourage caching/bookmarking them
@@ -38,12 +59,41 @@ sub call {
 				$url .= mid_escape($mid) . '/';
 			}
 		}
+		return redirect($code, $url);
+	}
 
-		my $h = [ Location => $url, 'Content-Type' => 'text/plain' ];
+	my @try = (join('/', @parts));
 
-		return [ $code, $h, [ "Redirecting to $url\n" ] ]
+	# trailing slash is in the rest of our WWW, so maybe some users
+	# will assume it:
+	if ($parts[-1] eq '') {
+		pop @parts;
+		push @try, join('/', @parts);
+	}
+	my $ALL = $pi_cfg->ALL;
+	if (my $over = $ALL ? $ALL->over : undef) {
+		my $by_eidx_key = $pi_cfg->{-by_eidx_key};
+		for my $mid (@try) {
+			my ($id, $prev);
+			while (my $x = $over->next_by_mid($mid, \$id, \$prev)) {
+				my $xr3 = $over->get_xref3($x->{num});
+				for (@$xr3) {
+					s/:[0-9]+:$x->{blob}\z// or next;
+					my $ibx = $by_eidx_key->{$_} // next;
+					my $url = $ibx->base_url or next;
+					$url .= mid_escape($mid) . '/';
+					return redirect(302, $url);
+				}
+			}
+		}
+	} else { # slow path, scan every inbox
+		for my $mid (@try) {
+			my $arg = [ $mid ]; # [1] => result
+			$pi_cfg->each_inbox(\&try_inbox, $arg);
+			return $arg->[1] if $arg->[1];
+		}
 	}
-	[ 404, [ 'Content-Type' => 'text/plain' ], [ "404 Not Found\n" ] ];
+	[ 404, [qw(Content-Type text/plain)], ["404 Not Found\n"] ];
 }
 
 1;