[PATCH v2] newswww: add /$MESSAGE_ID global redirector endpoint

[Eric Wong <e@80x24.org>]

Eric Wong <e@80x24.org> wrote:
> However, my screwing up solver hrefs in the Atom feeds got me
> thinking this can even be a 404 handler at the top level
> (similar to how PublicInbox::NewsWWW works).  That would allow
> it to be mapped to any path (or domain) via the PSGI builder
> file...

Or just use NewsWWW, because nntp://<HOSTNAME>/<Message-ID> is valid.
Going to think about it while I eat and do other things, but
will very likely merge it to master, soon.
--------8<-----------
Subject: [PATCH] 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
---
 MANIFEST                   |  1 +
 lib/PublicInbox/NewsWWW.pm | 50 ++++++++++++++++++++++-----
 t/psgi_scan_all.t          | 69 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 111 insertions(+), 9 deletions(-)
 create mode 100644 t/psgi_scan_all.t

diff --git a/MANIFEST b/MANIFEST
index c4a9349..6ff2bfe 100644
--- a/MANIFEST
+++ b/MANIFEST
@@ -208,6 +208,7 @@ t/psgi_attach.t
 t/psgi_bad_mids.t
 t/psgi_mount.t
 t/psgi_multipart_not.t
+t/psgi_scan_all.t
 t/psgi_search.t
 t/psgi_text.t
 t/psgi_v2.t
diff --git a/lib/PublicInbox/NewsWWW.pm b/lib/PublicInbox/NewsWWW.pm
index 01e34d7..d7fcb0d 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;
diff --git a/t/psgi_scan_all.t b/t/psgi_scan_all.t
new file mode 100644
index 0000000..e9c439e
--- /dev/null
+++ b/t/psgi_scan_all.t
@@ -0,0 +1,69 @@
+# Copyright (C) 2019 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
+use strict;
+use warnings;
+use Test::More;
+use Email::MIME;
+use File::Temp qw/tempdir/;
+use PublicInbox::Config;
+my @mods = qw(HTTP::Request::Common Plack::Test URI::Escape Search::Xapian
+	DBD::SQLite);
+foreach my $mod (@mods) {
+	eval "require $mod";
+	plan skip_all => "$mod missing for psgi_scan_all.t" if $@;
+}
+use_ok 'PublicInbox::V2Writable';
+foreach my $mod (@mods) { use_ok $mod; }
+my $tmp = tempdir('pi-scan_all-XXXXXX', TMPDIR => 1, CLEANUP => 1);
+my $cfg = {};
+
+foreach my $i (1..2) {
+	my $cfgpfx = "publicinbox.test-$i";
+	my $addr = $cfg->{"$cfgpfx.address"} = "test-$i\@example.com";
+	my $mainrepo = $cfg->{"$cfgpfx.mainrepo"} = "$tmp/$i";
+	$cfg->{"$cfgpfx.url"} = "http://example.com/$i";
+	my $opt = {
+		mainrepo => $mainrepo,
+		name => "test-$i",
+		version => 2,
+		-primary_address => $addr,
+	};
+	my $ibx = PublicInbox::Inbox->new($opt);
+	my $im = PublicInbox::V2Writable->new($ibx, 1);
+	$im->{parallel} = 0;
+	$im->init_inbox(0);
+	my $mime = PublicInbox::MIME->new(<<EOF);
+From: a\@example.com
+To: $addr
+Subject: s$i
+Message-ID: <a-mid-$i\@b>
+Date: Fri, 02 Oct 1993 00:00:00 +0000
+
+hello world
+EOF
+
+	ok($im->add($mime), "added message to $i");
+	$im->done;
+}
+my $config = PublicInbox::Config->new($cfg);
+use_ok 'PublicInbox::WWW';
+my $www = PublicInbox::WWW->new($config);
+
+test_psgi(sub { $www->call(@_) }, sub {
+	my ($cb) = @_;
+	foreach my $i (1..2) {
+		foreach my $end ('', '/') {
+			my $res = $cb->(GET("/a-mid-$i\@b$end"));
+			is($res->code, 302, 'got 302');
+			is($res->header('Location'),
+				"http://example.com/$i/a-mid-$i\@b/",
+				"redirected OK to $i");
+		}
+	}
+	foreach my $x (qw(inv@lid inv@lid/ i/v/a l/i/d/)) {
+		my $res = $cb->(GET("/$x"));
+		is($res->code, 404, "404 on $x");
+	}
+});
+
+done_testing();
-- 
EW