[RFC 2/2] www: add /~/$MESSAGE_ID global redirector endpoint

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

The "/~/" is not finalized, yet.  Initially I chose "/_/", but
it could conflict with valid git remote names.

Perhaps even "/.$MESSAGE_ID" or "/~$MESSAGE_ID" could work to
save a byte.

Requested-by: Konstantin Ryabitsev <konstantin@linuxfoundation.org>
cf. https://public-inbox.org/meta/20190107190719.GE9442@pure.paranoia.local/
---
 MANIFEST               |  1 +
 lib/PublicInbox/WWW.pm | 44 +++++++++++++++++++++++++--
 t/psgi_scan_all.t      | 69 ++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 111 insertions(+), 3 deletions(-)
 create mode 100644 t/psgi_scan_all.t

diff --git a/MANIFEST b/MANIFEST
index e4f3df8..73d1047 100644
--- a/MANIFEST
+++ b/MANIFEST
@@ -193,6 +193,7 @@ 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/WWW.pm b/lib/PublicInbox/WWW.pm
index 3562e46..9e0973f 100644
--- a/lib/PublicInbox/WWW.pm
+++ b/lib/PublicInbox/WWW.pm
@@ -360,11 +360,23 @@ sub legacy_redirects {
 		r301($ctx, $1, $2, $3 eq 't' ? 't/#u' : $3);
 	} elsif ($path_info =~ m!$INBOX_RE/(\S+/\S+)/f\z!o) {
 		r301($ctx, $1, $2);
+
+	# scan across all inboxes
+	# XXX '/~/$MESSAGE_ID' not finalized
+	} elsif ($path_info =~ m!\A/~/(\S+)\z!) {
+		scan_all($ctx, $1);
 	} else {
 		$ctx->{www}->news_www->call($ctx->{env});
 	}
 }
 
+sub redirect ($$) {
+	my ($code, $url) = @_;
+	[ $code,
+	  [ Location => $url, 'Content-Type' => 'text/plain' ],
+	  [ "Redirecting to $url\n" ] ]
+}
+
 sub r301 {
 	my ($ctx, $inbox, $mid_ue, $suffix) = @_;
 	my $obj = $ctx->{-inbox};
@@ -383,9 +395,7 @@ sub r301 {
 	$url .= $suffix if (defined $suffix);
 	$url .= "?$qs" if $qs ne '';
 
-	[ 301,
-	  [ Location => $url, 'Content-Type' => 'text/plain' ],
-	  [ "Redirecting to $url\n" ] ]
+	redirect(301, $url);
 }
 
 sub msg_page {
@@ -446,4 +456,32 @@ sub get_attach {
 	PublicInbox::WwwAttach::get_attach($ctx, $idx, $fn);
 }
 
+sub scan_all {
+	my ($ctx, $mid) = @_; # mid may have trailing slash
+
+	# TODO: user-sortable
+
+	my @found;
+	do {
+		$ctx->{www}->{pi_config}->each_inbox(sub {
+			my ($ibx) = @_;
+			# do not pass $env, since HTTP_HOST can be different
+			my $url = $ibx->base_url or next;
+
+			my $n = eval { $ibx->mm->num_for($mid) } or return;
+
+			# ambiguous, so 302 instead of 301:
+			push @found, redirect(302, $url .= "$mid/");
+		});
+
+	# account for trailing slash, since the rest of our API uses it
+	} while (!@found && $mid =~ s!/+\z!!);
+
+	# FIXME: It's possible for a message to have the same Message-ID but
+	# different content across multiple groups...
+	@found ? $found[0] : r404();
+
+	# n.b. we use trailing slash in most URLs to allow "wget -r" mirrors :)
+}
+
 1;
diff --git a/t/psgi_scan_all.t b/t/psgi_scan_all.t
new file mode 100644
index 0000000..bf03f22
--- /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