From 34d6aff1ca223521d8137f642a58db077ab70df0 Mon Sep 17 00:00:00 2001
From: "Eric Wong (Contractor, The Linux Foundation)" <e@80x24.org>
Date: Thu, 29 Mar 2018 09:57:56 +0000
Subject: [PATCH] www: cleanup expensive fallback for legacy URLs

Back in the day, we compressed long Message-IDs to SHA-1
hexdigests for the URL.  This now redirects to a 301 in
the hopes we can remove these checks some day to reduce
overhead.
---
 lib/PublicInbox/Inbox.pm | 11 ++++++++---
 lib/PublicInbox/WWW.pm   | 23 +++++++++--------------
 t/plack.t                | 18 ++++++++++++++++++
 3 files changed, 35 insertions(+), 17 deletions(-)

diff --git a/lib/PublicInbox/Inbox.pm b/lib/PublicInbox/Inbox.pm
index 01aa500c..265360d9 100644
--- a/lib/PublicInbox/Inbox.pm
+++ b/lib/PublicInbox/Inbox.pm
@@ -293,13 +293,18 @@ sub path_check {
 	git($self)->check('HEAD:'.$path);
 }
 
+sub mid2num($$) {
+	my ($self, $mid) = @_;
+	my $mm = mm($self) or return;
+	$mm->num_for($mid);
+}
+
 sub smsg_by_mid ($$) {
 	my ($self, $mid) = @_;
 	my $srch = search($self) or return;
 	# favor the Message-ID we used for the NNTP article number:
-	my $mm = mm($self) or return;
-	my $num = $mm->num_for($mid);
-	$srch->lookup_article($num);
+	my $num = mid2num($self, $mid);
+	defined $num ? $srch->lookup_article($num) : undef;
 }
 
 sub msg_by_mid ($$;$) {
diff --git a/lib/PublicInbox/WWW.pm b/lib/PublicInbox/WWW.pm
index 7bd29732..24e24f1e 100644
--- a/lib/PublicInbox/WWW.pm
+++ b/lib/PublicInbox/WWW.pm
@@ -169,14 +169,15 @@ sub invalid_inbox_mid {
 	return $ret if $ret;
 
 	$ctx->{mid} = $mid;
-	if ($mid =~ /\A[a-f0-9]{40}\z/) {
-		# this is horiffically wasteful for legacy URLs:
-		if ($mid = mid2blob($ctx)) {
-			require Email::Simple;
-			use PublicInbox::MID qw/mid_clean/;
-			my $s = Email::Simple->new($mid);
-			$ctx->{mid} = mid_clean($s->header('Message-ID'));
-		}
+	my $ibx = $ctx->{-inbox};
+	if ($mid =~ m!\A([a-f0-9]{2})([a-f0-9]{38})\z!) {
+		my ($x2, $x38) = ($1, $2);
+		# this is horrifically wasteful for legacy URLs:
+		my $str = $ctx->{-inbox}->msg_by_path("$x2/$x38") or return;
+		require Email::Simple;
+		my $s = Email::Simple->new($str);
+		$mid = PublicInbox::MID::mid_clean($s->header('Message-ID'));
+		return r301($ctx, $inbox, $mid);
 	}
 	undef;
 }
@@ -208,12 +209,6 @@ sub get_index {
 	}
 }
 
-# just returns a string ref for the blob in the current ctx
-sub mid2blob {
-	my ($ctx) = @_;
-	$ctx->{-inbox}->msg_by_mid($ctx->{mid});
-}
-
 # /$INBOX/$MESSAGE_ID/raw                    -> raw mbox
 sub get_mid_txt {
 	my ($ctx) = @_;
diff --git a/t/plack.t b/t/plack.t
index 26b03660..7eb7d7f2 100644
--- a/t/plack.t
+++ b/t/plack.t
@@ -18,6 +18,7 @@ foreach my $mod (@mods) {
 }
 use_ok 'PublicInbox::Import';
 use_ok 'PublicInbox::Git';
+my @ls;
 
 foreach my $mod (@mods) { use_ok $mod; }
 {
@@ -55,6 +56,8 @@ EOF
 		$im->done;
 		my $rev = `git --git-dir="$maindir" rev-list HEAD`;
 		like($rev, qr/\A[a-f0-9]{40}/, "good revision committed");
+		@ls = `git --git-dir="$maindir" ls-tree -r --name-only HEAD`;
+		chomp @ls;
 	}
 	my $app = eval {
 		local $ENV{PI_CONFIG} = $pi_config;
@@ -198,6 +201,21 @@ EOF
 			     "$sfx redirected to /mbox.gz");
 		});
 	}
+	test_psgi($app, sub {
+		my ($cb) = @_;
+		# for a while, we used to support /$INBOX/$X40/
+		# when we "compressed" long Message-IDs to SHA-1
+		# Now we're stuck supporting them forever :<
+		foreach my $path (@ls) {
+			$path =~ tr!/!!d;
+			my $from = "http://example.com/test/$path/";
+			my $res = $cb->(GET($from));
+			is(301, $res->code, 'is permanent redirect');
+			like($res->header('Location'),
+				qr!/test/blah\@example\.com/!,
+				'redirect from x40 MIDs works');
+		}
+	});
 }
 
 done_testing();
-- 
2.44.0