From f982abbaa39e07090d3fb641fd9de25434c0d74c Mon Sep 17 00:00:00 2001
From: Eric Wong <e@yhbt.net>
Date: Sun, 5 Jul 2020 23:27:28 +0000
Subject: [PATCH] qspawn: learn to gzip streaming responses

This will allow us to gzip responses generated by cgit
and any other CGI programs or long-lived streaming
responses we may spawn.
---
 lib/PublicInbox/GzipFilter.pm | 16 ++++++++++++++++
 lib/PublicInbox/Qspawn.pm     |  6 ++++--
 t/httpd-corner.psgi           |  7 +++++++
 t/httpd-corner.t              |  9 ++++++++-
 4 files changed, 35 insertions(+), 3 deletions(-)

diff --git a/lib/PublicInbox/GzipFilter.pm b/lib/PublicInbox/GzipFilter.pm
index 0fbb4476..0a6c56a5 100644
--- a/lib/PublicInbox/GzipFilter.pm
+++ b/lib/PublicInbox/GzipFilter.pm
@@ -32,6 +32,22 @@ sub gzf_maybe ($$) {
 	bless { gz => $gz }, __PACKAGE__;
 }
 
+sub qsp_maybe ($$) {
+	my ($res_hdr, $env) = @_;
+	return if ($env->{HTTP_ACCEPT_ENCODING} // '') !~ /\bgzip\b/;
+	my $hdr = join("\n", @$res_hdr);
+	return if $hdr !~ m!^Content-Type\n
+				(?:(?:text/(?:html|plain))|
+				application/atom\+xml)\b!ixsm;
+	return if $hdr =~ m!^Content-Encoding\ngzip\n!smi;
+	return if $hdr =~ m!^Content-Length\n[0-9]+\n!smi;
+	return if $hdr =~ m!^Transfer-Encoding\n!smi;
+	# in case Plack::Middleware::Deflater is loaded:
+	return if $env->{'plack.skip-deflater'}++;
+	push @$res_hdr, @GZIP_HDRS;
+	bless {}, __PACKAGE__;
+}
+
 sub gzip_or_die () {
 	my ($gz, $err) = Compress::Raw::Zlib::Deflate->new(%OPT);
 	$err == Z_OK or die "Deflate->new failed: $err";
diff --git a/lib/PublicInbox/Qspawn.pm b/lib/PublicInbox/Qspawn.pm
index d395a10b..88b6d390 100644
--- a/lib/PublicInbox/Qspawn.pm
+++ b/lib/PublicInbox/Qspawn.pm
@@ -25,8 +25,8 @@
 
 package PublicInbox::Qspawn;
 use strict;
-use warnings;
 use PublicInbox::Spawn qw(popen_rd);
+use PublicInbox::GzipFilter;
 
 # n.b.: we get EAGAIN with public-inbox-httpd, and EINTR on other PSGI servers
 use Errno qw(EAGAIN EINTR);
@@ -255,7 +255,9 @@ sub psgi_return_init_cb {
 	my ($self) = @_;
 	my $r = rd_hdr($self) or return;
 	my $env = $self->{psgi_env};
-	my $filter = delete $env->{'qspawn.filter'};
+	my $filter = delete $env->{'qspawn.filter'} //
+		PublicInbox::GzipFilter::qsp_maybe($r->[1], $env);
+
 	my $wcb = delete $env->{'qspawn.wcb'};
 	my $async = delete $self->{async};
 	if (scalar(@$r) == 3) { # error
diff --git a/t/httpd-corner.psgi b/t/httpd-corner.psgi
index 44629620..cb41cfa0 100644
--- a/t/httpd-corner.psgi
+++ b/t/httpd-corner.psgi
@@ -94,6 +94,13 @@ my $app = sub {
 		return $qsp->psgi_return($env, undef, sub {
 			[ 200, [ qw(Content-Type application/octet-stream)]]
 		});
+	} elsif ($path eq '/psgi-return-compressible') {
+		require PublicInbox::Qspawn;
+		my $cmd = [qw(echo goodbye world)];
+		my $qsp = PublicInbox::Qspawn->new($cmd);
+		return $qsp->psgi_return($env, undef, sub {
+			[200, [qw(Content-Type text/plain)]]
+		});
 	} elsif ($path eq '/psgi-return-enoent') {
 		require PublicInbox::Qspawn;
 		my $cmd = [ 'this-better-not-exist-in-PATH'.rand ];
diff --git a/t/httpd-corner.t b/t/httpd-corner.t
index 68148655..514672a1 100644
--- a/t/httpd-corner.t
+++ b/t/httpd-corner.t
@@ -340,11 +340,18 @@ SKIP: {
 	is($n, 30 * 1024 * 1024, 'got expected output from curl');
 	is($non_zero, 0, 'read all zeros');
 
-	require_mods(@zmods, 2);
+	require_mods(@zmods, 4);
 	my $buf = xqx([$curl, '-sS', "$base/psgi-return-gzip"]);
 	is($?, 0, 'curl succesful');
 	IO::Uncompress::Gunzip::gunzip(\$buf => \(my $out));
 	is($out, "hello world\n");
+	my $curl_rdr = { 2 => \(my $curl_err = '') };
+	$buf = xqx([$curl, qw(-sSv --compressed),
+			"$base/psgi-return-compressible"], undef, $curl_rdr);
+	is($?, 0, 'curl --compressed successful');
+	is($buf, "goodbye world\n", 'gzipped response as expected');
+	like($curl_err, qr/\bContent-Encoding: gzip\b/,
+		'curl got gzipped response');
 }
 
 {
-- 
2.44.0