From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <e@yhbt.net>
X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net
X-Spam-Level: 
X-Spam-Status: No, score=-4.0 required=3.0 tests=ALL_TRUSTED,BAYES_00
	shortcircuit=no autolearn=ham autolearn_force=no version=3.4.2
Received: from localhost (dcvr.yhbt.net [127.0.0.1])
	by dcvr.yhbt.net (Postfix) with ESMTP id 220881F8DB
	for <meta@public-inbox.org>; Sun,  5 Jul 2020 23:28:01 +0000 (UTC)
From: Eric Wong <e@yhbt.net>
To: meta@public-inbox.org
Subject: [PATCH 04/43] wwwtext: gzip text/plain responses, as well
Date: Sun,  5 Jul 2020 23:27:20 +0000
Message-Id: <20200705232759.3161-5-e@yhbt.net>
In-Reply-To: <20200705232759.3161-1-e@yhbt.net>
References: <20200705232759.3161-1-e@yhbt.net>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
List-Id: <meta.public-inbox.org>

Most of our plain-text responses are config files
big enough to warrant compression.
---
 lib/PublicInbox/WwwText.pm | 17 ++++++++++++++---
 t/psgi_text.t              | 33 ++++++++++++++++++++++++++-------
 2 files changed, 40 insertions(+), 10 deletions(-)

diff --git a/lib/PublicInbox/WwwText.pm b/lib/PublicInbox/WwwText.pm
index b23a415e4..508005fba 100644
--- a/lib/PublicInbox/WwwText.pm
+++ b/lib/PublicInbox/WwwText.pm
@@ -10,6 +10,8 @@ use PublicInbox::Linkify;
 use PublicInbox::WwwStream;
 use PublicInbox::Hval qw(ascii_html);
 use URI::Escape qw(uri_escape_utf8);
+use PublicInbox::GzipFilter qw(gzf_maybe);
+use Compress::Raw::Zlib qw(Z_FINISH Z_OK);
 our $QP_URL = 'https://xapian.org/docs/queryparser.html';
 our $WIKI_URL = 'https://en.wikipedia.org/wiki';
 my $hl = eval {
@@ -35,14 +37,23 @@ sub get_text {
 		$code = 404;
 		$txt = "404 Not Found ($key)\n";
 	}
+	my $env = $ctx->{env};
 	if ($raw) {
-		$hdr->[3] = bytes::length($txt);
-		return [ $code, $hdr, [ $txt ] ]
+		my $body;
+		if (my $gzf = $code == 200 ? gzf_maybe($hdr, $env) : undef) {
+			my $zbuf = $gzf->translate($txt);
+			undef $txt;
+			$body = [ $zbuf .= $gzf->translate(undef) ];
+		} else {
+			$body = [ $txt ];
+		}
+		$hdr->[3] = bytes::length($body->[0]);
+		return [ $code, $hdr, $body ]
 	}
 
 	# enforce trailing slash for "wget -r" compatibility
 	if (!$have_tslash && $code == 200) {
-		my $url = $ctx->{-inbox}->base_url($ctx->{env});
+		my $url = $ctx->{-inbox}->base_url($env);
 		$url .= "_/text/$key/";
 
 		return [ 302, [ 'Content-Type', 'text/plain',
diff --git a/t/psgi_text.t b/t/psgi_text.t
index 833bcaba7..9867feaa4 100644
--- a/t/psgi_text.t
+++ b/t/psgi_text.t
@@ -10,7 +10,7 @@ my $maindir = "$tmpdir/main.git";
 my $addr = 'test-public@example.com';
 my $cfgpfx = "publicinbox.test";
 my @mods = qw(HTTP::Request::Common Plack::Test URI::Escape Plack::Builder);
-require_mods(@mods);
+require_mods(@mods, 'IO::Uncompress::Gunzip');
 use_ok $_ foreach @mods;
 use PublicInbox::Import;
 use PublicInbox::Git;
@@ -26,17 +26,36 @@ my $www = PublicInbox::WWW->new($config);
 
 test_psgi(sub { $www->call(@_) }, sub {
 	my ($cb) = @_;
-	my $res;
-	$res = $cb->(GET('/test/_/text/help/'));
-	like($res->content, qr!<title>public-inbox help.*</title>!,
-		'default help');
-	$res = $cb->(GET('/test/_/text/config/raw'));
+	my $gunzipped;
+	my $req = GET('/test/_/text/help/');
+	my $res = $cb->($req);
+	my $content = $res->content;
+	like($content, qr!<title>public-inbox help.*</title>!, 'default help');
+	$req->header('Accept-Encoding' => 'gzip');
+	$res = $cb->($req);
+	is($res->header('Content-Encoding'), 'gzip', 'got gzip encoding');
+	is($res->header('Content-Type'), 'text/html; charset=UTF-8',
+		'got gzipped HTML');
+	IO::Uncompress::Gunzip::gunzip(\($res->content) => \$gunzipped);
+	is($gunzipped, $content, 'gzipped content is correct');
+
+	$req = GET('/test/_/text/config/raw');
+	$res = $cb->($req);
+	$content = $res->content;
+	my $olen = $res->header('Content-Length');
 	my $f = "$tmpdir/cfg";
 	open my $fh, '>', $f or die;
-	print $fh $res->content or die;
+	print $fh $content or die;
 	close $fh or die;
 	my $cfg = PublicInbox::Config->new($f);
 	is($cfg->{"$cfgpfx.address"}, $addr, 'got expected address in config');
+
+	$req->header('Accept-Encoding' => 'gzip');
+	$res = $cb->($req);
+	is($res->header('Content-Encoding'), 'gzip', 'got gzip encoding');
+	ok($res->header('Content-Length') < $olen, 'gzipped help is smaller');
+	IO::Uncompress::Gunzip::gunzip(\($res->content) => \$gunzipped);
+	is($gunzipped, $content);
 });
 
 done_testing();