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 3599B1F5B1
	for <meta@public-inbox.org>; Sun,  5 Jul 2020 23:28:00 +0000 (UTC)
From: Eric Wong <e@yhbt.net>
To: meta@public-inbox.org
Subject: [PATCH 02/43] wwwstream: oneshot: perform gzip without middleware
Date: Sun,  5 Jul 2020 23:27:18 +0000
Message-Id: <20200705232759.3161-3-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>

Plack::Middleware::Deflater forces us to use a memory-intensive
closure.  Instead, work towards building compressed strings in
memory to reduce the overhead of buffering large HTML output.
---
 lib/PublicInbox/GzipFilter.pm | 13 +++++++++++++
 lib/PublicInbox/WwwStream.pm  | 27 ++++++++++++++++++++++-----
 2 files changed, 35 insertions(+), 5 deletions(-)

diff --git a/lib/PublicInbox/GzipFilter.pm b/lib/PublicInbox/GzipFilter.pm
index a7355a8df..115660cb1 100644
--- a/lib/PublicInbox/GzipFilter.pm
+++ b/lib/PublicInbox/GzipFilter.pm
@@ -4,7 +4,9 @@
 # Qspawn filter
 package PublicInbox::GzipFilter;
 use strict;
+use parent qw(Exporter);
 use Compress::Raw::Zlib qw(Z_FINISH Z_OK);
+our @EXPORT_OK = qw(gzip_maybe);
 my %OPT = (-WindowBits => 15 + 16, -AppendOutput => 1);
 
 sub new { bless {}, shift }
@@ -16,6 +18,17 @@ sub attach {
 	$self
 }
 
+sub gzip_maybe ($) {
+	my ($env) = @_;
+	return if (($env->{HTTP_ACCEPT_ENCODING}) // '') !~ /\bgzip\b/;
+
+	# in case Plack::Middleware::Deflater is loaded:
+	$env->{'plack.skip-deflater'} = 1;
+
+	my ($gz, $err) = Compress::Raw::Zlib::Deflate->new(%OPT);
+	$err == Z_OK ? $gz : undef;
+}
+
 # for GetlineBody (via Qspawn) when NOT using $env->{'pi-httpd.async'}
 sub translate ($$) {
 	my $self = $_[0];
diff --git a/lib/PublicInbox/WwwStream.pm b/lib/PublicInbox/WwwStream.pm
index 915a71ba0..79ed6871e 100644
--- a/lib/PublicInbox/WwwStream.pm
+++ b/lib/PublicInbox/WwwStream.pm
@@ -13,6 +13,8 @@ use base qw(Exporter);
 our @EXPORT_OK = qw(html_oneshot);
 use bytes (); # length
 use PublicInbox::Hval qw(ascii_html prurl);
+use Compress::Raw::Zlib qw(Z_FINISH Z_OK);
+use PublicInbox::GzipFilter qw(gzip_maybe);
 our $TOR_URL = 'https://www.torproject.org/';
 our $CODE_URL = 'https://public-inbox.org/public-inbox.git';
 
@@ -178,13 +180,28 @@ sub html_oneshot ($$;$) {
 		ctx => $ctx,
 		base_url => base_url($ctx),
 	}, __PACKAGE__;
-	my @x = (_html_top($self), $sref ? $$sref : (), _html_end($self));
+	my @x;
+	my @h = ('Content-Type' => 'text/html; charset=UTF-8');
+	if (my $gz = gzip_maybe($ctx->{env})) {
+		my $err = $gz->deflate(_html_top($self), $x[0]);
+		die "gzip->deflate: $err" if $err != Z_OK;
+		if ($sref) {
+			$err = $gz->deflate($sref, $x[0]);
+			die "gzip->deflate: $err" if $err != Z_OK;
+		}
+		$err = $gz->deflate(_html_end($self), $x[0]);
+		die "gzip->deflate: $err" if $err != Z_OK;
+		$err = $gz->flush($x[0], Z_FINISH);
+		die "gzip->flush: $err" if $err != Z_OK;
+		push @h, qw(Vary Accept-Encoding Content-Encoding gzip);
+	} else {
+		@x = (_html_top($self), $sref ? $$sref : (), _html_end($self));
+	}
+
 	my $len = 0;
 	$len += bytes::length($_) for @x;
-	[ $code, [
-		'Content-Type' => 'text/html; charset=UTF-8',
-		'Content-Length' => $len
-	], \@x ];
+	push @h, 'Content-Length', $len;
+	[ $code, \@h, \@x ]
 }
 
 1;