X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FWwwStatic.pm;h=eeb5e565039ec47c7a715e1ae2c6d993cbb2dbbf;hb=8d2513221e73649aed85ce8c3f37f7025ec1fec9;hp=bc42236e57b6e6442db9c7351e76587f68d3d871;hpb=078f637c80cc33c7d29973b95fdc16205ad7bb32;p=public-inbox.git

diff --git a/lib/PublicInbox/WwwStatic.pm b/lib/PublicInbox/WwwStatic.pm
index bc42236e..eeb5e565 100644
--- a/lib/PublicInbox/WwwStatic.pm
+++ b/lib/PublicInbox/WwwStatic.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2016-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2016-2021 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
 # This package can either be a PSGI response body for a static file
@@ -9,14 +9,15 @@
 # functionality of nginx.
 package PublicInbox::WwwStatic;
 use strict;
+use v5.10.1;
 use parent qw(Exporter);
-use bytes ();
 use Fcntl qw(SEEK_SET O_RDONLY O_NONBLOCK);
-use POSIX qw(strftime lround);
+use POSIX qw(strftime);
 use HTTP::Date qw(time2str);
 use HTTP::Status qw(status_message);
 use Errno qw(EACCES ENOTDIR ENOENT);
 use URI::Escape qw(uri_escape_utf8);
+use PublicInbox::GzipFilter qw(gzf_maybe);
 use PublicInbox::Hval qw(ascii_html);
 use Plack::MIME;
 our @EXPORT_OK = qw(@NO_CACHE r path_info_raw);
@@ -51,7 +52,19 @@ sub r ($;$) {
 	  [ $msg ] ]
 }
 
-sub prepare_range {
+sub getline_response ($$$$$) {
+	my ($env, $in, $off, $len, $path) = @_;
+	my $r = bless {}, __PACKAGE__;
+	if ($env->{'pi-httpd.async'}) { # public-inbox-httpd-only mode
+		$env->{'psgix.no-compress'} = 1; # do not chunk response
+		%$r = ( bypass => [$in, $off, $len, $env->{'psgix.io'}] );
+	} else {
+		%$r = ( in => $in, off => $off, len => $len, path => $path );
+	}
+	$r;
+}
+
+sub setup_range {
 	my ($env, $in, $h, $beg, $end, $size) = @_;
 	my $code = 200;
 	my $len = $size;
@@ -81,9 +94,6 @@ sub prepare_range {
 		if ($len <= 0) {
 			$code = 416;
 		} else {
-			if ($in) {
-				sysseek($in, $beg, SEEK_SET) or return r(500);
-			}
 			push @$h, qw(Accept-Ranges bytes Content-Range);
 			push @$h, "bytes $beg-$end/$size";
 
@@ -95,7 +105,7 @@ sub prepare_range {
 		push @$h, 'Content-Range', "bytes */$size";
 		return [ 416, $h, [] ];
 	}
-	($code, $len);
+	($code, $beg, $len);
 }
 
 # returns a PSGI arrayref response iff .gz and non-.gz mtimes match
@@ -108,7 +118,9 @@ sub try_gzip_static ($$$$) {
 	return unless -f $gz && (stat(_))[9] == $mtime;
 	my $res = response($env, $h, $gz, $type);
 	return if ($res->[0] > 300 || $res->[0] < 200);
-	push @{$res->[1]}, qw(Cache-Control no-transform Content-Encoding gzip);
+	push @{$res->[1]}, qw(Cache-Control no-transform
+				Content-Encoding gzip
+				Vary Accept-Encoding);
 	$res;
 }
 
@@ -142,43 +154,41 @@ sub response ($$$;$) {
 	my $len = $size;
 	my $code = 200;
 	push @$h, 'Content-Type', $type;
+	my $off = 0;
 	if (($env->{HTTP_RANGE} || '') =~ /\bbytes=([0-9]*)-([0-9]*)\z/) {
-		($code, $len) = prepare_range($env, $in, $h, $1, $2, $size);
+		($code, $off, $len) = setup_range($env, $in, $h, $1, $2, $size);
 		return $code if ref($code);
 	}
 	push @$h, 'Content-Length', $len, 'Last-Modified', $mtime;
-	my $body = $in ? bless {
-		initial_rd => 65536,
-		len => $len,
-		in => $in,
-		path => $path,
-		env => $env,
-	}, __PACKAGE__ : [];
-	[ $code, $h, $body ];
+	[ $code, $h, $in ? getline_response($env, $in, $off, $len, $path) : [] ]
 }
 
 # called by PSGI servers on each response chunk:
 sub getline {
 	my ($self) = @_;
+
+	# avoid buffering, by becoming the buffer! (public-inbox-httpd)
+	if (my $tmpio = delete $self->{bypass}) {
+		my $http = pop @$tmpio; # PublicInbox::HTTP
+		push @{$http->{wbuf}}, $tmpio; # [ $in, $off, $len ]
+		$http->flush_write;
+		return; # undef, EOF
+	}
+
+	# generic PSGI runs this:
 	my $len = $self->{len} or return; # undef, tells server we're done
-	my $n = delete($self->{initial_rd}) // 8192;
+	my $n = 8192;
 	$n = $len if $len < $n;
+	sysseek($self->{in}, $self->{off}, SEEK_SET) or
+			die "sysseek ($self->{path}): $!";
 	my $r = sysread($self->{in}, my $buf, $n);
 	if (defined $r && $r > 0) { # success!
 		$self->{len} = $len - $r;
+		$self->{off} += $r;
 		return $buf;
 	}
 	my $m = defined $r ? "EOF with $len bytes left" : "read error: $!";
-	my $env = $self->{env};
-	$env->{'psgi.errors'}->print("$self->{path} $m\n");
-
-	# drop the client on error
-	if (my $io = $env->{'psgix.io'}) {
-		$io->close; # this is likely PublicInbox::DS::close
-	} else { # for some PSGI servers w/o psgix.io
-		die "dropping client socket\n";
-	}
-	undef;
+	die "$self->{path} $m, dropping client socket\n";
 }
 
 sub close {} # noop, called by PSGI server, just let everything go out-of-scope
@@ -208,7 +218,7 @@ my %path_re_cache;
 sub path_info_raw ($) {
 	my ($env) = @_;
 	my $sn = $env->{SCRIPT_NAME};
-	my $re = $path_re_cache{$sn} ||= do {
+	my $re = $path_re_cache{$sn} //= do {
 		$sn = '/'.$sn unless index($sn, '/') == 0;
 		$sn =~ s!/\z!!;
 		qr!\A(?:https?://[^/]+)?\Q$sn\E(/[^\?\#]+)!;
@@ -238,7 +248,7 @@ sub human_size ($) {
 			last;
 		}
 	}
-	lround($size).$suffix;
+	sprintf('%lu', $size).$suffix;
 }
 
 # by default, this returns "index.html" if it exists for a given directory
@@ -301,12 +311,15 @@ sub dir_response ($$$) {
 			(map { ${$other{$_}} } sort keys %other));
 
 	my $path_info_html = ascii_html($path_info);
-	my $body = "<html><head><title>Index of $path_info_html</title>" .
+	my $h = [qw(Content-Type text/html Content-Length), undef];
+	my $gzf = gzf_maybe($h, $env);
+	$gzf->zmore("<html><head><title>Index of $path_info_html</title>" .
 		${$self->{style}} .
-		"</head><body><pre>Index of $path_info_html</pre><hr><pre>\n";
-	$body .= join("\n", @entries) . "</pre><hr></body></html>\n";
-	[ 200, [ qw(Content-Type text/html
-			Content-Length), bytes::length($body) ], [ $body ] ]
+		"</head><body><pre>Index of $path_info_html</pre><hr><pre>\n");
+	$gzf->zmore(join("\n", @entries));
+	my $out = $gzf->zflush("</pre><hr></body></html>\n");
+	$h->[3] = length($out);
+	[ 200, $h, [ $out ] ]
 }
 
 sub call { # PSGI app endpoint