# Copyright (C) 2020 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
-
-# Qspawn filter
+#
+# In public-inbox <=1.5.0, public-inbox-httpd favored "getline"
+# response bodies to take a "pull"-based approach to feeding
+# slow clients (as opposed to a more common "push" model).
+#
+# In newer versions, public-inbox-httpd supports a backpressure-aware
+# pull/push model which also accounts for slow git blob storage.
+# {async_next} callbacks only run when the DS {wbuf} is drained
+# {async_eml} callbacks only run when a blob arrives from git.
+#
+# We continue to support getline+close for generic PSGI servers.
package PublicInbox::GzipFilter;
use strict;
use parent qw(Exporter);
-use Compress::Raw::Zlib qw(Z_FINISH Z_OK);
-our @EXPORT_OK = qw(gzip_maybe gzf_maybe);
+use Compress::Raw::Zlib qw(Z_OK);
+use PublicInbox::CompressNoop;
+use PublicInbox::Eml;
+use PublicInbox::GitAsyncCat;
+
+our @EXPORT_OK = qw(gzf_maybe);
my %OPT = (-WindowBits => 15 + 16, -AppendOutput => 1);
my @GZIP_HDRS = qw(Vary Accept-Encoding Content-Encoding gzip);
-sub new { bless {}, shift }
+sub new { bless {}, shift } # qspawn filter
# for Qspawn if using $env->{'pi-httpd.async'}
sub attach {
- my ($self, $fh) = @_;
- $self->{fh} = $fh;
+ my ($self, $http_out) = @_;
+ $self->{http_out} = $http_out; # PublicInbox::HTTP::{Chunked,Identity}
$self
}
-sub gzip_maybe ($$) {
+sub gz_or_noop {
my ($res_hdr, $env) = @_;
- return if (($env->{HTTP_ACCEPT_ENCODING}) // '') !~ /\bgzip\b/;
+ if (($env->{HTTP_ACCEPT_ENCODING} // '') =~ /\bgzip\b/) {
+ $env->{'plack.skip-deflater'} = 1;
+ push @$res_hdr, @GZIP_HDRS;
+ gzip_or_die();
+ } else {
+ PublicInbox::CompressNoop::new();
+ }
+}
- my ($gz, $err) = Compress::Raw::Zlib::Deflate->new(%OPT);
- return if $err != Z_OK;
+sub gzf_maybe ($$) { bless { gz => gz_or_noop(@_) }, __PACKAGE__ }
- # in case Plack::Middleware::Deflater is loaded:
- $env->{'plack.skip-deflater'} = 1;
+sub psgi_response {
+ my ($self, $code, $res_hdr, $next_cb, $eml_cb) = @_;
+ my $env = $self->{env};
+ $self->{gz} //= gz_or_noop($res_hdr, $env);
+ if ($env->{'pi-httpd.async'}) {
+ $self->{async_next} = $next_cb;
+ $self->{async_eml} = $eml_cb;
+ my $http = $env->{'psgix.io'}; # PublicInbox::HTTP
+ $http->{forward} = $self;
+ sub {
+ my ($wcb) = @_; # -httpd provided write callback
+ $self->{http_out} = $wcb->([$code, $res_hdr]);
+ $next_cb->($http); # start stepping
+ };
+ } else { # generic PSGI code path
+ [ $code, $res_hdr, $self ];
+ }
+}
+sub qsp_maybe ($$) {
+ my ($res_hdr, $env) = @_;
+ return if ($env->{HTTP_ACCEPT_ENCODING} // '') !~ /\bgzip\b/;
+ my $hdr = join("\n", @$res_hdr);
+ return if $hdr !~ m!^Content-Type\n
+ (?:(?:text/(?:html|plain))|
+ application/atom\+xml)\b!ixsm;
+ return if $hdr =~ m!^Content-Encoding\ngzip\n!smi;
+ return if $hdr =~ m!^Content-Length\n[0-9]+\n!smi;
+ return if $hdr =~ m!^Transfer-Encoding\n!smi;
+ # in case Plack::Middleware::Deflater is loaded:
+ return if $env->{'plack.skip-deflater'}++;
push @$res_hdr, @GZIP_HDRS;
- $gz;
+ bless {}, __PACKAGE__;
}
-sub gzf_maybe ($$) {
- my ($res_hdr, $env) = @_;
- my $gz = gzip_maybe($res_hdr, $env) or return 0;
- bless { gz => $gz }, __PACKAGE__;
+sub gzip_or_die () {
+ my ($gz, $err) = Compress::Raw::Zlib::Deflate->new(%OPT);
+ $err == Z_OK or die "Deflate->new failed: $err";
+ $gz;
}
# for GetlineBody (via Qspawn) when NOT using $env->{'pi-httpd.async'}
# Also used for ->getline callbacks
sub translate ($$) {
- my $self = $_[0];
+ my $self = $_[0]; # $_[1] => input
# allocate the zlib context lazily here, instead of in ->new.
# Deflate contexts are memory-intensive and this object may
# be sitting in the Qspawn limiter queue for a while.
- my $gz = $self->{gz} //= do {
- my ($g, $err) = Compress::Raw::Zlib::Deflate->new(%OPT);
- $err == Z_OK or die "Deflate->new failed: $err";
- $g;
- };
+ my $gz = $self->{gz} //= gzip_or_die();
my $zbuf = delete($self->{zbuf});
if (defined $_[1]) { # my $buf = $_[1];
my $err = $gz->deflate($_[1], $zbuf);
$self->{zbuf} = $zbuf;
'';
} else { # undef == EOF
- my $err = $gz->flush($zbuf, Z_FINISH);
+ my $err = $gz->flush($zbuf);
die "gzip->flush: $err" if $err != Z_OK;
$zbuf;
}
sub write {
# my $ret = bytes::length($_[1]); # XXX does anybody care?
- $_[0]->{fh}->write(translate($_[0], $_[1]));
+ $_[0]->{http_out}->write(translate($_[0], $_[1]));
+}
+
+# similar to ->translate; use this when we're sure we know we have
+# more data to buffer after this
+sub zmore {
+ my $self = $_[0]; # $_[1] => input
+ my $err = $self->{gz}->deflate($_[1], $self->{zbuf});
+ die "gzip->deflate: $err" if $err != Z_OK;
+ undef;
+}
+
+# flushes and returns the final bit of gzipped data
+sub zflush ($;$) {
+ my $self = $_[0]; # $_[1] => final input (optional)
+ my $zbuf = delete $self->{zbuf};
+ my $gz = delete $self->{gz};
+ my $err;
+ if (defined $_[1]) {
+ $err = $gz->deflate($_[1], $zbuf);
+ die "gzip->deflate: $err" if $err != Z_OK;
+ }
+ $err = $gz->flush($zbuf);
+ die "gzip->flush: $err" if $err != Z_OK;
+ $zbuf;
}
sub close {
my ($self) = @_;
- my $fh = delete $self->{fh};
- $fh->write(translate($self, undef));
- $fh->close;
+ if (my $http_out = delete $self->{http_out}) {
+ $http_out->write(zflush($self));
+ $http_out->close;
+ }
+}
+
+# this is public-inbox-httpd-specific
+sub async_blob_cb { # git->cat_async callback
+ my ($bref, $oid, $type, $size, $self) = @_;
+ my $http = $self->{env}->{'psgix.io'} or return; # client abort
+ my $smsg = $self->{smsg} or die 'BUG: no smsg';
+ if (!defined($oid)) {
+ # it's possible to have TOCTOU if an admin runs
+ # public-inbox-(edit|purge), just move onto the next message
+ return $http->next_step($self->{async_next});
+ }
+ $smsg->{blob} eq $oid or die "BUG: $smsg->{blob} != $oid";
+ $self->{async_eml}->($self, PublicInbox::Eml->new($bref));
+ $http->next_step($self->{async_next});
+}
+
+sub smsg_blob {
+ my ($self, $smsg) = @_;
+ git_async_cat($self->{-inbox}->git, $smsg->{blob},
+ \&async_blob_cb, $self);
}
1;