qspawn: reinstate filter support, add gzip filter

[public-inbox.git] / lib / PublicInbox / Qspawn.pm

diff --git a/lib/PublicInbox/Qspawn.pm b/lib/PublicInbox/Qspawn.pm
index 65bb178aba44a216f73c221338aebd5f7a9dba92..52aea3eba472e0ff8bfe2b79e21893eb24c1ff56 100644 (file)
--- a/lib/PublicInbox/Qspawn.pm
+++ b/lib/PublicInbox/Qspawn.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2016-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2016-2020 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
 # Like most Perl modules in public-inbox, this is internal and
@@ -45,25 +45,28 @@ sub new ($$$;) {
 sub _do_spawn {
        my ($self, $start_cb, $limiter) = @_;
        my $err;
-       my ($cmd, $cmd_env, $opts) = @{$self->{args}};
-       my %opts = %{$opts || {}};
+       my ($cmd, $cmd_env, $opt) = @{$self->{args}};
+       my %o = %{$opt || {}};
        $self->{limiter} = $limiter;
        foreach my $k (PublicInbox::Spawn::RLIMITS()) {
                if (defined(my $rlimit = $limiter->{$k})) {
-                       $opts{$k} = $rlimit;
+                       $o{$k} = $rlimit;
                }
        }
+       eval {
+               # popen_rd may die on EMFILE, ENFILE
+               ($self->{rpipe}, $self->{pid}) = popen_rd($cmd, $cmd_env, \%o);
+               $self->{args} = $o{quiet} ? undef : $cmd;
 
-       ($self->{rpipe}, $self->{pid}) = popen_rd($cmd, $cmd_env, \%opts);
+               die "E: $!" unless defined($self->{pid});
 
-       $self->{args} = $opts{quiet} ? undef : $cmd;
-
-       if (defined $self->{pid}) {
                $limiter->{running}++;
-       } else {
-               $self->{err} = $!;
+               $start_cb->($self); # EPOLL_CTL_ADD may ENOSPC/ENOMEM
+       };
+       if ($@) {
+               $self->{err} = $@;
+               finish($self);
        }
-       $start_cb->($self);
 }
 
 sub child_err ($) {
@@ -105,7 +108,11 @@ sub waitpid_err ($$) {
        }
 
        if ($err) {
-               $self->{err} = $err;
+               if ($self->{err}) {
+                       $self->{err} .= "; $err";
+               } else {
+                       $self->{err} = $err;
+               }
                if ($env && $self->{args}) {
                        log_err($env, join(' ', @{$self->{args}}) . ": $err");
                }
@@ -157,7 +164,7 @@ reread:
                $async->async_pass($self->{psgi_env}->{'psgix.io'},
                                        $qx_fh, \$buf);
        } elsif (defined $r) {
-               $r ? $qx_fh->write($buf) : event_step($self, undef);
+               $r ? (print $qx_fh $buf) : event_step($self, undef);
        } else {
                return if $! == EAGAIN; # try again when notified
                goto reread if $! == EINTR;
@@ -236,6 +243,7 @@ sub psgi_return_init_cb {
        my ($self) = @_;
        my $r = rd_hdr($self) or return;
        my $env = $self->{psgi_env};
+       my $filter = delete $env->{'qspawn.filter'};
        my $wcb = delete $env->{'qspawn.wcb'};
        my $async = delete $self->{async};
        if (scalar(@$r) == 3) { # error
@@ -250,6 +258,7 @@ sub psgi_return_init_cb {
        } elsif ($async) {
                # done reading headers, handoff to read body
                my $fh = $wcb->($r); # scalar @$r == 2
+               $fh = $filter->attach($fh) if $filter;
                $self->{fh} = $fh;
                $async->async_pass($env->{'psgix.io'}, $fh,
                                        delete($self->{hdr_buf}));
@@ -257,7 +266,7 @@ sub psgi_return_init_cb {
                require PublicInbox::GetlineBody;
                $r->[2] = PublicInbox::GetlineBody->new($self->{rpipe},
                                        \&event_step, $self,
-                                       ${$self->{hdr_buf}});
+                                       ${$self->{hdr_buf}}, $filter);
                $wcb->($r);
        }
 
@@ -287,6 +296,10 @@ sub psgi_return_start { # may run later, much later...
 #                          psgi_return will return an anonymous
 #                          sub for the PSGI server to call
 #
+#   $env->{'qspawn.filter'} - filter object, responds to ->attach for
+#                             pi-httpd.async and ->translate for generic
+#                             PSGI servers
+#
 # $limiter - the Limiter object to use (uses the def_limiter if not given)
 #
 # $parse_hdr - Initial read function; often for parsing CGI header output.