From b18ecb7707e83cb8cb38c3736aecd984999ca0a7 Mon Sep 17 00:00:00 2001
From: Eric Wong <e@80x24.org>
Date: Thu, 24 Aug 2023 01:22:33 +0000
Subject: introduce optional C++ xap_helper

This allows us to perform the expensive "dump_ibx" operations in
native C++ code using the Xapian C++ library.  This provides the
majority of the speedup with the -cindex --associate switch.

Eventually this may be expanded to cover all uses of Xapian
within the project to ensure we have access to Xapian APIs which
aren't available in XS|SWIG bindings; and also for
ease-of-installation on systems which don't provide
pre-packaged Perl Xapian bindings (e.g. OpenBSD 7.3) but
do provide Xapian development libraries.

Most of the C++ code is still C, as I'm not remotely familiar
with C++ compared to C.  I suspect many users and potential
hackers being from git, Linux kernel, and glibc world are in the
same boat.
---
 lib/PublicInbox/CidxXapHelperAux.pm | 48 +++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)
 create mode 100644 lib/PublicInbox/CidxXapHelperAux.pm

(limited to 'lib/PublicInbox/CidxXapHelperAux.pm')

diff --git a/lib/PublicInbox/CidxXapHelperAux.pm b/lib/PublicInbox/CidxXapHelperAux.pm
new file mode 100644
index 00000000..c9a5ddad
--- /dev/null
+++ b/lib/PublicInbox/CidxXapHelperAux.pm
@@ -0,0 +1,48 @@
+# Copyright (C) all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
+
+# Intended for PublicInbox::DS::event_loop for -cindex --associate,
+# this reports auxilliary status while dumping
+package PublicInbox::CidxXapHelperAux;
+use v5.12;
+use parent qw(PublicInbox::DS);
+use PublicInbox::Syscall qw(EPOLLIN);
+
+# rpipe connects to req->fp[1] in xap_helper.h
+sub new {
+	my ($cls, $rpipe, $cidx, $pfx, $associate) = @_;
+	my $self = bless {
+		cidx => $cidx,
+		pfx => $pfx,
+		associate => $associate
+	}, $cls;
+	$rpipe->blocking(0);
+	$self->SUPER::new($rpipe, EPOLLIN);
+}
+
+sub event_step {
+	my ($self) = @_; # xap_helper.h is line-buffered
+	my $buf = delete($self->{buf}) // '';
+	my $n = sysread($self->{sock}, $buf, 65536, length($buf));
+	if (!defined($n)) {
+		return if $!{EAGAIN};
+		die "sysread: $!";
+	}
+	my $pfx = $self->{pfx};
+	if ($n == 0) {
+		$self->{cidx}->progress("$pfx $buf") if $buf ne '';
+		return $self->close;
+	}
+	my @lines = split(/^/m, $buf);
+	$self->{buf} = pop @lines if substr($lines[-1], -1) ne "\n";
+	for my $l (@lines) {
+		if ($l =~ /\Amset\.size=[0-9]+\n\z/) {
+			delete $self->{cidx}->{PENDING}->{$pfx};
+			$self->{cidx}->index_next;
+		}
+		chomp $l;
+		$self->{cidx}->progress("$pfx $l");
+	}
+}
+
+1;
-- 
cgit v1.2.3-24-ge0c7