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/Search.pm | 56 +++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 49 insertions(+), 7 deletions(-)

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

diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index d5b0bceb..2e784646 100644
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -66,6 +66,15 @@ our $NVRP; # '$Xap::'.('NumberValueRangeProcessor' or 'NumberRangeProcessor')
 # let's hope the ABI is stable
 our $ENQ_DESCENDING = 0;
 our $ENQ_ASCENDING = 1;
+our @MAIL_VMAP = (
+	[ YYYYMMDD, 'd:'],
+	[ DT, 'dt:' ],
+	# these are undocumented for WWW, but lei and IMAP use them
+	[ BYTES, 'z:' ],
+	[ TS, 'rt:' ],
+	[ UID, 'uid:' ]
+);
+our @MAIL_NRP;
 
 sub load_xapian () {
 	return 1 if defined $Xap;
@@ -101,6 +110,7 @@ sub load_xapian () {
 		# or make indexlevel=medium as default
 		$QP_FLAGS = FLAG_PHRASE() | FLAG_BOOLEAN() | FLAG_LOVEHATE() |
 				FLAG_WILDCARD();
+		@MAIL_NRP = map { $NVRP->new(@$_) } @MAIL_VMAP;
 		return 1;
 	}
 	undef;
@@ -490,14 +500,8 @@ sub qparse_new {
 	my $qp = qp_init_common($self);
 	my $cb = $qp->can('add_valuerangeprocessor') //
 		$qp->can('add_rangeprocessor'); # Xapian 1.5.0+
-	$cb->($qp, $NVRP->new(YYYYMMDD, 'd:'));
-	$cb->($qp, $NVRP->new(DT, 'dt:'));
-
-	# for IMAP, undocumented for WWW and may be split off go away
-	$cb->($qp, $NVRP->new(BYTES, 'z:'));
-	$cb->($qp, $NVRP->new(TS, 'rt:'));
-	$cb->($qp, $NVRP->new(UID, 'uid:'));
 
+	$cb->($qp, $_) for @MAIL_NRP;
 	while (my ($name, $prefix) = each %bool_pfx_external) {
 		$qp->add_boolean_prefix($name, $_) foreach split(/ /, $prefix);
 	}
@@ -527,6 +531,40 @@ EOF
 	$qp;
 }
 
+sub generate_cxx () { # generates snippet for xap_helper.h
+	my $ret = <<EOM;
+# line ${\__LINE__} "${\__FILE__}"
+static NRP *mail_nrp[${\scalar(@MAIL_VMAP)}];
+static void mail_nrp_init(void)
+{
+EOM
+	for (0..$#MAIL_VMAP) {
+		my $x = $MAIL_VMAP[$_];
+		$ret .= qq{\tmail_nrp[$_] = new NRP($x->[0], "$x->[1]");\n}
+	}
+$ret .= <<EOM;
+}
+
+# line ${\__LINE__} "${\__FILE__}"
+static void qp_init_mail_search(Xapian::QueryParser *qp)
+{
+	for (size_t i = 0; i < MY_ARRAY_SIZE(mail_nrp); i++)
+		qp->ADD_RP(mail_nrp[i]);
+EOM
+	for my $name (sort keys %bool_pfx_external) {
+		for (split(/ /, $bool_pfx_external{$name})) {
+			$ret .= qq{\tqp->add_boolean_prefix("$name", "$_");\n}
+		}
+	}
+	# TODO: altid support
+	for my $name (sort keys %prob_prefix) {
+		for (split(/ /, $prob_prefix{$name})) {
+			$ret .= qq{\tqp->add_prefix("$name", "$_");\n}
+		}
+	}
+	$ret .= "}\n";
+}
+
 sub help {
 	my ($self) = @_;
 	$self->{qp} //= $self->qparse_new; # parse altids
@@ -585,4 +623,8 @@ sub all_terms {
 	wantarray ? (sort keys %ret) : \%ret;
 }
 
+sub xh_args { # prep getopt args to feed to xap_helper.h socket
+	map { ('-d', $_) } shard_dirs($_[0]);
+}
+
 1;
-- 
cgit v1.2.3-24-ge0c7