From 9987cc1cc687f3b2d03a78938773c4f0c5b64d98 Mon Sep 17 00:00:00 2001
From: Eric Wong <e@80x24.org>
Date: Wed, 24 Apr 2024 06:44:47 +0000
Subject: www: wire up search to use async xap_helper

The C++ version of xap_helper will allow more complex and
expensive queries.  Both the Perl and C++-only version will
allow offloading search into a separate process which can be
killed via ITIMER_REAL or RLIMIT_CPU in the face of overload.

The xap_helper `mset' command wrapper is simplified to
unconditionally return rank, percentage, and estimated matches
information.  This may slightly penalize mbox retrievals and
lei users, but perhaps that can be a different command entirely.
---
 lib/PublicInbox/Search.pm | 52 ++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 51 insertions(+), 1 deletion(-)

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

diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index 0196dd45..60d12dbf 100644
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -11,6 +11,7 @@ our @EXPORT_OK = qw(retry_reopen int_val get_pct xap_terms);
 use List::Util qw(max);
 use POSIX qw(strftime);
 use Carp ();
+our $XHC;
 
 # values for searching, changing the numeric value breaks
 # compatibility with old indices (so don't change them it)
@@ -85,7 +86,6 @@ our @XH_SPEC = (
 	'k=i', # sort column (like sort(1))
 	'm=i', # maximum number of results
 	'o=i', # offset
-	'p', # show percent
 	'r', # 1=relevance then column
 	't', # collapse threads
 	'A=s@', # prefixes
@@ -428,6 +428,56 @@ sub mset {
 	do_enquire($self, $qry, $opt, TS);
 }
 
+sub xhc_start_maybe () {
+	require PublicInbox::XapClient;
+	my $xhc = PublicInbox::XapClient::start_helper();
+	require PublicInbox::XhcMset if $xhc;
+	$xhc;
+}
+
+sub xh_opt ($) {
+	my ($opt) = @_;
+	my $lim = $opt->{limit} || 50;
+	my @ret;
+	push @ret, '-o', $opt->{offset} if $opt->{offset};
+	push @ret, '-m', $lim;
+	my $rel = $opt->{relevance} // 0;
+	if ($rel == -2) { # ORDER BY docid/UID (highest first)
+		push @ret, '-k', '-1';
+	} elsif ($rel == -1) { # ORDER BY docid/UID (lowest first)
+		push @ret, '-k', '-1';
+		push @ret, '-a';
+	} elsif ($rel == 0) {
+		push @ret, '-k', $opt->{sort_col} // TS;
+		push @ret, '-a' if $opt->{asc};
+	} else { # rel > 0
+		push @ret, '-r';
+		push @ret, '-k', $opt->{sort_col} // TS;
+		push @ret, '-a' if $opt->{asc};
+	}
+	push @ret, '-t' if $opt->{threads};
+	push @ret, '-T', $opt->{threadid} if defined $opt->{threadid};
+	push @ret, '-O', $opt->{eidx_key} if defined $opt->{eidx_key};
+	@ret;
+}
+
+# returns a true value if actually handled asynchronously,
+# and a falsy value if handled synchronously
+sub async_mset {
+	my ($self, $qry_str, $opt, $cb, @args) = @_;
+	$XHC //= xhc_start_maybe;
+	if ($XHC) { # unconditionally retrieving pct + rank for now
+		xdb($self); # populate {nshards}
+		my @margs = ($self->xh_args, xh_opt($opt));
+		my $rd = $XHC->mkreq(undef, 'mset', @margs, $qry_str);
+		PublicInbox::XhcMset->maybe_new($rd, $self, $cb, @args);
+	} else { # synchronous
+		my $mset = $self->mset($qry_str, $opt);
+		$cb->(@args, $mset);
+		undef;
+	}
+}
+
 sub do_enquire { # shared with CodeSearch
 	my ($self, $qry, $opt, $col) = @_;
 	my $enq = $X{Enquire}->new(xdb($self));
-- 
cgit v1.2.3-24-ge0c7