X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FMiscSearch.pm;h=c6d2a062a66865e8774aee9c8bee9ddf248c8db5;hb=99a78c2ac51f63de41ccfc27e504d9b0e54d0592;hp=c6ce255fc90ffebe94aba7d2de4619d28ad7ae3c;hpb=4a2e89007cb7b62151cb1869e49b27ebacfc27eb;p=public-inbox.git

diff --git a/lib/PublicInbox/MiscSearch.pm b/lib/PublicInbox/MiscSearch.pm
index c6ce255f..c6d2a062 100644
--- a/lib/PublicInbox/MiscSearch.pm
+++ b/lib/PublicInbox/MiscSearch.pm
@@ -1,11 +1,11 @@
-# Copyright (C) 2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2020-2021 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
 # read-only counterpart to MiscIdx
 package PublicInbox::MiscSearch;
 use strict;
 use v5.10.1;
-use PublicInbox::Search qw(retry_reopen int_val);
+use PublicInbox::Search qw(retry_reopen int_val xap_terms);
 my $json;
 
 # Xapian value columns:
@@ -59,7 +59,7 @@ sub misc_enquire_once { # retry_reopen callback
 	$eq->set_query($qr);
         my $desc = !$opt->{asc};
 	my $rel = $opt->{relevance} // 0;
-	if ($rel == -1) { # ORDER BY docid/UID
+	if ($rel == -1) { # ORDER BY docid
 		$eq->set_docid_order($PublicInbox::Search::ENQ_ASCENDING);
 		$eq->set_weighting_scheme($PublicInbox::Search::X{BoolWeight}->new);
 	} elsif ($rel) {
@@ -73,6 +73,7 @@ sub misc_enquire_once { # retry_reopen callback
 sub mset {
 	my ($self, $qs, $opt) = @_;
 	$opt ||= {};
+	reopen($self);
 	my $qp = $self->{qp} //= mi_qp_new($self);
 	$qs = 'type:inbox' if $qs eq '';
 	my $qr = $qp->parse_query($qs, $PublicInbox::Search::QP_FLAGS);
@@ -80,46 +81,6 @@ sub mset {
 	retry_reopen($self, \&misc_enquire_once, $qr, $opt);
 }
 
-sub ibx_matches_once { # retry_reopen callback
-	my ($self, $qr, $by_newsgroup) = @_;
-	# double in case no newsgroups are configured:
-	my $limit = scalar(keys %$by_newsgroup) * 2;
-	my $opt = { limit => $limit, offset => 0, relevance => -1 };
-	my $ret = {}; # newsgroup => $ibx of matches
-	while (1) {
-		my $mset = misc_enquire_once($self, $qr, $opt);
-		for my $mi ($mset->items) {
-			my $doc = $mi->get_document;
-			my $end = $doc->termlist_end;
-			my $cur = $doc->termlist_begin;
-			$cur->skip_to('Q');
-			if ($cur != $end) {
-				my $ng = $cur->get_termname; # eidx_key
-				$ng =~ s/\AQ// or warn "BUG: no `Q': $ng";
-				if (my $ibx = $by_newsgroup->{$ng}) {
-					$ret->{$ng} = $ibx;
-				}
-			} else {
-				warn <<EOF;
-W: docid=${\$mi->get_docid} has no `Q' (eidx_key) term
-EOF
-			}
-		}
-		my $nr = $mset->size;
-		return $ret if $nr < $limit;
-		$opt->{offset} += $nr;
-	}
-}
-
-# returns a newsgroup => PublicInbox::Inbox mapping
-sub newsgroup_matches {
-	my ($self, $qs, $pi_cfg) = @_;
-	my $qp = $self->{qp} //= mi_qp_new($self);
-	$qs .= ' type:inbox';
-	my $qr = $qp->parse_query($qs, $PublicInbox::Search::QP_FLAGS);
-	retry_reopen($self, \&ibx_matches_once, $qr, $pi_cfg->{-by_newsgroup});
-}
-
 sub ibx_data_once {
 	my ($self, $ibx) = @_;
 	my $xdb = $self->{xdb};
@@ -136,6 +97,23 @@ sub ibx_data_once {
 	}
 }
 
+sub doc2ibx_cache_ent { # @_ == ($self, $doc) OR ($doc)
+	my ($doc) = $_[-1];
+	my $d;
+	my $data = $json->decode($doc->get_data);
+	for (values %$data) {
+		$d = $_->{description} // next;
+		$d =~ s/ \[epoch [0-9]+\]\z// or next;
+		last;
+	}
+	{
+		uidvalidity => int_val($doc, $UIDVALIDITY),
+		-modified => int_val($doc, $MODIFIED),
+		# extract description from manifest.js.gz epoch description
+		description => $d
+	};
+}
+
 sub inbox_data {
 	my ($self, $ibx) = @_;
 	retry_reopen($self, \&ibx_data_once, $ibx);
@@ -143,26 +121,9 @@ sub inbox_data {
 
 sub ibx_cache_load {
 	my ($doc, $cache) = @_;
-	my $end = $doc->termlist_end;
-	my $cur = $doc->termlist_begin;
-	$cur->skip_to('Q');
-	return if $cur == $end;
-	my $eidx_key = $cur->get_termname;
-	$eidx_key =~ s/\AQ// or return; # expired
-	my $ce = $cache->{$eidx_key} = {};
-	$ce->{uidvalidity} = int_val($doc, $UIDVALIDITY);
-	$ce->{-modified} = int_val($doc, $MODIFIED);
-	$ce->{description} = do {
-		# extract description from manifest.js.gz epoch description
-		my $d;
-		my $data = $json->decode($doc->get_data);
-		for (values %$data) {
-			$d = $_->{description} // next;
-			$d =~ s/ \[epoch [0-9]+\]\z// or next;
-			last;
-		}
-		$d;
-	}
+	my ($eidx_key) = xap_terms('Q', $doc);
+	return unless defined($eidx_key); # expired
+	$cache->{$eidx_key} = doc2ibx_cache_ent($doc);
 }
 
 sub _nntpd_cache_load { # retry_reopen callback
@@ -184,4 +145,7 @@ sub nntpd_cache_load {
 	retry_reopen($self, \&_nntpd_cache_load);
 }
 
+no warnings 'once';
+*reopen = \&PublicInbox::Search::reopen;
+
 1;