From 86f7b16ee50081d4eed779372ccc198d8a1770dc Mon Sep 17 00:00:00 2001
From: Eric Wong <e@80x24.org>
Date: Wed, 17 Mar 2021 15:39:22 +0600
Subject: lei_store: keywords => vmd (volatile metadata), prepare for labels

Since keywords and mailboxes (AKA labels) are separate things in
JMAP; and only keywords can map reliably to Maildir and mbox;
we'll keep them separate in our internal data representations,
too.

I initially wanted to call this just "meta" for "metadata", but
that might be confused with our mailing list name.  "metadata"
is already used in Xapian's own API, to add another layer of
confusion.

"tags" was also considered, but probably confusing to notmuch
users since our "labels" are analogous to "tags" in notmuch,
and notmuch doesn't seem to cover "keywords" separately...

So "vmd" it is, since we haven't used this particular
three-letter-abbreviation anywhere before; and "volatile" seems
like a good description of this metadata since everything else
up to this point has been mostly WORM (write-once, read-many).
---
 lib/PublicInbox/SearchIdx.pm | 65 ++++++++++++++++++++++++++++----------------
 1 file changed, 41 insertions(+), 24 deletions(-)

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

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 772f5a64..e2a1a678 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -528,44 +528,61 @@ sub remove_eidx_info {
 	$self->{xdb}->replace_document($docid, $doc);
 }
 
-sub set_keywords {
-	my ($self, $docid, @kw) = @_;
+my @VMD_MAP = (kw => 'K', label => 'L');
+
+sub set_vmd {
+	my ($self, $docid, $vmd) = @_;
 	begin_txn_lazy($self);
 	my $doc = _get_doc($self, $docid) or return;
-	my %keep = map { $_ => 1 } @kw;
-	my %add = %keep;
-	my @rm;
-	my $end = $doc->termlist_end;
-	for (my $cur = $doc->termlist_begin; $cur != $end; $cur++) {
-		$cur->skip_to('K');
-		last if $cur == $end;
-		my $kw = $cur->get_termname;
-		$kw =~ s/\AK//s or next;
-		$keep{$kw} ? delete($add{$kw}) : push(@rm, $kw);
+	my ($end, @rm, @add);
+	my @x = @VMD_MAP;
+	while (my ($field, $pfx) = splice(@x, 0, 2)) {
+		my $set = $vmd->{$field} // next;
+		my %keep = map { $_ => 1 } @$set;
+		my %add = %keep;
+		$end //= $doc->termlist_end;
+		for (my $cur = $doc->termlist_begin; $cur != $end; $cur++) {
+			$cur->skip_to($pfx);
+			last if $cur == $end;
+			my $v = $cur->get_termname;
+			$v =~ s/\A$pfx//s or next;
+			$keep{$v} ? delete($add{$v}) : push(@rm, $pfx.$v);
+		}
+		push(@add, map { $pfx.$_ } keys %add);
 	}
-	return unless (scalar(@rm) + scalar(keys %add));
-	$doc->remove_term('K'.$_) for @rm;
-	$doc->add_boolean_term('K'.$_) for (keys %add);
+	return unless scalar(@rm) || scalar(@add);
+	$doc->remove_term($_) for @rm;
+	$doc->add_boolean_term($_) for @add;
 	$self->{xdb}->replace_document($docid, $doc);
 }
 
-sub add_keywords {
-	my ($self, $docid, @kw) = @_;
+sub add_vmd {
+	my ($self, $docid, $vmd) = @_;
 	begin_txn_lazy($self);
 	my $doc = _get_doc($self, $docid) or return;
-	$doc->add_boolean_term('K'.$_) for @kw;
+	my @x = @VMD_MAP;
+	while (my ($field, $pfx) = splice(@x, 0, 2)) {
+		my $add = $vmd->{$field} // next;
+		$doc->add_boolean_term($pfx . $_) for @$add;
+	}
 	$self->{xdb}->replace_document($docid, $doc);
 }
 
-sub remove_keywords {
-	my ($self, $docid, @kw) = @_;
+sub remove_vmd {
+	my ($self, $docid, $vmd) = @_;
 	begin_txn_lazy($self);
 	my $doc = _get_doc($self, $docid) or return;
 	my $replace;
-	eval {
-		$doc->remove_term('K'.$_);
-		$replace = 1
-	} for @kw;
+	my @x = @VMD_MAP;
+	while (my ($field, $pfx) = splice(@x, 0, 2)) {
+		my $rm = $vmd->{$field} // next;
+		for (@$rm) {
+			eval {
+				$doc->remove_term($pfx . $_);
+				$replace = 1;
+			};
+		}
+	}
 	$self->{xdb}->replace_document($docid, $doc) if $replace;
 }
 
-- 
cgit v1.2.3-24-ge0c7