From fe3883762faf67fd6c4624ee721000e1f36bc59b Mon Sep 17 00:00:00 2001
From: Eric Wong <e@80x24.org>
Date: Tue, 21 Nov 2023 12:43:15 +0000
Subject: cindex: rename --associate to --join, test w/ real repos

The association data is just stored as deflated JSON in Xapian
metadata keys of shard[0] for now.  It should be reasonably
compact and fit in memory for now since we'll assume sane,
non-malicious git coderepo history, for now.

The new cindex-join.t test requires TEST_REMOTE_JOIN=1 to be
set in the environment and tests the joins against the inboxes
and coderepos of two small projects with a common history.

Internally, we'll use `ibx_off', `root_off' instead of `ibx_id'
and `root_id' since `_id' may be mistaken for columns in an SQL
database which they are not.
---
 lib/PublicInbox/XapHelper.pm | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

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

diff --git a/lib/PublicInbox/XapHelper.pm b/lib/PublicInbox/XapHelper.pm
index 428b732e..fe831b8f 100644
--- a/lib/PublicInbox/XapHelper.pm
+++ b/lib/PublicInbox/XapHelper.pm
@@ -93,10 +93,10 @@ sub cmd_dump_ibx {
 }
 
 sub dump_roots_iter ($$$) {
-	my ($req, $root2id, $it) = @_;
+	my ($req, $root2off, $it) = @_;
 	eval {
 		my $doc = $it->get_document;
-		my $G = join(' ', map { $root2id->{$_} } xap_terms('G', $doc));
+		my $G = join(' ', map { $root2off->{$_} } xap_terms('G', $doc));
 		for my $p (@{$req->{A}}) {
 			for (xap_terms($p, $doc)) {
 				$req->{wbuf} .= "$_ $G\n";
@@ -118,14 +118,14 @@ sub dump_roots_flush ($$) {
 }
 
 sub cmd_dump_roots {
-	my ($req, $root2id_file, $qry_str) = @_;
+	my ($req, $root2off_file, $qry_str) = @_;
 	$qry_str // die 'usage: dump_roots [OPTIONS] ROOT2ID_FILE QRY_STR';
 	$req->{A} or die 'dump_roots requires -A PREFIX';
-	open my $fh, '<', $root2id_file;
-	my $root2id; # record format: $OIDHEX "\0" uint32_t
+	open my $fh, '<', $root2off_file;
+	my $root2off; # record format: $OIDHEX "\0" uint32_t
 	my @x = split(/\0/, read_all $fh);
 	while (defined(my $oidhex = shift @x)) {
-		$root2id->{$oidhex} = shift @x;
+		$root2off->{$oidhex} = shift @x;
 	}
 	my $opt = { relevance => -1, limit => $req->{'m'},
 			offset => $req->{o} // 0 };
@@ -134,7 +134,7 @@ sub cmd_dump_roots {
 	$req->{wbuf} = '';
 	for my $it ($mset->items) {
 		for (my $t = 10; $t > 0; --$t) {
-			$t = dump_roots_iter($req, $root2id, $it) // $t;
+			$t = dump_roots_iter($req, $root2off, $it) // $t;
 		}
 		if (!($req->{nr_out} & 0x3fff)) {
 			dump_roots_flush($req, $fh);
-- 
cgit v1.2.3-24-ge0c7