Added test for arrays

src/hnsw.h

@@ -362,11 +362,6 @@ typedef struct HnswVacuumState
 	MemoryContext tmpCtx;
 }			HnswVacuumState;
 
-typedef struct HnswQuery
-{
-	Datum		value;
-}			HnswQuery;
-
 /* Methods */
 int			HnswGetM(Relation index);
 int			HnswGetEfConstruction(Relation index);
@@ -375,14 +370,14 @@ bool		HnswNormValue(FmgrInfo *procinfo, Oid collation, Datum *value, Vector * re
 Buffer		HnswNewBuffer(Relation index, ForkNumber forkNum);
 void		HnswInitPage(Buffer buf, Page page);
 void		HnswInit(void);
-List	   *HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement);
+List	   *HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement);
 HnswElement HnswGetEntryPoint(Relation index);
 void		HnswGetMetaPageInfo(Relation index, int *m, HnswElement * entryPoint);
 void	   *HnswAlloc(HnswAllocator * allocator, Size size);
 HnswElement HnswInitElement(char *base, ItemPointer tid, int m, double ml, int maxLevel, HnswAllocator * alloc);
 HnswElement HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno);
 void		HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing);
-HnswCandidate *HnswEntryCandidate(char *base, HnswElement em, HnswQuery * q, Relation rel, FmgrInfo *procinfo, Oid collation, bool loadVec);
+HnswCandidate *HnswEntryCandidate(char *base, HnswElement em, Datum q, Relation rel, FmgrInfo *procinfo, Oid collation, bool loadVec);
 void		HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum, bool building);
 void		HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m);
 void		HnswAddHeapTid(HnswElement element, ItemPointer heaptid);
@@ -390,7 +385,7 @@ void		HnswInitNeighbors(char *base, HnswElement element, int m, HnswAllocator *
 bool		HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, bool building);
 void		HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting, bool building);
 void		HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec);
-void		HnswLoadElement(HnswElement element, float *distance, HnswQuery * q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec);
+void		HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec);
 void		HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element);
 void		HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation);
 void		HnswLoadNeighbors(HnswElement element, Relation index, int m);

src/hnswbuild.c

@@ -669,10 +669,6 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
 	buildstate->efConstruction = HnswGetEfConstruction(index);
 	buildstate->dimensions = TupleDescAttr(index->rd_att, 0)->atttypmod;
 
-	/* Require column to have dimensions to be indexed */
-	if (buildstate->dimensions < 0)
-		elog(ERROR, "column does not have dimensions");
-
 	if (buildstate->dimensions > HNSW_MAX_DIM)
 		elog(ERROR, "column cannot have more than %d dimensions for hnsw index", HNSW_MAX_DIM);
 

src/hnswscan.c

@@ -11,7 +11,7 @@
  * Algorithm 5 from paper
  */
 static List *
-GetScanItems(IndexScanDesc scan, Datum value)
+GetScanItems(IndexScanDesc scan, Datum q)
 {
 	HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
 	Relation	index = scan->indexRelation;
@@ -22,9 +22,6 @@ GetScanItems(IndexScanDesc scan, Datum value)
 	int			m;
 	HnswElement entryPoint;
 	char	   *base = NULL;
-	HnswQuery	q;
-
-	q.value = value;
 
 	/* Get m and entry point */
 	HnswGetMetaPageInfo(index, &m, &entryPoint);
@@ -32,15 +29,15 @@ GetScanItems(IndexScanDesc scan, Datum value)
 	if (entryPoint == NULL)
 		return NIL;
 
-	ep = list_make1(HnswEntryCandidate(base, entryPoint, &q, index, procinfo, collation, false));
+	ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, procinfo, collation, false));
 
 	for (int lc = entryPoint->level; lc >= 1; lc--)
 	{
-		w = HnswSearchLayer(base, &q, ep, 1, lc, index, procinfo, collation, m, false, NULL);
+		w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, false, NULL);
 		ep = w;
 	}
 
-	return HnswSearchLayer(base, &q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL);
+	return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL);
 }
 
 /*

src/hnswutils.c

@@ -555,7 +555,7 @@ HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHe
  * Load an element and optionally get its distance from q
  */
 void
-HnswLoadElement(HnswElement element, float *distance, HnswQuery * q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec)
+HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec)
 {
 	Buffer		buf;
 	Page		page;
@@ -575,7 +575,7 @@ HnswLoadElement(HnswElement element, float *distance, HnswQuery * q, Relation in
 
 	/* Calculate distance */
 	if (distance != NULL)
-		*distance = (float) DatumGetFloat8(FunctionCall2Coll(procinfo, collation, q->value, PointerGetDatum(&etup->data)));
+		*distance = (float) DatumGetFloat8(FunctionCall2Coll(procinfo, collation, *q, PointerGetDatum(&etup->data)));
 
 	UnlockReleaseBuffer(buf);
 }
@@ -584,19 +584,19 @@ HnswLoadElement(HnswElement element, float *distance, HnswQuery * q, Relation in
  * Get the distance for a candidate
  */
 static float
-GetCandidateDistance(char *base, HnswCandidate * hc, HnswQuery * q, FmgrInfo *procinfo, Oid collation)
+GetCandidateDistance(char *base, HnswCandidate * hc, Datum q, FmgrInfo *procinfo, Oid collation)
 {
 	HnswElement hce = HnswPtrAccess(base, hc->element);
 	Datum		value = HnswGetValue(base, hce);
 
-	return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, q->value, value));
+	return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, q, value));
 }
 
 /*
  * Create a candidate for the entry point
  */
 HnswCandidate *
-HnswEntryCandidate(char *base, HnswElement entryPoint, HnswQuery * q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec)
+HnswEntryCandidate(char *base, HnswElement entryPoint, Datum q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec)
 {
 	HnswCandidate *hc = palloc(sizeof(HnswCandidate));
 
@@ -604,7 +604,7 @@ HnswEntryCandidate(char *base, HnswElement entryPoint, HnswQuery * q, Relation i
 	if (index == NULL)
 		hc->distance = GetCandidateDistance(base, hc, q, procinfo, collation);
 	else
-		HnswLoadElement(entryPoint, &hc->distance, q, index, procinfo, collation, loadVec);
+		HnswLoadElement(entryPoint, &hc->distance, &q, index, procinfo, collation, loadVec);
 	return hc;
 }
 
@@ -722,7 +722,7 @@ CountElement(char *base, HnswElement skipElement, HnswCandidate * hc)
  * Algorithm 2 from paper
  */
 List *
-HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement)
+HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement)
 {
 	List	   *w = NIL;
 	pairingheap *C = pairingheap_allocate(CompareNearestCandidates, NULL);
@@ -806,7 +806,7 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 				if (index == NULL)
 					eDistance = GetCandidateDistance(base, e, q, procinfo, collation);
 				else
-					HnswLoadElement(eElement, &eDistance, q, index, procinfo, collation, inserting);
+					HnswLoadElement(eElement, &eDistance, &q, index, procinfo, collation, inserting);
 
 				Assert(!eElement->deleted);
 
@@ -1091,9 +1091,7 @@ HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm
 		/* Load elements on insert */
 		if (index != NULL)
 		{
-			HnswQuery	q;
-
-			q.value = HnswGetValue(base, hce);
+			Datum		q = HnswGetValue(base, hce);
 
 			for (int i = 0; i < currentNeighbors->length; i++)
 			{
@@ -1103,7 +1101,7 @@ HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm
 				if (HnswPtrIsNull(base, hc3Element->value))
 					HnswLoadElement(hc3Element, &hc3->distance, &q, index, procinfo, collation, true);
 				else
-					hc3->distance = GetCandidateDistance(base, hc3, &q, procinfo, collation);
+					hc3->distance = GetCandidateDistance(base, hc3, q, procinfo, collation);
 
 				/* Prune element if being deleted */
 				if (hc3Element->heaptidsLength == 0)
@@ -1203,11 +1201,9 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
 	List	   *w;
 	int			level = element->level;
 	int			entryLevel;
-	HnswQuery	q;
+	Datum		q = HnswGetValue(base, element);
 	HnswElement skipElement = existing ? element : NULL;
 
-	q.value = HnswGetValue(base, element);
-
 #if PG_VERSION_NUM >= 130000
 	/* Precompute hash */
 	if (index == NULL)
@@ -1219,13 +1215,13 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
 		return;
 
 	/* Get entry point and level */
-	ep = list_make1(HnswEntryCandidate(base, entryPoint, &q, index, procinfo, collation, true));
+	ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, procinfo, collation, true));
 	entryLevel = entryPoint->level;
 
 	/* 1st phase: greedy search to insert level */
 	for (int lc = entryLevel; lc >= level + 1; lc--)
 	{
-		w = HnswSearchLayer(base, &q, ep, 1, lc, index, procinfo, collation, m, true, skipElement);
+		w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, true, skipElement);
 		ep = w;
 	}
 
@@ -1243,7 +1239,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
 		List	   *neighbors;
 		List	   *lw;
 
-		w = HnswSearchLayer(base, &q, ep, efConstruction, lc, index, procinfo, collation, m, true, skipElement);
+		w = HnswSearchLayer(base, q, ep, efConstruction, lc, index, procinfo, collation, m, true, skipElement);
 
 		/* Elements being deleted or skipped can help with search */
 		/* but should be removed before selecting neighbors */

test/t/020_hnsw_array.pl

@@ -0,0 +1,113 @@
+use strict;
+use warnings;
+use PostgresNode;
+use TestLib;
+use Test::More;
+
+my $node;
+my @queries = ();
+my @expected;
+my $limit = 20;
+
+sub test_recall
+{
+	my ($min, $operator) = @_;
+	my $correct = 0;
+	my $total = 0;
+
+	my $explain = $node->safe_psql("postgres", qq(
+		SET enable_seqscan = off;
+		EXPLAIN ANALYZE SELECT i FROM tst ORDER BY v $operator '$queries[0]' LIMIT $limit;
+	));
+	like($explain, qr/Index Scan/);
+
+	for my $i (0 .. $#queries)
+	{
+		my $actual = $node->safe_psql("postgres", qq(
+			SET enable_seqscan = off;
+			SELECT i FROM tst ORDER BY v $operator '$queries[$i]' LIMIT $limit;
+		));
+		my @actual_ids = split("\n", $actual);
+		my %actual_set = map { $_ => 1 } @actual_ids;
+
+		my @expected_ids = split("\n", $expected[$i]);
+
+		foreach (@expected_ids)
+		{
+			if (exists($actual_set{$_}))
+			{
+				$correct++;
+			}
+			$total++;
+		}
+	}
+
+	cmp_ok($correct / $total, ">=", $min, $operator);
+}
+
+# Initialize node
+$node = get_new_node('node');
+$node->init;
+$node->start;
+
+# Create table
+$node->safe_psql("postgres", "CREATE EXTENSION vector;");
+$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v float4[3]);");
+$node->safe_psql("postgres",
+	"INSERT INTO tst SELECT i, ARRAY[random(), random(), random()] FROM generate_series(1, 10000) i;"
+);
+
+$node->safe_psql("postgres", qq(
+	CREATE FUNCTION float4_l2_distance(float4[], float4[]) RETURNS float8
+		AS 'BEGIN RETURN l2_distance(\$1::vector, \$2::vector); END;'
+		LANGUAGE plpgsql IMMUTABLE STRICT PARALLEL SAFE;
+
+	CREATE FUNCTION float4_l2_squared_distance(float4[], float4[]) RETURNS float8
+		AS 'BEGIN RETURN vector_l2_squared_distance(\$1::vector, \$2::vector); END;'
+		LANGUAGE plpgsql IMMUTABLE STRICT PARALLEL SAFE;
+
+	CREATE OPERATOR <-> (
+		LEFTARG = float4[], RIGHTARG = float4[], PROCEDURE = float4_l2_distance,
+		COMMUTATOR = '<->'
+	);
+
+	CREATE OPERATOR CLASS float4_l2_ops
+		FOR TYPE float4[] USING hnsw AS
+		OPERATOR 1 <-> (float4[], float4[]) FOR ORDER BY float_ops,
+		FUNCTION 1 float4_l2_squared_distance(float4[], float4[]);
+));
+
+# Generate queries
+for (1 .. 20)
+{
+	my $r1 = rand();
+	my $r2 = rand();
+	my $r3 = rand();
+	push(@queries, "{$r1,$r2,$r3}");
+}
+
+# Check each index type
+my @operators = ("<->");
+my @opclasses = ("float4_l2_ops");
+
+for my $i (0 .. $#operators)
+{
+	my $operator = $operators[$i];
+	my $opclass = $opclasses[$i];
+
+	# Get exact results
+	@expected = ();
+	foreach (@queries)
+	{
+		my $res = $node->safe_psql("postgres", "SELECT i FROM tst ORDER BY v $operator '$_' LIMIT $limit;");
+		push(@expected, $res);
+	}
+
+	# Add index
+	$node->safe_psql("postgres", "CREATE INDEX ON tst USING hnsw (v $opclass);");
+
+	my $min = $operator eq "<#>" ? 0.80 : 0.99;
+	test_recall($min, $operator);
+}
+
+done_testing();