Merge #53145 #53154 #53216 #53217

53145: colexec: add support for DISTINCT ordered aggregation r=yuzefovich a=yuzefovich

**rowexec: speed up DISTINCT aggregation a bit**

Previously, whenever we needed to clear `seen` map (which tracks the
tuples we have already seen for the aggregation group), we would create
a new map. However, it turns out that it is actually faster (according
to micro-benchmarks) to delete all entries from the old map instead
which is what this commit does.

Release note: None

**colexec: add support for DISTINCT ordered aggregation**

This commit adds the support for DISTINCT ordered aggregation by
reusing the same code (with minor modification to reset `seen` maps when
the new group is encountered) as we have for hash aggregation. Quick
benchmarks show about 6-7x improvement when comparing against a wrapped
row-by-row processor.

Closes: #39242.

Release note (sql change): Vectorized execution now natively supports
ordered aggregation with DISTINCT clause.

53154: sql: pass down index descriptors to stats generators r=mjibson a=mjibson

This allows for geo indexes to have their first defined inverted index
have its configuration be used when generating inverted index entries
for histogram stats.

Release note: None

Fixes #52363

53216: colexec: fix recent problem with hash joiner r=yuzefovich a=yuzefovich

#53169 has just introduced an optimization in populating of `toCheck`
slice by having a default `hjInitialToCheck` slice pre-populated.
However, it could be of insufficient length due to randomization of
`coldata.BatchSize()` which is now fixed.

Release note: None

53217: builtins: implement ST_IsEmpty and ST_IsCollection r=otan a=erikgrinaker

`ST_IsCollection` does not handle `geopb.ShapeType_Geometry` in any special way, and will always return `false` - is this sufficient?

Release note (sql change): Implement the geometry builtins `ST_IsEmpty`
and `ST_IsCollection`.

Closes #48954.
Closes #48955.

Co-authored-by: Yahor Yuzefovich <yahor@cockroachlabs.com>
Co-authored-by: Matt Jibson <matt.jibson@gmail.com>
Co-authored-by: Erik Grinaker <erik@grinaker.org>

docs/generated/sql/functions.md

@@ -1308,6 +1308,10 @@ calculated, the result is transformed back into a Geography with SRID 4326.</p>
 <p>This function variant will attempt to utilize any available geospatial index.</p>
 <p>This variant will cast all geometry_str arguments into Geometry types.</p>
 </span></td></tr>
+<tr><td><a name="st_iscollection"></a><code>st_iscollection(geometry: geometry) &rarr; <a href="bool.html">bool</a></code></td><td><span class="funcdesc"><p>Returns whether the geometry is of a collection type (including multi-types).</p>
+</span></td></tr>
+<tr><td><a name="st_isempty"></a><code>st_isempty(geometry: geometry) &rarr; <a href="bool.html">bool</a></code></td><td><span class="funcdesc"><p>Returns whether the geometry is empty.</p>
+</span></td></tr>
 <tr><td><a name="st_isvalid"></a><code>st_isvalid(geometry: geometry) &rarr; <a href="bool.html">bool</a></code></td><td><span class="funcdesc"><p>Returns whether the geometry is valid as defined by the OGC spec.</p>
 <p>This function utilizes the GEOS module.</p>
 </span></td></tr>

pkg/geo/geomfn/unary_predicates.go

@@ -0,0 +1,32 @@
+// Copyright 2020 The Cockroach Authors.
+//
+// Use of this software is governed by the Business Source License
+// included in the file licenses/BSL.txt.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+package geomfn
+
+import (
+	"github.com/cockroachdb/cockroach/pkg/geo"
+	"github.com/cockroachdb/cockroach/pkg/geo/geopb"
+)
+
+// IsCollection returns whether the given geometry is of a collection type.
+func IsCollection(g *geo.Geometry) (bool, error) {
+	switch g.ShapeType() {
+	case geopb.ShapeType_MultiPoint, geopb.ShapeType_MultiLineString, geopb.ShapeType_MultiPolygon,
+		geopb.ShapeType_GeometryCollection:
+		return true, nil
+	default:
+		return false, nil
+	}
+}
+
+// IsEmpty returns whether the given geometry is empty.
+func IsEmpty(g *geo.Geometry) (bool, error) {
+	return g.Empty(), nil
+}

pkg/geo/geomfn/unary_predicates_test.go

@@ -0,0 +1,86 @@
+// Copyright 2020 The Cockroach Authors.
+//
+// Use of this software is governed by the Business Source License
+// included in the file licenses/BSL.txt.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+package geomfn
+
+import (
+	"testing"
+
+	"github.com/cockroachdb/cockroach/pkg/geo"
+	"github.com/stretchr/testify/require"
+)
+
+func TestIsCollection(t *testing.T) {
+	testCases := []struct {
+		wkt      string
+		expected bool
+	}{
+		{"POINT(1.0 1.0)", false},
+		{"POINT EMPTY", false},
+		{"LINESTRING(1.0 1.0, 2.0 2.0)", false},
+		{"LINESTRING EMPTY", false},
+		{"POLYGON((0.0 0.0, 1.0 0.0, 1.0 1.0, 0.0 0.0))", false},
+		{"POLYGON EMPTY", false},
+		{"MULTIPOINT((1.0 1.0), (2.0 2.0))", true},
+		{"MULTIPOINT EMPTY", true},
+		{"MULTILINESTRING((1.0 1.0, 2.0 2.0, 3.0 3.0), (6.0 6.0, 7.0 6.0))", true},
+		{"MULTILINESTRING EMPTY", true},
+		{"MULTIPOLYGON(((3.0 3.0, 4.0 3.0, 4.0 4.0, 3.0 3.0)), ((0.0 0.0, 1.0 0.0, 1.0 1.0, 0.0 0.0), (0.1 0.1, 0.2 0.1, 0.2 0.2, 0.1 0.1)))", true},
+		{"MULTIPOLYGON EMPTY", true},
+		{"GEOMETRYCOLLECTION (POINT (40 10),LINESTRING (10 10, 20 20, 10 40))", true},
+		{"GEOMETRYCOLLECTION EMPTY", true},
+		{"GEOMETRYCOLLECTION (GEOMETRYCOLLECTION(POINT (40 10),LINESTRING (10 10, 20 20, 10 40)))", true},
+		{"GEOMETRYCOLLECTION (GEOMETRYCOLLECTION EMPTY)", true},
+	}
+
+	for _, tc := range testCases {
+		t.Run(tc.wkt, func(t *testing.T) {
+			g, err := geo.ParseGeometry(tc.wkt)
+			require.NoError(t, err)
+			ret, err := IsCollection(g)
+			require.NoError(t, err)
+			require.Equal(t, tc.expected, ret)
+		})
+	}
+}
+
+func TestIsEmpty(t *testing.T) {
+	testCases := []struct {
+		wkt      string
+		expected bool
+	}{
+		{"POINT(1.0 1.0)", false},
+		{"POINT EMPTY", true},
+		{"LINESTRING(1.0 1.0, 2.0 2.0)", false},
+		{"LINESTRING EMPTY", true},
+		{"POLYGON((0.0 0.0, 1.0 0.0, 1.0 1.0, 0.0 0.0))", false},
+		{"POLYGON EMPTY", true},
+		{"MULTIPOINT((1.0 1.0), (2.0 2.0))", false},
+		{"MULTIPOINT EMPTY", true},
+		{"MULTILINESTRING((1.0 1.0, 2.0 2.0, 3.0 3.0), (6.0 6.0, 7.0 6.0))", false},
+		{"MULTILINESTRING EMPTY", true},
+		{"MULTIPOLYGON(((3.0 3.0, 4.0 3.0, 4.0 4.0, 3.0 3.0)), ((0.0 0.0, 1.0 0.0, 1.0 1.0, 0.0 0.0), (0.1 0.1, 0.2 0.1, 0.2 0.2, 0.1 0.1)))", false},
+		{"MULTIPOLYGON EMPTY", true},
+		{"GEOMETRYCOLLECTION (POINT (40 10),LINESTRING (10 10, 20 20, 10 40))", false},
+		{"GEOMETRYCOLLECTION EMPTY", true},
+		{"GEOMETRYCOLLECTION (GEOMETRYCOLLECTION(POINT (40 10),LINESTRING (10 10, 20 20, 10 40)))", false},
+		{"GEOMETRYCOLLECTION (GEOMETRYCOLLECTION EMPTY)", true},
+	}
+
+	for _, tc := range testCases {
+		t.Run(tc.wkt, func(t *testing.T) {
+			g, err := geo.ParseGeometry(tc.wkt)
+			require.NoError(t, err)
+			ret, err := IsEmpty(g)
+			require.NoError(t, err)
+			require.Equal(t, tc.expected, ret)
+		})
+	}
+}

pkg/sql/colexec/aggregate_funcs.go

@@ -361,3 +361,42 @@ func ProcessAggregations(
 	}
 	return
 }
+
+// aggBucket stores the aggregation functions for the corresponding aggregation
+// group as well as other utility information.
+type aggBucket struct {
+	fns []aggregateFunc
+	// seen is a slice of maps used to handle distinct aggregation. A
+	// corresponding entry in the slice is nil if the function doesn't have a
+	// DISTINCT clause. The slice itself will be nil whenever no aggregate
+	// function has a DISTINCT clause.
+	seen []map[string]struct{}
+}
+
+func (b *aggBucket) init(
+	batch coldata.Batch, fns []aggregateFunc, seen []map[string]struct{}, groups []bool,
+) {
+	b.fns = fns
+	for fnIdx, fn := range b.fns {
+		fn.Init(groups, batch.ColVec(fnIdx))
+	}
+	b.seen = seen
+}
+
+const sizeOfAggBucket = unsafe.Sizeof(aggBucket{})
+
+// aggBucketAlloc is a utility struct that batches allocations of aggBuckets.
+type aggBucketAlloc struct {
+	allocator *colmem.Allocator
+	buf       []aggBucket
+}
+
+func (a *aggBucketAlloc) newAggBucket() *aggBucket {
+	if len(a.buf) == 0 {
+		a.allocator.AdjustMemoryUsage(int64(hashAggregatorAllocSize * sizeOfAggBucket))
+		a.buf = make([]aggBucket, hashAggregatorAllocSize)
+	}
+	ret := &a.buf[0]
+	a.buf = a.buf[1:]
+	return ret
+}