maropu commented on a change in pull request #33108:
URL: https://github.com/apache/spark/pull/33108#discussion_r659512018
##########
File path: sql/core/src/main/scala/org/apache/spark/sql/execution/Columnar.scala
##########
@@ -264,12 +264,12 @@ private object RowToColumnConverter {
case DoubleType => DoubleConverter
case StringType => StringConverter
case CalendarIntervalType => CalendarConverter
- case at: ArrayType => new
ArrayConverter(getConverterForType(at.elementType, nullable))
+ case at: ArrayType => ArrayConverter(getConverterForType(at.elementType,
at.containsNull))
Review comment:
Ah, I see. Nice catch.
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/RowToColumnConverterSuite.scala
##########
@@ -0,0 +1,145 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.sql.execution
+
+import org.apache.spark.SparkFunSuite
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.util.{ArrayBasedMapData, ArrayData,
GenericArrayData}
+import org.apache.spark.sql.execution.vectorized.{OnHeapColumnVector,
WritableColumnVector}
+import org.apache.spark.sql.types._
+import org.apache.spark.unsafe.types.UTF8String
+
+class RowToColumnConverterSuite extends SparkFunSuite {
+ def convertRows(rows: Seq[InternalRow], schema: StructType):
Seq[WritableColumnVector] = {
+ val converter = new RowToColumnConverter(schema)
+ val vectors =
+ schema.map(f => new OnHeapColumnVector(5,
f.dataType)).toArray[WritableColumnVector]
+ for (row <- rows) {
+ converter.convert(row, vectors)
+ }
+ vectors
+ }
+
+ test("integer column") {
+ val schema = StructType(Seq(StructField("i", IntegerType)))
+ val rows = (0 until 100).map(i => InternalRow(i))
+ val vectors = convertRows(rows, schema)
+ rows.zipWithIndex.map { case (row, i) =>
+ assert(vectors.head.getInt(i) === row.getInt(0))
+ }
+ }
+
+ test("array column") {
+ val schema = StructType(Seq(StructField("a", ArrayType(IntegerType))))
+ val rows = (0 until 100).map { i =>
+ InternalRow(new GenericArrayData(0 until i))
+ }
+ val vectors = convertRows(rows, schema)
+ rows.zipWithIndex.map { case (row, i) =>
+ assert(vectors.head.getArray(i).array().array === row.getArray(0).array)
+ }
+ }
+
+ test("non-nullable array column with null elements") {
+ val arrayType = ArrayType(IntegerType, containsNull = true)
+ val schema = StructType(Seq(StructField("a", arrayType, nullable = false)))
+ val rows = (0 until 100).map { i =>
+ InternalRow(new GenericArrayData((0 until i).map { j =>
+ if (j % 3 == 0) {
+ null
+ } else {
+ j
+ }
+ }))
+ }
+ val vectors = convertRows(rows, schema)
+ rows.zipWithIndex.map { case (row, i) =>
+ assert(vectors.head.getArray(i).array().array === row.getArray(0).array)
+ }
+ }
+
+ test("nested array column") {
+ val arrayType = ArrayType(ArrayType(IntegerType))
+ val schema = StructType(Seq(StructField("a", arrayType)))
+ val rows = (0 until 100).map { i =>
+ InternalRow(new GenericArrayData((0 until i).map(j => new
GenericArrayData(0 until j))))
+ }
+ val vectors = convertRows(rows, schema)
+ rows.zipWithIndex.map { case (row, i) =>
+ val result = vectors.head.getArray(i).array().array
+ .map(_.asInstanceOf[ArrayData].array)
+ val expected = row.getArray(0).array
+ .map(_.asInstanceOf[ArrayData].array)
+ assert(result === expected)
+ }
+ }
+
+ test("map column") {
+ val mapType = MapType(IntegerType, StringType)
+ val schema = StructType(Seq(StructField("m", mapType)))
+ val rows = (0 until 100).map { i =>
+ InternalRow(new ArrayBasedMapData(
Review comment:
nit: wrong indents.
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/vectorized/ColumnVectorSuite.scala
##########
@@ -243,6 +243,93 @@ class ColumnVectorSuite extends SparkFunSuite with
BeforeAndAfterEach {
assert(testVector.getArray(3).toIntArray() === Array(3, 4, 5))
}
+ testVectors("array append", 1, arrayType) { testVector =>
Review comment:
This is a bug fix, so could you add the prefix: `SPARK-35898:` in the
test names?
##########
File path:
sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/WritableColumnVector.java
##########
@@ -611,6 +611,9 @@ public final int appendByteArray(byte[] value, int offset,
int length) {
public final int appendArray(int length) {
reserve(elementsAppended + 1);
+ for (WritableColumnVector childColumn : childColumns) {
+ childColumn.reserve(childColumn.elementsAppended + length);
+ }
Review comment:
`arrayData().reserve(arrayData().elementsAppended + length)`?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
