[
https://issues.apache.org/jira/browse/DRILL-5323?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15958084#comment-15958084
]
ASF GitHub Bot commented on DRILL-5323:
---------------------------------------
Github user paul-rogers commented on a diff in the pull request:
https://github.com/apache/drill/pull/785#discussion_r109563707
--- Diff:
exec/java-exec/src/test/java/org/apache/drill/test/rowSet/AbstractSingleRowSet.java
---
@@ -0,0 +1,158 @@
+/*
+ * 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.drill.test.rowSet;
+
+import org.apache.drill.common.types.TypeProtos.MajorType;
+import org.apache.drill.common.types.TypeProtos.MinorType;
+import org.apache.drill.exec.expr.TypeHelper;
+import org.apache.drill.exec.memory.BufferAllocator;
+import org.apache.drill.exec.physical.impl.spill.RecordBatchSizer;
+import org.apache.drill.exec.record.BatchSchema;
+import org.apache.drill.exec.record.BatchSchema.SelectionVectorMode;
+import org.apache.drill.exec.record.VectorContainer;
+import org.apache.drill.exec.record.VectorWrapper;
+import org.apache.drill.exec.vector.ValueVector;
+import org.apache.drill.exec.vector.complex.MapVector;
+import org.apache.drill.test.rowSet.RowSet.SingleRowSet;
+import org.apache.drill.test.rowSet.RowSetSchema.LogicalColumn;
+import org.apache.drill.test.rowSet.RowSetSchema.PhysicalSchema;
+
+public abstract class AbstractSingleRowSet extends AbstractRowSet
implements SingleRowSet {
+
+ public abstract static class StructureBuilder {
+ protected final PhysicalSchema schema;
+ protected final BufferAllocator allocator;
+ protected final ValueVector[] valueVectors;
+ protected final MapVector[] mapVectors;
+ protected int vectorIndex;
+ protected int mapIndex;
+
+ public StructureBuilder(BufferAllocator allocator, RowSetSchema
schema) {
+ this.allocator = allocator;
+ this.schema = schema.physical();
+ valueVectors = new ValueVector[schema.access().count()];
+ if (schema.access().mapCount() == 0) {
+ mapVectors = null;
+ } else {
+ mapVectors = new MapVector[schema.access().mapCount()];
+ }
+ }
+ }
+
+ public static class VectorBuilder extends StructureBuilder {
+
+ public VectorBuilder(BufferAllocator allocator, RowSetSchema schema) {
+ super(allocator, schema);
+ }
+
+ public ValueVector[] buildContainer(VectorContainer container) {
+ for (int i = 0; i < schema.count(); i++) {
+ LogicalColumn colSchema = schema.column(i);
+ @SuppressWarnings("resource")
+ ValueVector v = TypeHelper.getNewVector(colSchema.field,
allocator, null);
+ container.add(v);
+ if (colSchema.field.getType().getMinorType() == MinorType.MAP) {
+ MapVector mv = (MapVector) v;
+ mapVectors[mapIndex++] = mv;
+ buildMap(mv, colSchema.mapSchema);
+ } else {
+ valueVectors[vectorIndex++] = v;
+ }
+ }
+ container.buildSchema(SelectionVectorMode.NONE);
+ return valueVectors;
+ }
+
+ private void buildMap(MapVector mapVector, PhysicalSchema mapSchema) {
+ for (int i = 0; i < mapSchema.count(); i++) {
+ LogicalColumn colSchema = mapSchema.column(i);
+ MajorType type = colSchema.field.getType();
+ Class<? extends ValueVector> vectorClass =
TypeHelper.getValueVectorClass(type.getMinorType(), type.getMode());
+ @SuppressWarnings("resource")
+ ValueVector v = mapVector.addOrGet(colSchema.field.getName(),
type, vectorClass);
+ if (type.getMinorType() == MinorType.MAP) {
+ MapVector mv = (MapVector) v;
+ mapVectors[mapIndex++] = mv;
+ buildMap(mv, colSchema.mapSchema);
+ } else {
+ valueVectors[vectorIndex++] = v;
+ }
+ }
+ }
+ }
+
+ public static class VectorMapper extends StructureBuilder {
+
+ public VectorMapper(BufferAllocator allocator, RowSetSchema schema) {
+ super(allocator, schema);
+ }
+
+ public ValueVector[] mapContainer(VectorContainer container) {
+ for (VectorWrapper<?> w : container) {
+ @SuppressWarnings("resource")
+ ValueVector v = w.getValueVector();
+ if (v.getField().getType().getMinorType() == MinorType.MAP) {
+ MapVector mv = (MapVector) v;
+ mapVectors[mapIndex++] = mv;
+ buildMap(mv);
+ } else {
+ valueVectors[vectorIndex++] = v;
+ }
+ }
+ return valueVectors;
+ }
+
+ private void buildMap(MapVector mapVector) {
+ for (ValueVector v : mapVector) {
+ if (v.getField().getType().getMinorType() == MinorType.MAP) {
+ MapVector mv = (MapVector) v;
+ mapVectors[mapIndex++] = mv;
+ buildMap(mv);
+ } else {
+ valueVectors[vectorIndex++] = v;
+ }
+ }
+ }
+ }
+
+ protected final ValueVector[] valueVectors;
+
+ public AbstractSingleRowSet(BufferAllocator allocator, BatchSchema
schema) {
+ super(allocator, schema, new VectorContainer());
+ valueVectors = new VectorBuilder(allocator,
super.schema).buildContainer(container);
+ }
+
+ public AbstractSingleRowSet(BufferAllocator allocator, VectorContainer
container) {
+ super(allocator, container.getSchema(), container);
+ valueVectors = new VectorMapper(allocator,
super.schema).mapContainer(container);
+ }
+
+ public AbstractSingleRowSet(AbstractSingleRowSet rowSet) {
+ super(rowSet.allocator, rowSet.schema.batch(), rowSet.container);
+ valueVectors = rowSet.valueVectors;
+ }
+
+ @Override
+ public ValueVector[] vectors() { return valueVectors; }
+
+ @Override
+ public int getSize() {
+ RecordBatchSizer sizer = new RecordBatchSizer(container);
+ return sizer.actualSize();
--- End diff --
Good eyes! This bit is just a bit tricky. We create the batch (container).
Then, we need to use a `RowSetWriterImpl` to populate the batch. The `done()`
method of the writer sets the row count.
Or, if we create a row set from an existing container, the container will
already carry a row count.
Still, it is a good idea to add a unit test to verify this case, which I
will do.
> Provide test tools to create, populate and compare row sets
> -----------------------------------------------------------
>
> Key: DRILL-5323
> URL: https://issues.apache.org/jira/browse/DRILL-5323
> Project: Apache Drill
> Issue Type: Sub-task
> Components: Tools, Build & Test
> Affects Versions: 1.11.0
> Reporter: Paul Rogers
> Assignee: Paul Rogers
> Fix For: 1.11.0
>
>
> Operators work with individual row sets. A row set is a collection of records
> stored as column vectors. (Drill uses various terms for this concept. A
> record batch is a row set with an operator implementation wrapped around it.
> A vector container is a row set, but with much functionality left as an
> exercise for the developer. And so on.)
> To simplify tests, we need a {{TestRowSet}} concept that wraps a
> {{VectorContainer}} and provides easy ways to:
> * Define a schema for the row set.
> * Create a set of vectors that implement the schema.
> * Populate the row set with test data via code.
> * Add an SV2 to the row set.
> * Pass the row set to operator components (such as generated code blocks.)
> * Compare the results of the operation with an expected result set.
> * Dispose of the underling direct memory when work is done.
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
