nsivabalan commented on code in PR #18829:
URL: https://github.com/apache/hudi/pull/18829#discussion_r3480025766
##########
hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/table/action/commit/SparkInsertOverwriteCommitActionExecutor.java:
##########
@@ -101,6 +103,26 @@ protected List<String> getAllExistingFileIds(String
partitionPath) {
return
table.getSliceView().getLatestFileSlices(partitionPath).map(FileSlice::getFileId).distinct().collect(Collectors.toList());
}
+ @Override
+ protected Set<HoodieFileGroupId>
getFileGroupsBeingReplaced(HoodieData<HoodieRecord<T>> inputRecords) {
+ String staticOverwritePartition =
config.getStringOrDefault(HoodieInternalConfig.STATIC_OVERWRITE_PARTITION_PATHS);
+ List<String> partitionPaths;
Review Comment:
Renamed in df3e2563162d to `staticOverwritePartitionPaths` across both
`SparkInsertOverwriteCommitActionExecutor` and
`DatasetBulkInsertOverwriteCommitActionExecutor`.
##########
hudi-client/hudi-spark-client/src/test/java/org/apache/hudi/table/action/commit/TestInsertOverwriteWithClustering.java:
##########
@@ -0,0 +1,834 @@
+/*
+ * 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.hudi.table.action.commit;
+
+import org.apache.hudi.client.HoodieWriteResult;
+import org.apache.hudi.client.SparkRDDWriteClient;
+import org.apache.hudi.client.WriteClientTestUtils;
+import org.apache.hudi.client.WriteStatus;
+import
org.apache.hudi.client.clustering.plan.strategy.SparkSingleFileSortPlanStrategy;
+import
org.apache.hudi.client.clustering.run.strategy.SparkSingleFileSortExecutionStrategy;
+import org.apache.hudi.common.data.HoodieData;
+import org.apache.hudi.common.model.HoodieFileGroupId;
+import org.apache.hudi.common.model.HoodieRecord;
+import org.apache.hudi.common.model.HoodieReplaceCommitMetadata;
+import org.apache.hudi.common.model.HoodieTableType;
+import org.apache.hudi.common.table.HoodieTableMetaClient;
+import org.apache.hudi.common.table.timeline.HoodieInstant;
+import org.apache.hudi.common.table.timeline.HoodieTimeline;
+import org.apache.hudi.common.testutils.HoodieTestDataGenerator;
+import org.apache.hudi.common.util.ClusteringUtils;
+import org.apache.hudi.common.util.Option;
+import org.apache.hudi.config.HoodieClusteringConfig;
+import org.apache.hudi.config.HoodieWriteConfig;
+import org.apache.hudi.data.HoodieJavaRDD;
+import org.apache.hudi.exception.HoodieUpsertException;
+import org.apache.hudi.table.HoodieSparkTable;
+import org.apache.hudi.table.HoodieTable;
+import org.apache.hudi.testutils.HoodieClientTestBase;
+
+import org.apache.spark.api.java.JavaRDD;
+import org.junit.jupiter.api.AfterEach;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Test;
+
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Map;
+import java.util.Set;
+import java.util.stream.Collectors;
+
+import static
org.apache.hudi.common.testutils.HoodieTestDataGenerator.TRIP_EXAMPLE_SCHEMA;
+import static org.junit.jupiter.api.Assertions.assertEquals;
+import static org.junit.jupiter.api.Assertions.assertFalse;
+import static org.junit.jupiter.api.Assertions.assertThrows;
+import static org.junit.jupiter.api.Assertions.assertTrue;
+
+/**
+ * Tests for INSERT_OVERWRITE, INSERT_OVERWRITE_TABLE, and DELETE_PARTITION
operations
+ * when there are pending clustering operations on the file groups being
replaced.
+ */
+public class TestInsertOverwriteWithClustering extends HoodieClientTestBase {
+
+ private HoodieTestDataGenerator dataGen;
+
+ @BeforeEach
+ public void setUp() throws Exception {
+ initPath();
+ initSparkContexts();
+ initTestDataGenerator();
+ initMetaClient(HoodieTableType.COPY_ON_WRITE);
+ dataGen = new HoodieTestDataGenerator();
+ }
+
+ @AfterEach
+ public void tearDown() throws Exception {
+ cleanupResources();
+ }
+
+ private HoodieClusteringConfig.Builder baseClusteringConfigBuilder(boolean
rollbackPendingClustering) {
+ return HoodieClusteringConfig.newBuilder()
+
.withClusteringPlanStrategyClass(SparkSingleFileSortPlanStrategy.class.getName())
+
.withClusteringExecutionStrategyClass(SparkSingleFileSortExecutionStrategy.class.getName())
+ .withClusteringMaxNumGroups(10)
+ .withRollbackPendingClustering(rollbackPendingClustering);
+ }
+
+ private HoodieWriteConfig.Builder getConfigBuilder(boolean
rollbackPendingClustering) {
+ return HoodieWriteConfig.newBuilder()
+ .withPath(basePath)
+ .withSchema(TRIP_EXAMPLE_SCHEMA)
+ .withParallelism(2, 2)
+ .withBulkInsertParallelism(2)
+ .withFinalizeWriteParallelism(2)
+ .withDeleteParallelism(2)
+ .withRollbackParallelism(2)
+
.withClusteringConfig(baseClusteringConfigBuilder(rollbackPendingClustering).build());
+ }
+
+ private HoodieWriteConfig.Builder
getConfigBuilderWithPartitionFilter(boolean rollbackPendingClustering, String
partitionFilter) {
Review Comment:
Covered by the `baseClusteringConfigBuilder` extraction in f086df5 —
`getConfigBuilder` and `getConfigBuilderWithPartitionFilter` both delegate to
the shared helper now, so the parallelism settings are defined in one place.
--
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]
