xushiyan commented on code in PR #8736: URL: https://github.com/apache/hudi/pull/8736#discussion_r1201962322
########## hudi-spark-datasource/hudi-spark/src/test/java/org/apache/hudi/functional/TestGlobalIndexEnableUpdatePartitions.java: ########## @@ -0,0 +1,224 @@ +/* + * 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.functional; + +import org.apache.hudi.client.SparkRDDWriteClient; +import org.apache.hudi.common.config.HoodieMetadataConfig; +import org.apache.hudi.common.model.DefaultHoodieRecordPayload; +import org.apache.hudi.common.model.HoodieRecord; +import org.apache.hudi.common.model.HoodieTableType; +import org.apache.hudi.common.table.HoodieTableMetaClient; +import org.apache.hudi.config.HoodieIndexConfig; +import org.apache.hudi.config.HoodiePayloadConfig; +import org.apache.hudi.config.HoodieWriteConfig; +import org.apache.hudi.index.HoodieIndex; +import org.apache.hudi.testutils.SparkClientFunctionalTestHarness; + +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.junit.jupiter.params.ParameterizedTest; +import org.junit.jupiter.params.provider.Arguments; +import org.junit.jupiter.params.provider.MethodSource; + +import java.io.IOException; +import java.util.List; +import java.util.stream.Stream; + +import static org.apache.hudi.common.model.HoodieTableType.COPY_ON_WRITE; +import static org.apache.hudi.common.model.HoodieTableType.MERGE_ON_READ; +import static org.apache.hudi.common.testutils.HoodieAdaptablePayloadDataGenerator.SCHEMA_STR; +import static org.apache.hudi.common.testutils.HoodieAdaptablePayloadDataGenerator.getDeletes; +import static org.apache.hudi.common.testutils.HoodieAdaptablePayloadDataGenerator.getInserts; +import static org.apache.hudi.common.testutils.HoodieAdaptablePayloadDataGenerator.getKeyGenProps; +import static org.apache.hudi.common.testutils.HoodieAdaptablePayloadDataGenerator.getPayloadProps; +import static org.apache.hudi.common.testutils.HoodieAdaptablePayloadDataGenerator.getUpdates; +import static org.apache.hudi.common.testutils.HoodieTestDataGenerator.getCommitTimeAtUTC; +import static org.apache.hudi.index.HoodieIndex.IndexType.GLOBAL_BLOOM; +import static org.apache.hudi.index.HoodieIndex.IndexType.GLOBAL_SIMPLE; +import static org.apache.hudi.testutils.Assertions.assertNoWriteErrors; +import static org.junit.jupiter.api.Assertions.assertEquals; + +public class TestGlobalIndexEnableUpdatePartitions extends SparkClientFunctionalTestHarness { + + private static Stream<Arguments> getTableTypeAndIndexType() { + return Stream.of( + Arguments.of(COPY_ON_WRITE, GLOBAL_SIMPLE), + Arguments.of(COPY_ON_WRITE, GLOBAL_BLOOM), + Arguments.of(MERGE_ON_READ, GLOBAL_SIMPLE), + Arguments.of(MERGE_ON_READ, GLOBAL_BLOOM) + ); + } + + @ParameterizedTest + @MethodSource("getTableTypeAndIndexType") + public void testPartitionChanges(HoodieTableType tableType, HoodieIndex.IndexType indexType) throws IOException { + final Class<?> payloadClass = DefaultHoodieRecordPayload.class; + HoodieWriteConfig writeConfig = getWriteConfig(payloadClass, indexType); + HoodieTableMetaClient metaClient = getHoodieMetaClient(tableType, writeConfig.getProps()); + try (SparkRDDWriteClient client = getHoodieWriteClient(writeConfig)) { + final int totalRecords = 4; + final String p1 = "p1"; + final String p2 = "p2"; + final String p3 = "p3"; + final String p4 = "p4"; + + // 1st batch: inserts + String commitTimeAtEpoch0 = getCommitTimeAtUTC(0); + List<HoodieRecord> insertsAtEpoch0 = getInserts(totalRecords, p1, 0, payloadClass); + client.startCommitWithTime(commitTimeAtEpoch0); + assertNoWriteErrors(client.upsert(jsc().parallelize(insertsAtEpoch0, 2), commitTimeAtEpoch0).collect()); + + // 2nd batch: normal updates same partition + String commitTimeAtEpoch5 = getCommitTimeAtUTC(5); + List<HoodieRecord> updatesAtEpoch5 = getUpdates(insertsAtEpoch0, 5, payloadClass); + client.startCommitWithTime(commitTimeAtEpoch5); + assertNoWriteErrors(client.upsert(jsc().parallelize(updatesAtEpoch5, 2), commitTimeAtEpoch5).collect()); + readTableAndValidate(metaClient, new int[] {0, 1, 2, 3}, p1, 5); + + // 3rd batch: update all from p1 to p2 + String commitTimeAtEpoch6 = getCommitTimeAtUTC(6); + List<HoodieRecord> updatesAtEpoch6 = getUpdates(updatesAtEpoch5, p2, 6, payloadClass); + client.startCommitWithTime(commitTimeAtEpoch6); + assertNoWriteErrors(client.upsert(jsc().parallelize(updatesAtEpoch6, 2), commitTimeAtEpoch6).collect()); + readTableAndValidate(metaClient, new int[] {0, 1, 2, 3}, p2, 6); + + // 4th batch: update all from p2 to p3 + String commitTimeAtEpoch7 = getCommitTimeAtUTC(7); + List<HoodieRecord> updatesAtEpoch7 = getUpdates(updatesAtEpoch6, p3, 7, payloadClass); + client.startCommitWithTime(commitTimeAtEpoch7); + assertNoWriteErrors(client.upsert(jsc().parallelize(updatesAtEpoch7, 2), commitTimeAtEpoch7).collect()); + readTableAndValidate(metaClient, new int[] {0, 1, 2, 3}, p3, 7); + + // 5th batch: late update all to p4; discarded Review Comment: meaning this batch has an older ordering value and won't update the table (discarded). -- 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: commits-unsubscr...@hudi.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
