beyond1920 commented on code in PR #9921: URL: https://github.com/apache/hudi/pull/9921#discussion_r1378334583
########## hudi-client/hudi-spark-client/src/test/java/org/apache/hudi/table/functional/TestHoodieSparkNBCC.java: ########## @@ -0,0 +1,437 @@ +/* + * 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.functional; + +import org.apache.hudi.client.SparkRDDWriteClient; +import org.apache.hudi.client.WriteStatus; +import org.apache.hudi.client.transaction.BucketIndexConcurrentFileWritesConflictResolutionStrategy; +import org.apache.hudi.client.transaction.lock.InProcessLockProvider; +import org.apache.hudi.common.config.HoodieStorageConfig; +import org.apache.hudi.common.fs.FSUtils; +import org.apache.hudi.common.model.HoodieAvroRecord; +import org.apache.hudi.common.model.HoodieFailedWritesCleaningPolicy; +import org.apache.hudi.common.model.HoodieKey; +import org.apache.hudi.common.model.HoodieRecord; +import org.apache.hudi.common.model.HoodieTableType; +import org.apache.hudi.common.model.HoodieWriteStat; +import org.apache.hudi.common.model.PartialUpdateAvroPayload; +import org.apache.hudi.common.model.WriteConcurrencyMode; +import org.apache.hudi.common.model.WriteOperationType; +import org.apache.hudi.common.table.HoodieTableMetaClient; +import org.apache.hudi.common.table.marker.MarkerType; +import org.apache.hudi.common.util.Option; +import org.apache.hudi.common.util.StringUtils; +import org.apache.hudi.common.util.ValidationUtils; +import org.apache.hudi.config.HoodieCleanConfig; +import org.apache.hudi.config.HoodieCompactionConfig; +import org.apache.hudi.config.HoodieIndexConfig; +import org.apache.hudi.config.HoodieLayoutConfig; +import org.apache.hudi.config.HoodieLockConfig; +import org.apache.hudi.config.HoodiePayloadConfig; +import org.apache.hudi.config.HoodieWriteConfig; +import org.apache.hudi.exception.HoodieWriteConflictException; +import org.apache.hudi.index.HoodieIndex; +import org.apache.hudi.table.action.commit.SparkBucketIndexPartitioner; +import org.apache.hudi.table.storage.HoodieStorageLayout; +import org.apache.hudi.testutils.SparkClientFunctionalTestHarness; + +import org.apache.avro.Schema; +import org.apache.avro.generic.GenericData; +import org.apache.avro.generic.GenericRecord; +import org.apache.hadoop.fs.Path; +import org.apache.parquet.avro.AvroParquetReader; +import org.apache.parquet.hadoop.ParquetReader; +import org.apache.spark.api.java.JavaRDD; +import org.junit.jupiter.api.Assertions; +import org.junit.jupiter.api.BeforeEach; +import org.junit.jupiter.api.Tag; +import org.junit.jupiter.api.Test; + +import java.io.File; +import java.io.FileFilter; +import java.io.IOException; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.Collections; +import java.util.Comparator; +import java.util.List; +import java.util.Map; +import java.util.Objects; +import java.util.Properties; +import java.util.stream.Collectors; + +import static org.apache.hudi.common.table.HoodieTableConfig.TYPE; +import static org.hamcrest.CoreMatchers.is; +import static org.hamcrest.MatcherAssert.assertThat; +import static org.junit.jupiter.api.Assertions.assertFalse; +import static org.junit.jupiter.api.Assertions.assertNotNull; +import static org.junit.jupiter.api.Assertions.assertThrows; + +@Tag("functional") +public class TestHoodieSparkNBCC extends SparkClientFunctionalTestHarness { + + String jsonSchema = "{\n" + + " \"type\": \"record\",\n" + + " \"name\": \"partialRecord\", \"namespace\":\"org.apache.hudi\",\n" + + " \"fields\": [\n" + + " {\"name\": \"_hoodie_commit_time\", \"type\": [\"null\", \"string\"]},\n" + + " {\"name\": \"_hoodie_commit_seqno\", \"type\": [\"null\", \"string\"]},\n" + + " {\"name\": \"_hoodie_record_key\", \"type\": [\"null\", \"string\"]},\n" + + " {\"name\": \"_hoodie_partition_path\", \"type\": [\"null\", \"string\"]},\n" + + " {\"name\": \"_hoodie_file_name\", \"type\": [\"null\", \"string\"]},\n" Review Comment: In fact, I already follows the common way in spark test cases, please check `TestHoodieMergeOnReadTable`, `TestHoodieSparkMergeOnReadTableCompaction`, `TestHoodieSparkCopyOnWriteTableArchiveWithReplace`, `TestHoodieClientMultiWriter` and so on. There are only 2 differences between `TestHoodieSparkNBCC` and those cases: 1. I didn't use `HoodieTestDataGenerator` to generate specified number of records, because the record column values are random value. I need generate fixed record values to verify the behavior is expected. 2. I didn't only check the number of query results is expected, but also the each column values are expected. -- 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
