jonvex commented on code in PR #7179: URL: https://github.com/apache/hudi/pull/7179#discussion_r1028164269
########## hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/functional/TestSparkDataSource.scala: ########## @@ -0,0 +1,368 @@ +/* + * 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.common.config.HoodieMetadataConfig +import org.apache.hudi.common.fs.FSUtils +import org.apache.hudi.common.model.HoodieRecord +import org.apache.hudi.common.table.HoodieTableMetaClient +import org.apache.hudi.common.table.timeline.{HoodieInstant, HoodieTimeline} +import org.apache.hudi.common.testutils.HoodieTestDataGenerator +import org.apache.hudi.common.testutils.RawTripTestPayload.recordsToStrings +import org.apache.hudi.config.{HoodieCompactionConfig, HoodieIndexConfig, HoodieWriteConfig} +import org.apache.hudi.keygen.TimestampBasedKeyGenerator +import org.apache.hudi.keygen.constant.KeyGeneratorOptions.Config +import org.apache.hudi.testutils.SparkClientFunctionalTestHarness +import org.apache.hudi.{DataSourceReadOptions, DataSourceWriteOptions, HoodieDataSourceHelpers} +import org.apache.spark.sql._ +import org.apache.spark.sql.functions.{col, lit} +import org.junit.jupiter.api.Assertions.{assertEquals, assertFalse, assertTrue} +import org.junit.jupiter.api.Tag +import org.junit.jupiter.params.ParameterizedTest +import org.junit.jupiter.params.provider.{CsvSource, ValueSource} + +import scala.collection.JavaConversions._ + +class TestSparkDataSource extends SparkClientFunctionalTestHarness { + + var commonOpts = Map( + "hoodie.insert.shuffle.parallelism" -> "4", + "hoodie.upsert.shuffle.parallelism" -> "4", + "hoodie.bulkinsert.shuffle.parallelism" -> "4", + "hoodie.delete.shuffle.parallelism" -> "2", + DataSourceWriteOptions.RECORDKEY_FIELD.key -> "_row_key", + DataSourceWriteOptions.PARTITIONPATH_FIELD.key -> "partition", + DataSourceWriteOptions.PRECOMBINE_FIELD.key -> "timestamp", + HoodieWriteConfig.TBL_NAME.key -> "hoodie_test" + ) + + @ParameterizedTest + @CsvSource(value = Array( + "COPY_ON_WRITE|false|false|org.apache.hudi.keygen.SimpleKeyGenerator|BLOOM", + "COPY_ON_WRITE|true|false|org.apache.hudi.keygen.SimpleKeyGenerator|BLOOM", + "COPY_ON_WRITE|true|true|org.apache.hudi.keygen.SimpleKeyGenerator|BLOOM", + "COPY_ON_WRITE|false|false|org.apache.hudi.keygen.SimpleKeyGenerator|SIMPLE", + "COPY_ON_WRITE|true|false|org.apache.hudi.keygen.SimpleKeyGenerator|SIMPLE", + "COPY_ON_WRITE|true|true|org.apache.hudi.keygen.SimpleKeyGenerator|SIMPLE", + "COPY_ON_WRITE|false|false|org.apache.hudi.keygen.NonpartitionedKeyGenerator|GLOBAL_BLOOM", + "COPY_ON_WRITE|true|false|org.apache.hudi.keygen.NonpartitionedKeyGenerator|GLOBAL_BLOOM", + "COPY_ON_WRITE|true|true|org.apache.hudi.keygen.NonpartitionedKeyGenerator|GLOBAL_BLOOM", + "MERGE_ON_READ|false|false|org.apache.hudi.keygen.SimpleKeyGenerator|BLOOM", + "MERGE_ON_READ|true|false|org.apache.hudi.keygen.SimpleKeyGenerator|BLOOM", + "MERGE_ON_READ|true|true|org.apache.hudi.keygen.SimpleKeyGenerator|BLOOM", + "MERGE_ON_READ|false|false|org.apache.hudi.keygen.SimpleKeyGenerator|SIMPLE", + "MERGE_ON_READ|true|false|org.apache.hudi.keygen.SimpleKeyGenerator|SIMPLE", + "MERGE_ON_READ|true|true|org.apache.hudi.keygen.SimpleKeyGenerator|SIMPLE", + "MERGE_ON_READ|false|false|org.apache.hudi.keygen.NonpartitionedKeyGenerator|GLOBAL_BLOOM", + "MERGE_ON_READ|true|false|org.apache.hudi.keygen.NonpartitionedKeyGenerator|GLOBAL_BLOOM", + "MERGE_ON_READ|true|true|org.apache.hudi.keygen.NonpartitionedKeyGenerator|GLOBAL_BLOOM" + ), delimiter = '|') + def testCoreFlow(tableType: String, isMetadataEnabledOnWrite: Boolean, isMetadataEnabledOnRead: Boolean, keyGenClass: String, indexType: String): Unit = { + var options: Map[String, String] = commonOpts + + (HoodieMetadataConfig.ENABLE.key -> String.valueOf(isMetadataEnabledOnWrite)) + + (DataSourceWriteOptions.KEYGENERATOR_CLASS_NAME.key() -> keyGenClass) + + (DataSourceWriteOptions.TABLE_TYPE.key() -> tableType) + + (HoodieIndexConfig.INDEX_TYPE.key() -> indexType) + // order of cols in inputDf and hudiDf differs slightly. so had to choose columns specifically to compare df directly. + val colsToSelect = "_row_key, begin_lat, begin_lon, city_to_state.LA, current_date, current_ts, distance_in_meters, driver, end_lat, end_lon, fare.amount, fare.currency, partition, partition_path, rider, timestamp, weight, _hoodie_is_deleted" + val dataGen = new HoodieTestDataGenerator(0xDEED) + val fs = FSUtils.getFs(basePath, spark.sparkContext.hadoopConfiguration) + // Insert Operation + val records0 = recordsToStrings(dataGen.generateInserts("000", 100)).toList + val inputDf0 = spark.read.json(spark.sparkContext.parallelize(records0, 2)) + inputDf0.write.format("org.apache.hudi") + .options(options) + .option(DataSourceWriteOptions.OPERATION.key, DataSourceWriteOptions.BULK_INSERT_OPERATION_OPT_VAL) + .mode(SaveMode.Overwrite) + .save(basePath) + + assertTrue(HoodieDataSourceHelpers.hasNewCommits(fs, basePath, "000")) + + // Snapshot query + val snapshotDf1 = spark.read.format("org.apache.hudi") + .option(HoodieMetadataConfig.ENABLE.key, isMetadataEnabledOnRead) + .load(basePath) + snapshotDf1.cache() + assertEquals(100, snapshotDf1.count()) + Review Comment: In my review you suggested verifying the insert. So `compareEntireInputDfWithHudiDf(inputDf0, snapshotDf1, colsToSelect)` Should be added here -- 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]
