voonhous commented on code in PR #19205: URL: https://github.com/apache/hudi/pull/19205#discussion_r3794340563
########## hudi-spark-datasource/hudi-spark/src/test/java/org/apache/hudi/functional/TestMetaFieldsModeE2E.java: ########## @@ -0,0 +1,830 @@ +/* + * 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.DataSourceReadOptions; +import org.apache.hudi.DataSourceWriteOptions; +import org.apache.hudi.SparkAdapterSupport$; +import org.apache.hudi.common.config.HoodieMetadataConfig; +import org.apache.hudi.common.model.HoodieRecord; +import org.apache.hudi.common.model.MetaFieldsMode; +import org.apache.hudi.common.table.HoodieTableConfig; +import org.apache.hudi.common.table.HoodieTableMetaClient; +import org.apache.hudi.common.table.timeline.HoodieInstant; +import org.apache.hudi.testutils.SparkClientFunctionalTestHarness; + +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.RowFactory; +import org.apache.spark.sql.SaveMode; +import org.apache.spark.sql.functions; +import org.apache.spark.sql.types.DataTypes; +import org.apache.spark.sql.types.StructField; +import org.apache.spark.sql.types.StructType; +import org.junit.jupiter.api.Test; +import org.junit.jupiter.params.ParameterizedTest; +import org.junit.jupiter.params.provider.EnumSource; + +import java.util.Arrays; +import java.util.Collections; +import java.util.HashMap; +import java.util.List; +import java.util.Map; +import java.util.stream.Collectors; + +import static org.junit.jupiter.api.Assertions.assertEquals; +import static org.junit.jupiter.api.Assertions.assertFalse; +import static org.junit.jupiter.api.Assertions.assertNotNull; +import static org.junit.jupiter.api.Assertions.assertNull; +import static org.junit.jupiter.api.Assertions.assertThrows; +import static org.junit.jupiter.api.Assertions.assertTrue; + +/** + * Spark-datasource end-to-end tests for the {@code hoodie.meta.fields.mode} property on CoW tables. + * Every {@link MetaFieldsMode} value is exercised via a write / re-read round trip; on-disk column + * population is verified by reading the parquet files back and inspecting the meta-column values. + */ +class TestMetaFieldsModeE2E extends SparkClientFunctionalTestHarness { + + private static StructType simpleSchema() { + return DataTypes.createStructType(new StructField[]{ + DataTypes.createStructField("column1", DataTypes.StringType, true), + DataTypes.createStructField("column2", DataTypes.StringType, true), + DataTypes.createStructField("column3", DataTypes.StringType, true) + }).asNullable(); + } + + private Map<String, String> baseOptions() { + Map<String, String> opts = new HashMap<>(); + opts.put(DataSourceWriteOptions.RECORDKEY_FIELD().key(), "column1"); Review Comment: Checked the latest push (6c8f179): the matrix ({simple, single-field complex, non-partitioned} x hive_style on/off) and the HoodieBaseRelation comment correction are not in yet, so keeping this thread open until those land. On the split: agree, the writer-side field-count check can go to its own issue. I don't see it filed yet though, please link it here once it is. -- 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]
