voonhous commented on code in PR #19163: URL: https://github.com/apache/hudi/pull/19163#discussion_r3870784009
########## hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/spark/sql/hudi/dml/insert/TestBulkInsertRowWriterCommitCoverage.scala: ########## @@ -0,0 +1,210 @@ +/* + * 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.spark.sql.hudi.dml.insert + +import org.apache.hudi.HoodieCLIUtils +import org.apache.hudi.common.util.{Option => HOption} + +import org.apache.spark.sql.hudi.common.HoodieSparkSqlTestBase + +/** + * Focused coverage for the row-writer bulk-insert commit executors in + * `org.apache.hudi.commit`: [[org.apache.hudi.commit.BaseDatasetBulkInsertCommitActionExecutor]] + * and [[org.apache.hudi.commit.DatasetBulkInsertOverwriteCommitActionExecutor]]. + * + * All tests set `hoodie.spark.sql.insert.into.operation = bulk_insert` and keep the default + * row-writer path enabled, so INSERT / INSERT OVERWRITE flow through the Dataset-based executors. + */ +class TestBulkInsertRowWriterCommitCoverage extends HoodieSparkSqlTestBase { + + test("Test row-writer bulk_insert into partitioned table") { + withSQLConf( + "hoodie.metadata.enable" -> "false", + "hoodie.spark.sql.insert.into.operation" -> "bulk_insert", + "hoodie.bulkinsert.shuffle.parallelism" -> "1") { + Seq("cow", "mor").foreach { tableType => + withTempDir { tmp => + val tableName = generateTableName + spark.sql( + s""" + |create table $tableName ( + | id int, + | name string, + | price double, + | dt string + |) using hudi + | partitioned by (dt) + | location '${tmp.getCanonicalPath}' + | tblproperties (type = '$tableType', primaryKey = 'id') + """.stripMargin) + + spark.sql( + s"""insert into $tableName values + | (1, 'a1', 10.0, '2024-01-01'), + | (2, 'a2', 20.0, '2024-01-01'), + | (3, 'a3', 30.0, '2024-01-02') + """.stripMargin) + + checkAnswer(s"select id, name, price, dt from $tableName order by id")( Review Comment: That test is gone (line-37 thread). The tests that replaced this suite in `TestInsertTable2` assert `WriteOperationType.INSERT_OVERWRITE` via `getLastCommitMetadata` and read `partitionToReplaceFileIds` back from the replace-commit metadata, so the resolved partition set is pinned rather than just the rows. -- 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]
