rdblue commented on a change in pull request #1986: URL: https://github.com/apache/iceberg/pull/1986#discussion_r551644760
########## File path: spark3-extensions/src/test/java/org/apache/iceberg/spark/extensions/TestMerge.java ########## @@ -0,0 +1,336 @@ +/* + * 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.iceberg.spark.extensions; + +import java.util.Arrays; +import java.util.Map; +import org.apache.iceberg.AssertHelpers; +import org.apache.spark.sql.AnalysisException; +import org.junit.After; +import org.junit.BeforeClass; +import org.junit.Test; + +public abstract class TestMerge extends SparkRowLevelOperationsTestBase { + + public TestMerge(String catalogName, String implementation, Map<String, String> config, + String fileFormat, boolean vectorized) { + super(catalogName, implementation, config, fileFormat, vectorized); + } + + @BeforeClass + public static void setupSparkConf() { + spark.conf().set("spark.sql.shuffle.partitions", "4"); + } + + @After + public void removeTables() { + sql("DROP TABLE IF EXISTS %s", tableName); + sql("DROP TABLE IF EXISTS source"); + } + + // TODO: tests for reordering when operations succeed (both insert and update actions) + // TODO: tests for modifying fields in a null struct + // TODO: tests for subqueries in conditions + + @Test + public void testMergeWithNonExistingColumns() { + createAndInitNestedColumnsTable(); + createOrReplaceView("source", "{ \"c1\": -100, \"c2\": -200 }"); + + AssertHelpers.assertThrows("Should complain about the invalid top-level column", + AnalysisException.class, "cannot resolve '`t.invalid_col`'", + () -> { + sql("MERGE INTO %s t USING source s " + + "ON t.id == s.c1 " + + "WHEN MATCHED THEN " + + " UPDATE SET t.invalid_col = s.c2", tableName); + }); + + AssertHelpers.assertThrows("Should complain about the invalid nested column", + AnalysisException.class, "No such struct field invalid_col", + () -> { + sql("MERGE INTO %s t USING source s " + + "ON t.id == s.c1 " + + "WHEN MATCHED THEN " + + " UPDATE SET t.c.n2.invalid_col = s.c2", tableName); + }); + + AssertHelpers.assertThrows("Should complain about the invalid top-level column", + AnalysisException.class, "cannot resolve '`invalid_col`'", + () -> { + sql("MERGE INTO %s t USING source s " + + "ON t.id == s.c1 " + + "WHEN MATCHED THEN " + + " UPDATE SET t.c.n2.dn1 = s.c2 " + + "WHEN NOT MATCHED THEN " + + " INSERT (id, invalid_col) VALUES (s.c1, null)", tableName); + }); + } + + @Test + public void testMergeWithInvalidColumnsInInsert() { + createAndInitNestedColumnsTable(); + createOrReplaceView("source", "{ \"c1\": -100, \"c2\": -200 }"); + + AssertHelpers.assertThrows("Should complain about the nested column", + AnalysisException.class, "Nested fields are not supported inside INSERT clauses", + () -> { + sql("MERGE INTO %s t USING source s " + + "ON t.id == s.c1 " + + "WHEN MATCHED THEN " + + " UPDATE SET t.c.n2.dn1 = s.c2 " + + "WHEN NOT MATCHED THEN " + + " INSERT (id, c.n2) VALUES (s.c1, null)", tableName); + }); + + AssertHelpers.assertThrows("Should complain about duplicate columns", + AnalysisException.class, "Duplicate column names inside INSERT clause", + () -> { + sql("MERGE INTO %s t USING source s " + + "ON t.id == s.c1 " + + "WHEN MATCHED THEN " + + " UPDATE SET t.c.n2.dn1 = s.c2 " + + "WHEN NOT MATCHED THEN " + + " INSERT (id, id) VALUES (s.c1, null)", tableName); + }); + + AssertHelpers.assertThrows("Should complain about missing columns", + AnalysisException.class, "must provide values for all columns of the target table", + () -> { + sql("MERGE INTO %s t USING source s " + + "ON t.id == s.c1 " + + "WHEN MATCHED THEN " + + " UPDATE SET t.c.n2.dn1 = s.c2 " + Review comment: I don't think that this should have a `WHEN MATCHED` case, to ensure that it is failing for the `NOT MATCHED THEN INSERT`. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
