rdblue commented on code in PR #12736: URL: https://github.com/apache/iceberg/pull/12736#discussion_r2053133869
########## spark/v3.5/spark-extensions/src/test/java/org/apache/iceberg/spark/extensions/TestRowLevelOperationsWithLineage.java: ########## @@ -0,0 +1,443 @@ +/* + * 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 static org.apache.iceberg.TableUtil.schemaWithRowLineage; +import static org.apache.iceberg.spark.Spark3Util.loadIcebergTable; +import static org.assertj.core.api.Assertions.assertThat; +import static org.assertj.core.api.Assumptions.assumeThat; + +import java.io.IOException; +import java.util.Comparator; +import java.util.List; +import java.util.Map; +import java.util.UUID; +import java.util.function.Function; +import java.util.stream.Collectors; +import org.apache.iceberg.AppendFiles; +import org.apache.iceberg.Files; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.Schema; +import org.apache.iceberg.Snapshot; +import org.apache.iceberg.SnapshotRef; +import org.apache.iceberg.StructLike; +import org.apache.iceberg.Table; +import org.apache.iceberg.TestHelpers; +import org.apache.iceberg.data.GenericAppenderFactory; +import org.apache.iceberg.data.GenericRecord; +import org.apache.iceberg.data.IcebergGenerics; +import org.apache.iceberg.data.Record; +import org.apache.iceberg.encryption.EncryptionUtil; +import org.apache.iceberg.io.CloseableIterable; +import org.apache.iceberg.io.DataWriter; +import org.apache.iceberg.io.OutputFile; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.util.Pair; +import org.apache.iceberg.util.PartitionMap; +import org.apache.spark.sql.catalyst.analysis.NoSuchTableException; +import org.apache.spark.sql.catalyst.parser.ParseException; +import org.junit.jupiter.api.AfterEach; +import org.junit.jupiter.api.BeforeAll; +import org.junit.jupiter.api.TestTemplate; + +public abstract class TestRowLevelOperationsWithLineage extends SparkRowLevelOperationsTestBase { + static final Function<Record, StructLike> UNPARTITIONED_GENERATOR = record -> null; + // Use the first field in the row as identity partition + static final Function<Record, StructLike> IDENTITY_PARTITIONED_GENERATOR = + record -> TestHelpers.Row.of(record.get(0, Integer.class)); + + @BeforeAll + public static void setupSparkConf() { + spark.conf().set("spark.sql.shuffle.partitions", "4"); + } + + @AfterEach + public void removeTables() { + sql("DROP TABLE IF EXISTS %s", tableName); + sql("DROP TABLE IF EXISTS source"); + } + + @TestTemplate + public void testMergeIntoWithBothMatchedAndNonMatched() + throws NoSuchTableException, ParseException, IOException { + assumeThat(formatVersion).isGreaterThanOrEqualTo(3); + + createAndInitTable("data INT", null); + createBranchIfNeeded(); + Table table = loadIcebergTable(spark, tableName); + PartitionMap<List<Record>> recordsByPartition = + createRecordsWithRowLineage( Review Comment: `numRecords` is always 5 and there are only 2 partition functions. I think it may be better to just have constants up at the top, rather than generating the records. I still have some trouble reading these tests because I have to remember that the IDs are assigned 0-4. Also, a constant sequence number would be helpful to make this match reality a bit more closely. -- 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: issues-unsubscr...@iceberg.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For additional commands, e-mail: issues-h...@iceberg.apache.org
