rdblue commented on code in PR #12736: URL: https://github.com/apache/iceberg/pull/12736#discussion_r2060979914
########## spark/v3.5/spark-extensions/src/test/java/org/apache/iceberg/spark/extensions/TestRowLevelOperationsWithLineage.java: ########## @@ -0,0 +1,490 @@ +/* + * 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.MetadataColumns.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.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.FileFormat; +import org.apache.iceberg.Files; +import org.apache.iceberg.MetadataColumns; +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.Record; +import org.apache.iceberg.encryption.EncryptionUtil; +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.spark.functions.BucketFunction; +import org.apache.iceberg.types.Types; +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.BeforeEach; +import org.junit.jupiter.api.TestTemplate; + +public abstract class TestRowLevelOperationsWithLineage extends SparkRowLevelOperationsTestBase { + static final Function<StructLike, StructLike> BUCKET_PARTITION_GENERATOR = + record -> + TestHelpers.Row.of(BucketFunction.BucketInt.invoke(2, record.get(0, Integer.class))); + + static final Schema SCHEMA = + new Schema( + ImmutableList.of( + Types.NestedField.required(1, "id", Types.IntegerType.get()), + Types.NestedField.required(2, "data", Types.StringType.get()), + MetadataColumns.ROW_ID, + MetadataColumns.LAST_UPDATED_SEQUENCE_NUMBER)); + + static final List<Record> INITIAL_RECORDS = + ImmutableList.of( + createRecord(SCHEMA, 100, "a", 0L, 1L), + createRecord(SCHEMA, 101, "b", 1L, 1L), + createRecord(SCHEMA, 102, "c", 2L, 1L), + createRecord(SCHEMA, 103, "d", 3L, 1L), + createRecord(SCHEMA, 104, "e", 4L, 1L)); + + @BeforeAll + public static void setupSparkConf() { + spark.conf().set("spark.sql.shuffle.partitions", "4"); + } + + @BeforeEach + public void beforeEach() { + assumeThat(formatVersion).isGreaterThanOrEqualTo(3); + // ToDo: Remove these as row lineage inheritance gets implemented in the other readers + assumeThat(fileFormat).isEqualTo(FileFormat.PARQUET); + assumeThat(vectorized).isFalse(); + } + + @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 { + createAndInitTable("id INT, data STRING", null); + createBranchIfNeeded(); + Table table = loadIcebergTable(spark, tableName); + appendUnpartitionedRecords(table, INITIAL_RECORDS); + createOrReplaceView( + "source", + "id int, data string", + "{ \"id\": 101, \"data\": \"updated_b\" }\n " + "{ \"id\": 200, \"data\": \"f\" }\n"); + sql( + "MERGE INTO %s AS t USING source AS s " + + "ON t.id == s.id " + + "WHEN MATCHED THEN " + + " UPDATE SET t.data = s.data " + + "WHEN NOT MATCHED THEN " + + " INSERT *", + commitTarget()); + + Snapshot updateSnapshot = latestSnapshot(table); + long updateSnapshotFirstRowId = updateSnapshot.firstRowId(); + List<Object[]> allRows = rowsWithLineageAndFilePos(); + List<Object[]> carriedOverAndUpdatedRows = + allRows.stream() + .filter(row -> (long) row[2] < updateSnapshotFirstRowId) + .collect(Collectors.toList()); + + assertEquals( + "Rows which are carried over or updated should have expected lineage", + ImmutableList.of( + row(100, "a", 0L, 1L, ANY, ANY), + row(101, "updated_b", 1L, updateSnapshot.sequenceNumber(), ANY, ANY), + row(102, "c", 2L, 1L, ANY, ANY), + row(103, "d", 3L, 1L, ANY, ANY), + row(104, "e", 4L, 1L, ANY, ANY)), + carriedOverAndUpdatedRows); + + Object[] newRow = + allRows.stream().filter(row -> (long) row[2] >= updateSnapshotFirstRowId).findFirst().get(); + assertAddedRowLineage(row(200, "f", updateSnapshot.sequenceNumber()), newRow); + } + + @TestTemplate + public void testMergeIntoWithBothMatchedAndNonMatchedPartitioned() + throws NoSuchTableException, ParseException, IOException { + + createAndInitTable("id INT, data STRING", null); Review Comment: Is this creating a partitioned table? -- 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
