openinx commented on a change in pull request #3477: URL: https://github.com/apache/iceberg/pull/3477#discussion_r749028562
########## File path: flink/v1.12/flink/src/test/java/org/apache/iceberg/flink/source/TestProjectMetaColumn.java ########## @@ -0,0 +1,180 @@ +/* + * 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.flink.source; + +import java.io.IOException; +import java.util.List; +import org.apache.flink.table.data.GenericRowData; +import org.apache.flink.table.data.RowData; +import org.apache.iceberg.DataFile; +import org.apache.iceberg.DeleteFile; +import org.apache.iceberg.FileFormat; +import org.apache.iceberg.RowDelta; +import org.apache.iceberg.SerializableTable; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.flink.SimpleDataUtil; +import org.apache.iceberg.flink.TableLoader; +import org.apache.iceberg.flink.TestHelpers; +import org.apache.iceberg.flink.data.RowDataProjection; +import org.apache.iceberg.flink.sink.RowDataTaskWriterFactory; +import org.apache.iceberg.flink.sink.TaskWriterFactory; +import org.apache.iceberg.io.TaskWriter; +import org.apache.iceberg.io.WriteResult; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.junit.Assert; +import org.junit.Rule; +import org.junit.Test; +import org.junit.rules.TemporaryFolder; +import org.junit.runner.RunWith; +import org.junit.runners.Parameterized; + +@RunWith(Parameterized.class) +public class TestProjectMetaColumn { + + @Rule + public final TemporaryFolder folder = new TemporaryFolder(); + private final FileFormat format; + + @Parameterized.Parameters(name = "fileFormat={0}") + public static Iterable<Object[]> parameters() { + return Lists.newArrayList( + new Object[] {FileFormat.PARQUET}, + new Object[] {FileFormat.ORC}, + new Object[] {FileFormat.AVRO} + ); + } + + public TestProjectMetaColumn(FileFormat format) { + this.format = format; + } + + private void testSkipToRemoveMetaColumn(int formatVersion) throws IOException { + // Create the table with given format version. + String location = folder.getRoot().getAbsolutePath(); + Table table = SimpleDataUtil.createTable(location, + ImmutableMap.of("format-version", String.valueOf(formatVersion)), + false); + + List<RowData> rows = Lists.newArrayList( + SimpleDataUtil.createInsert(1, "AAA"), + SimpleDataUtil.createInsert(2, "BBB"), + SimpleDataUtil.createInsert(3, "CCC") + ); + writeAndCommit(table, ImmutableList.of(), false, rows); + + FlinkInputFormat input = FlinkSource + .forRowData() + .tableLoader(TableLoader.fromHadoopTable(location)) + .buildFormat(); + + List<RowData> results = Lists.newArrayList(); + TestHelpers.readRowData(input, rowData -> { + // If project to remove the meta columns, it will get a RowDataProjection. + Assert.assertTrue(rowData instanceof GenericRowData); + results.add(TestHelpers.copyRowData(rowData, SimpleDataUtil.ROW_TYPE)); + }); + + // Assert the results. + TestHelpers.assertRows(rows, results, SimpleDataUtil.ROW_TYPE); + } + + @Test + public void testV1SkipToRemoveMetaColumn() throws IOException { + testSkipToRemoveMetaColumn(1); + } + + @Test + public void testV2SkipToRemoveMetaColumn() throws IOException { + testSkipToRemoveMetaColumn(2); + } + + @Test + public void testV2RemoveMetaColumn() throws Exception { + // Create the v2 table. + String location = folder.getRoot().getAbsolutePath(); + Table table = SimpleDataUtil.createTable(location, ImmutableMap.of("format-version", "2"), false); + + List<RowData> rows = Lists.newArrayList( + SimpleDataUtil.createInsert(1, "AAA"), + SimpleDataUtil.createDelete(1, "AAA"), + SimpleDataUtil.createInsert(2, "AAA"), + SimpleDataUtil.createInsert(2, "BBB") + ); + int eqFieldId = table.schema().findField("data").fieldId(); + writeAndCommit(table, ImmutableList.of(eqFieldId), true, rows); + + FlinkInputFormat input = FlinkSource + .forRowData() + .tableLoader(TableLoader.fromHadoopTable(location)) + .buildFormat(); + + List<RowData> results = Lists.newArrayList(); + TestHelpers.readRowData(input, rowData -> { + // If project to remove the meta columns, it will get a RowDataProjection. + Assert.assertTrue(rowData instanceof RowDataProjection); Review comment: For v2 table with eq-deletes or pos-deletes to merge, we will add `_pos`, `file_path`, `is_deleted` meta columns. For flink engine, we will need to project the row data to remove the extra meta columns for users. The `RowDataProjection` was introduced since here https://github.com/apache/iceberg/pull/3240/files#diff-aed36b23cf7e6110f84bd3b34307240d2174b2be2edb987dfcd22ff15ab75f72R81-R83 -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
