openinx commented on a change in pull request #3477: URL: https://github.com/apache/iceberg/pull/3477#discussion_r749027060
########## File path: flink/v1.13/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); Review comment: Thanks @stevenzwu for the comment. I did not use the parameterized `formatVersion` approach before because not all of the unit tests are need to be addressed in both v1 and v2 tables. For example, the `testV2RemoveMetaColumn` should only be checked for v2 tables. If we use the parameterized `formatVersion`, then there will introduce more unit tests that be ignored because we will usually provide a line in `testV2RemoveMetaColumn` as : Assume.assumeTrue("xxx", formatVersion==2). -- 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]
