rdblue commented on a change in pull request #1974: URL: https://github.com/apache/iceberg/pull/1974#discussion_r547413103
########## File path: flink/src/test/java/org/apache/iceberg/flink/sink/TestFlinkIcebergSinkV2.java ########## @@ -0,0 +1,330 @@ +/* + * 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.sink; + +import java.io.File; +import java.io.IOException; +import java.util.List; +import java.util.Locale; +import java.util.Map; +import org.apache.flink.api.common.typeinfo.TypeInformation; +import org.apache.flink.api.java.functions.KeySelector; +import org.apache.flink.api.java.typeutils.RowTypeInfo; +import org.apache.flink.streaming.api.datastream.DataStream; +import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment; +import org.apache.flink.types.Row; +import org.apache.flink.types.RowKind; +import org.apache.iceberg.FileFormat; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.Snapshot; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.TableTestBase; +import org.apache.iceberg.data.IcebergGenerics; +import org.apache.iceberg.data.Record; +import org.apache.iceberg.flink.SimpleDataUtil; +import org.apache.iceberg.flink.TestTableLoader; +import org.apache.iceberg.flink.source.BoundedTestSource; +import org.apache.iceberg.io.CloseableIterable; +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.apache.iceberg.util.StructLikeSet; +import org.junit.Assert; +import org.junit.Before; +import org.junit.Test; +import org.junit.runner.RunWith; +import org.junit.runners.Parameterized; + +@RunWith(Parameterized.class) +public class TestFlinkIcebergSinkV2 extends TableTestBase { + private static final int FORMAT_V2 = 2; + private static final TypeInformation<Row> ROW_TYPE_INFO = + new RowTypeInfo(SimpleDataUtil.FLINK_SCHEMA.getFieldTypes()); + + private final FileFormat format; + private final int parallelism; + private final boolean partitioned; + + private StreamExecutionEnvironment env; + private TestTableLoader tableLoader; + + @Parameterized.Parameters(name = "FileFormat = {0}, Parallelism = {1}, Partitioned={2}") + public static Object[][] parameters() { + return new Object[][] { + new Object[] {"avro", 1, true}, + new Object[] {"avro", 1, false}, + new Object[] {"avro", 2, true}, + new Object[] {"avro", 2, false}, + new Object[] {"parquet", 1, true}, + new Object[] {"parquet", 1, false}, + new Object[] {"parquet", 2, true}, + new Object[] {"parquet", 2, false} + }; + } + + public TestFlinkIcebergSinkV2(String format, int parallelism, boolean partitioned) { + super(FORMAT_V2); + this.format = FileFormat.valueOf(format.toUpperCase(Locale.ENGLISH)); + this.parallelism = parallelism; + this.partitioned = partitioned; + } + + @Before + public void setupTable() throws IOException { + this.tableDir = temp.newFolder(); + this.metadataDir = new File(tableDir, "metadata"); + Assert.assertTrue(tableDir.delete()); + + if (!partitioned) { + table = create(SimpleDataUtil.SCHEMA, PartitionSpec.unpartitioned()); + } else { + table = create(SimpleDataUtil.SCHEMA, PartitionSpec.builderFor(SimpleDataUtil.SCHEMA).identity("data").build()); + } + + table.updateProperties() + .set(TableProperties.DEFAULT_FILE_FORMAT, format.name()) + .commit(); + + env = StreamExecutionEnvironment.getExecutionEnvironment() + .enableCheckpointing(100L) + .setParallelism(parallelism) + .setMaxParallelism(parallelism); + + tableLoader = new TestTableLoader(tableDir.getAbsolutePath()); + } + + private List<Snapshot> findValidSnapshots(Table table) { + List<Snapshot> validSnapshots = Lists.newArrayList(); + for (Snapshot snapshot : table.snapshots()) { + if (snapshot.allManifests().stream().anyMatch(m -> snapshot.snapshotId() == m.snapshotId())) { + validSnapshots.add(snapshot); + } + } + return validSnapshots; + } + + private void testChangeLogs(List<String> equalityFieldColumns, + KeySelector<Row, Row> keySelector, + List<List<Row>> elementsPerCheckpoint, + List<List<Record>> expectedRecordsPerCheckpoint) throws Exception { + DataStream<Row> dataStream = env.addSource(new BoundedTestSource<>(elementsPerCheckpoint), ROW_TYPE_INFO); + + // Shuffle by the equality key, so that different operations from the same key could be wrote in order when + // executing tasks in parallelism. Review comment: Nit: I think you mean "executing tasks in parallel" rather than "parallelism". ---------------------------------------------------------------- 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]
