pvary commented on code in PR #10179: URL: https://github.com/apache/iceberg/pull/10179#discussion_r1592005960
########## flink/v1.19/flink/src/test/java/org/apache/iceberg/flink/sink/TestIcebergSink.java: ########## @@ -0,0 +1,399 @@ +/* + * 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.IOException; +import java.util.Collections; +import java.util.List; +import java.util.Map; +import org.apache.flink.configuration.Configuration; +import org.apache.flink.streaming.api.datastream.DataStream; +import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment; +import org.apache.flink.table.api.TableSchema; +import org.apache.flink.table.data.RowData; +import org.apache.flink.test.util.MiniClusterWithClientResource; +import org.apache.flink.types.Row; +import org.apache.iceberg.DistributionMode; +import org.apache.iceberg.FileFormat; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.catalog.TableIdentifier; +import org.apache.iceberg.flink.FlinkWriteOptions; +import org.apache.iceberg.flink.HadoopCatalogResource; +import org.apache.iceberg.flink.MiniClusterResource; +import org.apache.iceberg.flink.SimpleDataUtil; +import org.apache.iceberg.flink.TableLoader; +import org.apache.iceberg.flink.TestFixtures; +import org.apache.iceberg.flink.util.FlinkCompatibilityUtil; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.assertj.core.api.Assertions; +import org.junit.Assert; +import org.junit.Before; +import org.junit.ClassRule; +import org.junit.Ignore; +import org.junit.Rule; +import org.junit.Test; +import org.junit.rules.TemporaryFolder; +import org.junit.runner.RunWith; +import org.junit.runners.Parameterized; + +// Like TestFlinkIcebergSink but only using the new IcebergSink +@RunWith(Parameterized.class) +public class TestIcebergSink extends TestFlinkIcebergSinkBase { + + @ClassRule + public static final MiniClusterWithClientResource MINI_CLUSTER_RESOURCE = + MiniClusterResource.createWithClassloaderCheckDisabled(); + + @ClassRule public static final TemporaryFolder TEMPORARY_FOLDER = new TemporaryFolder(); + + @Rule + public final HadoopCatalogResource catalogResource = + new HadoopCatalogResource(TEMPORARY_FOLDER, TestFixtures.DATABASE, TestFixtures.TABLE); + + private TableLoader tableLoader; + + private final FileFormat format; + private final int parallelism; + private final boolean partitioned; + + @Parameterized.Parameters(name = "format={0}, parallelism = {1}, partitioned = {2}") + public static Object[][] parameters() { + return new Object[][] { + {"avro", 1, true}, + {"avro", 1, false}, + {"avro", 2, true}, + {"avro", 2, false}, + {"orc", 1, true}, + {"orc", 1, false}, + {"orc", 2, true}, + {"orc", 2, false}, + {"parquet", 1, true}, + {"parquet", 1, false}, + {"parquet", 2, true}, + {"parquet", 2, false} + }; + } + + public TestIcebergSink(String format, int parallelism, boolean partitioned) { + this.format = FileFormat.fromString(format); + this.parallelism = parallelism; + this.partitioned = partitioned; + } + + @Before + public void before() throws IOException { + table = + catalogResource + .catalog() + .createTable( + TestFixtures.TABLE_IDENTIFIER, + SimpleDataUtil.SCHEMA, + partitioned + ? PartitionSpec.builderFor(SimpleDataUtil.SCHEMA).identity("data").build() + : PartitionSpec.unpartitioned(), + ImmutableMap.of(TableProperties.DEFAULT_FILE_FORMAT, format.name())); + + env = + StreamExecutionEnvironment.getExecutionEnvironment( + MiniClusterResource.DISABLE_CLASSLOADER_CHECK_CONFIG) + .enableCheckpointing(100) + .setParallelism(parallelism) + .setMaxParallelism(parallelism); + + tableLoader = catalogResource.tableLoader(); + } + + @Test + public void testWriteRowData() throws Exception { + List<Row> rows = Lists.newArrayList(Row.of(1, "hello"), Row.of(2, "world"), Row.of(3, "foo")); + DataStream<RowData> dataStream = + env.addSource(createBoundedSource(rows), ROW_TYPE_INFO) + .map(CONVERTER::toInternal, FlinkCompatibilityUtil.toTypeInfo(SimpleDataUtil.ROW_TYPE)); + + IcebergSink.forRowData(dataStream) + .table(table) + .tableLoader(tableLoader) + .writeParallelism(parallelism) + .append(); + + // Execute the program. + env.execute("Test Iceberg DataStream"); + + // Assert the iceberg table's records. + SimpleDataUtil.assertTableRows(table, convertToRowData(rows)); + } + + private void testWriteRow(TableSchema tableSchema, DistributionMode distributionMode) + throws Exception { + List<Row> rows = createRows(""); + DataStream<Row> dataStream = env.addSource(createBoundedSource(rows), ROW_TYPE_INFO); + + IcebergSink.forRow(dataStream, SimpleDataUtil.FLINK_SCHEMA) + .table(table) + .tableLoader(tableLoader) + .tableSchema(tableSchema) + .writeParallelism(parallelism) + .distributionMode(distributionMode) + .append(); + + // Execute the program. + env.execute("Test Iceberg DataStream."); + + SimpleDataUtil.assertTableRows(table, convertToRowData(rows)); + } + + private int partitionFiles(String partition) throws IOException { + return SimpleDataUtil.partitionDataFiles(table, ImmutableMap.of("data", partition)).size(); + } Review Comment: nit: Please move these to the bottom of the class -- 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
