stevenzwu commented on code in PR #10777: URL: https://github.com/apache/iceberg/pull/10777#discussion_r1697583182
########## flink/v1.19/flink/src/test/java/org/apache/iceberg/flink/TestFlinkTableSinkExtended.java: ########## @@ -0,0 +1,248 @@ +/* + * 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; + +import static org.apache.iceberg.flink.FlinkCatalogFactory.ICEBERG_CATALOG_TYPE_HADOOP; +import static org.assertj.core.api.Assertions.assertThat; + +import java.io.File; +import java.util.Arrays; +import java.util.Collections; +import java.util.List; +import java.util.Map; +import java.util.stream.Collectors; +import java.util.stream.IntStream; +import org.apache.flink.api.dag.Transformation; +import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment; +import org.apache.flink.table.api.EnvironmentSettings; +import org.apache.flink.table.api.TableEnvironment; +import org.apache.flink.table.api.bridge.java.StreamTableEnvironment; +import org.apache.flink.table.api.internal.TableEnvironmentImpl; +import org.apache.flink.table.operations.ModifyOperation; +import org.apache.flink.table.planner.delegation.PlannerBase; +import org.apache.flink.test.junit5.MiniClusterExtension; +import org.apache.flink.types.Row; +import org.apache.hadoop.conf.Configuration; +import org.apache.iceberg.CatalogProperties; +import org.apache.iceberg.DataFile; +import org.apache.iceberg.DistributionMode; +import org.apache.iceberg.FileFormat; +import org.apache.iceberg.Parameter; +import org.apache.iceberg.ParameterizedTestExtension; +import org.apache.iceberg.Parameters; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.catalog.Namespace; +import org.apache.iceberg.catalog.TableIdentifier; +import org.apache.iceberg.flink.source.BoundedTableFactory; +import org.apache.iceberg.hadoop.HadoopCatalog; +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.Maps; +import org.junit.jupiter.api.AfterEach; +import org.junit.jupiter.api.BeforeEach; +import org.junit.jupiter.api.TestTemplate; +import org.junit.jupiter.api.extension.ExtendWith; +import org.junit.jupiter.api.extension.RegisterExtension; +import org.junit.jupiter.api.io.TempDir; + +/** + * This tests the more extended features of Flink sink. Extract them separately since it is Review Comment: `This` is actually correct. but I see why it is confusing. let me change it to `This class tests ...` ########## flink/v1.19/flink/src/test/java/org/apache/iceberg/flink/TestFlinkTableSinkExtended.java: ########## @@ -0,0 +1,248 @@ +/* + * 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; + +import static org.apache.iceberg.flink.FlinkCatalogFactory.ICEBERG_CATALOG_TYPE_HADOOP; +import static org.assertj.core.api.Assertions.assertThat; + +import java.io.File; +import java.util.Arrays; +import java.util.Collections; +import java.util.List; +import java.util.Map; +import java.util.stream.Collectors; +import java.util.stream.IntStream; +import org.apache.flink.api.dag.Transformation; +import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment; +import org.apache.flink.table.api.EnvironmentSettings; +import org.apache.flink.table.api.TableEnvironment; +import org.apache.flink.table.api.bridge.java.StreamTableEnvironment; +import org.apache.flink.table.api.internal.TableEnvironmentImpl; +import org.apache.flink.table.operations.ModifyOperation; +import org.apache.flink.table.planner.delegation.PlannerBase; +import org.apache.flink.test.junit5.MiniClusterExtension; +import org.apache.flink.types.Row; +import org.apache.hadoop.conf.Configuration; +import org.apache.iceberg.CatalogProperties; +import org.apache.iceberg.DataFile; +import org.apache.iceberg.DistributionMode; +import org.apache.iceberg.FileFormat; +import org.apache.iceberg.Parameter; +import org.apache.iceberg.ParameterizedTestExtension; +import org.apache.iceberg.Parameters; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.catalog.Namespace; +import org.apache.iceberg.catalog.TableIdentifier; +import org.apache.iceberg.flink.source.BoundedTableFactory; +import org.apache.iceberg.hadoop.HadoopCatalog; +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.Maps; +import org.junit.jupiter.api.AfterEach; +import org.junit.jupiter.api.BeforeEach; +import org.junit.jupiter.api.TestTemplate; +import org.junit.jupiter.api.extension.ExtendWith; +import org.junit.jupiter.api.extension.RegisterExtension; +import org.junit.jupiter.api.io.TempDir; + +/** + * This tests the more extended features of Flink sink. Extract them separately since it is + * unnecessary to test all the parameters combinations in {@link TestFlinkTableSink}, like catalog + * types, namespaces, file format, streaming/batch. Those combinations explode exponentially. Each + * test method in {@link TestFlinkTableSink} runs 21 combinations, which are expensive and slow. + */ +@ExtendWith(ParameterizedTestExtension.class) +public class TestFlinkTableSinkExtended extends SqlBase { + Review Comment: sure. will remove. but one empty line at the beginning is also ok with Iceberg coding style ########## flink/v1.19/flink/src/test/java/org/apache/iceberg/flink/TestFlinkTableSinkExtended.java: ########## @@ -0,0 +1,248 @@ +/* + * 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; + +import static org.apache.iceberg.flink.FlinkCatalogFactory.ICEBERG_CATALOG_TYPE_HADOOP; +import static org.assertj.core.api.Assertions.assertThat; + +import java.io.File; +import java.util.Arrays; +import java.util.Collections; +import java.util.List; +import java.util.Map; +import java.util.stream.Collectors; +import java.util.stream.IntStream; +import org.apache.flink.api.dag.Transformation; +import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment; +import org.apache.flink.table.api.EnvironmentSettings; +import org.apache.flink.table.api.TableEnvironment; +import org.apache.flink.table.api.bridge.java.StreamTableEnvironment; +import org.apache.flink.table.api.internal.TableEnvironmentImpl; +import org.apache.flink.table.operations.ModifyOperation; +import org.apache.flink.table.planner.delegation.PlannerBase; +import org.apache.flink.test.junit5.MiniClusterExtension; +import org.apache.flink.types.Row; +import org.apache.hadoop.conf.Configuration; +import org.apache.iceberg.CatalogProperties; +import org.apache.iceberg.DataFile; +import org.apache.iceberg.DistributionMode; +import org.apache.iceberg.FileFormat; +import org.apache.iceberg.Parameter; +import org.apache.iceberg.ParameterizedTestExtension; +import org.apache.iceberg.Parameters; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.catalog.Namespace; +import org.apache.iceberg.catalog.TableIdentifier; +import org.apache.iceberg.flink.source.BoundedTableFactory; +import org.apache.iceberg.hadoop.HadoopCatalog; +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.Maps; +import org.junit.jupiter.api.AfterEach; +import org.junit.jupiter.api.BeforeEach; +import org.junit.jupiter.api.TestTemplate; +import org.junit.jupiter.api.extension.ExtendWith; +import org.junit.jupiter.api.extension.RegisterExtension; +import org.junit.jupiter.api.io.TempDir; + +/** + * This tests the more extended features of Flink sink. Extract them separately since it is + * unnecessary to test all the parameters combinations in {@link TestFlinkTableSink}, like catalog + * types, namespaces, file format, streaming/batch. Those combinations explode exponentially. Each + * test method in {@link TestFlinkTableSink} runs 21 combinations, which are expensive and slow. + */ +@ExtendWith(ParameterizedTestExtension.class) +public class TestFlinkTableSinkExtended extends SqlBase { + + protected static final String CATALOG = "testhadoop"; + protected static final String DATABASE = "db"; + protected static final String TABLE = "tbl"; + + @RegisterExtension + public static MiniClusterExtension miniClusterResource = + MiniFlinkClusterExtension.createWithClassloaderCheckDisabled(); + + private static final String SOURCE_TABLE = "default_catalog.default_database.bounded_source"; + + @TempDir protected File warehouseRoot; + + protected final String flinkDatabase = CATALOG + "." + DATABASE; Review Comment: will do ########## flink/v1.19/flink/src/test/java/org/apache/iceberg/flink/TestFlinkTableSinkExtended.java: ########## @@ -0,0 +1,248 @@ +/* + * 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; + +import static org.apache.iceberg.flink.FlinkCatalogFactory.ICEBERG_CATALOG_TYPE_HADOOP; +import static org.assertj.core.api.Assertions.assertThat; + +import java.io.File; +import java.util.Arrays; +import java.util.Collections; +import java.util.List; +import java.util.Map; +import java.util.stream.Collectors; +import java.util.stream.IntStream; +import org.apache.flink.api.dag.Transformation; +import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment; +import org.apache.flink.table.api.EnvironmentSettings; +import org.apache.flink.table.api.TableEnvironment; +import org.apache.flink.table.api.bridge.java.StreamTableEnvironment; +import org.apache.flink.table.api.internal.TableEnvironmentImpl; +import org.apache.flink.table.operations.ModifyOperation; +import org.apache.flink.table.planner.delegation.PlannerBase; +import org.apache.flink.test.junit5.MiniClusterExtension; +import org.apache.flink.types.Row; +import org.apache.hadoop.conf.Configuration; +import org.apache.iceberg.CatalogProperties; +import org.apache.iceberg.DataFile; +import org.apache.iceberg.DistributionMode; +import org.apache.iceberg.FileFormat; +import org.apache.iceberg.Parameter; +import org.apache.iceberg.ParameterizedTestExtension; +import org.apache.iceberg.Parameters; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.catalog.Namespace; +import org.apache.iceberg.catalog.TableIdentifier; +import org.apache.iceberg.flink.source.BoundedTableFactory; +import org.apache.iceberg.hadoop.HadoopCatalog; +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.Maps; +import org.junit.jupiter.api.AfterEach; +import org.junit.jupiter.api.BeforeEach; +import org.junit.jupiter.api.TestTemplate; +import org.junit.jupiter.api.extension.ExtendWith; +import org.junit.jupiter.api.extension.RegisterExtension; +import org.junit.jupiter.api.io.TempDir; + +/** + * This tests the more extended features of Flink sink. Extract them separately since it is + * unnecessary to test all the parameters combinations in {@link TestFlinkTableSink}, like catalog + * types, namespaces, file format, streaming/batch. Those combinations explode exponentially. Each + * test method in {@link TestFlinkTableSink} runs 21 combinations, which are expensive and slow. + */ +@ExtendWith(ParameterizedTestExtension.class) +public class TestFlinkTableSinkExtended extends SqlBase { + + protected static final String CATALOG = "testhadoop"; + protected static final String DATABASE = "db"; + protected static final String TABLE = "tbl"; + + @RegisterExtension + public static MiniClusterExtension miniClusterResource = + MiniFlinkClusterExtension.createWithClassloaderCheckDisabled(); + + private static final String SOURCE_TABLE = "default_catalog.default_database.bounded_source"; + + @TempDir protected File warehouseRoot; + + protected final String flinkDatabase = CATALOG + "." + DATABASE; + protected final Namespace icebergNamespace = Namespace.of(new String[] {DATABASE}); + + protected HadoopCatalog catalog = null; + + private TableEnvironment tEnv; + + @Parameter protected boolean isStreamingJob; + + @Parameters(name = "isStreamingJob={0}") + protected static List<Object[]> parameters() { + return Arrays.asList(new Boolean[] {true}, new Boolean[] {false}); + } + + protected TableEnvironment getTableEnv() { + if (tEnv == null) { + synchronized (this) { + EnvironmentSettings.Builder settingsBuilder = EnvironmentSettings.newInstance(); Review Comment: I probably copied it somewhere. we don't actually need double checked locking. I will just make the method synchronized to simplify the code. -- 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]
