amogh-jahagirdar commented on code in PR #6660: URL: https://github.com/apache/iceberg/pull/6660#discussion_r1100543216
########## flink/v1.16/flink/src/test/java/org/apache/iceberg/flink/sink/TestFlinkIcebergSinkBranch.java: ########## @@ -0,0 +1,398 @@ +/* + * 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.List; +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.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.SnapshotRef; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.data.Record; +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.source.BoundedTestSource; +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.relocated.com.google.common.collect.Sets; +import org.apache.iceberg.types.Types; +import org.junit.Assert; +import org.junit.Assume; +import org.junit.Before; +import org.junit.ClassRule; +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 TestFlinkIcebergSinkBranch 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 Table table; + private StreamExecutionEnvironment env; + private final String branch; + private final int formatVersion; + + @Parameterized.Parameters(name = "formatVersion = {0}, branch = {1}") + public static Object[][] parameters() { + return new Object[][] { + {1, "main"}, + {1, "test-branch"}, + {2, "main"}, + {2, "test-branch"}, + }; + } + + public TestFlinkIcebergSinkBranch(int formatVersion, String branch) { + this.formatVersion = formatVersion; + this.branch = branch; + } + + @Before + public void before() throws IOException { + table = + catalogResource + .catalog() + .createTable( + TestFixtures.TABLE_IDENTIFIER, + SimpleDataUtil.SCHEMA, + PartitionSpec.unpartitioned(), + ImmutableMap.of( + TableProperties.DEFAULT_FILE_FORMAT, + FileFormat.AVRO.name(), + TableProperties.FORMAT_VERSION, + String.valueOf(formatVersion))); + + env = + StreamExecutionEnvironment.getExecutionEnvironment( + MiniClusterResource.DISABLE_CLASSLOADER_CHECK_CONFIG) + .enableCheckpointing(100); + + tableLoader = catalogResource.tableLoader(); + } + + @Test + public void testWriteRow() throws Exception { + testWriteRow(null, DistributionMode.NONE); + } + + @Test + public void testWriteRowWithTableSchema() throws Exception { + testWriteRow(SimpleDataUtil.FLINK_SCHEMA, DistributionMode.NONE); + verifyOtherBranchUnmodified(); + } + + private void testWriteRow(TableSchema tableSchema, DistributionMode distributionMode) + throws Exception { + List<Row> rows = createRows(""); + DataStream<Row> dataStream = env.addSource(createBoundedSource(rows), ROW_TYPE_INFO); + + FlinkSink.forRow(dataStream, SimpleDataUtil.FLINK_SCHEMA) + .table(table) + .tableLoader(tableLoader) + .tableSchema(tableSchema) + .toBranch(branch) + .distributionMode(distributionMode) + .append(); + + // Execute the program. + env.execute("Test Iceberg DataStream."); + + SimpleDataUtil.assertTableRows(table, convertToRowData(rows), branch); + SimpleDataUtil.assertTableRows( + table, + ImmutableList.of(), + branch.equals(SnapshotRef.MAIN_BRANCH) ? "test-branch" : SnapshotRef.MAIN_BRANCH); + + verifyOtherBranchUnmodified(); + } + + @Test + public void testCheckAndGetEqualityFieldIds() { + Assume.assumeTrue(formatVersion == 2); + table + .updateSchema() + .allowIncompatibleChanges() + .addRequiredColumn("type", Types.StringType.get()) + .setIdentifierFields("type") + .commit(); + + DataStream<Row> dataStream = + env.addSource(new BoundedTestSource<>(ImmutableList.of()), ROW_TYPE_INFO); + FlinkSink.Builder builder = + FlinkSink.forRow(dataStream, SimpleDataUtil.FLINK_SCHEMA).table(table); + + // Use schema identifier field IDs as equality field id list by default + Assert.assertEquals( + table.schema().identifierFieldIds(), + Sets.newHashSet(builder.checkAndGetEqualityFieldIds())); + + // Use user-provided equality field column as equality field id list + builder.equalityFieldColumns(Lists.newArrayList("id")); + Assert.assertEquals( + Sets.newHashSet(table.schema().findField("id").fieldId()), + Sets.newHashSet(builder.checkAndGetEqualityFieldIds())); + + builder.equalityFieldColumns(Lists.newArrayList("type")); + Assert.assertEquals( + Sets.newHashSet(table.schema().findField("type").fieldId()), + Sets.newHashSet(builder.checkAndGetEqualityFieldIds())); + + verifyOtherBranchUnmodified(); + } + + @Test + public void testChangeLogOnIdKey() throws Exception { + Assume.assumeTrue(formatVersion == 2); + List<List<Row>> elementsPerCheckpoint = Review Comment: Good point, I did some more refactoring to further reduce the duplication. The common test cases with v2 will be shared (so the row data and the append will be the same) but we'll pass in a branch. For the non branch test cases we pass in just main, but parameterize based on all the existing properties (like file format, partitioning etc). For the branch ones we'll pass in just the branches with a fixed file format, partitioning. In this way we can reduce the duplication and get the benefit of not exponentially increasing the number of tests. ########## flink/v1.16/flink/src/test/java/org/apache/iceberg/flink/sink/TestFlinkIcebergSinkBranch.java: ########## @@ -0,0 +1,398 @@ +/* + * 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.List; +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.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.SnapshotRef; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.data.Record; +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.source.BoundedTestSource; +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.relocated.com.google.common.collect.Sets; +import org.apache.iceberg.types.Types; +import org.junit.Assert; +import org.junit.Assume; +import org.junit.Before; +import org.junit.ClassRule; +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 TestFlinkIcebergSinkBranch 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 Table table; + private StreamExecutionEnvironment env; + private final String branch; + private final int formatVersion; + + @Parameterized.Parameters(name = "formatVersion = {0}, branch = {1}") + public static Object[][] parameters() { + return new Object[][] { + {1, "main"}, + {1, "test-branch"}, + {2, "main"}, + {2, "test-branch"}, + }; + } + + public TestFlinkIcebergSinkBranch(int formatVersion, String branch) { + this.formatVersion = formatVersion; + this.branch = branch; + } + + @Before + public void before() throws IOException { + table = + catalogResource + .catalog() + .createTable( + TestFixtures.TABLE_IDENTIFIER, + SimpleDataUtil.SCHEMA, + PartitionSpec.unpartitioned(), + ImmutableMap.of( + TableProperties.DEFAULT_FILE_FORMAT, + FileFormat.AVRO.name(), + TableProperties.FORMAT_VERSION, + String.valueOf(formatVersion))); + + env = + StreamExecutionEnvironment.getExecutionEnvironment( + MiniClusterResource.DISABLE_CLASSLOADER_CHECK_CONFIG) + .enableCheckpointing(100); + + tableLoader = catalogResource.tableLoader(); + } + + @Test + public void testWriteRow() throws Exception { + testWriteRow(null, DistributionMode.NONE); + } + + @Test + public void testWriteRowWithTableSchema() throws Exception { + testWriteRow(SimpleDataUtil.FLINK_SCHEMA, DistributionMode.NONE); + verifyOtherBranchUnmodified(); + } + + private void testWriteRow(TableSchema tableSchema, DistributionMode distributionMode) + throws Exception { + List<Row> rows = createRows(""); + DataStream<Row> dataStream = env.addSource(createBoundedSource(rows), ROW_TYPE_INFO); + + FlinkSink.forRow(dataStream, SimpleDataUtil.FLINK_SCHEMA) + .table(table) + .tableLoader(tableLoader) + .tableSchema(tableSchema) + .toBranch(branch) + .distributionMode(distributionMode) + .append(); + + // Execute the program. + env.execute("Test Iceberg DataStream."); + + SimpleDataUtil.assertTableRows(table, convertToRowData(rows), branch); + SimpleDataUtil.assertTableRows( + table, + ImmutableList.of(), + branch.equals(SnapshotRef.MAIN_BRANCH) ? "test-branch" : SnapshotRef.MAIN_BRANCH); + + verifyOtherBranchUnmodified(); + } + + @Test + public void testCheckAndGetEqualityFieldIds() { + Assume.assumeTrue(formatVersion == 2); + table + .updateSchema() + .allowIncompatibleChanges() + .addRequiredColumn("type", Types.StringType.get()) + .setIdentifierFields("type") + .commit(); + + DataStream<Row> dataStream = + env.addSource(new BoundedTestSource<>(ImmutableList.of()), ROW_TYPE_INFO); + FlinkSink.Builder builder = + FlinkSink.forRow(dataStream, SimpleDataUtil.FLINK_SCHEMA).table(table); + + // Use schema identifier field IDs as equality field id list by default + Assert.assertEquals( + table.schema().identifierFieldIds(), + Sets.newHashSet(builder.checkAndGetEqualityFieldIds())); + + // Use user-provided equality field column as equality field id list + builder.equalityFieldColumns(Lists.newArrayList("id")); + Assert.assertEquals( + Sets.newHashSet(table.schema().findField("id").fieldId()), + Sets.newHashSet(builder.checkAndGetEqualityFieldIds())); + + builder.equalityFieldColumns(Lists.newArrayList("type")); + Assert.assertEquals( + Sets.newHashSet(table.schema().findField("type").fieldId()), + Sets.newHashSet(builder.checkAndGetEqualityFieldIds())); + + verifyOtherBranchUnmodified(); + } + + @Test + public void testChangeLogOnIdKey() throws Exception { + Assume.assumeTrue(formatVersion == 2); + List<List<Row>> elementsPerCheckpoint = Review Comment: Good point, I did some more refactoring to further reduce the duplication. The common test cases with v2 will be shared (so the row data and the append will be the same) but we'll pass in a branch. For the non branch test cases we pass in just main, but parameterize based on all the existing properties (like file format, partitioning etc). For the branch ones we'll pass in just the branches with a fixed file format, partitioning. In this way we can reduce the duplication and get the benefit of not doubling the number of tests. -- 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
