kbendick commented on a change in pull request #4316: URL: https://github.com/apache/iceberg/pull/4316#discussion_r825379734
########## File path: api/src/main/java/org/apache/iceberg/expressions/ExpressionRemove.java ########## @@ -0,0 +1,81 @@ +/* + * 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.expressions; + +import java.util.Set; +import org.apache.iceberg.Schema; +import org.apache.iceberg.exceptions.ValidationException; + +public class ExpressionRemove { Review comment: Can you please add a javadoc to this class, explaining what it does and also possibly linking to related classes? It doesn’t have to be very long, as this PR will likely see a lot of review given the importance of this bug, so I wouldn’t invest too much time in the javadoc until closer to when it’s ready to go in. But it would help reviewers to add one. 👍 ########## File path: core/src/main/java/org/apache/iceberg/ManifestReader.java ########## @@ -166,6 +169,13 @@ public PartitionSpec spec() { } public ManifestReader<F> filterRows(Expression expr) { + if (this.content.equals(FileType.DELETE_FILES) && this.metadataSchema.identifierFieldIds() != null && + !this.metadataSchema.identifierFieldIds().isEmpty()) { Review comment: Nit: normally we only use `this` when accessing properties if we’re assigning to them. They’re not needed here. ########## File path: core/src/main/java/org/apache/iceberg/ManifestReader.java ########## @@ -166,6 +169,13 @@ public PartitionSpec spec() { } public ManifestReader<F> filterRows(Expression expr) { + if (this.content.equals(FileType.DELETE_FILES) && this.metadataSchema.identifierFieldIds() != null && + !this.metadataSchema.identifierFieldIds().isEmpty()) { Review comment: Note these style nits can be resolved when we’re closer to merging the PR if you’d like. ########## File path: flink/v1.14/flink/src/test/java/org/apache/iceberg/flink/TestFlinkUpsert.java ########## @@ -0,0 +1,155 @@ +/* + * 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 java.util.List; +import java.util.Map; +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.test.util.MiniClusterWithClientResource; +import org.apache.flink.types.Row; +import org.apache.iceberg.FileFormat; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.catalog.Namespace; +import org.apache.iceberg.flink.source.BoundedTableFactory; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.junit.After; +import org.junit.Assert; +import org.junit.Before; +import org.junit.ClassRule; +import org.junit.Test; +import org.junit.rules.TemporaryFolder; +import org.junit.runner.RunWith; +import org.junit.runners.Parameterized; + +@RunWith(Parameterized.class) +public class TestFlinkUpsert extends FlinkCatalogTestBase { + + @ClassRule + public static final MiniClusterWithClientResource MINI_CLUSTER_RESOURCE = + MiniClusterResource.createWithClassloaderCheckDisabled(); + + @ClassRule + public static final TemporaryFolder TEMPORARY_FOLDER = new TemporaryFolder(); + + private TableEnvironment tEnv; + + private final FileFormat format; + private final boolean isStreamingJob; + private final Map<String, String> tableUpsertProps = Maps.newHashMap(); + + @Parameterized.Parameters(name = "catalogName={0}, baseNamespace={1}, format={2}, isStreaming={3}") + public static Iterable<Object[]> parameters() { + List<Object[]> parameters = Lists.newArrayList(); + for (FileFormat format : new FileFormat[] {FileFormat.ORC, FileFormat.AVRO, FileFormat.PARQUET}) { + for (Boolean isStreaming : new Boolean[] {true, false}) { + for (Object[] catalogParams : FlinkCatalogTestBase.parameters()) { + String catalogName = (String) catalogParams[0]; + Namespace baseNamespace = (Namespace) catalogParams[1]; + parameters.add(new Object[] {catalogName, baseNamespace, format, isStreaming}); + } + } + } + return parameters; + } + + public TestFlinkUpsert(String catalogName, Namespace baseNamespace, FileFormat format, Boolean isStreamingJob) { + super(catalogName, baseNamespace); + this.format = format; + this.isStreamingJob = isStreamingJob; + tableUpsertProps.put(TableProperties.FORMAT_VERSION, "2"); + tableUpsertProps.put(TableProperties.UPSERT_ENABLED, "true"); + tableUpsertProps.put(TableProperties.DEFAULT_FILE_FORMAT, format.name()); + } + + @Override + protected TableEnvironment getTableEnv() { + if (tEnv == null) { + synchronized (this) { + EnvironmentSettings.Builder settingsBuilder = EnvironmentSettings + .newInstance(); + if (isStreamingJob) { + settingsBuilder.inStreamingMode(); + StreamExecutionEnvironment env = StreamExecutionEnvironment + .getExecutionEnvironment(MiniClusterResource.DISABLE_CLASSLOADER_CHECK_CONFIG); + env.enableCheckpointing(400); + env.setMaxParallelism(2); + env.setParallelism(2); + tEnv = StreamTableEnvironment.create(env, settingsBuilder.build()); + } else { + settingsBuilder.inBatchMode(); + tEnv = TableEnvironment.create(settingsBuilder.build()); + } + } + } + return tEnv; + } + + @Override + @Before + public void before() { + super.before(); + sql("CREATE DATABASE %s", flinkDatabase); + sql("USE CATALOG %s", catalogName); + sql("USE %s", DATABASE); + } + + @Override + @After + public void clean() { + sql("DROP DATABASE IF EXISTS %s", flinkDatabase); + BoundedTableFactory.clearDataSets(); + super.clean(); + } + + @Test + public void testUpsertAndQuery() { + String tableName = "test_upsert_query"; + + sql("CREATE TABLE %s(id INT NOT NULL, province STRING NOT NULL, dt DATE, PRIMARY KEY(id,province) NOT ENFORCED) " + + "PARTITIONED BY (province) WITH %s", + tableName, toWithClause(tableUpsertProps)); + + sql("INSERT INTO %s VALUES " + + "(1, 'a', TO_DATE('2022-03-01'))," + + "(2, 'b', TO_DATE('2022-03-01'))," + + "(1, 'b', TO_DATE('2022-03-01'))", + tableName); + + sql("INSERT INTO %s VALUES " + + "(4, 'a', TO_DATE('2022-03-02'))," + + "(5, 'b', TO_DATE('2022-03-02'))," + + "(1, 'b', TO_DATE('2022-03-02'))", + tableName); + + List<Row> result = sql("SELECT * FROM %s WHERE dt < '2022-03-02'", tableName); + + Assert.assertEquals("result should have 2 rows!", 2, result.size()); + + result = sql("SELECT * FROM %s WHERE dt < '2022-03-03'", tableName); + + Assert.assertEquals("result should have 5 rows!", 5, result.size()); + + sql("DROP TABLE IF EXISTS %s.%s", flinkDatabase, tableName); Review comment: Nit: Please make sure the table gets dropped, even with failures etc. Two options: 1) Use `try … finally` 2) Create and drop table in before / after functions (or any of `BeforeEach` etc). Option 2 is preferable if possible, but it’s not always possible in which case 1 at least makes sure the DROP TABLE statement runs no matter what. ########## File path: flink/v1.14/flink/src/test/java/org/apache/iceberg/flink/TestFlinkUpsert.java ########## @@ -0,0 +1,155 @@ +/* + * 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 java.util.List; +import java.util.Map; +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.test.util.MiniClusterWithClientResource; +import org.apache.flink.types.Row; +import org.apache.iceberg.FileFormat; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.catalog.Namespace; +import org.apache.iceberg.flink.source.BoundedTableFactory; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.junit.After; +import org.junit.Assert; +import org.junit.Before; +import org.junit.ClassRule; +import org.junit.Test; +import org.junit.rules.TemporaryFolder; +import org.junit.runner.RunWith; +import org.junit.runners.Parameterized; + +@RunWith(Parameterized.class) +public class TestFlinkUpsert extends FlinkCatalogTestBase { + + @ClassRule + public static final MiniClusterWithClientResource MINI_CLUSTER_RESOURCE = + MiniClusterResource.createWithClassloaderCheckDisabled(); + + @ClassRule + public static final TemporaryFolder TEMPORARY_FOLDER = new TemporaryFolder(); + + private TableEnvironment tEnv; + + private final FileFormat format; + private final boolean isStreamingJob; + private final Map<String, String> tableUpsertProps = Maps.newHashMap(); + + @Parameterized.Parameters(name = "catalogName={0}, baseNamespace={1}, format={2}, isStreaming={3}") + public static Iterable<Object[]> parameters() { + List<Object[]> parameters = Lists.newArrayList(); + for (FileFormat format : new FileFormat[] {FileFormat.ORC, FileFormat.AVRO, FileFormat.PARQUET}) { + for (Boolean isStreaming : new Boolean[] {true, false}) { + for (Object[] catalogParams : FlinkCatalogTestBase.parameters()) { + String catalogName = (String) catalogParams[0]; + Namespace baseNamespace = (Namespace) catalogParams[1]; + parameters.add(new Object[] {catalogName, baseNamespace, format, isStreaming}); + } + } + } + return parameters; + } + + public TestFlinkUpsert(String catalogName, Namespace baseNamespace, FileFormat format, Boolean isStreamingJob) { + super(catalogName, baseNamespace); + this.format = format; + this.isStreamingJob = isStreamingJob; + tableUpsertProps.put(TableProperties.FORMAT_VERSION, "2"); + tableUpsertProps.put(TableProperties.UPSERT_ENABLED, "true"); + tableUpsertProps.put(TableProperties.DEFAULT_FILE_FORMAT, format.name()); + } + + @Override + protected TableEnvironment getTableEnv() { + if (tEnv == null) { + synchronized (this) { + EnvironmentSettings.Builder settingsBuilder = EnvironmentSettings + .newInstance(); + if (isStreamingJob) { + settingsBuilder.inStreamingMode(); + StreamExecutionEnvironment env = StreamExecutionEnvironment + .getExecutionEnvironment(MiniClusterResource.DISABLE_CLASSLOADER_CHECK_CONFIG); + env.enableCheckpointing(400); + env.setMaxParallelism(2); + env.setParallelism(2); + tEnv = StreamTableEnvironment.create(env, settingsBuilder.build()); + } else { + settingsBuilder.inBatchMode(); + tEnv = TableEnvironment.create(settingsBuilder.build()); + } + } + } + return tEnv; + } + + @Override + @Before + public void before() { + super.before(); + sql("CREATE DATABASE %s", flinkDatabase); Review comment: Nit: Please add IF NOT EXISTS in tests whenever possible. It reduces log noise and future proofs much better (failed tests where clean up doesn’t happen, etc) -- 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]
