FrankChen021 commented on code in PR #20183: URL: https://github.com/apache/druid/pull/20183#discussion_r3964484012
########## embedded-tests/src/test/java/org/apache/druid/testing/embedded/query/NativeSysTasksQueryTest.java: ########## @@ -0,0 +1,344 @@ +/* + * 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.druid.testing.embedded.query; + +import org.apache.druid.indexing.common.task.NoopTask; +import org.apache.druid.java.util.common.StringUtils; +import org.apache.druid.query.QueryContexts; +import org.apache.druid.sql.calcite.planner.PlannerContext; +import org.apache.druid.sql.calcite.run.NativeSqlEngine; +import org.apache.druid.testing.embedded.EmbeddedBroker; +import org.apache.druid.testing.embedded.EmbeddedCoordinator; +import org.apache.druid.testing.embedded.EmbeddedDruidCluster; +import org.apache.druid.testing.embedded.EmbeddedIndexer; +import org.apache.druid.testing.embedded.EmbeddedOverlord; +import org.apache.druid.testing.embedded.junit5.EmbeddedClusterTestBase; +import org.junit.jupiter.api.Assertions; +import org.junit.jupiter.api.BeforeAll; +import org.junit.jupiter.params.ParameterizedTest; +import org.junit.jupiter.params.provider.ValueSource; + +import java.util.Arrays; +import java.util.Map; +import java.util.Set; +import java.util.stream.Collectors; + +public class NativeSysTasksQueryTest extends EmbeddedClusterTestBase +{ + private static final String TASK_PREFIX = "native_sys_mvp_"; + + private final EmbeddedOverlord overlord = new EmbeddedOverlord(); + private final EmbeddedBroker broker = new EmbeddedBroker(); + + @Override + protected EmbeddedDruidCluster createCluster() + { + return EmbeddedDruidCluster.withEmbeddedDerbyAndZookeeper() + .useLatchableEmitter() + .addServer(new EmbeddedCoordinator()) + .addServer(new EmbeddedIndexer() + .addProperty("druid.worker.capacity", "5")) + .addServer(overlord) + .addServer(broker); + } + + @BeforeAll + public void createTasks() + { + createTasks("a", "native_sys_a", 2); + createTasks("b", "native_sys_b", 3); + } + + @ParameterizedTest(name = "plannerStrategy = {0}") + @ValueSource(strings = { + QueryContexts.NATIVE_QUERY_SQL_PLANNING_MODE_COUPLED, + QueryContexts.NATIVE_QUERY_SQL_PLANNING_MODE_DECOUPLED + }) + public void testGroupByUsesOverlordProvider(final String plannerStrategy) + { + final String result = cluster.runSql( + "SELECT datasource, COUNT(*) " + + "FROM sys.tasks " + + "WHERE task_id = 'native_sys_mvp_a_0' AND datasource = 'native_sys_a' " + + "GROUP BY datasource", + nativeQueryContext(plannerStrategy) + ); + + final Set<String> rows = Arrays.stream(result.split("\\n")).collect(Collectors.toSet()); + Assertions.assertEquals(Set.of("native_sys_a,1"), rows); + } + + @ParameterizedTest(name = "plannerStrategy = {0}") + @ValueSource(strings = { + QueryContexts.NATIVE_QUERY_SQL_PLANNING_MODE_COUPLED, + QueryContexts.NATIVE_QUERY_SQL_PLANNING_MODE_DECOUPLED + }) + public void testNativeAggregationsSupportDistinctCount(final String plannerStrategy) + { + final String result = cluster.runSql( + "SELECT COUNT(*), COUNT(DISTINCT task_id), COUNT(DISTINCT datasource), SUM(1) " + + "FROM sys.tasks " + + "WHERE datasource IN ('native_sys_a', 'native_sys_b')", + nativeQueryContext(plannerStrategy) + ); + + Assertions.assertEquals("5,5,2,5", result); + } + + /** + * Verifies execution when native planning represents the inner aggregation as a query datasource. + * + * <pre>{@code + * SELECT COUNT(*) + * FROM + * ( + * SELECT + * task_id, + * COUNT(*) AS task_count + * FROM sys.tasks + * WHERE datasource IN ('native_sys_a', 'native_sys_b') + * GROUP BY task_id + * ) + * WHERE task_count > 0 + * }</pre> + */ Review Comment: Addressed in the stacked sys.tasks PR: the redundant test Javadocs were removed. See FrankChen021/druid#198. ########## embedded-tests/src/test/java/org/apache/druid/testing/embedded/query/NativeSysTasksQueryTest.java: ########## @@ -0,0 +1,344 @@ +/* + * 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.druid.testing.embedded.query; + +import org.apache.druid.indexing.common.task.NoopTask; +import org.apache.druid.java.util.common.StringUtils; +import org.apache.druid.query.QueryContexts; +import org.apache.druid.sql.calcite.planner.PlannerContext; +import org.apache.druid.sql.calcite.run.NativeSqlEngine; +import org.apache.druid.testing.embedded.EmbeddedBroker; +import org.apache.druid.testing.embedded.EmbeddedCoordinator; +import org.apache.druid.testing.embedded.EmbeddedDruidCluster; +import org.apache.druid.testing.embedded.EmbeddedIndexer; +import org.apache.druid.testing.embedded.EmbeddedOverlord; +import org.apache.druid.testing.embedded.junit5.EmbeddedClusterTestBase; +import org.junit.jupiter.api.Assertions; +import org.junit.jupiter.api.BeforeAll; +import org.junit.jupiter.params.ParameterizedTest; +import org.junit.jupiter.params.provider.ValueSource; + +import java.util.Arrays; +import java.util.Map; +import java.util.Set; +import java.util.stream.Collectors; + +public class NativeSysTasksQueryTest extends EmbeddedClusterTestBase +{ + private static final String TASK_PREFIX = "native_sys_mvp_"; + + private final EmbeddedOverlord overlord = new EmbeddedOverlord(); + private final EmbeddedBroker broker = new EmbeddedBroker(); + + @Override + protected EmbeddedDruidCluster createCluster() + { + return EmbeddedDruidCluster.withEmbeddedDerbyAndZookeeper() + .useLatchableEmitter() + .addServer(new EmbeddedCoordinator()) + .addServer(new EmbeddedIndexer() + .addProperty("druid.worker.capacity", "5")) + .addServer(overlord) + .addServer(broker); + } + + @BeforeAll + public void createTasks() + { + createTasks("a", "native_sys_a", 2); + createTasks("b", "native_sys_b", 3); + } + + @ParameterizedTest(name = "plannerStrategy = {0}") + @ValueSource(strings = { + QueryContexts.NATIVE_QUERY_SQL_PLANNING_MODE_COUPLED, + QueryContexts.NATIVE_QUERY_SQL_PLANNING_MODE_DECOUPLED + }) + public void testGroupByUsesOverlordProvider(final String plannerStrategy) + { + final String result = cluster.runSql( + "SELECT datasource, COUNT(*) " + + "FROM sys.tasks " + + "WHERE task_id = 'native_sys_mvp_a_0' AND datasource = 'native_sys_a' " + + "GROUP BY datasource", + nativeQueryContext(plannerStrategy) + ); + + final Set<String> rows = Arrays.stream(result.split("\\n")).collect(Collectors.toSet()); + Assertions.assertEquals(Set.of("native_sys_a,1"), rows); + } + + @ParameterizedTest(name = "plannerStrategy = {0}") + @ValueSource(strings = { + QueryContexts.NATIVE_QUERY_SQL_PLANNING_MODE_COUPLED, + QueryContexts.NATIVE_QUERY_SQL_PLANNING_MODE_DECOUPLED + }) + public void testNativeAggregationsSupportDistinctCount(final String plannerStrategy) + { + final String result = cluster.runSql( + "SELECT COUNT(*), COUNT(DISTINCT task_id), COUNT(DISTINCT datasource), SUM(1) " + + "FROM sys.tasks " + + "WHERE datasource IN ('native_sys_a', 'native_sys_b')", + nativeQueryContext(plannerStrategy) + ); + + Assertions.assertEquals("5,5,2,5", result); + } + + /** + * Verifies execution when native planning represents the inner aggregation as a query datasource. + * + * <pre>{@code + * SELECT COUNT(*) + * FROM + * ( + * SELECT + * task_id, + * COUNT(*) AS task_count + * FROM sys.tasks + * WHERE datasource IN ('native_sys_a', 'native_sys_b') + * GROUP BY task_id + * ) + * WHERE task_count > 0 + * }</pre> + */ + @ParameterizedTest(name = "plannerStrategy = {0}") + @ValueSource(strings = { + QueryContexts.NATIVE_QUERY_SQL_PLANNING_MODE_COUPLED, + QueryContexts.NATIVE_QUERY_SQL_PLANNING_MODE_DECOUPLED + }) + public void testNestedTaskAggregation(final String plannerStrategy) + { + final String result = cluster.runSql( + "SELECT COUNT(*) " + + "FROM (" + + " SELECT task_id, COUNT(*) AS task_count " + + " FROM sys.tasks " + + " WHERE datasource IN ('native_sys_a', 'native_sys_b') " + + " GROUP BY task_id" + + ") " + + "WHERE task_count > 0", + nativeQueryContext(plannerStrategy) + ); + + Assertions.assertEquals("5", result); + } + + /** + * Verifies that an outer aggregation can consume grouped rows from a native system-table subquery. + * + * <pre>{@code + * SELECT SUM(task_count) + * FROM + * ( + * SELECT + * datasource, + * COUNT(*) AS task_count + * FROM sys.tasks + * WHERE datasource IN ('native_sys_a', 'native_sys_b') + * GROUP BY datasource + * ) + * }</pre> + */ + @ParameterizedTest(name = "plannerStrategy = {0}") + @ValueSource(strings = { + QueryContexts.NATIVE_QUERY_SQL_PLANNING_MODE_COUPLED, + QueryContexts.NATIVE_QUERY_SQL_PLANNING_MODE_DECOUPLED + }) + public void testOuterAggregationOverTaskSubquery(final String plannerStrategy) + { + final String result = cluster.runSql( + "SELECT SUM(task_count) " + + "FROM (" + + " SELECT datasource, COUNT(*) AS task_count " + + " FROM sys.tasks " + + " WHERE datasource IN ('native_sys_a', 'native_sys_b') " + + " GROUP BY datasource" + + ")", + nativeQueryContext(plannerStrategy) + ); + + Assertions.assertEquals("5", result); + } + + @ParameterizedTest(name = "plannerStrategy = {0}") + @ValueSource(strings = { + QueryContexts.NATIVE_QUERY_SQL_PLANNING_MODE_COUPLED, + QueryContexts.NATIVE_QUERY_SQL_PLANNING_MODE_DECOUPLED + }) + public void testInAndOrFilters(final String plannerStrategy) + { + assertTaskFilterQuery( + "task_id IN ('native_sys_mvp_a_0', 'native_sys_mvp_b_2') " + + "OR task_id = 'native_sys_mvp_missing'", + Set.of("native_sys_mvp_a_0", "native_sys_mvp_b_2"), + plannerStrategy + ); + } + + @ParameterizedTest(name = "plannerStrategy = {0}") + @ValueSource(strings = { + QueryContexts.NATIVE_QUERY_SQL_PLANNING_MODE_COUPLED, + QueryContexts.NATIVE_QUERY_SQL_PLANNING_MODE_DECOUPLED + }) + public void testRangeAndLikeFilters(final String plannerStrategy) + { + assertTaskFilterQuery( + "task_id >= 'native_sys_mvp_b_0' " + + "AND task_id < 'native_sys_mvp_b_2' " + + "AND task_id LIKE 'native_sys_mvp_b_%'", + Set.of("native_sys_mvp_b_0", "native_sys_mvp_b_1"), + plannerStrategy + ); + } + + /** + * Verifies that expression virtual columns required by a pushed node filter are preserved. + * + * <pre>{@code + * SELECT task_id + * FROM sys.tasks + * WHERE UPPER(task_id) = 'NATIVE_SYS_MVP_A_0' + * }</pre> + */ Review Comment: Addressed in the stacked sys.tasks PR: the repeated SQL Javadocs in this test were removed. See FrankChen021/druid#198. -- 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]
