lkokhreidze commented on a change in pull request #9237: URL: https://github.com/apache/kafka/pull/9237#discussion_r500023844
########## File path: streams/src/test/java/org/apache/kafka/streams/integration/StreamTableJoinTopologyOptimizationIntegrationTest.java ########## @@ -0,0 +1,256 @@ +/* + * 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.kafka.streams.integration; + +import org.apache.kafka.clients.admin.AdminClient; +import org.apache.kafka.clients.admin.AdminClientConfig; +import org.apache.kafka.clients.admin.TopicDescription; +import org.apache.kafka.clients.consumer.ConsumerConfig; +import org.apache.kafka.common.serialization.Deserializer; +import org.apache.kafka.common.serialization.IntegerDeserializer; +import org.apache.kafka.common.serialization.IntegerSerializer; +import org.apache.kafka.common.serialization.Serdes; +import org.apache.kafka.common.serialization.StringDeserializer; +import org.apache.kafka.common.serialization.StringSerializer; +import org.apache.kafka.streams.KafkaStreams; +import org.apache.kafka.streams.KeyValue; +import org.apache.kafka.streams.StreamsBuilder; +import org.apache.kafka.streams.StreamsConfig; +import org.apache.kafka.streams.integration.utils.EmbeddedKafkaCluster; +import org.apache.kafka.streams.integration.utils.IntegrationTestUtils; +import org.apache.kafka.streams.kstream.KStream; +import org.apache.kafka.streams.kstream.KTable; +import org.apache.kafka.streams.kstream.Materialized; +import org.apache.kafka.streams.kstream.Named; +import org.apache.kafka.test.IntegrationTest; +import org.apache.kafka.test.TestUtils; +import org.junit.After; +import org.junit.Before; +import org.junit.ClassRule; +import org.junit.Rule; +import org.junit.Test; +import org.junit.experimental.categories.Category; +import org.junit.rules.TestName; +import org.junit.runner.RunWith; +import org.junit.runners.Parameterized; + +import java.io.IOException; +import java.util.Arrays; +import java.util.Collection; +import java.util.Collections; +import java.util.List; +import java.util.Properties; +import java.util.Set; +import java.util.concurrent.CountDownLatch; +import java.util.concurrent.TimeUnit; + +import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.safeUniqueTestName; +import static org.junit.Assert.assertEquals; +import static org.junit.Assert.assertFalse; +import static org.junit.Assert.assertTrue; + +@RunWith(value = Parameterized.class) +@Category({IntegrationTest.class}) +public class StreamTableJoinTopologyOptimizationIntegrationTest { + private static final int NUM_BROKERS = 1; + + @ClassRule + public static final EmbeddedKafkaCluster CLUSTER = new EmbeddedKafkaCluster(NUM_BROKERS); + + private String tableTopic; + private String inputTopic; + private String outputTopic; + private String applicationId; + + private Properties streamsConfiguration; + + @Rule + public TestName testName = new TestName(); + + @Parameterized.Parameter + public String topologyOptimization; + + @Parameterized.Parameters(name = "Optimization = {0}") + public static Collection<?> topologyOptimization() { + return Arrays.asList(new String[][]{ + {StreamsConfig.OPTIMIZE}, + {StreamsConfig.NO_OPTIMIZATION} + }); + } + + @Before + public void before() throws InterruptedException { + streamsConfiguration = new Properties(); + + final String safeTestName = safeUniqueTestName(getClass(), testName); + + tableTopic = "table-topic" + safeTestName; + inputTopic = "stream-topic-" + safeTestName; + outputTopic = "output-topic-" + safeTestName; + applicationId = "app-" + safeTestName; + + CLUSTER.createTopic(inputTopic, 4, 1); + CLUSTER.createTopic(tableTopic, 2, 1); + CLUSTER.createTopic(outputTopic, 4, 1); + + streamsConfiguration.put(StreamsConfig.APPLICATION_ID_CONFIG, applicationId); + streamsConfiguration.put(StreamsConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers()); + streamsConfiguration.put(StreamsConfig.STATE_DIR_CONFIG, TestUtils.tempDirectory().getPath()); + streamsConfiguration.put(StreamsConfig.CACHE_MAX_BYTES_BUFFERING_CONFIG, 0); + streamsConfiguration.put(StreamsConfig.COMMIT_INTERVAL_MS_CONFIG, 100); + streamsConfiguration.put(StreamsConfig.DEFAULT_KEY_SERDE_CLASS_CONFIG, Serdes.Integer().getClass()); + streamsConfiguration.put(StreamsConfig.DEFAULT_VALUE_SERDE_CLASS_CONFIG, Serdes.String().getClass()); + streamsConfiguration.put(StreamsConfig.TOPOLOGY_OPTIMIZATION_CONFIG, topologyOptimization); + } + + @After + public void whenShuttingDown() throws IOException { + IntegrationTestUtils.purgeLocalStreamsState(streamsConfiguration); + } + + @Test + public void shouldDoStreamTableJoinWithDifferentNumberOfPartitions() throws Exception { + final String storeName = "store"; + final String selectKeyName = "selectKey"; + + final StreamsBuilder streamsBuilder = new StreamsBuilder(); + + final KStream<Integer, String> stream = streamsBuilder.stream(inputTopic); + final KTable<Integer, String> table = streamsBuilder.table(tableTopic, Materialized.as(storeName)); + + stream + .selectKey((key, value) -> key, Named.as(selectKeyName)) + .join(table, (value1, value2) -> value2) + .to(outputTopic); + + startStreams(streamsBuilder); + + final long timestamp = System.currentTimeMillis(); + + final List<KeyValue<Integer, String>> expectedRecords = Arrays.asList( + new KeyValue<>(1, "A"), + new KeyValue<>(2, "B") + ); + + sendEvents(inputTopic, timestamp, expectedRecords); + sendEvents(outputTopic, timestamp, expectedRecords); + + startStreams(streamsBuilder); + + validateReceivedMessages( + outputTopic, + new IntegerDeserializer(), + new StringDeserializer(), + expectedRecords + ); + + final Set<String> allTopicsInCluster = CLUSTER.getAllTopicsInCluster(); + + final String repartitionTopicName = applicationId + "-" + selectKeyName + "-repartition"; + final String tableChangelogStoreName = applicationId + "-" + storeName + "-changelog"; + + assertTrue(topicExists(repartitionTopicName)); + assertEquals(2, getNumberOfPartitionsForTopic(repartitionTopicName)); + + if (StreamsConfig.OPTIMIZE.equals(topologyOptimization)) { + assertFalse(allTopicsInCluster.contains(tableChangelogStoreName)); + } else if (StreamsConfig.NO_OPTIMIZATION.equals(topologyOptimization)) { Review comment: I did it on purpose. Potentially there can be some changes regarding those values and felt like being explicit on what is being tested would be better. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org
