You are viewing a plain text version of this content. The canonical link for it is here.
Posted to jira@kafka.apache.org by "mjsax (via GitHub)" <gi...@apache.org> on 2023/04/17 22:12:45 UTC
[GitHub] [kafka] mjsax opened a new pull request, #13592: KAFKA-14862: Outer stream-stream join does not output all results with multiple input partitions
mjsax opened a new pull request, #13592:
URL: https://github.com/apache/kafka/pull/13592
Stream-stream outer join, uses a "shared time tracker" to track stream-time progress for left and right input in a single place. This time tracker is incorrectly shared across tasks.
This PR introduces a supplier to create a "shared time tracker" object per task, to be shared between the left and right join processors.
--
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: jira-unsubscribe@kafka.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [kafka] mjsax commented on pull request #13592: KAFKA-14862: Outer stream-stream join does not output all results with multiple input partitions
Posted by "mjsax (via GitHub)" <gi...@apache.org>.
mjsax commented on PR #13592:
URL: https://github.com/apache/kafka/pull/13592#issuecomment-1520757094
Merged to `trunk` and cherry-picked to `3.5` and `3.4` branches.
--
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: jira-unsubscribe@kafka.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [kafka] vcrfxia commented on a diff in pull request #13592: KAFKA-14862: Outer stream-stream join does not output all results with multiple input partitions
Posted by "vcrfxia (via GitHub)" <gi...@apache.org>.
vcrfxia commented on code in PR #13592:
URL: https://github.com/apache/kafka/pull/13592#discussion_r1171766477
##########
streams/src/test/java/org/apache/kafka/streams/integration/KStreamKStreamIntegrationTest.java:
##########
@@ -0,0 +1,186 @@
+/*
+ * 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 kafka.utils.MockTime;
+import org.apache.kafka.clients.consumer.ConsumerConfig;
+import org.apache.kafka.clients.producer.ProducerConfig;
+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.JoinWindows;
+import org.apache.kafka.streams.kstream.KStream;
+import org.apache.kafka.streams.kstream.ValueJoiner;
+import org.apache.kafka.test.TestUtils;
+import org.junit.jupiter.api.AfterAll;
+import org.junit.jupiter.api.AfterEach;
+import org.junit.jupiter.api.BeforeAll;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Tag;
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.api.TestInfo;
+import org.junit.jupiter.api.Timeout;
+
+import java.io.IOException;
+import java.time.Duration;
+import java.util.Collections;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Properties;
+import java.util.Set;
+
+import static java.time.Duration.ofSeconds;
+import static java.util.Arrays.asList;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.safeUniqueTestName;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.startApplicationAndWaitUntilRunning;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.waitUntilMinKeyValueRecordsReceived;
+import static org.hamcrest.MatcherAssert.assertThat;
+import static org.hamcrest.core.IsEqual.equalTo;
+
+@Timeout(600)
+@Tag("integration")
+public class KStreamKStreamIntegrationTest {
+ private final static int NUM_BROKERS = 1;
+
+ public final static EmbeddedKafkaCluster CLUSTER = new EmbeddedKafkaCluster(NUM_BROKERS);
+ private final static MockTime MOCK_TIME = CLUSTER.time;
+ private final static String STREAM_1 = "stream1";
+ private final static String STREAM_2 = "stream2";
+ private final static String OUTPUT = "output-";
+ private Properties streamsConfig;
+ private KafkaStreams streams;
+ private final static Properties CONSUMER_CONFIG = new Properties();
+ private final static Properties PRODUCER_CONFIG = new Properties();
+
+ @BeforeAll
+ public static void startCluster() throws Exception {
+ CLUSTER.start();
+ //Use multiple partitions to ensure distribution of keys.
+
+ CLUSTER.createTopic(STREAM_1, 4, 1);
+ CLUSTER.createTopic(STREAM_2, 4, 1);
+ CLUSTER.createTopic(OUTPUT, 1, 1);
+
+ CONSUMER_CONFIG.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
+ CONSUMER_CONFIG.put(ConsumerConfig.GROUP_ID_CONFIG, "result-consumer");
+ CONSUMER_CONFIG.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
+ CONSUMER_CONFIG.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
+ }
+
+ @AfterAll
+ public static void closeCluster() {
+ CLUSTER.stop();
+ }
+
+ @BeforeEach
+ public void before(final TestInfo testInfo) throws IOException {
+ final String stateDirBasePath = TestUtils.tempDirectory().getPath();
+ final String safeTestName = safeUniqueTestName(getClass(), testInfo);
+ streamsConfig = getStreamsConfig(safeTestName);
+ streamsConfig.put(StreamsConfig.STATE_DIR_CONFIG, stateDirBasePath);
+ }
+
+ @AfterEach
+ public void after() throws IOException {
+ if (streams != null) {
+ streams.close();
+ streams = null;
+ }
+ IntegrationTestUtils.purgeLocalStreamsState(streamsConfig);
+ }
+
+ @Test
+ public void shouldOuterJoin() throws Exception {
+ final Set<KeyValue<String, String>> expectedOne = new HashSet<>();
+ expectedOne.add(new KeyValue<>("Key-1", "value1=left-1,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-2", "value1=left-2,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-3", "value1=left-3,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-4", "value1=left-4,value2=null"));
+
+ verifyKStreamKStreamOuterJoin(expectedOne);
+ }
+
+ private void verifyKStreamKStreamOuterJoin(final Set<KeyValue<String, String>> expectedResult) throws Exception {
+ streams = prepareTopology(streamsConfig);
+
+ startApplicationAndWaitUntilRunning(Collections.singletonList(streams), ofSeconds(120));
+
+ PRODUCER_CONFIG.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
+ PRODUCER_CONFIG.put(ProducerConfig.ACKS_CONFIG, "all");
+ PRODUCER_CONFIG.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
+ PRODUCER_CONFIG.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
+
+ final List<KeyValue<String, String>> stream1 = asList(
+ new KeyValue<>("Key-1", "left-1"),
+ new KeyValue<>("Key-2", "left-2"),
+ new KeyValue<>("Key-3", "left-3"),
+ new KeyValue<>("Key-4", "left-4")
+ );
+
+ final List<KeyValue<String, String>> stream2 = asList(
+ new KeyValue<>("Key-1", "right-1"),
+ new KeyValue<>("Key-2", "right-2"),
+ new KeyValue<>("Key-3", "right-3"),
+ new KeyValue<>("Key-4", "right-4")
+ );
+
+ IntegrationTestUtils.produceKeyValuesSynchronously(STREAM_1, stream1, PRODUCER_CONFIG, MOCK_TIME);
+ MOCK_TIME.sleep(11000);
+ Thread.sleep(11000);
+ IntegrationTestUtils.produceKeyValuesSynchronously(STREAM_1, stream2, PRODUCER_CONFIG, MOCK_TIME);
+
+ final Set<KeyValue<String, String>> result = new HashSet<>(waitUntilMinKeyValueRecordsReceived(
Review Comment:
Ah! I missed that. Thanks for clearing it up.
--
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: jira-unsubscribe@kafka.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [kafka] mjsax commented on a diff in pull request #13592: KAFKA-14862: Outer stream-stream join does not output all results with multiple input partitions
Posted by "mjsax (via GitHub)" <gi...@apache.org>.
mjsax commented on code in PR #13592:
URL: https://github.com/apache/kafka/pull/13592#discussion_r1169381571
##########
streams/src/test/java/org/apache/kafka/streams/integration/KStreamKStreamIntegrationTest.java:
##########
@@ -0,0 +1,186 @@
+/*
+ * 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 kafka.utils.MockTime;
+import org.apache.kafka.clients.consumer.ConsumerConfig;
+import org.apache.kafka.clients.producer.ProducerConfig;
+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.JoinWindows;
+import org.apache.kafka.streams.kstream.KStream;
+import org.apache.kafka.streams.kstream.ValueJoiner;
+import org.apache.kafka.test.TestUtils;
+import org.junit.jupiter.api.AfterAll;
+import org.junit.jupiter.api.AfterEach;
+import org.junit.jupiter.api.BeforeAll;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Tag;
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.api.TestInfo;
+import org.junit.jupiter.api.Timeout;
+
+import java.io.IOException;
+import java.time.Duration;
+import java.util.Collections;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Properties;
+import java.util.Set;
+
+import static java.time.Duration.ofSeconds;
+import static java.util.Arrays.asList;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.safeUniqueTestName;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.startApplicationAndWaitUntilRunning;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.waitUntilMinKeyValueRecordsReceived;
+import static org.hamcrest.MatcherAssert.assertThat;
+import static org.hamcrest.core.IsEqual.equalTo;
+
+@Timeout(600)
+@Tag("integration")
+public class KStreamKStreamIntegrationTest {
+ private final static int NUM_BROKERS = 1;
+
+ public final static EmbeddedKafkaCluster CLUSTER = new EmbeddedKafkaCluster(NUM_BROKERS);
+ private final static MockTime MOCK_TIME = CLUSTER.time;
+ private final static String STREAM_1 = "stream1";
+ private final static String STREAM_2 = "stream2";
+ private final static String OUTPUT = "output-";
+ private Properties streamsConfig;
+ private KafkaStreams streams;
+ private final static Properties CONSUMER_CONFIG = new Properties();
+ private final static Properties PRODUCER_CONFIG = new Properties();
+
+ @BeforeAll
+ public static void startCluster() throws Exception {
+ CLUSTER.start();
+ //Use multiple partitions to ensure distribution of keys.
+
+ CLUSTER.createTopic(STREAM_1, 4, 1);
+ CLUSTER.createTopic(STREAM_2, 4, 1);
+ CLUSTER.createTopic(OUTPUT, 1, 1);
+
+ CONSUMER_CONFIG.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
+ CONSUMER_CONFIG.put(ConsumerConfig.GROUP_ID_CONFIG, "result-consumer");
+ CONSUMER_CONFIG.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
+ CONSUMER_CONFIG.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
+ }
+
+ @AfterAll
+ public static void closeCluster() {
+ CLUSTER.stop();
+ }
+
+ @BeforeEach
+ public void before(final TestInfo testInfo) throws IOException {
+ final String stateDirBasePath = TestUtils.tempDirectory().getPath();
+ final String safeTestName = safeUniqueTestName(getClass(), testInfo);
+ streamsConfig = getStreamsConfig(safeTestName);
+ streamsConfig.put(StreamsConfig.STATE_DIR_CONFIG, stateDirBasePath);
+ }
+
+ @AfterEach
+ public void after() throws IOException {
+ if (streams != null) {
+ streams.close();
+ streams = null;
+ }
+ IntegrationTestUtils.purgeLocalStreamsState(streamsConfig);
+ }
+
+ @Test
+ public void shouldOuterJoin() throws Exception {
+ final Set<KeyValue<String, String>> expectedOne = new HashSet<>();
+ expectedOne.add(new KeyValue<>("Key-1", "value1=left-1,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-2", "value1=left-2,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-3", "value1=left-3,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-4", "value1=left-4,value2=null"));
+
+ verifyKStreamKStreamOuterJoin(expectedOne);
+ }
+
+ private void verifyKStreamKStreamOuterJoin(final Set<KeyValue<String, String>> expectedResult) throws Exception {
+ streams = prepareTopology(streamsConfig);
+
+ startApplicationAndWaitUntilRunning(Collections.singletonList(streams), ofSeconds(120));
+
+ PRODUCER_CONFIG.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
+ PRODUCER_CONFIG.put(ProducerConfig.ACKS_CONFIG, "all");
+ PRODUCER_CONFIG.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
+ PRODUCER_CONFIG.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
+
+ final List<KeyValue<String, String>> stream1 = asList(
+ new KeyValue<>("Key-1", "left-1"),
+ new KeyValue<>("Key-2", "left-2"),
+ new KeyValue<>("Key-3", "left-3"),
+ new KeyValue<>("Key-4", "left-4")
+ );
+
+ final List<KeyValue<String, String>> stream2 = asList(
+ new KeyValue<>("Key-1", "right-1"),
+ new KeyValue<>("Key-2", "right-2"),
+ new KeyValue<>("Key-3", "right-3"),
+ new KeyValue<>("Key-4", "right-4")
+ );
+
+ IntegrationTestUtils.produceKeyValuesSynchronously(STREAM_1, stream1, PRODUCER_CONFIG, MOCK_TIME);
+ MOCK_TIME.sleep(11000);
+ Thread.sleep(11000);
+ IntegrationTestUtils.produceKeyValuesSynchronously(STREAM_1, stream2, PRODUCER_CONFIG, MOCK_TIME);
Review Comment:
Maybe I should rename `stream1` and `stream2` in `firstInputBatch` and `secondInputBatch` or similar to decouple the same from "left" and "right" input, as both should go into the left input.
##########
streams/src/test/java/org/apache/kafka/streams/integration/KStreamKStreamIntegrationTest.java:
##########
@@ -0,0 +1,186 @@
+/*
+ * 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 kafka.utils.MockTime;
+import org.apache.kafka.clients.consumer.ConsumerConfig;
+import org.apache.kafka.clients.producer.ProducerConfig;
+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.JoinWindows;
+import org.apache.kafka.streams.kstream.KStream;
+import org.apache.kafka.streams.kstream.ValueJoiner;
+import org.apache.kafka.test.TestUtils;
+import org.junit.jupiter.api.AfterAll;
+import org.junit.jupiter.api.AfterEach;
+import org.junit.jupiter.api.BeforeAll;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Tag;
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.api.TestInfo;
+import org.junit.jupiter.api.Timeout;
+
+import java.io.IOException;
+import java.time.Duration;
+import java.util.Collections;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Properties;
+import java.util.Set;
+
+import static java.time.Duration.ofSeconds;
+import static java.util.Arrays.asList;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.safeUniqueTestName;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.startApplicationAndWaitUntilRunning;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.waitUntilMinKeyValueRecordsReceived;
+import static org.hamcrest.MatcherAssert.assertThat;
+import static org.hamcrest.core.IsEqual.equalTo;
+
+@Timeout(600)
+@Tag("integration")
+public class KStreamKStreamIntegrationTest {
+ private final static int NUM_BROKERS = 1;
+
+ public final static EmbeddedKafkaCluster CLUSTER = new EmbeddedKafkaCluster(NUM_BROKERS);
+ private final static MockTime MOCK_TIME = CLUSTER.time;
+ private final static String STREAM_1 = "stream1";
+ private final static String STREAM_2 = "stream2";
+ private final static String OUTPUT = "output-";
+ private Properties streamsConfig;
+ private KafkaStreams streams;
+ private final static Properties CONSUMER_CONFIG = new Properties();
+ private final static Properties PRODUCER_CONFIG = new Properties();
+
+ @BeforeAll
+ public static void startCluster() throws Exception {
+ CLUSTER.start();
+ //Use multiple partitions to ensure distribution of keys.
+
+ CLUSTER.createTopic(STREAM_1, 4, 1);
+ CLUSTER.createTopic(STREAM_2, 4, 1);
+ CLUSTER.createTopic(OUTPUT, 1, 1);
+
+ CONSUMER_CONFIG.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
+ CONSUMER_CONFIG.put(ConsumerConfig.GROUP_ID_CONFIG, "result-consumer");
+ CONSUMER_CONFIG.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
+ CONSUMER_CONFIG.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
+ }
+
+ @AfterAll
+ public static void closeCluster() {
+ CLUSTER.stop();
+ }
+
+ @BeforeEach
+ public void before(final TestInfo testInfo) throws IOException {
+ final String stateDirBasePath = TestUtils.tempDirectory().getPath();
+ final String safeTestName = safeUniqueTestName(getClass(), testInfo);
+ streamsConfig = getStreamsConfig(safeTestName);
+ streamsConfig.put(StreamsConfig.STATE_DIR_CONFIG, stateDirBasePath);
+ }
+
+ @AfterEach
+ public void after() throws IOException {
+ if (streams != null) {
+ streams.close();
+ streams = null;
+ }
+ IntegrationTestUtils.purgeLocalStreamsState(streamsConfig);
+ }
+
+ @Test
+ public void shouldOuterJoin() throws Exception {
+ final Set<KeyValue<String, String>> expectedOne = new HashSet<>();
+ expectedOne.add(new KeyValue<>("Key-1", "value1=left-1,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-2", "value1=left-2,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-3", "value1=left-3,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-4", "value1=left-4,value2=null"));
+
+ verifyKStreamKStreamOuterJoin(expectedOne);
+ }
+
+ private void verifyKStreamKStreamOuterJoin(final Set<KeyValue<String, String>> expectedResult) throws Exception {
+ streams = prepareTopology(streamsConfig);
+
+ startApplicationAndWaitUntilRunning(Collections.singletonList(streams), ofSeconds(120));
+
+ PRODUCER_CONFIG.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
+ PRODUCER_CONFIG.put(ProducerConfig.ACKS_CONFIG, "all");
+ PRODUCER_CONFIG.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
+ PRODUCER_CONFIG.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
+
+ final List<KeyValue<String, String>> stream1 = asList(
+ new KeyValue<>("Key-1", "left-1"),
+ new KeyValue<>("Key-2", "left-2"),
+ new KeyValue<>("Key-3", "left-3"),
+ new KeyValue<>("Key-4", "left-4")
+ );
+
+ final List<KeyValue<String, String>> stream2 = asList(
+ new KeyValue<>("Key-1", "right-1"),
+ new KeyValue<>("Key-2", "right-2"),
+ new KeyValue<>("Key-3", "right-3"),
+ new KeyValue<>("Key-4", "right-4")
+ );
+
+ IntegrationTestUtils.produceKeyValuesSynchronously(STREAM_1, stream1, PRODUCER_CONFIG, MOCK_TIME);
+ MOCK_TIME.sleep(11000);
+ Thread.sleep(11000);
Review Comment:
Guess I should test if we can remove this.
--
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: jira-unsubscribe@kafka.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [kafka] mjsax commented on a diff in pull request #13592: KAFKA-14862: Outer stream-stream join does not output all results with multiple input partitions
Posted by "mjsax (via GitHub)" <gi...@apache.org>.
mjsax commented on code in PR #13592:
URL: https://github.com/apache/kafka/pull/13592#discussion_r1169380664
##########
streams/src/test/java/org/apache/kafka/streams/integration/KStreamKStreamIntegrationTest.java:
##########
@@ -0,0 +1,186 @@
+/*
+ * 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 kafka.utils.MockTime;
+import org.apache.kafka.clients.consumer.ConsumerConfig;
+import org.apache.kafka.clients.producer.ProducerConfig;
+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.JoinWindows;
+import org.apache.kafka.streams.kstream.KStream;
+import org.apache.kafka.streams.kstream.ValueJoiner;
+import org.apache.kafka.test.TestUtils;
+import org.junit.jupiter.api.AfterAll;
+import org.junit.jupiter.api.AfterEach;
+import org.junit.jupiter.api.BeforeAll;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Tag;
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.api.TestInfo;
+import org.junit.jupiter.api.Timeout;
+
+import java.io.IOException;
+import java.time.Duration;
+import java.util.Collections;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Properties;
+import java.util.Set;
+
+import static java.time.Duration.ofSeconds;
+import static java.util.Arrays.asList;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.safeUniqueTestName;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.startApplicationAndWaitUntilRunning;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.waitUntilMinKeyValueRecordsReceived;
+import static org.hamcrest.MatcherAssert.assertThat;
+import static org.hamcrest.core.IsEqual.equalTo;
+
+@Timeout(600)
+@Tag("integration")
+public class KStreamKStreamIntegrationTest {
+ private final static int NUM_BROKERS = 1;
+
+ public final static EmbeddedKafkaCluster CLUSTER = new EmbeddedKafkaCluster(NUM_BROKERS);
+ private final static MockTime MOCK_TIME = CLUSTER.time;
+ private final static String STREAM_1 = "stream1";
+ private final static String STREAM_2 = "stream2";
+ private final static String OUTPUT = "output-";
+ private Properties streamsConfig;
+ private KafkaStreams streams;
+ private final static Properties CONSUMER_CONFIG = new Properties();
+ private final static Properties PRODUCER_CONFIG = new Properties();
+
+ @BeforeAll
+ public static void startCluster() throws Exception {
+ CLUSTER.start();
+ //Use multiple partitions to ensure distribution of keys.
+
+ CLUSTER.createTopic(STREAM_1, 4, 1);
+ CLUSTER.createTopic(STREAM_2, 4, 1);
+ CLUSTER.createTopic(OUTPUT, 1, 1);
+
+ CONSUMER_CONFIG.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
+ CONSUMER_CONFIG.put(ConsumerConfig.GROUP_ID_CONFIG, "result-consumer");
+ CONSUMER_CONFIG.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
+ CONSUMER_CONFIG.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
+ }
+
+ @AfterAll
+ public static void closeCluster() {
+ CLUSTER.stop();
+ }
+
+ @BeforeEach
+ public void before(final TestInfo testInfo) throws IOException {
+ final String stateDirBasePath = TestUtils.tempDirectory().getPath();
+ final String safeTestName = safeUniqueTestName(getClass(), testInfo);
+ streamsConfig = getStreamsConfig(safeTestName);
+ streamsConfig.put(StreamsConfig.STATE_DIR_CONFIG, stateDirBasePath);
+ }
+
+ @AfterEach
+ public void after() throws IOException {
+ if (streams != null) {
+ streams.close();
+ streams = null;
+ }
+ IntegrationTestUtils.purgeLocalStreamsState(streamsConfig);
+ }
+
+ @Test
+ public void shouldOuterJoin() throws Exception {
+ final Set<KeyValue<String, String>> expectedOne = new HashSet<>();
+ expectedOne.add(new KeyValue<>("Key-1", "value1=left-1,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-2", "value1=left-2,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-3", "value1=left-3,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-4", "value1=left-4,value2=null"));
+
+ verifyKStreamKStreamOuterJoin(expectedOne);
+ }
+
+ private void verifyKStreamKStreamOuterJoin(final Set<KeyValue<String, String>> expectedResult) throws Exception {
+ streams = prepareTopology(streamsConfig);
+
+ startApplicationAndWaitUntilRunning(Collections.singletonList(streams), ofSeconds(120));
+
+ PRODUCER_CONFIG.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
+ PRODUCER_CONFIG.put(ProducerConfig.ACKS_CONFIG, "all");
+ PRODUCER_CONFIG.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
+ PRODUCER_CONFIG.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
+
+ final List<KeyValue<String, String>> stream1 = asList(
+ new KeyValue<>("Key-1", "left-1"),
+ new KeyValue<>("Key-2", "left-2"),
+ new KeyValue<>("Key-3", "left-3"),
+ new KeyValue<>("Key-4", "left-4")
+ );
+
+ final List<KeyValue<String, String>> stream2 = asList(
+ new KeyValue<>("Key-1", "right-1"),
+ new KeyValue<>("Key-2", "right-2"),
+ new KeyValue<>("Key-3", "right-3"),
+ new KeyValue<>("Key-4", "right-4")
Review Comment:
Think I should rename those to `left-X`....
##########
streams/src/test/java/org/apache/kafka/streams/integration/KStreamKStreamIntegrationTest.java:
##########
@@ -0,0 +1,186 @@
+/*
+ * 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 kafka.utils.MockTime;
+import org.apache.kafka.clients.consumer.ConsumerConfig;
+import org.apache.kafka.clients.producer.ProducerConfig;
+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.JoinWindows;
+import org.apache.kafka.streams.kstream.KStream;
+import org.apache.kafka.streams.kstream.ValueJoiner;
+import org.apache.kafka.test.TestUtils;
+import org.junit.jupiter.api.AfterAll;
+import org.junit.jupiter.api.AfterEach;
+import org.junit.jupiter.api.BeforeAll;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Tag;
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.api.TestInfo;
+import org.junit.jupiter.api.Timeout;
+
+import java.io.IOException;
+import java.time.Duration;
+import java.util.Collections;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Properties;
+import java.util.Set;
+
+import static java.time.Duration.ofSeconds;
+import static java.util.Arrays.asList;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.safeUniqueTestName;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.startApplicationAndWaitUntilRunning;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.waitUntilMinKeyValueRecordsReceived;
+import static org.hamcrest.MatcherAssert.assertThat;
+import static org.hamcrest.core.IsEqual.equalTo;
+
+@Timeout(600)
+@Tag("integration")
+public class KStreamKStreamIntegrationTest {
+ private final static int NUM_BROKERS = 1;
+
+ public final static EmbeddedKafkaCluster CLUSTER = new EmbeddedKafkaCluster(NUM_BROKERS);
+ private final static MockTime MOCK_TIME = CLUSTER.time;
+ private final static String STREAM_1 = "stream1";
+ private final static String STREAM_2 = "stream2";
+ private final static String OUTPUT = "output-";
+ private Properties streamsConfig;
+ private KafkaStreams streams;
+ private final static Properties CONSUMER_CONFIG = new Properties();
+ private final static Properties PRODUCER_CONFIG = new Properties();
+
+ @BeforeAll
+ public static void startCluster() throws Exception {
+ CLUSTER.start();
+ //Use multiple partitions to ensure distribution of keys.
+
+ CLUSTER.createTopic(STREAM_1, 4, 1);
+ CLUSTER.createTopic(STREAM_2, 4, 1);
+ CLUSTER.createTopic(OUTPUT, 1, 1);
Review Comment:
Should also make the output topic with 4 partitions.
--
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: jira-unsubscribe@kafka.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [kafka] mjsax commented on a diff in pull request #13592: KAFKA-14862: Outer stream-stream join does not output all results with multiple input partitions
Posted by "mjsax (via GitHub)" <gi...@apache.org>.
mjsax commented on code in PR #13592:
URL: https://github.com/apache/kafka/pull/13592#discussion_r1169379949
##########
streams/src/test/java/org/apache/kafka/streams/integration/KStreamKStreamIntegrationTest.java:
##########
@@ -0,0 +1,186 @@
+/*
+ * 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 kafka.utils.MockTime;
+import org.apache.kafka.clients.consumer.ConsumerConfig;
+import org.apache.kafka.clients.producer.ProducerConfig;
+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.JoinWindows;
+import org.apache.kafka.streams.kstream.KStream;
+import org.apache.kafka.streams.kstream.ValueJoiner;
+import org.apache.kafka.test.TestUtils;
+import org.junit.jupiter.api.AfterAll;
+import org.junit.jupiter.api.AfterEach;
+import org.junit.jupiter.api.BeforeAll;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Tag;
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.api.TestInfo;
+import org.junit.jupiter.api.Timeout;
+
+import java.io.IOException;
+import java.time.Duration;
+import java.util.Collections;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Properties;
+import java.util.Set;
+
+import static java.time.Duration.ofSeconds;
+import static java.util.Arrays.asList;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.safeUniqueTestName;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.startApplicationAndWaitUntilRunning;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.waitUntilMinKeyValueRecordsReceived;
+import static org.hamcrest.MatcherAssert.assertThat;
+import static org.hamcrest.core.IsEqual.equalTo;
+
+@Timeout(600)
+@Tag("integration")
+public class KStreamKStreamIntegrationTest {
+ private final static int NUM_BROKERS = 1;
+
+ public final static EmbeddedKafkaCluster CLUSTER = new EmbeddedKafkaCluster(NUM_BROKERS);
+ private final static MockTime MOCK_TIME = CLUSTER.time;
+ private final static String STREAM_1 = "stream1";
+ private final static String STREAM_2 = "stream2";
+ private final static String OUTPUT = "output-";
+ private Properties streamsConfig;
+ private KafkaStreams streams;
+ private final static Properties CONSUMER_CONFIG = new Properties();
+ private final static Properties PRODUCER_CONFIG = new Properties();
+
+ @BeforeAll
+ public static void startCluster() throws Exception {
+ CLUSTER.start();
+ //Use multiple partitions to ensure distribution of keys.
+
+ CLUSTER.createTopic(STREAM_1, 4, 1);
+ CLUSTER.createTopic(STREAM_2, 4, 1);
+ CLUSTER.createTopic(OUTPUT, 1, 1);
+
+ CONSUMER_CONFIG.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
+ CONSUMER_CONFIG.put(ConsumerConfig.GROUP_ID_CONFIG, "result-consumer");
+ CONSUMER_CONFIG.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
+ CONSUMER_CONFIG.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
+ }
+
+ @AfterAll
+ public static void closeCluster() {
+ CLUSTER.stop();
+ }
+
+ @BeforeEach
+ public void before(final TestInfo testInfo) throws IOException {
+ final String stateDirBasePath = TestUtils.tempDirectory().getPath();
+ final String safeTestName = safeUniqueTestName(getClass(), testInfo);
+ streamsConfig = getStreamsConfig(safeTestName);
+ streamsConfig.put(StreamsConfig.STATE_DIR_CONFIG, stateDirBasePath);
+ }
+
+ @AfterEach
+ public void after() throws IOException {
+ if (streams != null) {
+ streams.close();
+ streams = null;
+ }
+ IntegrationTestUtils.purgeLocalStreamsState(streamsConfig);
+ }
+
+ @Test
+ public void shouldOuterJoin() throws Exception {
+ final Set<KeyValue<String, String>> expectedOne = new HashSet<>();
+ expectedOne.add(new KeyValue<>("Key-1", "value1=left-1,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-2", "value1=left-2,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-3", "value1=left-3,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-4", "value1=left-4,value2=null"));
+
+ verifyKStreamKStreamOuterJoin(expectedOne);
+ }
+
+ private void verifyKStreamKStreamOuterJoin(final Set<KeyValue<String, String>> expectedResult) throws Exception {
+ streams = prepareTopology(streamsConfig);
+
+ startApplicationAndWaitUntilRunning(Collections.singletonList(streams), ofSeconds(120));
+
+ PRODUCER_CONFIG.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
+ PRODUCER_CONFIG.put(ProducerConfig.ACKS_CONFIG, "all");
+ PRODUCER_CONFIG.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
+ PRODUCER_CONFIG.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
+
+ final List<KeyValue<String, String>> stream1 = asList(
+ new KeyValue<>("Key-1", "left-1"),
+ new KeyValue<>("Key-2", "left-2"),
+ new KeyValue<>("Key-3", "left-3"),
+ new KeyValue<>("Key-4", "left-4")
+ );
+
+ final List<KeyValue<String, String>> stream2 = asList(
+ new KeyValue<>("Key-1", "right-1"),
+ new KeyValue<>("Key-2", "right-2"),
+ new KeyValue<>("Key-3", "right-3"),
+ new KeyValue<>("Key-4", "right-4")
+ );
+
+ IntegrationTestUtils.produceKeyValuesSynchronously(STREAM_1, stream1, PRODUCER_CONFIG, MOCK_TIME);
+ MOCK_TIME.sleep(11000);
+ Thread.sleep(11000);
+ IntegrationTestUtils.produceKeyValuesSynchronously(STREAM_1, stream2, PRODUCER_CONFIG, MOCK_TIME);
+
+ final Set<KeyValue<String, String>> result = new HashSet<>(waitUntilMinKeyValueRecordsReceived(
Review Comment:
> Looks like the test produces 8 records, but only waits for 4 result records and only validates those first 4?
Yes, we only get 4 result for the first "batch / window" -- all 4 are outer-join result. The remaining 4 records won't get emitted, because they are "stuck": without new input record, stream-time does not advance, and the join window does not close. -- The goal of the second batch it really just to ensure to flush out the first 4 records.
--
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: jira-unsubscribe@kafka.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [kafka] mjsax merged pull request #13592: KAFKA-14862: Outer stream-stream join does not output all results with multiple input partitions
Posted by "mjsax (via GitHub)" <gi...@apache.org>.
mjsax merged PR #13592:
URL: https://github.com/apache/kafka/pull/13592
--
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: jira-unsubscribe@kafka.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [kafka] mjsax commented on a diff in pull request #13592: KAFKA-14862: Outer stream-stream join does not output all results with multiple input partitions
Posted by "mjsax (via GitHub)" <gi...@apache.org>.
mjsax commented on code in PR #13592:
URL: https://github.com/apache/kafka/pull/13592#discussion_r1169376737
##########
streams/src/test/java/org/apache/kafka/streams/integration/KStreamKStreamIntegrationTest.java:
##########
@@ -0,0 +1,186 @@
+/*
+ * 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 kafka.utils.MockTime;
+import org.apache.kafka.clients.consumer.ConsumerConfig;
+import org.apache.kafka.clients.producer.ProducerConfig;
+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.JoinWindows;
+import org.apache.kafka.streams.kstream.KStream;
+import org.apache.kafka.streams.kstream.ValueJoiner;
+import org.apache.kafka.test.TestUtils;
+import org.junit.jupiter.api.AfterAll;
+import org.junit.jupiter.api.AfterEach;
+import org.junit.jupiter.api.BeforeAll;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Tag;
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.api.TestInfo;
+import org.junit.jupiter.api.Timeout;
+
+import java.io.IOException;
+import java.time.Duration;
+import java.util.Collections;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Properties;
+import java.util.Set;
+
+import static java.time.Duration.ofSeconds;
+import static java.util.Arrays.asList;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.safeUniqueTestName;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.startApplicationAndWaitUntilRunning;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.waitUntilMinKeyValueRecordsReceived;
+import static org.hamcrest.MatcherAssert.assertThat;
+import static org.hamcrest.core.IsEqual.equalTo;
+
+@Timeout(600)
+@Tag("integration")
+public class KStreamKStreamIntegrationTest {
Review Comment:
Yes, that's the reason -- I did follow the existing naming pattern (which is very subtle though)
- StreamStreamJoinIntegration, StreamTableJoinIntegration etc (without K using TTD)
- KStreamKStreamJoin
- Integration, KStreamKTableJoinIntegeration (with K, using EmbeddedKafka)
I am happy to rename, but maybe we should do it across the board and not as side thing in this PR?
--
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: jira-unsubscribe@kafka.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [kafka] mjsax commented on a diff in pull request #13592: KAFKA-14862: Outer stream-stream join does not output all results with multiple input partitions
Posted by "mjsax (via GitHub)" <gi...@apache.org>.
mjsax commented on code in PR #13592:
URL: https://github.com/apache/kafka/pull/13592#discussion_r1169380378
##########
streams/src/test/java/org/apache/kafka/streams/integration/KStreamKStreamIntegrationTest.java:
##########
@@ -0,0 +1,186 @@
+/*
+ * 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 kafka.utils.MockTime;
+import org.apache.kafka.clients.consumer.ConsumerConfig;
+import org.apache.kafka.clients.producer.ProducerConfig;
+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.JoinWindows;
+import org.apache.kafka.streams.kstream.KStream;
+import org.apache.kafka.streams.kstream.ValueJoiner;
+import org.apache.kafka.test.TestUtils;
+import org.junit.jupiter.api.AfterAll;
+import org.junit.jupiter.api.AfterEach;
+import org.junit.jupiter.api.BeforeAll;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Tag;
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.api.TestInfo;
+import org.junit.jupiter.api.Timeout;
+
+import java.io.IOException;
+import java.time.Duration;
+import java.util.Collections;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Properties;
+import java.util.Set;
+
+import static java.time.Duration.ofSeconds;
+import static java.util.Arrays.asList;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.safeUniqueTestName;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.startApplicationAndWaitUntilRunning;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.waitUntilMinKeyValueRecordsReceived;
+import static org.hamcrest.MatcherAssert.assertThat;
+import static org.hamcrest.core.IsEqual.equalTo;
+
+@Timeout(600)
+@Tag("integration")
+public class KStreamKStreamIntegrationTest {
+ private final static int NUM_BROKERS = 1;
+
+ public final static EmbeddedKafkaCluster CLUSTER = new EmbeddedKafkaCluster(NUM_BROKERS);
+ private final static MockTime MOCK_TIME = CLUSTER.time;
+ private final static String STREAM_1 = "stream1";
+ private final static String STREAM_2 = "stream2";
+ private final static String OUTPUT = "output-";
+ private Properties streamsConfig;
+ private KafkaStreams streams;
+ private final static Properties CONSUMER_CONFIG = new Properties();
+ private final static Properties PRODUCER_CONFIG = new Properties();
+
+ @BeforeAll
+ public static void startCluster() throws Exception {
+ CLUSTER.start();
+ //Use multiple partitions to ensure distribution of keys.
+
+ CLUSTER.createTopic(STREAM_1, 4, 1);
+ CLUSTER.createTopic(STREAM_2, 4, 1);
+ CLUSTER.createTopic(OUTPUT, 1, 1);
+
+ CONSUMER_CONFIG.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
+ CONSUMER_CONFIG.put(ConsumerConfig.GROUP_ID_CONFIG, "result-consumer");
+ CONSUMER_CONFIG.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
+ CONSUMER_CONFIG.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
+ }
+
+ @AfterAll
+ public static void closeCluster() {
+ CLUSTER.stop();
+ }
+
+ @BeforeEach
+ public void before(final TestInfo testInfo) throws IOException {
+ final String stateDirBasePath = TestUtils.tempDirectory().getPath();
+ final String safeTestName = safeUniqueTestName(getClass(), testInfo);
+ streamsConfig = getStreamsConfig(safeTestName);
+ streamsConfig.put(StreamsConfig.STATE_DIR_CONFIG, stateDirBasePath);
+ }
+
+ @AfterEach
+ public void after() throws IOException {
+ if (streams != null) {
+ streams.close();
+ streams = null;
+ }
+ IntegrationTestUtils.purgeLocalStreamsState(streamsConfig);
+ }
+
+ @Test
+ public void shouldOuterJoin() throws Exception {
+ final Set<KeyValue<String, String>> expectedOne = new HashSet<>();
+ expectedOne.add(new KeyValue<>("Key-1", "value1=left-1,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-2", "value1=left-2,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-3", "value1=left-3,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-4", "value1=left-4,value2=null"));
+
+ verifyKStreamKStreamOuterJoin(expectedOne);
+ }
+
+ private void verifyKStreamKStreamOuterJoin(final Set<KeyValue<String, String>> expectedResult) throws Exception {
+ streams = prepareTopology(streamsConfig);
+
+ startApplicationAndWaitUntilRunning(Collections.singletonList(streams), ofSeconds(120));
+
+ PRODUCER_CONFIG.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
+ PRODUCER_CONFIG.put(ProducerConfig.ACKS_CONFIG, "all");
+ PRODUCER_CONFIG.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
+ PRODUCER_CONFIG.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
+
+ final List<KeyValue<String, String>> stream1 = asList(
+ new KeyValue<>("Key-1", "left-1"),
+ new KeyValue<>("Key-2", "left-2"),
+ new KeyValue<>("Key-3", "left-3"),
+ new KeyValue<>("Key-4", "left-4")
+ );
+
+ final List<KeyValue<String, String>> stream2 = asList(
+ new KeyValue<>("Key-1", "right-1"),
+ new KeyValue<>("Key-2", "right-2"),
+ new KeyValue<>("Key-3", "right-3"),
+ new KeyValue<>("Key-4", "right-4")
+ );
+
+ IntegrationTestUtils.produceKeyValuesSynchronously(STREAM_1, stream1, PRODUCER_CONFIG, MOCK_TIME);
+ MOCK_TIME.sleep(11000);
+ Thread.sleep(11000);
+ IntegrationTestUtils.produceKeyValuesSynchronously(STREAM_1, stream2, PRODUCER_CONFIG, MOCK_TIME);
+
+ final Set<KeyValue<String, String>> result = new HashSet<>(waitUntilMinKeyValueRecordsReceived(
Review Comment:
> Also, how does this test guarantee the order in which the input records are processed, given that there are multiple input partitions? I think I'm missing something :)
We cannot. That is why a `Set` is used to compare expected to retrieved results.
--
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: jira-unsubscribe@kafka.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [kafka] mjsax commented on a diff in pull request #13592: KAFKA-14862: Outer stream-stream join does not output all results with multiple input partitions
Posted by "mjsax (via GitHub)" <gi...@apache.org>.
mjsax commented on code in PR #13592:
URL: https://github.com/apache/kafka/pull/13592#discussion_r1169376737
##########
streams/src/test/java/org/apache/kafka/streams/integration/KStreamKStreamIntegrationTest.java:
##########
@@ -0,0 +1,186 @@
+/*
+ * 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 kafka.utils.MockTime;
+import org.apache.kafka.clients.consumer.ConsumerConfig;
+import org.apache.kafka.clients.producer.ProducerConfig;
+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.JoinWindows;
+import org.apache.kafka.streams.kstream.KStream;
+import org.apache.kafka.streams.kstream.ValueJoiner;
+import org.apache.kafka.test.TestUtils;
+import org.junit.jupiter.api.AfterAll;
+import org.junit.jupiter.api.AfterEach;
+import org.junit.jupiter.api.BeforeAll;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Tag;
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.api.TestInfo;
+import org.junit.jupiter.api.Timeout;
+
+import java.io.IOException;
+import java.time.Duration;
+import java.util.Collections;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Properties;
+import java.util.Set;
+
+import static java.time.Duration.ofSeconds;
+import static java.util.Arrays.asList;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.safeUniqueTestName;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.startApplicationAndWaitUntilRunning;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.waitUntilMinKeyValueRecordsReceived;
+import static org.hamcrest.MatcherAssert.assertThat;
+import static org.hamcrest.core.IsEqual.equalTo;
+
+@Timeout(600)
+@Tag("integration")
+public class KStreamKStreamIntegrationTest {
Review Comment:
Yes, that's the reason -- I did follow the existing naming pattern (which is very subtle though)
- StreamStreamsIntegration, StreamTableIntegration etc (without K using TTD)
- KStreamKStreamIntegration, KStreamKTableIntegeration (with K, using EmbeddedKafka)
I am happy to rename, but maybe we should do it across the board and not as side thing in this PR?
--
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: jira-unsubscribe@kafka.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [kafka] vcrfxia commented on a diff in pull request #13592: KAFKA-14862: Outer stream-stream join does not output all results with multiple input partitions
Posted by "vcrfxia (via GitHub)" <gi...@apache.org>.
vcrfxia commented on code in PR #13592:
URL: https://github.com/apache/kafka/pull/13592#discussion_r1169351304
##########
streams/src/test/java/org/apache/kafka/streams/integration/KStreamKStreamIntegrationTest.java:
##########
@@ -0,0 +1,186 @@
+/*
+ * 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 kafka.utils.MockTime;
+import org.apache.kafka.clients.consumer.ConsumerConfig;
+import org.apache.kafka.clients.producer.ProducerConfig;
+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.JoinWindows;
+import org.apache.kafka.streams.kstream.KStream;
+import org.apache.kafka.streams.kstream.ValueJoiner;
+import org.apache.kafka.test.TestUtils;
+import org.junit.jupiter.api.AfterAll;
+import org.junit.jupiter.api.AfterEach;
+import org.junit.jupiter.api.BeforeAll;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Tag;
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.api.TestInfo;
+import org.junit.jupiter.api.Timeout;
+
+import java.io.IOException;
+import java.time.Duration;
+import java.util.Collections;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Properties;
+import java.util.Set;
+
+import static java.time.Duration.ofSeconds;
+import static java.util.Arrays.asList;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.safeUniqueTestName;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.startApplicationAndWaitUntilRunning;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.waitUntilMinKeyValueRecordsReceived;
+import static org.hamcrest.MatcherAssert.assertThat;
+import static org.hamcrest.core.IsEqual.equalTo;
+
+@Timeout(600)
+@Tag("integration")
+public class KStreamKStreamIntegrationTest {
Review Comment:
I'm guessing the reason this is added as a new test file rather than being added into the existing StreamStreamJoinIntegrationTest.java is because the existing test uses the TopologyTestDriver, which doesn't support testing with multiple partitions -- is that true?
If that's the case, should we name the new file `KStreamKStreamMultiPartitionIntegrationTest` or similar, in order to better distinguish the two?
##########
streams/src/test/java/org/apache/kafka/streams/integration/KStreamKStreamIntegrationTest.java:
##########
@@ -0,0 +1,186 @@
+/*
+ * 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 kafka.utils.MockTime;
+import org.apache.kafka.clients.consumer.ConsumerConfig;
+import org.apache.kafka.clients.producer.ProducerConfig;
+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.JoinWindows;
+import org.apache.kafka.streams.kstream.KStream;
+import org.apache.kafka.streams.kstream.ValueJoiner;
+import org.apache.kafka.test.TestUtils;
+import org.junit.jupiter.api.AfterAll;
+import org.junit.jupiter.api.AfterEach;
+import org.junit.jupiter.api.BeforeAll;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Tag;
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.api.TestInfo;
+import org.junit.jupiter.api.Timeout;
+
+import java.io.IOException;
+import java.time.Duration;
+import java.util.Collections;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Properties;
+import java.util.Set;
+
+import static java.time.Duration.ofSeconds;
+import static java.util.Arrays.asList;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.safeUniqueTestName;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.startApplicationAndWaitUntilRunning;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.waitUntilMinKeyValueRecordsReceived;
+import static org.hamcrest.MatcherAssert.assertThat;
+import static org.hamcrest.core.IsEqual.equalTo;
+
+@Timeout(600)
+@Tag("integration")
+public class KStreamKStreamIntegrationTest {
+ private final static int NUM_BROKERS = 1;
+
+ public final static EmbeddedKafkaCluster CLUSTER = new EmbeddedKafkaCluster(NUM_BROKERS);
+ private final static MockTime MOCK_TIME = CLUSTER.time;
+ private final static String STREAM_1 = "stream1";
+ private final static String STREAM_2 = "stream2";
+ private final static String OUTPUT = "output-";
+ private Properties streamsConfig;
+ private KafkaStreams streams;
+ private final static Properties CONSUMER_CONFIG = new Properties();
+ private final static Properties PRODUCER_CONFIG = new Properties();
+
+ @BeforeAll
+ public static void startCluster() throws Exception {
+ CLUSTER.start();
+ //Use multiple partitions to ensure distribution of keys.
+
+ CLUSTER.createTopic(STREAM_1, 4, 1);
+ CLUSTER.createTopic(STREAM_2, 4, 1);
+ CLUSTER.createTopic(OUTPUT, 1, 1);
+
+ CONSUMER_CONFIG.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
+ CONSUMER_CONFIG.put(ConsumerConfig.GROUP_ID_CONFIG, "result-consumer");
+ CONSUMER_CONFIG.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
+ CONSUMER_CONFIG.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
+ }
+
+ @AfterAll
+ public static void closeCluster() {
+ CLUSTER.stop();
+ }
+
+ @BeforeEach
+ public void before(final TestInfo testInfo) throws IOException {
+ final String stateDirBasePath = TestUtils.tempDirectory().getPath();
+ final String safeTestName = safeUniqueTestName(getClass(), testInfo);
+ streamsConfig = getStreamsConfig(safeTestName);
+ streamsConfig.put(StreamsConfig.STATE_DIR_CONFIG, stateDirBasePath);
+ }
+
+ @AfterEach
+ public void after() throws IOException {
+ if (streams != null) {
+ streams.close();
+ streams = null;
+ }
+ IntegrationTestUtils.purgeLocalStreamsState(streamsConfig);
+ }
+
+ @Test
+ public void shouldOuterJoin() throws Exception {
+ final Set<KeyValue<String, String>> expectedOne = new HashSet<>();
+ expectedOne.add(new KeyValue<>("Key-1", "value1=left-1,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-2", "value1=left-2,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-3", "value1=left-3,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-4", "value1=left-4,value2=null"));
+
+ verifyKStreamKStreamOuterJoin(expectedOne);
+ }
+
+ private void verifyKStreamKStreamOuterJoin(final Set<KeyValue<String, String>> expectedResult) throws Exception {
+ streams = prepareTopology(streamsConfig);
+
+ startApplicationAndWaitUntilRunning(Collections.singletonList(streams), ofSeconds(120));
+
+ PRODUCER_CONFIG.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
+ PRODUCER_CONFIG.put(ProducerConfig.ACKS_CONFIG, "all");
+ PRODUCER_CONFIG.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
+ PRODUCER_CONFIG.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
+
+ final List<KeyValue<String, String>> stream1 = asList(
+ new KeyValue<>("Key-1", "left-1"),
+ new KeyValue<>("Key-2", "left-2"),
+ new KeyValue<>("Key-3", "left-3"),
+ new KeyValue<>("Key-4", "left-4")
+ );
+
+ final List<KeyValue<String, String>> stream2 = asList(
+ new KeyValue<>("Key-1", "right-1"),
+ new KeyValue<>("Key-2", "right-2"),
+ new KeyValue<>("Key-3", "right-3"),
+ new KeyValue<>("Key-4", "right-4")
+ );
+
+ IntegrationTestUtils.produceKeyValuesSynchronously(STREAM_1, stream1, PRODUCER_CONFIG, MOCK_TIME);
+ MOCK_TIME.sleep(11000);
+ Thread.sleep(11000);
+ IntegrationTestUtils.produceKeyValuesSynchronously(STREAM_1, stream2, PRODUCER_CONFIG, MOCK_TIME);
+
+ final Set<KeyValue<String, String>> result = new HashSet<>(waitUntilMinKeyValueRecordsReceived(
Review Comment:
Looks like the test produces 8 records, but only waits for 4 result records and only validates those first 4?
Also, how does this test guarantee the order in which the input records are processed, given that there are multiple input partitions? I think I'm missing something :)
##########
streams/src/test/java/org/apache/kafka/streams/integration/KStreamKStreamIntegrationTest.java:
##########
@@ -0,0 +1,186 @@
+/*
+ * 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 kafka.utils.MockTime;
+import org.apache.kafka.clients.consumer.ConsumerConfig;
+import org.apache.kafka.clients.producer.ProducerConfig;
+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.JoinWindows;
+import org.apache.kafka.streams.kstream.KStream;
+import org.apache.kafka.streams.kstream.ValueJoiner;
+import org.apache.kafka.test.TestUtils;
+import org.junit.jupiter.api.AfterAll;
+import org.junit.jupiter.api.AfterEach;
+import org.junit.jupiter.api.BeforeAll;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Tag;
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.api.TestInfo;
+import org.junit.jupiter.api.Timeout;
+
+import java.io.IOException;
+import java.time.Duration;
+import java.util.Collections;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Properties;
+import java.util.Set;
+
+import static java.time.Duration.ofSeconds;
+import static java.util.Arrays.asList;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.safeUniqueTestName;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.startApplicationAndWaitUntilRunning;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.waitUntilMinKeyValueRecordsReceived;
+import static org.hamcrest.MatcherAssert.assertThat;
+import static org.hamcrest.core.IsEqual.equalTo;
+
+@Timeout(600)
+@Tag("integration")
+public class KStreamKStreamIntegrationTest {
+ private final static int NUM_BROKERS = 1;
+
+ public final static EmbeddedKafkaCluster CLUSTER = new EmbeddedKafkaCluster(NUM_BROKERS);
+ private final static MockTime MOCK_TIME = CLUSTER.time;
+ private final static String STREAM_1 = "stream1";
+ private final static String STREAM_2 = "stream2";
+ private final static String OUTPUT = "output-";
+ private Properties streamsConfig;
+ private KafkaStreams streams;
+ private final static Properties CONSUMER_CONFIG = new Properties();
+ private final static Properties PRODUCER_CONFIG = new Properties();
+
+ @BeforeAll
+ public static void startCluster() throws Exception {
+ CLUSTER.start();
+ //Use multiple partitions to ensure distribution of keys.
+
+ CLUSTER.createTopic(STREAM_1, 4, 1);
+ CLUSTER.createTopic(STREAM_2, 4, 1);
+ CLUSTER.createTopic(OUTPUT, 1, 1);
+
+ CONSUMER_CONFIG.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
+ CONSUMER_CONFIG.put(ConsumerConfig.GROUP_ID_CONFIG, "result-consumer");
+ CONSUMER_CONFIG.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
+ CONSUMER_CONFIG.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
+ }
+
+ @AfterAll
+ public static void closeCluster() {
+ CLUSTER.stop();
+ }
+
+ @BeforeEach
+ public void before(final TestInfo testInfo) throws IOException {
+ final String stateDirBasePath = TestUtils.tempDirectory().getPath();
+ final String safeTestName = safeUniqueTestName(getClass(), testInfo);
+ streamsConfig = getStreamsConfig(safeTestName);
+ streamsConfig.put(StreamsConfig.STATE_DIR_CONFIG, stateDirBasePath);
+ }
+
+ @AfterEach
+ public void after() throws IOException {
+ if (streams != null) {
+ streams.close();
+ streams = null;
+ }
+ IntegrationTestUtils.purgeLocalStreamsState(streamsConfig);
+ }
+
+ @Test
+ public void shouldOuterJoin() throws Exception {
+ final Set<KeyValue<String, String>> expectedOne = new HashSet<>();
Review Comment:
nit: should this be `expectedResult` or just `expected`, instead of `expectedOne`?
##########
streams/src/test/java/org/apache/kafka/streams/integration/KStreamKStreamIntegrationTest.java:
##########
@@ -0,0 +1,186 @@
+/*
+ * 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 kafka.utils.MockTime;
+import org.apache.kafka.clients.consumer.ConsumerConfig;
+import org.apache.kafka.clients.producer.ProducerConfig;
+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.JoinWindows;
+import org.apache.kafka.streams.kstream.KStream;
+import org.apache.kafka.streams.kstream.ValueJoiner;
+import org.apache.kafka.test.TestUtils;
+import org.junit.jupiter.api.AfterAll;
+import org.junit.jupiter.api.AfterEach;
+import org.junit.jupiter.api.BeforeAll;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Tag;
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.api.TestInfo;
+import org.junit.jupiter.api.Timeout;
+
+import java.io.IOException;
+import java.time.Duration;
+import java.util.Collections;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Properties;
+import java.util.Set;
+
+import static java.time.Duration.ofSeconds;
+import static java.util.Arrays.asList;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.safeUniqueTestName;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.startApplicationAndWaitUntilRunning;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.waitUntilMinKeyValueRecordsReceived;
+import static org.hamcrest.MatcherAssert.assertThat;
+import static org.hamcrest.core.IsEqual.equalTo;
+
+@Timeout(600)
+@Tag("integration")
+public class KStreamKStreamIntegrationTest {
+ private final static int NUM_BROKERS = 1;
+
+ public final static EmbeddedKafkaCluster CLUSTER = new EmbeddedKafkaCluster(NUM_BROKERS);
+ private final static MockTime MOCK_TIME = CLUSTER.time;
+ private final static String STREAM_1 = "stream1";
+ private final static String STREAM_2 = "stream2";
+ private final static String OUTPUT = "output-";
+ private Properties streamsConfig;
+ private KafkaStreams streams;
+ private final static Properties CONSUMER_CONFIG = new Properties();
+ private final static Properties PRODUCER_CONFIG = new Properties();
+
+ @BeforeAll
+ public static void startCluster() throws Exception {
+ CLUSTER.start();
+ //Use multiple partitions to ensure distribution of keys.
+
+ CLUSTER.createTopic(STREAM_1, 4, 1);
+ CLUSTER.createTopic(STREAM_2, 4, 1);
+ CLUSTER.createTopic(OUTPUT, 1, 1);
+
+ CONSUMER_CONFIG.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
+ CONSUMER_CONFIG.put(ConsumerConfig.GROUP_ID_CONFIG, "result-consumer");
+ CONSUMER_CONFIG.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
+ CONSUMER_CONFIG.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
+ }
+
+ @AfterAll
+ public static void closeCluster() {
+ CLUSTER.stop();
+ }
+
+ @BeforeEach
+ public void before(final TestInfo testInfo) throws IOException {
+ final String stateDirBasePath = TestUtils.tempDirectory().getPath();
+ final String safeTestName = safeUniqueTestName(getClass(), testInfo);
+ streamsConfig = getStreamsConfig(safeTestName);
+ streamsConfig.put(StreamsConfig.STATE_DIR_CONFIG, stateDirBasePath);
+ }
+
+ @AfterEach
+ public void after() throws IOException {
+ if (streams != null) {
+ streams.close();
+ streams = null;
+ }
+ IntegrationTestUtils.purgeLocalStreamsState(streamsConfig);
+ }
+
+ @Test
+ public void shouldOuterJoin() throws Exception {
+ final Set<KeyValue<String, String>> expectedOne = new HashSet<>();
+ expectedOne.add(new KeyValue<>("Key-1", "value1=left-1,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-2", "value1=left-2,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-3", "value1=left-3,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-4", "value1=left-4,value2=null"));
+
+ verifyKStreamKStreamOuterJoin(expectedOne);
+ }
+
+ private void verifyKStreamKStreamOuterJoin(final Set<KeyValue<String, String>> expectedResult) throws Exception {
+ streams = prepareTopology(streamsConfig);
+
+ startApplicationAndWaitUntilRunning(Collections.singletonList(streams), ofSeconds(120));
+
+ PRODUCER_CONFIG.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
+ PRODUCER_CONFIG.put(ProducerConfig.ACKS_CONFIG, "all");
+ PRODUCER_CONFIG.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
+ PRODUCER_CONFIG.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
+
+ final List<KeyValue<String, String>> stream1 = asList(
+ new KeyValue<>("Key-1", "left-1"),
+ new KeyValue<>("Key-2", "left-2"),
+ new KeyValue<>("Key-3", "left-3"),
+ new KeyValue<>("Key-4", "left-4")
+ );
+
+ final List<KeyValue<String, String>> stream2 = asList(
+ new KeyValue<>("Key-1", "right-1"),
+ new KeyValue<>("Key-2", "right-2"),
+ new KeyValue<>("Key-3", "right-3"),
+ new KeyValue<>("Key-4", "right-4")
+ );
+
+ IntegrationTestUtils.produceKeyValuesSynchronously(STREAM_1, stream1, PRODUCER_CONFIG, MOCK_TIME);
+ MOCK_TIME.sleep(11000);
+ Thread.sleep(11000);
+ IntegrationTestUtils.produceKeyValuesSynchronously(STREAM_1, stream2, PRODUCER_CONFIG, MOCK_TIME);
Review Comment:
Is this supposed to be `STREAM_2` instead of `STREAM_1`?
--
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: jira-unsubscribe@kafka.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [kafka] cadonna commented on a diff in pull request #13592: KAFKA-14862: Outer stream-stream join does not output all results with multiple input partitions
Posted by "cadonna (via GitHub)" <gi...@apache.org>.
cadonna commented on code in PR #13592:
URL: https://github.com/apache/kafka/pull/13592#discussion_r1169637261
##########
streams/src/test/java/org/apache/kafka/streams/integration/KStreamKStreamIntegrationTest.java:
##########
@@ -0,0 +1,186 @@
+/*
+ * 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 kafka.utils.MockTime;
+import org.apache.kafka.clients.consumer.ConsumerConfig;
+import org.apache.kafka.clients.producer.ProducerConfig;
+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.JoinWindows;
+import org.apache.kafka.streams.kstream.KStream;
+import org.apache.kafka.streams.kstream.ValueJoiner;
+import org.apache.kafka.test.TestUtils;
+import org.junit.jupiter.api.AfterAll;
+import org.junit.jupiter.api.AfterEach;
+import org.junit.jupiter.api.BeforeAll;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Tag;
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.api.TestInfo;
+import org.junit.jupiter.api.Timeout;
+
+import java.io.IOException;
+import java.time.Duration;
+import java.util.Collections;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Properties;
+import java.util.Set;
+
+import static java.time.Duration.ofSeconds;
+import static java.util.Arrays.asList;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.safeUniqueTestName;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.startApplicationAndWaitUntilRunning;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.waitUntilMinKeyValueRecordsReceived;
+import static org.hamcrest.MatcherAssert.assertThat;
+import static org.hamcrest.core.IsEqual.equalTo;
+
+@Timeout(600)
+@Tag("integration")
+public class KStreamKStreamIntegrationTest {
Review Comment:
+1 to what @vcrfxia said. I was not aware of that naming pattern.
--
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: jira-unsubscribe@kafka.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [kafka] mjsax commented on a diff in pull request #13592: KAFKA-14862: Outer stream-stream join does not output all results with multiple input partitions
Posted by "mjsax (via GitHub)" <gi...@apache.org>.
mjsax commented on code in PR #13592:
URL: https://github.com/apache/kafka/pull/13592#discussion_r1169378795
##########
streams/src/test/java/org/apache/kafka/streams/integration/KStreamKStreamIntegrationTest.java:
##########
@@ -0,0 +1,186 @@
+/*
+ * 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 kafka.utils.MockTime;
+import org.apache.kafka.clients.consumer.ConsumerConfig;
+import org.apache.kafka.clients.producer.ProducerConfig;
+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.JoinWindows;
+import org.apache.kafka.streams.kstream.KStream;
+import org.apache.kafka.streams.kstream.ValueJoiner;
+import org.apache.kafka.test.TestUtils;
+import org.junit.jupiter.api.AfterAll;
+import org.junit.jupiter.api.AfterEach;
+import org.junit.jupiter.api.BeforeAll;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Tag;
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.api.TestInfo;
+import org.junit.jupiter.api.Timeout;
+
+import java.io.IOException;
+import java.time.Duration;
+import java.util.Collections;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Properties;
+import java.util.Set;
+
+import static java.time.Duration.ofSeconds;
+import static java.util.Arrays.asList;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.safeUniqueTestName;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.startApplicationAndWaitUntilRunning;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.waitUntilMinKeyValueRecordsReceived;
+import static org.hamcrest.MatcherAssert.assertThat;
+import static org.hamcrest.core.IsEqual.equalTo;
+
+@Timeout(600)
+@Tag("integration")
+public class KStreamKStreamIntegrationTest {
+ private final static int NUM_BROKERS = 1;
+
+ public final static EmbeddedKafkaCluster CLUSTER = new EmbeddedKafkaCluster(NUM_BROKERS);
+ private final static MockTime MOCK_TIME = CLUSTER.time;
+ private final static String STREAM_1 = "stream1";
+ private final static String STREAM_2 = "stream2";
+ private final static String OUTPUT = "output-";
+ private Properties streamsConfig;
+ private KafkaStreams streams;
+ private final static Properties CONSUMER_CONFIG = new Properties();
+ private final static Properties PRODUCER_CONFIG = new Properties();
+
+ @BeforeAll
+ public static void startCluster() throws Exception {
+ CLUSTER.start();
+ //Use multiple partitions to ensure distribution of keys.
+
+ CLUSTER.createTopic(STREAM_1, 4, 1);
+ CLUSTER.createTopic(STREAM_2, 4, 1);
+ CLUSTER.createTopic(OUTPUT, 1, 1);
+
+ CONSUMER_CONFIG.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
+ CONSUMER_CONFIG.put(ConsumerConfig.GROUP_ID_CONFIG, "result-consumer");
+ CONSUMER_CONFIG.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
+ CONSUMER_CONFIG.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
+ }
+
+ @AfterAll
+ public static void closeCluster() {
+ CLUSTER.stop();
+ }
+
+ @BeforeEach
+ public void before(final TestInfo testInfo) throws IOException {
+ final String stateDirBasePath = TestUtils.tempDirectory().getPath();
+ final String safeTestName = safeUniqueTestName(getClass(), testInfo);
+ streamsConfig = getStreamsConfig(safeTestName);
+ streamsConfig.put(StreamsConfig.STATE_DIR_CONFIG, stateDirBasePath);
+ }
+
+ @AfterEach
+ public void after() throws IOException {
+ if (streams != null) {
+ streams.close();
+ streams = null;
+ }
+ IntegrationTestUtils.purgeLocalStreamsState(streamsConfig);
+ }
+
+ @Test
+ public void shouldOuterJoin() throws Exception {
+ final Set<KeyValue<String, String>> expectedOne = new HashSet<>();
+ expectedOne.add(new KeyValue<>("Key-1", "value1=left-1,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-2", "value1=left-2,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-3", "value1=left-3,value2=null"));
+ expectedOne.add(new KeyValue<>("Key-4", "value1=left-4,value2=null"));
+
+ verifyKStreamKStreamOuterJoin(expectedOne);
+ }
+
+ private void verifyKStreamKStreamOuterJoin(final Set<KeyValue<String, String>> expectedResult) throws Exception {
+ streams = prepareTopology(streamsConfig);
+
+ startApplicationAndWaitUntilRunning(Collections.singletonList(streams), ofSeconds(120));
+
+ PRODUCER_CONFIG.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
+ PRODUCER_CONFIG.put(ProducerConfig.ACKS_CONFIG, "all");
+ PRODUCER_CONFIG.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
+ PRODUCER_CONFIG.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
+
+ final List<KeyValue<String, String>> stream1 = asList(
+ new KeyValue<>("Key-1", "left-1"),
+ new KeyValue<>("Key-2", "left-2"),
+ new KeyValue<>("Key-3", "left-3"),
+ new KeyValue<>("Key-4", "left-4")
+ );
+
+ final List<KeyValue<String, String>> stream2 = asList(
+ new KeyValue<>("Key-1", "right-1"),
+ new KeyValue<>("Key-2", "right-2"),
+ new KeyValue<>("Key-3", "right-3"),
+ new KeyValue<>("Key-4", "right-4")
+ );
+
+ IntegrationTestUtils.produceKeyValuesSynchronously(STREAM_1, stream1, PRODUCER_CONFIG, MOCK_TIME);
+ MOCK_TIME.sleep(11000);
+ Thread.sleep(11000);
+ IntegrationTestUtils.produceKeyValuesSynchronously(STREAM_1, stream2, PRODUCER_CONFIG, MOCK_TIME);
Review Comment:
Actually no (cf the original description on the ticket). But I guess it does not matter to much anyway, and we could use both.
The point about using `STREAM_1` is, to make sure that the original keys are written twice into the same input topic partitions to advance time (given that for stream-stream join we have the "shared time tracker" it should not matter though.
--
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: jira-unsubscribe@kafka.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [kafka] cadonna commented on a diff in pull request #13592: KAFKA-14862: Outer stream-stream join does not output all results with multiple input partitions
Posted by "cadonna (via GitHub)" <gi...@apache.org>.
cadonna commented on code in PR #13592:
URL: https://github.com/apache/kafka/pull/13592#discussion_r1169669170
##########
streams/src/test/java/org/apache/kafka/streams/integration/KStreamKStreamIntegrationTest.java:
##########
@@ -0,0 +1,185 @@
+/*
+ * 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 kafka.utils.MockTime;
+import org.apache.kafka.clients.consumer.ConsumerConfig;
+import org.apache.kafka.clients.producer.ProducerConfig;
+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.JoinWindows;
+import org.apache.kafka.streams.kstream.KStream;
+import org.apache.kafka.streams.kstream.ValueJoiner;
+import org.apache.kafka.test.TestUtils;
+import org.junit.jupiter.api.AfterAll;
+import org.junit.jupiter.api.AfterEach;
+import org.junit.jupiter.api.BeforeAll;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Tag;
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.api.TestInfo;
+import org.junit.jupiter.api.Timeout;
+
+import java.io.IOException;
+import java.time.Duration;
+import java.util.Collections;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Properties;
+import java.util.Set;
+
+import static java.time.Duration.ofSeconds;
+import static java.util.Arrays.asList;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.safeUniqueTestName;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.startApplicationAndWaitUntilRunning;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.waitUntilMinKeyValueRecordsReceived;
+import static org.hamcrest.MatcherAssert.assertThat;
+import static org.hamcrest.core.IsEqual.equalTo;
+
+@Timeout(600)
+@Tag("integration")
+public class KStreamKStreamIntegrationTest {
+ private final static int NUM_BROKERS = 1;
+
+ public final static EmbeddedKafkaCluster CLUSTER = new EmbeddedKafkaCluster(NUM_BROKERS);
+ private final static MockTime MOCK_TIME = CLUSTER.time;
+ private final static String STREAM_1 = "stream1";
+ private final static String STREAM_2 = "stream2";
Review Comment:
nit:
```suggestion
private final static String LEFT_STREAM = "leftStream";
private final static String RIGHT_STREAM = "rightStream";
```
##########
streams/src/test/java/org/apache/kafka/streams/integration/KStreamKStreamIntegrationTest.java:
##########
@@ -0,0 +1,185 @@
+/*
+ * 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 kafka.utils.MockTime;
+import org.apache.kafka.clients.consumer.ConsumerConfig;
+import org.apache.kafka.clients.producer.ProducerConfig;
+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.JoinWindows;
+import org.apache.kafka.streams.kstream.KStream;
+import org.apache.kafka.streams.kstream.ValueJoiner;
+import org.apache.kafka.test.TestUtils;
+import org.junit.jupiter.api.AfterAll;
+import org.junit.jupiter.api.AfterEach;
+import org.junit.jupiter.api.BeforeAll;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Tag;
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.api.TestInfo;
+import org.junit.jupiter.api.Timeout;
+
+import java.io.IOException;
+import java.time.Duration;
+import java.util.Collections;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Properties;
+import java.util.Set;
+
+import static java.time.Duration.ofSeconds;
+import static java.util.Arrays.asList;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.safeUniqueTestName;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.startApplicationAndWaitUntilRunning;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.waitUntilMinKeyValueRecordsReceived;
+import static org.hamcrest.MatcherAssert.assertThat;
+import static org.hamcrest.core.IsEqual.equalTo;
+
+@Timeout(600)
+@Tag("integration")
+public class KStreamKStreamIntegrationTest {
+ private final static int NUM_BROKERS = 1;
+
+ public final static EmbeddedKafkaCluster CLUSTER = new EmbeddedKafkaCluster(NUM_BROKERS);
+ private final static MockTime MOCK_TIME = CLUSTER.time;
+ private final static String STREAM_1 = "stream1";
+ private final static String STREAM_2 = "stream2";
+ private final static String OUTPUT = "output-";
Review Comment:
nit:
```suggestion
private final static String OUTPUT = "output";
```
--
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: jira-unsubscribe@kafka.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [kafka] mjsax closed pull request #13592: KAFKA-14862: Outer stream-stream join does not output all results with multiple input partitions
Posted by "mjsax (via GitHub)" <gi...@apache.org>.
mjsax closed pull request #13592: KAFKA-14862: Outer stream-stream join does not output all results with multiple input partitions
URL: https://github.com/apache/kafka/pull/13592
--
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: jira-unsubscribe@kafka.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [kafka] mjsax commented on a diff in pull request #13592: KAFKA-14862: Outer stream-stream join does not output all results with multiple input partitions
Posted by "mjsax (via GitHub)" <gi...@apache.org>.
mjsax commented on code in PR #13592:
URL: https://github.com/apache/kafka/pull/13592#discussion_r1169379331
##########
streams/src/test/java/org/apache/kafka/streams/integration/KStreamKStreamIntegrationTest.java:
##########
@@ -0,0 +1,186 @@
+/*
+ * 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 kafka.utils.MockTime;
+import org.apache.kafka.clients.consumer.ConsumerConfig;
+import org.apache.kafka.clients.producer.ProducerConfig;
+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.JoinWindows;
+import org.apache.kafka.streams.kstream.KStream;
+import org.apache.kafka.streams.kstream.ValueJoiner;
+import org.apache.kafka.test.TestUtils;
+import org.junit.jupiter.api.AfterAll;
+import org.junit.jupiter.api.AfterEach;
+import org.junit.jupiter.api.BeforeAll;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Tag;
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.api.TestInfo;
+import org.junit.jupiter.api.Timeout;
+
+import java.io.IOException;
+import java.time.Duration;
+import java.util.Collections;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Properties;
+import java.util.Set;
+
+import static java.time.Duration.ofSeconds;
+import static java.util.Arrays.asList;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.safeUniqueTestName;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.startApplicationAndWaitUntilRunning;
+import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.waitUntilMinKeyValueRecordsReceived;
+import static org.hamcrest.MatcherAssert.assertThat;
+import static org.hamcrest.core.IsEqual.equalTo;
+
+@Timeout(600)
+@Tag("integration")
+public class KStreamKStreamIntegrationTest {
+ private final static int NUM_BROKERS = 1;
+
+ public final static EmbeddedKafkaCluster CLUSTER = new EmbeddedKafkaCluster(NUM_BROKERS);
+ private final static MockTime MOCK_TIME = CLUSTER.time;
+ private final static String STREAM_1 = "stream1";
+ private final static String STREAM_2 = "stream2";
+ private final static String OUTPUT = "output-";
+ private Properties streamsConfig;
+ private KafkaStreams streams;
+ private final static Properties CONSUMER_CONFIG = new Properties();
+ private final static Properties PRODUCER_CONFIG = new Properties();
+
+ @BeforeAll
+ public static void startCluster() throws Exception {
+ CLUSTER.start();
+ //Use multiple partitions to ensure distribution of keys.
+
+ CLUSTER.createTopic(STREAM_1, 4, 1);
+ CLUSTER.createTopic(STREAM_2, 4, 1);
+ CLUSTER.createTopic(OUTPUT, 1, 1);
+
+ CONSUMER_CONFIG.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
+ CONSUMER_CONFIG.put(ConsumerConfig.GROUP_ID_CONFIG, "result-consumer");
+ CONSUMER_CONFIG.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
+ CONSUMER_CONFIG.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
+ }
+
+ @AfterAll
+ public static void closeCluster() {
+ CLUSTER.stop();
+ }
+
+ @BeforeEach
+ public void before(final TestInfo testInfo) throws IOException {
+ final String stateDirBasePath = TestUtils.tempDirectory().getPath();
+ final String safeTestName = safeUniqueTestName(getClass(), testInfo);
+ streamsConfig = getStreamsConfig(safeTestName);
+ streamsConfig.put(StreamsConfig.STATE_DIR_CONFIG, stateDirBasePath);
+ }
+
+ @AfterEach
+ public void after() throws IOException {
+ if (streams != null) {
+ streams.close();
+ streams = null;
+ }
+ IntegrationTestUtils.purgeLocalStreamsState(streamsConfig);
+ }
+
+ @Test
+ public void shouldOuterJoin() throws Exception {
+ final Set<KeyValue<String, String>> expectedOne = new HashSet<>();
Review Comment:
Yes, will fix (I did c&p from a different test and missed to update this one).
--
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: jira-unsubscribe@kafka.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org