forked from skylinemarketing/kafka-streams-examples
-
Notifications
You must be signed in to change notification settings - Fork 0
/
WordCountLambdaIntegrationTest.java
157 lines (138 loc) · 6.73 KB
/
WordCountLambdaIntegrationTest.java
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
/*
* Copyright Confluent Inc.
*
* Licensed 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 io.confluent.examples.streams;
import io.confluent.examples.streams.kafka.EmbeddedSingleNodeKafkaCluster;
import org.apache.kafka.clients.consumer.ConsumerConfig;
import org.apache.kafka.clients.producer.ProducerConfig;
import org.apache.kafka.common.serialization.LongDeserializer;
import org.apache.kafka.common.serialization.Serde;
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.kstream.KStream;
import org.apache.kafka.streams.kstream.KTable;
import org.apache.kafka.streams.kstream.Produced;
import org.apache.kafka.test.TestUtils;
import org.junit.BeforeClass;
import org.junit.ClassRule;
import org.junit.Test;
import java.util.Arrays;
import java.util.List;
import java.util.Properties;
import java.util.regex.Pattern;
import static org.assertj.core.api.Assertions.assertThat;
/**
* End-to-end integration test based on {@link WordCountLambdaExample}, using an embedded Kafka
* cluster.
*
* See {@link WordCountLambdaExample} for further documentation.
*
* See {@link WordCountScalaIntegrationTest} for the equivalent Scala example.
*
* Note: This example uses lambda expressions and thus works with Java 8+ only.
*/
public class WordCountLambdaIntegrationTest {
@ClassRule
public static final EmbeddedSingleNodeKafkaCluster CLUSTER = new EmbeddedSingleNodeKafkaCluster();
private static final String inputTopic = "inputTopic";
private static final String outputTopic = "outputTopic";
@BeforeClass
public static void startKafkaCluster() throws Exception {
CLUSTER.createTopic(inputTopic);
CLUSTER.createTopic(outputTopic);
}
@Test
public void shouldCountWords() throws Exception {
final List<String> inputValues = Arrays.asList(
"Hello Kafka Streams",
"All streams lead to Kafka",
"Join Kafka Summit",
"И теперь пошли русские слова"
);
final List<KeyValue<String, Long>> expectedWordCounts = Arrays.asList(
new KeyValue<>("hello", 1L),
new KeyValue<>("all", 1L),
new KeyValue<>("streams", 2L),
new KeyValue<>("lead", 1L),
new KeyValue<>("to", 1L),
new KeyValue<>("join", 1L),
new KeyValue<>("kafka", 3L),
new KeyValue<>("summit", 1L),
new KeyValue<>("и", 1L),
new KeyValue<>("теперь", 1L),
new KeyValue<>("пошли", 1L),
new KeyValue<>("русские", 1L),
new KeyValue<>("слова", 1L)
);
//
// Step 1: Configure and start the processor topology.
//
final Serde<String> stringSerde = Serdes.String();
final Serde<Long> longSerde = Serdes.Long();
final Properties streamsConfiguration = new Properties();
streamsConfiguration.put(StreamsConfig.APPLICATION_ID_CONFIG, "wordcount-lambda-integration-test");
streamsConfiguration.put(StreamsConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
streamsConfiguration.put(StreamsConfig.DEFAULT_KEY_SERDE_CLASS_CONFIG, Serdes.String().getClass().getName());
streamsConfiguration.put(StreamsConfig.DEFAULT_VALUE_SERDE_CLASS_CONFIG, Serdes.String().getClass().getName());
// The commit interval for flushing records to state stores and downstream must be lower than
// this integration test's timeout (30 secs) to ensure we observe the expected processing results.
streamsConfiguration.put(StreamsConfig.COMMIT_INTERVAL_MS_CONFIG, 10 * 1000);
streamsConfiguration.put(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest");
// Use a temporary directory for storing state, which will be automatically removed after the test.
streamsConfiguration.put(StreamsConfig.STATE_DIR_CONFIG, TestUtils.tempDirectory().getAbsolutePath());
final StreamsBuilder builder = new StreamsBuilder();
final KStream<String, String> textLines = builder.stream(inputTopic);
final Pattern pattern = Pattern.compile("\\W+", Pattern.UNICODE_CHARACTER_CLASS);
final KTable<String, Long> wordCounts = textLines
.flatMapValues(value -> Arrays.asList(pattern.split(value.toLowerCase())))
// no need to specify explicit serdes because the resulting key and value types match our default serde settings
.groupBy((key, word) -> word)
.count();
wordCounts.toStream().to(outputTopic, Produced.with(stringSerde, longSerde));
final KafkaStreams streams = new KafkaStreams(builder.build(), streamsConfiguration);
streams.start();
//
// Step 2: Produce some input data to the input topic.
//
final Properties producerConfig = new Properties();
producerConfig.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
producerConfig.put(ProducerConfig.ACKS_CONFIG, "all");
producerConfig.put(ProducerConfig.RETRIES_CONFIG, 0);
producerConfig.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
producerConfig.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
IntegrationTestUtils.produceValuesSynchronously(inputTopic, inputValues, producerConfig);
//
// Step 3: Verify the application's output data.
//
final Properties consumerConfig = new Properties();
consumerConfig.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
consumerConfig.put(ConsumerConfig.GROUP_ID_CONFIG, "wordcount-lambda-integration-test-standard-consumer");
consumerConfig.put(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest");
consumerConfig.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
consumerConfig.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, LongDeserializer.class);
final List<KeyValue<String, Long>> actualWordCounts = IntegrationTestUtils.waitUntilMinKeyValueRecordsReceived(
consumerConfig,
outputTopic,
expectedWordCounts.size()
);
streams.close();
assertThat(actualWordCounts).containsExactlyElementsOf(expectedWordCounts);
}
}