-
Notifications
You must be signed in to change notification settings - Fork 1.1k
/
StateStoresInTheDSLIntegrationTest.java
189 lines (163 loc) · 7.77 KB
/
StateStoresInTheDSLIntegrationTest.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
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
/*
* 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 org.apache.kafka.common.serialization.LongDeserializer;
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.KeyValue;
import org.apache.kafka.streams.StreamsBuilder;
import org.apache.kafka.streams.StreamsConfig;
import org.apache.kafka.streams.TestInputTopic;
import org.apache.kafka.streams.TestOutputTopic;
import org.apache.kafka.streams.TopologyTestDriver;
import org.apache.kafka.streams.kstream.KStream;
import org.apache.kafka.streams.kstream.Produced;
import org.apache.kafka.streams.processor.api.Processor;
import org.apache.kafka.streams.processor.api.ProcessorContext;
import org.apache.kafka.streams.processor.api.ProcessorSupplier;
import org.apache.kafka.streams.processor.api.Record;
import org.apache.kafka.streams.state.KeyValueStore;
import org.apache.kafka.streams.state.StoreBuilder;
import org.apache.kafka.streams.state.Stores;
import org.apache.kafka.test.TestUtils;
import org.junit.Test;
import java.util.Arrays;
import java.util.List;
import java.util.Optional;
import java.util.Properties;
import static org.assertj.core.api.Assertions.assertThat;
/**
* End-to-end integration test that shows how to use state stores in the Kafka Streams DSL.
* <p>
* Don't pay too much attention to the output data of the application (or to the output data of the
* Transformer). What we want to showcase here is the technical interaction between state stores
* and the Kafka Streams DSL, at the example of {@link KStream#process(ProcessorSupplier, String...)}.
* What the application is actually computing is of secondary concern.
* <p>
* Note: This example works with Java 8+ only.
*/
public class StateStoresInTheDSLIntegrationTest {
private static final String inputTopic = "inputTopic";
private static final String outputTopic = "outputTopic";
/**
* Returns a transformer that computes running, ever-incrementing word counts.
*/
private static final class WordCountTransformerSupplier
implements ProcessorSupplier<byte[], String, String, Long> {
final private String stateStoreName;
WordCountTransformerSupplier(final String stateStoreName) {
this.stateStoreName = stateStoreName;
}
@Override
public Processor<byte[], String, String, Long> get() {
return new Processor<byte[], String, String, Long>() {
private ProcessorContext<String, Long> context;
private KeyValueStore<String, Long> stateStore;
@Override
public void init(final ProcessorContext<String, Long> context) {
this.context = context;
stateStore = context.getStateStore(stateStoreName);
}
@Override
public void process(final Record<byte[], String> record) {
// For simplification (and unlike the traditional wordcount) we assume that the value is
// a single word, i.e. we don't split the value by whitespace into potentially one or more
// words.
final Optional<Long> count = Optional.ofNullable(stateStore.get(record.value()));
final Long incrementedCount = count.orElse(0L) + 1;
stateStore.put(record.value(), incrementedCount);
context.forward(new Record<>(record.value(), incrementedCount, record.timestamp(), record.headers()));
}
@Override
public void close() {
// Note: The store should NOT be closed manually here via `stateStore.close()`!
// The Kafka Streams API will automatically close stores when necessary.
}
};
}
}
@Test
public void shouldAllowStateStoreAccessFromDSL() {
final List<String> inputValues = Arrays.asList(
"foo",
"bar",
"foo",
"quux",
"bar",
"foo");
final List<KeyValue<String, Long>> expectedRecords = Arrays.asList(
new KeyValue<>("foo", 1L),
new KeyValue<>("bar", 1L),
new KeyValue<>("foo", 2L),
new KeyValue<>("quux", 1L),
new KeyValue<>("bar", 2L),
new KeyValue<>("foo", 3L)
);
//
// Step 1: Configure and start the processor topology.
//
final StreamsBuilder builder = new StreamsBuilder();
final Properties streamsConfiguration = new Properties();
streamsConfiguration.put(StreamsConfig.APPLICATION_ID_CONFIG, "state-store-dsl-lambda-integration-test");
streamsConfiguration.put(StreamsConfig.BOOTSTRAP_SERVERS_CONFIG, "dummy config");
streamsConfiguration.put(StreamsConfig.DEFAULT_KEY_SERDE_CLASS_CONFIG, Serdes.ByteArraySerde.class);
streamsConfiguration.put(StreamsConfig.DEFAULT_VALUE_SERDE_CLASS_CONFIG, Serdes.StringSerde.class);
// Use a temporary directory for storing state, which will be automatically removed after the test.
streamsConfiguration.put(StreamsConfig.STATE_DIR_CONFIG, TestUtils.tempDirectory().getAbsolutePath());
// Create a state store manually.
final StoreBuilder<KeyValueStore<String, Long>> wordCountsStore = Stores
.keyValueStoreBuilder(
Stores.persistentKeyValueStore("WordCountsStore"),
Serdes.String(),
Serdes.Long())
.withCachingEnabled();
// Important (1 of 2): You must add the state store to the topology, otherwise your application
// will fail at run-time (because the state store is referred to in `transform()` below.
builder.addStateStore(wordCountsStore);
// Read the input data. (In this example we ignore whatever is stored in the record keys.)
final KStream<byte[], String> words = builder.stream(inputTopic);
// Important (2 of 2): When we call `transform()` we must provide the name of the state store
// that is going to be used by the `Transformer` returned by `WordCountTransformerSupplier` as
// the second parameter of `transform()` (note: we are also passing the state store name to the
// constructor of `WordCountTransformerSupplier`, which we do primarily for cleaner code).
// Otherwise our application will fail at run-time when attempting to operate on the state store
// (within the transformer) because `ProcessorContext#getStateStore("WordCountsStore")` will
// return `null`.
final KStream<String, Long> wordCounts =
words.process(new WordCountTransformerSupplier(wordCountsStore.name()), wordCountsStore.name());
wordCounts.to(outputTopic, Produced.with(Serdes.String(), Serdes.Long()));
try (final TopologyTestDriver topologyTestDriver = new TopologyTestDriver(builder.build(), streamsConfiguration)) {
//
// Step 2: Setup input and output topics.
//
final TestInputTopic<Void, String> input = topologyTestDriver
.createInputTopic(inputTopic,
new IntegrationTestUtils.NothingSerde<>(),
new StringSerializer());
final TestOutputTopic<String, Long> output = topologyTestDriver
.createOutputTopic(outputTopic, new StringDeserializer(), new LongDeserializer());
//
// Step 3: Produce some input data to the input topic.
//
input.pipeValueList(inputValues);
//
// Step 4: Verify the application's output data.
//
assertThat(output.readKeyValuesToList()).isEqualTo(expectedRecords);
}
}
}