kafka WordCountTransformerDemo 源码
kafka WordCountTransformerDemo 代码
文件路径:/streams/examples/src/main/java/org/apache/kafka/streams/examples/wordcount/WordCountTransformerDemo.java
/*
* 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.examples.wordcount;
import org.apache.kafka.clients.consumer.ConsumerConfig;
import org.apache.kafka.common.serialization.Serdes;
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.Transformer;
import org.apache.kafka.streams.kstream.TransformerSupplier;
import org.apache.kafka.streams.processor.ConnectedStoreProvider;
import org.apache.kafka.streams.processor.PunctuationType;
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.KeyValueIterator;
import org.apache.kafka.streams.state.KeyValueStore;
import org.apache.kafka.streams.state.StoreBuilder;
import org.apache.kafka.streams.state.Stores;
import java.io.FileInputStream;
import java.io.IOException;
import java.time.Duration;
import java.util.Collections;
import java.util.Locale;
import java.util.Properties;
import java.util.Set;
import java.util.concurrent.CountDownLatch;
/**
* Demonstrates, using a {@link Transformer} which combines the low-level Processor APIs with the high-level Kafka Streams DSL,
* how to implement the WordCount program that computes a simple word occurrence histogram from an input text.
* <p>
* <strong>Note: This is simplified code that only works correctly for single partition input topics.
* Check out {@link WordCountDemo} for a generic example.</strong>
* <p>
* In this example, the input stream reads from a topic named "streams-plaintext-input", where the values of messages
* represent lines of text; and the histogram output is written to topic "streams-wordcount-processor-output" where each record
* is an updated count of a single word.
* <p>
* This example differs from {@link WordCountProcessorDemo} in that it uses a {@link Transformer} to define the word
* count logic, and the topology is wired up through a {@link StreamsBuilder}, which more closely resembles the high-level DSL.
* Additionally, the {@link TransformerSupplier} specifies the {@link StoreBuilder} that the {@link Transformer} needs
* by implementing {@link ConnectedStoreProvider#stores()}.
* <p>
* Before running this example you must create the input topic and the output topic (e.g. via
* {@code bin/kafka-topics.sh --create ...}), and write some data to the input topic (e.g. via
* {@code bin/kafka-console-producer.sh}). Otherwise you won't see any data arriving in the output topic.
*/
public final class WordCountTransformerDemo {
static class MyProcessorSupplier implements ProcessorSupplier<String, String, String, String> {
@Override
public Processor<String, String, String, String> get() {
return new Processor<String, String, String, String>() {
private KeyValueStore<String, Integer> kvStore;
@Override
public void init(final ProcessorContext<String, String> context) {
context.schedule(Duration.ofSeconds(1), PunctuationType.STREAM_TIME, timestamp -> {
try (final KeyValueIterator<String, Integer> iter = kvStore.all()) {
System.out.println("----------- " + timestamp + " ----------- ");
while (iter.hasNext()) {
final KeyValue<String, Integer> entry = iter.next();
System.out.println("[" + entry.key + ", " + entry.value + "]");
context.forward(new Record<>(entry.key, entry.value.toString(), timestamp));
}
}
});
this.kvStore = context.getStateStore("Counts");
}
@Override
public void process(final Record<String, String> record) {
final String[] words = record.value().toLowerCase(Locale.getDefault()).split("\\W+");
for (final String word : words) {
final Integer oldValue = this.kvStore.get(word);
if (oldValue == null) {
this.kvStore.put(word, 1);
} else {
this.kvStore.put(word, oldValue + 1);
}
}
}
@Override
public void close() {}
};
}
@Override
public Set<StoreBuilder<?>> stores() {
return Collections.singleton(Stores.keyValueStoreBuilder(
Stores.inMemoryKeyValueStore("Counts"),
Serdes.String(),
Serdes.Integer()));
}
}
public static void main(final String[] args) throws IOException {
final Properties props = new Properties();
if (args != null && args.length > 0) {
try (final FileInputStream fis = new FileInputStream(args[0])) {
props.load(fis);
}
if (args.length > 1) {
System.out.println("Warning: Some command line arguments were ignored. This demo only accepts an optional configuration file.");
}
}
props.putIfAbsent(StreamsConfig.APPLICATION_ID_CONFIG, "streams-wordcount-transformer");
props.putIfAbsent(StreamsConfig.BOOTSTRAP_SERVERS_CONFIG, "localhost:9092");
props.putIfAbsent(StreamsConfig.CACHE_MAX_BYTES_BUFFERING_CONFIG, 0);
props.putIfAbsent(StreamsConfig.DEFAULT_KEY_SERDE_CLASS_CONFIG, Serdes.String().getClass());
props.putIfAbsent(StreamsConfig.DEFAULT_VALUE_SERDE_CLASS_CONFIG, Serdes.String().getClass());
// setting offset reset to earliest so that we can re-run the demo code with the same pre-loaded data
props.putIfAbsent(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest");
final StreamsBuilder builder = new StreamsBuilder();
builder.<String, String>stream("streams-plaintext-input")
.process(new MyProcessorSupplier())
.to("streams-wordcount-processor-output");
final KafkaStreams streams = new KafkaStreams(builder.build(), props);
final CountDownLatch latch = new CountDownLatch(1);
// attach shutdown handler to catch control-c
Runtime.getRuntime().addShutdownHook(new Thread("streams-wordcount-shutdown-hook") {
@Override
public void run() {
streams.close();
latch.countDown();
}
});
try {
streams.start();
latch.await();
} catch (final Throwable e) {
System.exit(1);
}
System.exit(0);
}
}
相关信息
相关文章
0
赞
热门推荐
-
2、 - 优质文章
-
3、 gate.io
-
8、 golang
-
9、 openharmony
-
10、 Vue中input框自动聚焦