以 WordCount 为例子，了解一下 kafka stream 的开发流程。

创建项目

mvn archetype:generate -DgroupId=com.kafkademo -DartifactId=KafkaStreamWordCount -DarchetypeArtifactId=maven-archetype-quickstart -DinteractiveMode=false

添加依赖

<dependency>
    <groupId>org.apache.kafka</groupId>
    <artifactId>kafka-clients</artifactId>
    <version>2.0.0</version>
</dependency>
<dependency>
    <groupId>org.apache.kafka</groupId>
    <artifactId>kafka-streams</artifactId>
    <version>2.0.0</version>
</dependency>
...
<build>
    <plugins>
        <plugin>
            <groupId>org.apache.maven.plugins</groupId>
            <artifactId>maven-compiler-plugin</artifactId>
            <configuration>
                <source>1.8</source>
                <target>1.8</target>
            </configuration>
        </plugin>
    </plugins>
</build>    

代码

package com.kafkademo;

import java.util.Arrays;
import java.util.Locale;
import java.util.Properties;
import java.util.concurrent.CountDownLatch;

import org.apache.kafka.common.serialization.Serdes;
import org.apache.kafka.streams.KafkaStreams;
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;

public class WordCount {
    public static void main(String[] args) {
        Properties props = new Properties();
        props.put(StreamsConfig.APPLICATION_ID_CONFIG, "streams-wordcount");
        props.put(StreamsConfig.BOOTSTRAP_SERVERS_CONFIG, "localhost:9092");
        props.put(StreamsConfig.DEFAULT_KEY_SERDE_CLASS_CONFIG, Serdes.String().getClass());
        props.put(StreamsConfig.DEFAULT_VALUE_SERDE_CLASS_CONFIG, Serdes.String().getClass());

        final StreamsBuilder builder = new StreamsBuilder();

        KStream<String, String> source = builder.stream("streams-plaintext-input");

        KTable<String, Long> counts = source
                .flatMapValues(value -> Arrays.asList(value.toLowerCase(Locale.getDefault()).split(" ")))
                .groupBy((key, value) -> value).count();

        counts.toStream().to("streams-wordcount-output", Produced.with(Serdes.String(), Serdes.Long()));

        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-shutdown-hook") {
            @Override
            public void run() {
                streams.close();
                latch.countDown();
            }
        });

        try {
            streams.start();
            latch.await();
        } catch (Throwable e) {
            System.exit(1);
        }
        System.exit(0);
    }
}

运行

mvn compile
mvn exec:java -Dexec.mainClass="com.kafkademo.WordCount"

创建 topic

bin/kafka-topics.sh --create --zookeeper localhost:2181 --replication-factor 1 --partitions 1 --topic streams-plaintext-input

bin/kafka-topics.sh --create --zookeeper localhost:2181 --replication-factor 1 --partitions 1 --topic streams-plaintext-output

生产消息

bin/kafka-console-producer.sh  --broker-list localhost:9092 --topic streams-plaintext-input

消费验证

bin/kafka-console-consumer.sh --bootstrap-server localhost:9092 \
    --topic streams-wordcount-output \
    --from-beginning \
    --formatter kafka.tools.DefaultMessageFormatter \
    --property print.key=true \
    --property print.value=true \
    --property key.deserializer=org.apache.kafka.common.serialization.StringDeserializer \
    --property value.deserializer=org.apache.kafka.common.serialization.LongDeserializer

再producer终端发送消息：

>a
>abc
>a
>a

consumer 终端显示：

a   1
abc 1
a   2
a   3