Kafka Streams开发单词计数应用

pom.xml

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>com.kafkaspace</groupId>
    <artifactId>kafkaWorkspace</artifactId>
    <version>1.0-SNAPSHOT</version>

    <build>
        <sourceDirectory>src/main/scala</sourceDirectory>
        <testSourceDirectory>src/test/scala</testSourceDirectory>
        <plugins>
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>3.2.2</version>
                <executions>
                    <execution>
                        <goals>
                            <goal>compile</goal>
                            <goal>testCompile</goal>
                        </goals>
                        <configuration>
                            <args>
                                <arg>-dependencyfile</arg>
                                <arg>${project.build.directory}/.scala_dependencies</arg>
                            </args>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>2.4.3</version>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                        <configuration>
                            <filters>
                                <filter>
                                    <artifact>*:*</artifact>
                                    <excludes>
                                        <exclude>META-INF/*.SF</exclude>
                                        <exclude>META-INF/*.DSA</exclude>
                                        <exclude>META-INF/*.RSA</exclude>
                                    </excludes>
                                </filter>
                            </filters>
                            <transformers>
                                <transformer implementation=
                                                     "org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
                                    <mainClass></mainClass>
                                </transformer>
                            </transformers>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <source>6</source>
                    <target>6</target>
                </configuration>
            </plugin>
        </plugins>
    </build>


    <!--设置依赖版本号-->
    <properties>
        <scala.version>2.11.8</scala.version>
        <hadoop.version>2.7.4</hadoop.version>
        <spark.version>2.3.2</spark.version>
    </properties>
    <dependencies>
        <!--Scala-->
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>
        <!--Spark-->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <!--Hadoop-->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.11</artifactId>
            <version>2.3.2</version>
        </dependency>

        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.46</version>
        </dependency>
        <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>
    </dependencies>
</project>

LogProcessor.java

import org.apache.kafka.streams.processor.Processor;
import org.apache.kafka.streams.processor.ProcessorContext;
import java.util.HashMap;

public class LogProcessor implements Processor<byte[], byte[]> {
    private ProcessorContext processorContext;
    @Override
    public void init(ProcessorContext processorContext) {
        this.processorContext = processorContext;
    }

    @Override
    public void process(byte[] key, byte[] value) {
        String inputOri = new String(value);
        HashMap<String, Integer>map = new HashMap<String, Integer>();
        int times = 1;
        if (inputOri.contains(" ")){
            //截取字段
            String[] words = inputOri.split(" ");
            for (String word:words){
                if (map.containsKey(word)){
                    map.put(word, map.get(word)+1);
                }else {
                    map.put(word, times);
                }
            }
        }
        inputOri = map.toString();
        processorContext.forward(key, inputOri.getBytes());
    }

    @Override
    public void close() {

    }
}

App.java

import org.apache.kafka.streams.KafkaStreams;
import org.apache.kafka.streams.StreamsConfig;
import org.apache.kafka.streams.Topology;
import org.apache.kafka.streams.processor.Processor;
import org.apache.kafka.streams.processor.ProcessorSupplier;

import java.util.Properties;

public class App {
    public static void main(String[] args) {
        //声明来源主题
        String fromTopic = "testStreams1";
        //声明目标主题
        String toTopic = "testStreams2";
        //设置KafkaStreams参数信息
        Properties props = new Properties();
        props.put(StreamsConfig.APPLICATION_ID_CONFIG, "logProcessor");
        props.put(StreamsConfig.BOOTSTRAP_SERVERS_CONFIG, "hadoop01:9092,hadoop02:9092,hadoop03:9092");
        //实例化StreamsConfig对象
        StreamsConfig config = new StreamsConfig(props);
        //创建拓扑结构
        Topology topology = new Topology();
        //添加处理节点，为源处理节点指定名称和它订阅的主题
        topology.addSource("SOURCE", fromTopic)
                //添加自定义处理节点，指定处理器类和上一节点的名称
                .addProcessor("PROCESSOR", new ProcessorSupplier() {
                    @Override
                    public Processor get() {
                        return new LogProcessor();
                    }
                }, "SOURCE")
                //添加目标处理节点，需要指定目标处理节点和上一节点的名称
                .addSink("SINK", toTopic, "PROCESSOR");
        //实例化KafkaStreams对象
        KafkaStreams streams = new KafkaStreams(topology, config);
        streams.start();
    }
}

各节点启动kafka和zookeeper集群

在hadoop01中创建两个主题

kafka-topics.sh --create \
--topic testStreams1 \
--partitions 3 \
--replication-factor 2 \
--zookeeper hadoop01:2181,hadoop02:2181,hadoop03:2181

kafka-topics.sh --create \
--topic testStreams2 \
--partitions 3 \
--replication-factor 2 \
--zookeeper hadoop01:2181,hadoop02:2181,hadoop03:2181

hadoop01中启动生产者服务

kafka-console-producer.sh \
--broker-list hadoop01:9092,hadoop02:9092,hadoop03:9092 \
--topic testStreams1

Hadoop02中启动消费者服务

kafka-console-consumer.sh \
--from-beginning \
--topic testStreams2 \
--bootstrap-server hadoop01:9092,hadoop02:9092,hadoop03:9092

运行App.java，在生产者服务中输入内容，统计后将在消费者中输出。