原创

Java操作Kafka

温馨提示:
本文最后更新于 2019年03月21日,已超过 1,835 天没有更新。若文章内的图片失效(无法正常加载),请留言反馈或直接联系我

pom依赖:

<dependency>
    <groupId>org.apache.kafka</groupId>
    <artifactId>kafka-clients</artifactId>
    <version>0.11.0.0</version>
</dependency>
<dependency>
    <groupId>org.apache.kafka</groupId>
    <artifactId>kafka_2.12</artifactId>
    <version>0.11.0.0</version>
</dependency>
<dependency>
    <groupId>log4j</groupId>
    <artifactId>log4j</artifactId>
    <version>1.2.17</version>
</dependency>
<dependency>
    <groupId>org.apache.kafka</groupId>
    <artifactId>kafka-streams</artifactId>
    <version>0.11.0.2</version>
</dependency>

创建生产者

Java代码:

package com.lzhpo.kafka.createProducer;

import org.apache.kafka.clients.producer.KafkaProducer;
import org.apache.kafka.clients.producer.ProducerRecord;

import java.util.Properties;

/**
 * <p> Author:lzhpo </p>
 * <p> Title:</p>
 * <p> Description:
 * 创建生产者(新API)
 * </p>
 */
public class NewProducer {

    public static void main(String[] args) {

        Properties properties = new Properties();
        // Kafka服务端的主机名和端口号
        properties.put("bootstrap.servers", "192.168.200.111:9092");
        // 等待所有副本节点的应答
        properties.put("acks", "all");
        // 消息发送最大尝试次数
        properties.put("retries", 0);
        // 一批消息处理大小
        properties.put("batch.size", 16384);
        // 请求延时
        properties.put("linger.ms", 1);
        // 发送缓存区内存大小
        properties.put("buffer.memory",33554432);
        // key序列化
        properties.put("key.serializer", "org.apache.kafka.common.serialization.StringSerializer");
        // value序列化
        properties.put("value.serializer", "org.apache.kafka.common.serialization.StringSerializer");

        KafkaProducer<String, String> producer = new KafkaProducer<>(properties);
        for (int i = 0; i < 50; i++) {
            producer.send(new ProducerRecord<String, String>("first", Integer.toString(i), "HelloWorld-" +i));
        }

        producer.close();
    }
}

先在Kafka中创建一个topic:

kafka-topics.sh --zookeeper localhost:2181 --create --replication-factor 1 --partitions 1 --topic first

然后在Kafka中开一个消费者(用于查看Java发送的消息):

kafka-console-consumer.sh --zookeeper localhost:2181 --from-beginning --topic first

如果要使用带有回调函数的:

KafkaProducer<String, String> producer = new KafkaProducer<>(properties);
        for (int i = 0; i < 50; i++) {
            producer.send(new ProducerRecord<String, String>("first", "Hello" + i), new Callback() {
                @Override
                public void onCompletion(RecordMetadata recordMetadata, Exception e) {
                    if (recordMetadata != null){
                        System.out.println(recordMetadata.partition() + "---" +recordMetadata.offset());
                    }
                }
            });
        }

消费者

package com.lzhpo.kafka.consumer.highAPI;

import org.apache.kafka.clients.consumer.ConsumerRecord;
import org.apache.kafka.clients.consumer.ConsumerRecords;
import org.apache.kafka.clients.consumer.KafkaConsumer;

import java.util.Arrays;
import java.util.Properties;

/**
 * <p> Author:lzhpo </p>
 * <p> Title:</p>
 * <p> Description:
 * 官方提供案例(自动维护消费情况)(新API)
 * </p>
 */
public class CustomNewConsumer {

    public static void main(String[] args) {

        Properties props = new Properties();
        // 定义kakfa 服务的地址,不需要将所有broker指定上
        props.put("bootstrap.servers", "192.168.200.111:9092");
        // 制定consumer group
        props.put("group.id", "test");
        // 是否自动确认offset
        props.put("enable.auto.commit", "true");
        // 自动确认offset的时间间隔
        props.put("auto.commit.interval.ms", "1000");
        // key的序列化类
        props.put("key.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
        // value的序列化类
        props.put("value.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
        // 定义consumer
        KafkaConsumer<String, String> consumer = new KafkaConsumer<>(props);

        // 消费者订阅的topic, 可同时订阅多个
        consumer.subscribe(Arrays.asList("first", "second","third"));

        while (true) {
            // 读取数据,读取超时时间为100ms
            ConsumerRecords<String, String> records = consumer.poll(100);

            for (ConsumerRecord<String, String> record : records)
                System.out.printf("offset = %d, key = %s, value = %s%n", record.offset(), record.key(), record.value());
        }
    }
}

在Kafka中开启一个生产者控制台:

kafka-console-producer.sh --broker-list localhost:9092 --topic first

然后运行Java代码,在开启的Kafka控制台中发送消息,然后在idea中查看发送的消息。

自定义分区

package com.lzhpo.kafka.custompartitionProducer;

import org.apache.kafka.clients.producer.Partitioner;
import org.apache.kafka.common.Cluster;

import java.util.Map;

/**
 * <p> Author:lzhpo </p>
 * <p> Title:</p>
 * <p> Description:
 * 自定义分区(新API)
 * </p>
 */
public class CustomPartitioner implements Partitioner {

    @Override
    public int partition(String s, Object o, byte[] bytes, Object o1, byte[] bytes1, Cluster cluster) {
        //控制分区
        return 0;
    }

    @Override
    public void close() {

    }

    @Override
    public void configure(Map<String, ?> map) {

    }
}
package com.lzhpo.kafka.custompartitionProducer;

import org.apache.kafka.clients.producer.KafkaProducer;
import org.apache.kafka.clients.producer.Producer;
import org.apache.kafka.clients.producer.ProducerRecord;

import java.util.Properties;

/**
 * <p> Author:lzhpo </p>
 * <p> Title:</p>
 * <p> Description:
 * 在Kafka中(logs日志包下的first-0里面的)查看:tail -f 00000000000000000000.log分区变化情况
 *
 * </p>
 */
public class App {

    public static void main(String[] args) {

        Properties props = new Properties();
        // Kafka服务端的主机名和端口号
        props.put("bootstrap.servers", "192.168.200.111:9092");
        // 等待所有副本节点的应答
        props.put("acks", "all");
        // 消息发送最大尝试次数
        props.put("retries", 0);
        // 一批消息处理大小
        props.put("batch.size", 16384);
        // 增加服务端请求延时
        props.put("linger.ms", 1);
        // 发送缓存区内存大小
        props.put("buffer.memory", 33554432);
        // key序列化
        props.put("key.serializer", "org.apache.kafka.common.serialization.StringSerializer");
        // value序列化
        props.put("value.serializer", "org.apache.kafka.common.serialization.StringSerializer");
        // 自定义分区(com.lzhpo.kafka.custompartitionProducer.CustomPartitioner)
        props.put("partitioner.class", "com.lzhpo.kafka.custompartitionProducer.CustomPartitioner");

        Producer<String, String> producer = new KafkaProducer<>(props);
        producer.send(new ProducerRecord<String, String>("first", "1", "lzhpo"));

        producer.close();
    }
}

在Kafka中(logs日志包下的first-0里面的)查看:tail -f 00000000000000000000.log分区变化情况。

自定义拦截器

package com.lzhpo.kafka.interceptor;

import org.apache.kafka.clients.producer.ProducerInterceptor;
import org.apache.kafka.clients.producer.ProducerRecord;
import org.apache.kafka.clients.producer.RecordMetadata;

import java.util.Map;

/**
 * <p> Author:lzhpo </p>
 * <p> Title:</p>
 * <p> Description:</p>
 */
public class TimeInterceptor implements ProducerInterceptor<String, String> {

    @Override
    public void configure(Map<String, ?> configs) {

    }

    @Override
    public ProducerRecord<String, String> onSend(ProducerRecord<String, String> record) {
        // 创建一个新的record,把时间戳写入消息体的最前部
        return new ProducerRecord(record.topic(), record.partition(), record.timestamp(), record.key(),
                System.currentTimeMillis() + "," + record.value().toString());
    }

    @Override
    public void onAcknowledgement(RecordMetadata metadata, Exception exception) {

    }

    @Override
    public void close() {

    }
}
package com.lzhpo.kafka.interceptor;

import org.apache.kafka.clients.producer.ProducerInterceptor;
import org.apache.kafka.clients.producer.ProducerRecord;
import org.apache.kafka.clients.producer.RecordMetadata;

import java.util.Map;

/**
 * <p> Author:lzhpo </p>
 * <p> Title:</p>
 * <p> Description:</p>
 */
public class CounterInterceptor implements ProducerInterceptor<String, String> {
    private int errorCounter = 0;
    private int successCounter = 0;

    @Override
    public void configure(Map<String, ?> configs) {

    }

    @Override
    public ProducerRecord<String, String> onSend(ProducerRecord<String, String> record) {
        return record;
    }

    @Override
    public void onAcknowledgement(RecordMetadata metadata, Exception exception) {
        // 统计成功和失败的次数
        if (exception == null) {
            successCounter++;
        } else {
            errorCounter++;
        }
    }

    @Override
    public void close() {
        // 保存结果
        System.out.println("Successful sent: " + successCounter);
        System.out.println("Failed sent: " + errorCounter);
    }
}
package com.lzhpo.kafka.interceptor;

import org.apache.kafka.clients.producer.KafkaProducer;
import org.apache.kafka.clients.producer.Producer;
import org.apache.kafka.clients.producer.ProducerConfig;
import org.apache.kafka.clients.producer.ProducerRecord;

import java.util.ArrayList;
import java.util.List;
import java.util.Properties;

/**
 * <p> Author:lzhpo </p>
 * <p> Title:</p>
 * <p> Description:
 * 实现一个简单的双interceptor组成的拦截链。第一个interceptor会在消息发送前将时间戳信息加到消息value的最前部;第二个interceptor会在消息发送后更新成功发送消息数或失败发送消息数。
 * </p>
 */
public class App {

    public static void main(String[] args) throws Exception {
        // 1 设置配置信息
        Properties props = new Properties();
        props.put("bootstrap.servers", "192.168.200.111:9092");
        props.put("acks", "all");
        props.put("retries", 0);
        props.put("batch.size", 16384);
        props.put("linger.ms", 1);
        props.put("buffer.memory", 33554432);
        props.put("key.serializer", "org.apache.kafka.common.serialization.StringSerializer");
        props.put("value.serializer", "org.apache.kafka.common.serialization.StringSerializer");

        // 2 构建拦截链
        List<String> interceptors = new ArrayList<>();
        interceptors.add("com.lzhpo.kafka.timeinterceptor.TimeInterceptor");     interceptors.add("com.lzhpo.kafka.timeinterceptor.CounterInterceptor");
        props.put(ProducerConfig.INTERCEPTOR_CLASSES_CONFIG, interceptors);

        String topic = "first";
        Producer<String, String> producer = new KafkaProducer<>(props);

        // 3 发送消息
        for (int i = 0; i < 10; i++) {

            ProducerRecord<String, String> record = new ProducerRecord<>(topic, "message" + i);
            producer.send(record);
        }

        // 4 一定要关闭producer,这样才会调用interceptor的close方法
        producer.close();
    }

}

先在Kafka中开启一个消费者:

kafka-console-consumer.sh --zookeeper localhost:2181 --from-beginning --topic first

Java控制台:

Kafka中的消费者:

本文目录