Kafka快速入门系列(10) | Kafka的Consumer API操作

  本篇博主带来的是Kafka的Consumer API操作。

---

  Consumer消费数据时的可靠性是很容易保证的，因为数据在Kafka中是持久化的，故不用担心数据丢失问题。
  由于consumer在消费过程中可能会出现断电宕机等故障，consumer恢复后，需要从故障前的位置的继续消费，所以consumer需要实时记录自己消费到了哪个offset，以便故障恢复后继续消费。
  所以offset的维护是Consumer消费数据是必须考虑的问题。

1. 手动提交offset

• 1. 导入依赖

    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <source>8</source>
                    <target>8</target>
                </configuration>
            </plugin>
        </plugins>

    </build>


    <dependencies>
    <dependency>
        <groupId>org.apache.kafka</groupId>
        <artifactId>kafka-clients</artifactId>
        <version>0.11.0.2</version>
    </dependency>
    </dependencies>

• 2. 编写代码

需要用到的类：
KafkaConsumer：需要创建一个消费者对象，用来消费数据
ConsumerConfig：获取所需的一系列配置参数
ConsuemrRecord：每条数据都要封装成一个ConsumerRecord对象

package com.buwenbuhuo.kafka.consumer;

import org.apache.kafka.clients.consumer.ConsumerConfig;
import org.apache.kafka.clients.consumer.ConsumerRecord;
import org.apache.kafka.clients.consumer.ConsumerRecords;
import org.apache.kafka.clients.consumer.KafkaConsumer;
import org.apache.kafka.common.serialization.StringDeserializer;

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

/**
 * @author 卜温不火
 * @create 2020-05-06 23:22
 * com.buwenbuhuo.kafka.consumer - the name of the target package where the new class or interface will be created.
 * kafka0506 - the name of the current project.
 */
public class CustomConsumer {

    public static void main(String[] args) {

        Properties props = new Properties();
        props.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, "hadoop002:9092");
        props.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class.getName());
        props.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class.getName());
        props.put(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest");

        props.put(ConsumerConfig.GROUP_ID_CONFIG, "bigData-0507");
        props.put(ConsumerConfig.ENABLE_AUTO_COMMIT_CONFIG,true);
        props.put(ConsumerConfig.AUTO_COMMIT_INTERVAL_MS_CONFIG,3000);

        //1.创建1个消费者
        KafkaConsumer<String, String> consumer = new KafkaConsumer<>(props);
        consumer.subscribe(Arrays.asList("first"));

        //2.调用poll
     try {

         while (true) {
             ConsumerRecords<String, String> records = consumer.poll(100);
             for (ConsumerRecord<String, String> record : records) {
             System.out.println("record = " + record);

             }
         }
     }finally {
         consumer.close();
     }
    }
}

• 3. 结果呈现

• 4. 代码分析

  手动提交offset的方法有两种：分别是commitSync（同步提交）和commitAsync（异步提交）。两者的相同点是，都会将本次poll的一批数据最高的偏移量提交；不同点是，commitSync会失败重试，一直到提交成功（如果由于不可恢复原因导致，也会提交失败）；而commitAsync则没有失败重试机制，故有可能提交失败。

• 5. 此为异步提交代码

package com.buwenbuhuo.kafka.consumer;

import org.apache.kafka.clients.consumer.ConsumerConfig;
import org.apache.kafka.clients.consumer.ConsumerRecord;
import org.apache.kafka.clients.consumer.ConsumerRecords;
import org.apache.kafka.clients.consumer.KafkaConsumer;
import org.apache.kafka.common.serialization.StringDeserializer;

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

/**
 * @author 卜温不火
 * @create 2020-05-06 23:22
 * com.buwenbuhuo.kafka.consumer - the name of the target package where the new class or interface will be created.
 * kafka0506 - the name of the current project.
 */
public class CustomConsumer {

    public static void main(String[] args) {

        Properties props = new Properties();
        props.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, "hadoop002:9092");
        props.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class.getName());
        props.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class.getName());
        props.put(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest");

        props.put(ConsumerConfig.GROUP_ID_CONFIG, "bigData-0507");
        props.put(ConsumerConfig.ENABLE_AUTO_COMMIT_CONFIG,false);


        //1.创建1个消费者
        KafkaConsumer<String, String> consumer = new KafkaConsumer<>(props);
        consumer.subscribe(Arrays.asList("second"));

        //2.调用poll
     try {

         while (true) {
             ConsumerRecords<String, String> records = consumer.poll(100);
             for (ConsumerRecord<String, String> record : records) {
             System.out.println("record = " + record);
             }
             // 异步提交
             consumer.commitAsync();
         }
     }finally {
         consumer.close();
     }
    }
}

• 6. 此为同步提交代码

package com.buwenbuhuo.kafka.consumer;

import org.apache.kafka.clients.consumer.ConsumerConfig;
import org.apache.kafka.clients.consumer.ConsumerRecord;
import org.apache.kafka.clients.consumer.ConsumerRecords;
import org.apache.kafka.clients.consumer.KafkaConsumer;
import org.apache.kafka.common.serialization.StringDeserializer;

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

/**
 * @author 卜温不火
 * @create 2020-05-06 23:22
 * com.buwenbuhuo.kafka.consumer - the name of the target package where the new class or interface will be created.
 * kafka0506 - the name of the current project.
 */
public class CustomConsumer {

    public static void main(String[] args) {

        Properties props = new Properties();
        props.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, "hadoop002:9092");
        props.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class.getName());
        props.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class.getName());
        props.put(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest");

        props.put(ConsumerConfig.GROUP_ID_CONFIG, "bigData-0507");
        props.put(ConsumerConfig.ENABLE_AUTO_COMMIT_CONFIG,false);


        //1.创建1个消费者
        KafkaConsumer<String, String> consumer = new KafkaConsumer<>(props);
        consumer.subscribe(Arrays.asList("second"));

        //2.调用poll
     try {

         while (true) {
             ConsumerRecords<String, String> records = consumer.poll(100);
             for (ConsumerRecord<String, String> record : records) {
             System.out.println("record = " + record);
             }
             // 同步提交
             consumer.commitSync();
         }
     }finally {
         consumer.close();
     }
    }
}

• 7. 结果图

2. 自动提交offset

  为了使我们能够专注于自己的业务逻辑，Kafka提供了自动提交offset的功能。
自动提交offset的相关参数：
enable.auto.commit：是否开启自动提交offset功能
auto.commit.interval.ms：自动提交offset的时间间隔

• 1. 代码

package com.buwenbuhuo.kafka.consumer;

import org.apache.kafka.clients.consumer.ConsumerConfig;
import org.apache.kafka.clients.consumer.ConsumerRecord;
import org.apache.kafka.clients.consumer.ConsumerRecords;
import org.apache.kafka.clients.consumer.KafkaConsumer;
import org.apache.kafka.common.serialization.StringDeserializer;

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

/**
 * @author 卜温不火
 * @create 2020-05-06 23:22
 * com.buwenbuhuo.kafka.consumer - the name of the target package where the new class or interface will be created.
 * kafka0506 - the name of the current project.
 */
public class CustomConsumer {

    public static void main(String[] args) {
        Properties props = new Properties();
        props.put("bootstrap.servers", "hadoop002:9092");
        props.put("group.id", "test");
        props.put("enable.auto.commit", "true");
        props.put("auto.commit.interval.ms", "1000");
        props.put("key.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
        props.put("value.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
        KafkaConsumer<String, String> consumer = new KafkaConsumer<>(props);
        consumer.subscribe(Arrays.asList("second"));
        while (true) {
            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());
        }
    }
}

• 2. 运行结果
  

3. 自己维护offset

• 1. 代码

package com.buwenbuhuo.kafka.consumer;

import org.apache.kafka.clients.consumer.ConsumerRebalanceListener;
import org.apache.kafka.clients.consumer.ConsumerRecord;
import org.apache.kafka.clients.consumer.ConsumerRecords;
import org.apache.kafka.clients.consumer.KafkaConsumer;
import org.apache.kafka.common.TopicPartition;

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

/**
 * @author 卜温不火
 * @create 2020-05-07 15:16
 * com.buwenbuhuo.kafka.consumer - the name of the target package where the new class or interface will be created.
 * kafka0506 - the name of the current project.
 */
public class CustomOffsetConsumer {

    public static void main(String[] args) {

        Properties props = new Properties();
        props.put("bootstrap.servers", "hadoop002:9092");
        props.put("group.id", "test");//消费者组，只要group.id相同，就属于同一个消费者组
        props.put("enable.auto.commit", "false");//自动提交offset
        props.put("key.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
        props.put("value.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
        KafkaConsumer<String, String> consumer = new KafkaConsumer<>(props);
        consumer.subscribe(Arrays.asList("second"), new ConsumerRebalanceListener() {

            //提交当前负责的分区的offset
            @Override
            public void onPartitionsRevoked(Collection<TopicPartition> partitions) {
                System.out.println("==========回收的分区===========");
                for (TopicPartition partition : partitions){
                    System.out.println("partition = " + partition);   // 啥也没干不写东西也可以
                }

            }

            //定位新分配的分区的offset
            @Override
            public void onPartitionsAssigned(Collection<TopicPartition> partitions) {
                System.out.println("========重新得到的分区===========");
                for (TopicPartition partition : partitions) {
                    Long offset = getPartitionOffset(partition);
                    consumer.seek(partition,offset);
                }
            }
        });


        while (true) {
            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());
                TopicPartition topicPartition = new TopicPartition(record.topic(), record.partition());
                commitOffset(topicPartition,record.offset()+1);
            }
        }
    }

    private static void commitOffset(TopicPartition topicPartition, long l) {

    }

    private static Long getPartitionOffset(TopicPartition partition) {
        return null;
    }

}

• 2. 结果
  

  本次的分享就到这里了,

---

  $看完就赞，养成习惯！！！$^ _ ^ ❤️ ❤️ ❤️
  码字不易，大家的支持就是我坚持下去的动力。点赞后不要忘了关注我哦！