四.KafkaAPI实战

4.1 环境准备

1）在eclipse中创建一个java工程

2）在工程的根目录创建一个lib文件夹

3）解压kafka安装包，将安装包libs目录下的jar包拷贝到工程的lib目录下，并build path。

4）启动zk和kafka集群，在kafka集群中打开一个消费者

[itstar@bigdata11 kafka]$ bin/kafka-console-consumer.sh --zookeeper

bigdata11:2181 --topic first

4.2 Kafka生产者Java API

4.2.1 创建生产者（过时的API）

package com.itstar.kafka;

import java.util.Properties;

import kafka.javaapi.producer.Producer;

import kafka.producer.KeyedMessage;

import kafka.producer.ProducerConfig;

public class OldProducer {

@SuppressWarnings("deprecation")

public static void main(String[] args) {

Properties properties = new Properties();

properties.put("metadata.broker.list", "bigdata11:9092");

properties.put("request.required.acks", "1");

properties.put("serializer.class", "kafka.serializer.StringEncoder");

Producer producer = new Producer(new

ProducerConfig(properties));

KeyedMessage message = new KeyedMessage

String>("first", "hello world");

producer.send(message );

}

}

4.2.2 创建生产者（新API）

package com.itstar.kafka;

import java.util.Properties;

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

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

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

public class NewProducer {

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", "bigdata12:9092");

// 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);

// 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");

KafkaProducer producer = new KafkaProducer<>(props);

for (int i = 0; i < 50; i++) {

producer.send(new ProducerRecord("first",

Integer.toString(i), "hello world-" + i));

}

producer.close();

}

}

4.2.3 创建生产者带回调函数（新API）

package com.itstar.kafka;

import java.util.Properties;

import org.apache.kafka.clients.producer.Callback;

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

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

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

public class CallBackProducer {

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", "bigdata12:9092");

// 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");

KafkaProducer kafkaProducer = new KafkaProducer<>

(props);

for (int i = 0; i < 50; i++) {

kafkaProducer.send(new ProducerRecord("first",

"hello" + i), new Callback() {

@Override

public void onCompletion(RecordMetadata metadata, Exception

exception) {

if (metadata != null) {

System.out.println(metadata.partition() + "---" +

metadata.offset());

}

}

});

}

kafkaProducer.close();

}

}

4.2.4 自定义分区生产者

0）需求：将所有数据存储到topic的第0号分区上

1）定义一个类实现Partitioner接口，重写里面的方法（过时API）

package com.itstar.kafka;

import java.util.Map;

import kafka.producer.Partitioner;

public class CustomPartitioner implements Partitioner {

public CustomPartitioner() {

super();

}

@Override

public int partition(Object key, int numPartitions) {

// 控制分区

return 0;

}

}

2）自定义分区（新API）

package com.itstar.kafka;

import java.util.Map;

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

import org.apache.kafka.common.Cluster;

public class CustomPartitioner implements Partitioner {

@Override

public void configure(Map configs) {

}

@Override

public int partition(String topic, Object key, byte[] keyBytes, Object

value, byte[] valueBytes, Cluster cluster) {

// 控制分区

return 0;

}

@Override

public void close() {

}

}

3）在代码中调用

package com.itstar.kafka;

import java.util.Properties;

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

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

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

public class PartitionerProducer {

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", "bigdata12:9092");

// 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

props.put("partitioner.class", "com.itstar.kafka.CustomPartitioner");

Producer producer = new KafkaProducer<>(props);

producer.send(new ProducerRecord("first", "1",

"itstar"));

producer.close();

}

}

4）测试

（1）在bigdata11上监控/opt/module/kafka/logs/目录下fifirst主题3个分区的log日志动态变化情况

[itstar@bigdata11 first-0]$ tail -f 00000000000000000000.log

[itstar@bigdata11 first-1]$ tail -f 00000000000000000000.log

[itstar@bigdata11 first-2]$ tail -f 00000000000000000000.log

（2）发现数据都存储到指定的分区了。

4.3 Kafka消费者Java API

0）在控制台创建发送者

[itstar@bigdata13 kafka]$ bin/kafka-console-producer.sh --broker-list

bigdata11:9092 --topic first

>hello world

1）创建消费者（过时API）

package com.itstar.kafka.consume;

import java.util.HashMap;

import java.util.List;

import java.util.Map;

import java.util.Properties;

import kafka.consumer.Consumer;

import kafka.consumer.ConsumerConfig;

import kafka.consumer.ConsumerIterator;

import kafka.consumer.KafkaStream;

import kafka.javaapi.consumer.ConsumerConnector;

public class CustomConsumer {

@SuppressWarnings("deprecation")

public static void main(String[] args) {

Properties properties = new Properties();

properties.put("zookeeper.connect", "bigdata11:2181");

properties.put("group.id", "g1");

properties.put("zookeeper.session.timeout.ms", "500");

properties.put("zookeeper.sync.time.ms", "250");

properties.put("auto.commit.interval.ms", "1000");

// 创建消费者连接器

ConsumerConnector consumer = Consumer.createJavaConsumerConnector(new

ConsumerConfig(properties));

HashMap topicCount = new HashMap<>();

topicCount.put("first", 1);

Map>> consumerMap =

consumer.createMessageStreams(topicCount);

KafkaStream stream = consumerMap.get("first").get(0);

ConsumerIterator it = stream.iterator();

while (it.hasNext()) {

System.out.println(new String(it.next().message()));

}

}

}

2）官方提供案例（自动维护消费情况）（新API）

package com.itstar.kafka.consume;

import java.util.Arrays;

import java.util.Properties;

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

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

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

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", "bigdata11:9092");

// 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 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 records = consumer.poll(100);

for (ConsumerRecord record : records)

System.out.printf("offset = %d, key = %s, value = %s%n",

record.offset(), record.key(), record.value());

}

}

}