环境准备
启动zk和kafka集群,在kafka集群中打开一个消费者:
bin/kafka-console-consumer.sh --zookeeper hd101:2181 --topic first
导入pom依赖:
<dependencies>
<!-- https://mvnrepository.com/artifact/org.apache.kafka/kafka-clients -->
<dependency>
<groupId>org.apache.kafka</groupId>
<artifactId>kafka-clients</artifactId>
<version>0.11.0.0</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.kafka/kafka -->
<dependency>
<groupId>org.apache.kafka</groupId>
<artifactId>kafka_2.12</artifactId>
<version>0.11.0.0</version>
</dependency>
</dependencies>
Kafka生产者Java API
- 创建生产者(过时的API)
public class OldProducer {
@SuppressWarnings("deprecation")
public static void main(String[] args) {
Properties properties = new Properties();
properties.put("metadata.broker.list", "hadoop102:9092");
properties.put("request.required.acks", "1");
properties.put("serializer.class", "kafka.serializer.StringEncoder");
Producer<Integer, String> producer = new Producer<Integer,String>(new ProducerConfig(properties));
KeyedMessage<Integer, String> message = new KeyedMessage<Integer, String>("first", "hello world");
producer.send(message );
}
}
- 创建生产者(新API)
public class NewProducer {
public static void main(String[] args) {
Properties prop = new Properties();
//Kafka的服务端的主机名和端口号
prop.put("bootstrap.servers","hd101:9092");
//等待所有副本的应答
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);
//发送缓冲区内存大小
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");
Producer<String, String> producer = new KafkaProducer<>(props);
for (int i = 0; i < 50; i++) {
producer.send(new ProducerRecord<String, String>("first", Integer.toString(i), "hello world-" + i));
}
producer.close();
- 创建生产者 带回调函数(新API)
public class CallBackProducer {
public static void main(String[] args) {
Properties prop = new Properties();
//Kafka的服务端的主机名和端口号
prop.put("bootstrap.servers","hd101:9092");
//等待所有副本的应答
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);
//发送缓冲区内存大小
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");
Producer<String, String> producer = new KafkaProducer<>(props);
for (int i = 0; i < 50; i++) {
kafkaProducer.send(new ProducerRecord<String, String>("first", "hello" + i), new Callback() {
@Override
public void onCompletion(RecordMetadata metadata, Exception exception) {
if (metadata != null) {
System.err.println(metadata.partition() + "---" + metadata.offset());
}
}
});
kafkaProducer.close();
}
}
- 自定义分区生产者
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)
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)
public class CustomPartitioner implements Partitioner {
@Override
public void configure(Map<String, ?> 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
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", "hadoop103:9092");
// 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.atguigu.kafka.CustomPartitioner");
Producer<String, String> producer = new
KafkaProducer<>(props);
producer.send(new ProducerRecord<String,
String>("first", "1", "atguigu"));
producer.close();
}
}
4)测试:
在hd101监控/opt/module/kafka/logs/目录下first主题3个分区的log日志动态变化情况:
[zy@hd101 first-0]$ tail -f 00000000000000000000.log
[zy@hd101 first-1]$ tail -f 00000000000000000000.log
[zy@hd101 first-2]$ tail -f 00000000000000000000.log
Kafka消费者Java API
- 高级API
0)在控制台创建发送者:
[zy@hd103 kafka]$ bin/kafka-console-producer.sh --broker-list hd101:9092 --topic first
>hello world
1)创建消费者(过时API)
public class CustomConsumer {
@SuppressWarnings("deprecation")
public static void main(String[] args) {
Properties properties = new Properties();
properties.put("zookeeper.connect", "hd101:2181");
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<String, Integer> topicCount = new HashMap<>();
topicCount.put("first", 1);
Map<String, List<KafkaStream<byte[], byte[]>>> consumerMap = consumer.createMessageStreams(topicCount);
KafkaStream<byte[], byte[]> stream = consumerMap.get("first").get(0);
ConsumerIterator<byte[], byte[]> 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)
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", "hadoop102:9092");
// 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());
}
}
}
Kafka producer拦截器(interceptor)
-
拦截器原理
Producer拦截器(interceptor)是在Kafka 0.10版本被引入的,主要用于实现clients端的定制化控制逻辑。
对于producer而言,interceptor使得用户在消息发送前以及producer回调逻辑前有机会对消息做一些定制化需求,比如修改消息等。同时,producer允许用户指定多个interceptor按序作用于同一条消息从而形成一个拦截链(interceptor chain)。Intercetpor的实现接口是org.apache.kafka.clients.producer.ProducerInterceptor,其定义的方法包括:- configure(configs):
获取配置信息和初始化数据时调用。 - onSend(ProducerRecord):
该方法封装进KafkaProducer.send方法中,即它运行在用户主线程中,Producer确保在消息被序列化以及计算分区前调用该方法。用户可以在该方法中对消息做任何操作,但最好保证不要修改消息所属的topic和分区,否则会影响目标分区的计算。 - onAcknowledgement(RecordMetadata, Exception):
该方法会在消息被应答或消息发送失败时调用,并且通常都是在producer回调逻辑触发之前。onAcknowledgement运行在producer的IO线程中,因此不要在该方法中放入很重的逻辑,否则会拖慢producer的消息发送效率。 - close():
关闭interceptor,主要用于执行一些资源清理工作;如前所述,interceptor可能被运行在多个线程中,因此在具体实现时用户需要自行确保线程安全。另外倘若指定了多个interceptor,则producer将按照指定顺序调用它们,并仅仅是捕获每个interceptor可能抛出的异常记录到错误日志中而非在向上传递。这在使用过程中要特别留意
- configure(configs):
-
拦截器案例
1) 需求: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。
2)案例实操:
①增加时间戳拦截器:
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() {
}
}
②统计发送消息成功和发送失败消息数,并在producer关闭时打印这两个计数器
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);
}
}
③producer主程序
public class InterceptorProducer {
public static void main(String[] args) throws Exception {
// 1 设置配置信息
Properties props = new Properties();
props.put("bootstrap.servers", "hd101:9092");
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.atguigu.kafka.interceptor.TimeInterceptor"); interceptors.add("com.atguigu.kafka.interceptor.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();
}
}
④测试:在kafka上启动消费者,然后运行客户端java程序