首先创建Producer,
其次创建Consumer,
最后自定义Partition
1)Kafka的生产者
KafkaProducer
package com.sinovatech.framework.kafka;
import java.util.Properties;
import kafka.javaapi.producer.Producer;
import kafka.producer.KeyedMessage;
import kafka.producer.ProducerConfig;
public class KafkaProducer {
private static String brokers = "192.168.30.104:9092,192.168.30.105:9092,192.168.30.106:9092";
private static String serializer = "kafka.serializer.StringEncoder";
private static String partition = "com.sinovatech.framework.kafka.KafkaPartitioner";
private static final String topic = "mall";
private static Properties props = new Properties();
public static void main(String[] args) {
// serializer.class为消息的序列化类
props.put("serializer.class", serializer);
// 配置metadata.broker.list, 为了高可用, 最好配两个broker实例
props.put("metadata.broker.list", brokers);
// ACK机制, 消息发送需要kafka服务端确认
props.put("request.required.acks", "1");
props.put("partitioner.class", partition);
ProducerConfig config = new ProducerConfig(props);
Producer<String, String> producer = new Producer<String, String>(config);
for (int i = 0; i < 500; i++) {
String message = "hello=" + i;
String key = i + "";
producer.send(new KeyedMessage<String, String>(topic, key, message));
}
}
}
1)Kafka的消费者
KafkaConsumer
package com.sinovatech.framework.kafka;
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 KafkaConsumer extends Thread {
private static String zookeepers = "192.168.30.104:2181,192.168.30.105:2181,192.168.30.106:2181";
private static Properties props = new Properties();
private static String group = "mallGroup";
private static final String topic = "mall";
private final ConsumerConnector consumer;
public static void main(String[] args) {
KafkaConsumer consumerThread = new KafkaConsumer();
consumerThread.start();
}
public KafkaConsumer() {
consumer = Consumer.createJavaConsumerConnector(createConsumerConfig());
}
private static ConsumerConfig createConsumerConfig() {
// 设置zookeeper的链接地址
props.put("zookeeper.connect", zookeepers);
// 设置group id
props.put("group.id", group);
// kafka的group 消费记录是保存在zookeeper上的, 但这个信息在zookeeper上不是实时更新的, 需要有个间隔时间更新
props.put("auto.commit.interval.ms", "1000");
props.put("zookeeper.session.timeout.ms", "10000");
return new ConsumerConfig(props);
}
public void run() {
// 设置Topic=>Thread Num映射关系, 构建具体的流
Map<String, Integer> topickMap = new HashMap<String, Integer>();
topickMap.put(topic, 1);
Map<String, List<KafkaStream<byte[], byte[]>>> streamMap = consumer
.createMessageStreams(topickMap);
KafkaStream<byte[], byte[]> stream = streamMap.get(topic).get(0);
ConsumerIterator<byte[], byte[]> it = stream.iterator();
System.out.println("*********Results********");
while (it.hasNext()) {
System.err.println("get data:" + new String(it.next().message()));
try {
Thread.sleep(500);
} catch (InterruptedException e) {
e.printStackTrace();
}
}
}
}
3)Kafka自定义Partition
发 送一条消息时,可以指定这条消息的key,producer根据这个key和partition机制来判断将这条消息发送到哪个parition。 paritition机制可以通过指定producer的paritition.class这一参数来指定,该class必须实现
kafka.producer.Partitioner
接口。本例中如果key可以被解析为整数则将对应的整数与partition总数取余,该消息会被发送到该数对应的partition。(每个parition都会有个序号)
package com.sinovatech.framework.kafka;
import kafka.producer.Partitioner;
public class KafkaPartitioner implements Partitioner {
// 解决执行报错的问题:Caused by: java.lang.NoSuchMethodException: //com.sinovatech.framework.kafka.KafkaPartitioner.<init>(kafka.utils.VerifiableProperties)
public KafkaPartitioner(VerifiableProperties props) {
}
}
public int partition(Object key, int numPartitions) {
try {
return Math.abs(Integer.parseInt((String) key) % numPartitions);
} catch (Exception e) {
return Math.abs(key.hashCode() % numPartitions);
}
}
}