kafka Java实例

import java.util.*;

import kafka.javaapi.producer.Producer;
import kafka.producer.KeyedMessage;
import kafka.producer.Partitioner;
import kafka.producer.ProducerConfig;
import kafka.utils.VerifiableProperties;

public class TestProducer {
     class SimplePartitioner implements Partitioner {
        public SimplePartitioner (VerifiableProperties props) {

        }

        public int partition(Object key, int a_numPartitions) {
            int partition = 0;
            String stringKey = (String) key;
            int offset = stringKey.lastIndexOf('.');
            if (offset > 0) {
                partition = Integer.parseInt( stringKey.substring(offset+1)) % a_numPartitions;
            }
            return partition;
        }

    }
    public static void main(String[] args) {
        long events =30;
        Random rnd = new Random();

        Properties props = new Properties();
        props.put("metadata.broker.list", "kafka1:9092,kafka2:9092,kafka3:9092");
        props.put("serializer.class", "kafka.serializer.StringEncoder");
        props.put("partitioner.class", "com.xf.kafa.TestProducer.SimplePartitioner");
        props.put("request.required.acks", "1");

        ProducerConfig config = new ProducerConfig(props);
        //The first is the type of the Partition key, the second the type of the message.
        Producer<String, String> producer = new Producer<String, String>(config);

        for (long nEvents = 0; nEvents < events; nEvents++) {
            long runtime = new Date().getTime();
            String ip = "192.168.2." + rnd.nextInt(255);
            String msg = runtime + ",www.example.com," + ip;
            //参数分别为topic，IP as the partition key，msg为消息
            KeyedMessage<String, String> data = new KeyedMessage<String, String>("page_visits", ip, msg);
            producer.send(data);
        }
        producer.close();
    }
}

public class ConsumerGroupExample {
    private final ConsumerConnector consumer;
    private final String topic;
    private ExecutorService executor;

    class ConsumerTest implements Runnable {
        private KafkaStream m_stream;
        //标识线程名称，可以使用Thread.getCurrentTreandName()代替
        private int m_threadNumber;

        public ConsumerTest(KafkaStream a_stream, int a_threadNumber) {
            m_threadNumber = a_threadNumber;
            m_stream = a_stream;
        }

        public void run() {
            ConsumerIterator<byte[], byte[]> it = m_stream.iterator();
            //有趣的是 while (it.hasNext())部分. 基于此处会不停的读取topic的信息，除非你停止它。
            while (it.hasNext())
                System.out.println("Thread " + m_threadNumber + ": " + new String(it.next().message()));
            System.out.println("Shutting down Thread: " + m_threadNumber);
        }
    }

    public ConsumerGroupExample(String a_zookeeper, String a_groupId, String a_topic) {
        consumer = kafka.consumer.Consumer.createJavaConsumerConnector(
                createConsumerConfig(a_zookeeper, a_groupId));
        this.topic = a_topic;
    }

    public void shutdown() {
        if (consumer != null) consumer.shutdown();
        if (executor != null) executor.shutdown();
        try {
            if (!executor.awaitTermination(5000, TimeUnit.MILLISECONDS)) {
                System.out.println("Timed out waiting for consumer threads to shut down, exiting uncleanly");
            }
        } catch (InterruptedException e) {
            System.out.println("Interrupted during shutdown, exiting uncleanly");
        }
    }

    public void run(int a_numThreads) {
        /**
         * First we create a Map that tells Kafka how many threads we are providing for which topics.
         * The consumer.createMessageStreams is how we pass this information to Kafka.
         * The return is a map of KafkaStream to listen on for each topic.
         * (Note here we only asked Kafka for a single Topic but we could have asked for multiple by
         * adding another element to the Map.)
         Finally we create the thread pool and pass a new ConsumerTest object to each thread as our business logic.
         */

        //首先我们创建一个map，map能告诉kafka我们为每个topic启动多少个线程
        Map<String, Integer> topicCountMap = new HashMap<String, Integer>();
        topicCountMap.put(topic, new Integer(a_numThreads));
        //consumer.createMessageStreams是我们把信息传递给kafka的方式，返回的是 a map of KafkaStream，来监听每个topic
        //注意在这我们仅仅向kafka请求一个topic，但是我们可以通过向map添加另外一个元素来请求多个topic
        Map<String, List<KafkaStream<byte[], byte[]>>> consumerMap = consumer.createMessageStreams(topicCountMap);
        List<KafkaStream<byte[], byte[]>> streams = consumerMap.get(topic);

        // now launch all the threads
        executor = Executors.newFixedThreadPool(a_numThreads);

        // now create an object to consume the messages
        int threadNumber = 0;
        for (final KafkaStream stream : streams) {
            //最后我们创建线程池，并且传递ConsumerTest线程给线程池
            executor.submit(new ConsumerTest(stream, threadNumber));
            threadNumber++;
        }
    }

    private static ConsumerConfig createConsumerConfig(String a_zookeeper, String a_groupId) {
        Properties props = new Properties();
        props.put("zookeeper.connect", a_zookeeper);
        props.put("group.id", a_groupId);
        props.put("zookeeper.session.timeout.ms", "400");
        props.put("zookeeper.sync.time.ms", "200");
        props.put("auto.commit.interval.ms", "1000");

        return new ConsumerConfig(props);
    }

    public static void main(String[] args) {
        String zooKeeper = "192.168.8.121:2181,192.168.8.122:2181,192.168.8.123:2181";
        String groupId = "test";
        String topic = "page_visits";
        int threads = 1;

        ConsumerGroupExample example = new ConsumerGroupExample(zooKeeper, groupId, topic);
        example.run(threads);

        try {
            Thread.sleep(1000000);
        } catch (InterruptedException ie) {

        }
        example.shutdown();
    }
}