kafka 在java中的使用

kafka  Producer  Api

Procuder API有两种：kafka.producer.SyncProducer和kafka.producer.async.AsyncProducer.它们都实现了同一个接口：

class Producer {
　　/* 将消息发送到指定分区 */
　　publicvoid send(kafka.javaapi.producer.ProducerData<K,V> producerData);

　　/* 批量发送一批消息 */
　　publicvoid send(java.util.List<kafka.javaapi.producer.ProducerData<K,V>> producerData);

　　/* 关闭producer */
　　publicvoid close();
}

Producer API提供了以下功能：

• 可以将多个消息缓存到本地队列里，然后异步的批量发送到broker，可以通过参数producer.type=async做到。缓存的大小可以通过一些参数指定：queue.time和batch.size。一个后台线程（(kafka.producer.async.ProducerSendThread）从队列中取出数据并让kafka.producer.EventHandler将消息发送到broker，也可以通过参数event.handler定制handler，在producer端处理数据的不同的阶段注册处理器，比如可以对这一过程进行日志追踪，或进行一些监控。只需实现kafka.producer.async.CallbackHandler接口，并在callback.handler中配置。
• 自己编写Encoder来序列化消息，只需实现下面这个接口。默认的Encoder是kafka.serializer.DefaultEncoder。
  
  • interface Encoder<T> {
  • public Message toMessage(T data);
  • }
• 提供了基于Zookeeper的broker自动感知能力，可以通过参数zk.connect实现。如果不使用Zookeeper，也可以使用broker.list参数指定一个静态的brokers列表，这样消息将被随机的发送到一个broker上，一旦选中的broker失败了，消息发送也就失败了。
• 通过分区函数kafka.producer.Partitioner类对消息分区。
  
  • interface Partitioner<T> {
  • int partition(T key, int numPartitions);
  • }
  
  分区函数有两个参数：key和可用的分区数量，从分区列表中选择一个分区并返回id。默认的分区策略是hash(key)%numPartitions.如果key是null,就随机的选择一个。可以通过参数partitioner.class定制分区函数。

import java.util.*;

import kafka.javaapi.producer.Producer;
import kafka.producer.KeyedMessage;
import kafka.producer.ProducerConfig;


public class ASyncProduce {
    public static void main(String[] args) {
        Properties props = new Properties();
        props.put("metadata.broker.list", "192.168.1.1:19092,192.168.1.2:19092,192.168.1.3:19092");
        props.put("serializer.class", "kafka.serializer.StringEncoder");//kafka.serializer.DefaultEncoder
        props.put("partitioner.class", "kafka.producer.partiton.SimplePartitioner");
        //kafka.producer.DefaultPartitioner: based on the hash of the key
        //props.put("request.required.acks", "1");
        props.put("producer.type", "async");//1: async 2: sync
        //props.put("producer.type", "1");
        // 1: async 2: sync
 
        ProducerConfig config = new ProducerConfig(props);
 
        Producer<String, String> producer = new Producer<String, String>(config);
 
        for (int i = 0; i < Integer.MAX_VALUE; i++) { 
               long runtime = new Date().getTime();  
               String ip = "192.168.2.1"; 
               String msg = "message"; 
               KeyedMessage<String, String> data = new KeyedMessage<String, String>("topic", ip, msg);
               producer.send(data);
               try {
                   Thread.sleep(1000);
               } catch (InterruptedException e) {
                   e.printStackTrace();
               }
        }
        producer.close();
    }
}

import kafka.javaapi.producer.Producer;
import kafka.producer.KeyedMessage;
import kafka.producer.ProducerConfig;

public class SyncProduce {
    public static void main(String[] args) {
 
        Properties props = new Properties();
        props.put("metadata.broker.list", "192.168.1.1:19092,192.168.1.2:19092,192.168.1.3:19092");
        props.put("serializer.class", "kafka.serializer.StringEncoder");
        //kafka.serializer.DefaultEncoder
        props.put("partitioner.class", "kafka.producer.partiton.SimplePartitioner");
        //kafka.producer.DefaultPartitioner: based on the hash of the key
        props.put("request.required.acks", "1");
        //0;  绝不等确认  1:   leader的一个副本收到这条消息，并发回确认 -1：   leader的所有副本都收到这条消息，并发回确认
 
        ProducerConfig config = new ProducerConfig(props);
 
        Producer<String, String> producer = new Producer<String, String>(config);
 
        for (int i = 0; i < Integer.MAX_VALUE; i++) { 
               String ip = "192.168.2.1"; 
               String msg = "message"; 
               //eventKey必须有（即使自己的分区算法不会用到这个key，也不能设为null或者""）,否者自己的分区算法根本得不到调用
               KeyedMessage<String, String> data = new KeyedMessage<String, String>("topic", ip, msg);
               producer.send(data);
               try {
                   Thread.sleep(1000);
               } catch (InterruptedException ie) {
               }
        }
        producer.close();
    }
}

KafKa Consumer APIs

Consumer API有两个级别。低级别的和一个指定的broker保持连接，并在接收完消息后关闭连接，这个级别是无状态的，每次读取消息都带着offset。
高级别的API隐藏了和brokers连接的细节，在不必关心服务端架构的情况下和服务端通信。还可以自己维护消费状态，并可以通过一些条件指定订阅特定的topic,比如白名单黑名单或者正则表达式。

import kafka.api.FetchRequest;
import kafka.api.FetchRequestBuilder;
import kafka.api.PartitionOffsetRequestInfo;
import kafka.common.ErrorMapping;
import kafka.common.TopicAndPartition;
import kafka.javaapi.*;
import kafka.javaapi.consumer.SimpleConsumer;
import kafka.message.MessageAndOffset;
 
import java.nio.ByteBuffer;
import java.util.ArrayList;
import java.util.Collections;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

public class PartitionConsumerTest {
    
    public static void main(String args[]) {
        PartitionConsumerTest example = new PartitionConsumerTest();
        long maxReads = Long.MAX_VALUE;
        String topic = "topic";
        if(args.length < 1){
            System.out.println("Please assign partition number.");
        }
        
        List<String> seeds = new ArrayList<String>();
        seeds.add("192.168.2.1");
        seeds.add("192.168.2.2");
        seeds.add("192.168.2.3");
        
        int port = 19092;
         
        int partLen = Integer.parseInt(args[0]);
        for(int index=0;index < partLen;index++){
            try {
                example.run(maxReads, topic, index/*partition*/, seeds, port);
            } catch (Exception e) {
                System.out.println("Oops:" + e);
                 e.printStackTrace();
            }
        }
    }
    
    private List<String> m_replicaBrokers = new ArrayList<String>();
     
    public PartitionConsumerTest() {
        m_replicaBrokers = new ArrayList<String>();
    }
 
    public void run(long a_maxReads, String a_topic, int a_partition, List<String> a_seedBrokers, int a_port) throws Exception {

        PartitionMetadata metadata = findLeader(a_seedBrokers, a_port, a_topic, a_partition);
        if (metadata == null) {
            System.out.println("Can't find metadata for Topic and Partition. Exiting");
            return;
        }
        if (metadata.leader() == null) {
            System.out.println("Can't find Leader for Topic and Partition. Exiting");
            return;
        }
        String leadBroker = metadata.leader().host();
        String clientName = "Client_" + a_topic + "_" + a_partition;
 
        SimpleConsumer consumer = new SimpleConsumer(leadBroker, a_port, 100000, 64 * 1024, clientName);
        long readOffset = getLastOffset(consumer,a_topic, a_partition, kafka.api.OffsetRequest.EarliestTime(), clientName);
 
        int numErrors = 0;
        while (a_maxReads > 0) {
            if (consumer == null) {
                consumer = new SimpleConsumer(leadBroker, a_port, 100000, 64 * 1024, clientName);
            }
            FetchRequest req = new FetchRequestBuilder()
                    .clientId(clientName)
                    .addFetch(a_topic, a_partition, readOffset, 100000) // Note: this fetchSize of 100000 might need to be increased if large batches are written to Kafka
                    .build();
            FetchResponse fetchResponse = consumer.fetch(req);
 
            if (fetchResponse.hasError()) {
                numErrors++;
                // Something went wrong!
                short code = fetchResponse.errorCode(a_topic, a_partition);
                System.out.println("Error fetching data from the Broker:" + leadBroker + " Reason: " + code);
                if (numErrors > 5) break;
                if (code == ErrorMapping.OffsetOutOfRangeCode())  {
                    // We asked for an invalid offset. For simple case ask for the last element to reset
                    readOffset = getLastOffset(consumer,a_topic, a_partition, kafka.api.OffsetRequest.LatestTime(), clientName);
                    continue;
                }
                consumer.close();
                consumer = null;
                leadBroker = findNewLeader(leadBroker, a_topic, a_partition, a_port);
                continue;
            }
            numErrors = 0;
 
            long numRead = 0;
            for (MessageAndOffset messageAndOffset : fetchResponse.messageSet(a_topic, a_partition)) {
                long currentOffset = messageAndOffset.offset();
                if (currentOffset < readOffset) {
                    System.out.println("Found an old offset: " + currentOffset + " Expecting: " + readOffset);
                    continue;
                }
                readOffset = messageAndOffset.nextOffset();
                ByteBuffer payload = messageAndOffset.message().payload();
 
                byte[] bytes = new byte[payload.limit()];
                payload.get(bytes);
                System.out.println(String.valueOf(messageAndOffset.offset()) + ": " + new String(bytes, "UTF-8"));
                numRead++;
                a_maxReads--;
            }
 
            if (numRead == 0) {
                try {
                    Thread.sleep(1000);
                } catch (InterruptedException ie) {
                }
            }
        }
        if (consumer != null) consumer.close();
    }
 
    public static long getLastOffset(SimpleConsumer consumer, String topic, int partition,
                                     long whichTime, String clientName) {
        TopicAndPartition topicAndPartition = new TopicAndPartition(topic, partition);
        Map<TopicAndPartition, PartitionOffsetRequestInfo> requestInfo = new HashMap<TopicAndPartition, PartitionOffsetRequestInfo>();
        requestInfo.put(topicAndPartition, new PartitionOffsetRequestInfo(whichTime, 1));
        kafka.javaapi.OffsetRequest request = new kafka.javaapi.OffsetRequest(
                requestInfo, kafka.api.OffsetRequest.CurrentVersion(), clientName);
        OffsetResponse response = consumer.getOffsetsBefore(request);
 
        if (response.hasError()) {
            System.out.println("Error fetching data Offset Data the Broker. Reason: " + response.errorCode(topic, partition) );
            return 0;
        }
        long[] offsets = response.offsets(topic, partition);
        return offsets[0];
    }
 
    private String findNewLeader(String a_oldLeader, String a_topic, int a_partition, int a_port) throws Exception {
        for (int i = 0; i < 3; i++) {
            boolean goToSleep = false;
            PartitionMetadata metadata = findLeader(m_replicaBrokers, a_port, a_topic, a_partition);
            if (metadata == null) {
                goToSleep = true;
            } else if (metadata.leader() == null) {
                goToSleep = true;
            } else if (a_oldLeader.equalsIgnoreCase(metadata.leader().host()) && i == 0) {
                // first time through if the leader hasn't changed give ZooKeeper a second to recover
                // second time, assume the broker did recover before failover, or it was a non-Broker issue
                //
                goToSleep = true;
            } else {
                return metadata.leader().host();
            }
            if (goToSleep) {
                try {
                    Thread.sleep(1000);
                } catch (InterruptedException ie) {
                }
            }
        }
        System.out.println("Unable to find new leader after Broker failure. Exiting");
        throw new Exception("Unable to find new leader after Broker failure. Exiting");
    }
 
    private PartitionMetadata findLeader(List<String> a_seedBrokers, int a_port, String a_topic, int a_partition) {
        PartitionMetadata returnMetaData = null;
        loop:
        for (String seed : a_seedBrokers) {
            SimpleConsumer consumer = null;
            try {
                consumer = new SimpleConsumer(seed, a_port, 100000, 64 * 1024, "leaderLookup");
                List<String> topics = Collections.singletonList(a_topic);
                TopicMetadataRequest req = new TopicMetadataRequest(topics);
                kafka.javaapi.TopicMetadataResponse resp = consumer.send(req);
 
                List<TopicMetadata> metaData = resp.topicsMetadata();
                for (TopicMetadata item : metaData) {
                    for (PartitionMetadata part : item.partitionsMetadata()) {
                        if (part.partitionId() == a_partition) {
                            returnMetaData = part;
                            break loop;
                        }
                    }
                }
            } catch (Exception e) {
                System.out.println("Error communicating with Broker [" + seed + "] to find Leader for [" + a_topic
                        + ", " + a_partition + "] Reason: " + e);
            } finally {
                if (consumer != null) consumer.close();
            }
        }
        if (returnMetaData != null) {
            m_replicaBrokers.clear();
            for (kafka.cluster.Broker replica : returnMetaData.replicas()) {
                m_replicaBrokers.add(replica.host());
            }
        }
        return returnMetaData;
    }
}

import kafka.consumer.ConsumerConfig;
import kafka.consumer.KafkaStream;
import kafka.javaapi.consumer.ConsumerConnector;
 
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.Properties;
import java.util.concurrent.ExecutorService;
import java.util.concurrent.Executors;
import java.util.concurrent.TimeUnit;

public class GroupConsumerTest extends Thread {
    private final ConsumerConnector consumer;
    private final String topic;
    private  ExecutorService executor;
    
    public GroupConsumerTest(String zookeeper, String groupId, String topic){
        consumer = kafka.consumer.Consumer.createJavaConsumerConnector(createConsumerConfig(zookeeper, groupId));
        this.topic = topic;
    }
    
    public void shutdown() {
        if (consumer != null) consumer.shutdown();
        if (executor != null) executor.shutdown();
        try {
            if (!executor.awaitTermination(Long.MAX_VALUE, 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) {
        Map<String, Integer> topicCountMap = new HashMap<String, Integer>();
        topicCountMap.put(topic, new Integer(a_numThreads));
        Map<String, List<KafkaStream<byte[], byte[]>>> consumerMap = consumer.createMessageStreams(topicCountMap);
        List<KafkaStream<byte[], byte[]>> streams = consumerMap.get(topic);
 
        executor = Executors.newFixedThreadPool(a_numThreads);
 
        int threadNumber = 0;
        for (final KafkaStream stream : streams) {
            executor.submit(new ConsumerTest(stream, threadNumber));
            threadNumber++;
        }
    }
    
    private static ConsumerConfig createConsumerConfig(String zookeeper, StringgroupId) {
        Properties props = new Properties();
        props.put("zookeeper.connect", zookeeper);
        props.put("group.id", groupId);
        props.put("zookeeper.session.timeout.ms", "40000");
        props.put("zookeeper.sync.time.ms", "2000");
        props.put("auto.commit.interval.ms", "1000");
        return new ConsumerConfig(props);
    }
    
    public static void main(String[] args) {
        if(args.length < 1){
            System.out.println("Please assign partition number.");
        }
        
        String zooKeeper = "192.168.1.1:12181,192.168.1.1:12181,192.168.1.1:12181";
        String groupId = "grouptest";
        String topic = "topic";
        int threads = Integer.parseInt(args[0]);
 
        GroupConsumerTest example = new GroupConsumerTest(zooKeeper, groupId, topic);
        example.run(threads);
 
        try {
            Thread.sleep(Long.MAX_VALUE);
        } catch (InterruptedException ie) {
 
        }
        example.shutdown();
    }
}

参考：https://blog.csdn.net/tangdong3415/article/details/53432166