我的kafka JAVA调试代码

仅供自己参考，别人可能看不懂。

kafka 是很好的供所有分析库从生产库多次提取数据的中转库，特别是kafka 0.9后出现的kafka connect，个人认为能作为实时的ETL工具。

另外，kafka和storm都是流，但kafka不处理数据，storm可在kafka的基础上处理数据。storm在原理上和hadoop的mapreduce差不多，都有map reduce的过程，只是hadoop处理完一次MR后，就会结束，但storm不会结束，除非手动kill。这篇介绍storm的文章不错： http://os.51cto.com/art/201308/408739.htm

个人认为，对于每次都是处理结构化数据的工作，可以不用storm。

下面是kafka的java调试程序，含json处理。

/**
 * Created by hadoop on 16-6-21.
 */
import java.io.IOException;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.Properties;

import com.fasterxml.jackson.databind.ObjectMapper;
import kafka.consumer.ConsumerConfig;
import kafka.consumer.ConsumerIterator;
import kafka.consumer.KafkaStream;
import kafka.javaapi.consumer.ConsumerConnector;
import kafka.serializer.StringDecoder;
import kafka.utils.VerifiableProperties;
public class ceshi {

    private final ConsumerConnector consumer;

    private ceshi() {
        Properties props = new Properties();
        //zookeeper 配置
        props.put("zookeeper.connect", "192.168.3.31:2181");

        //group 代表一个消费组
        props.put("group.id", "jd-group");

        //zk连接超时
        props.put("zookeeper.session.timeout.ms", "4000");
        props.put("zookeeper.sync.time.ms", "200");
        props.put("auto.commit.interval.ms", "1000");
        props.put("auto.offset.reset", "smallest");
        //序列化类
        props.put("serializer.class", "kafka.serializer.StringEncoder");

        ConsumerConfig config = new ConsumerConfig(props);

        consumer = kafka.consumer.Consumer.createJavaConsumerConnector(config);
    }

    void consume() {
        Map<String, Integer> topicCountMap = new HashMap<String, Integer>();
        topicCountMap.put("test1", new Integer(1));

        StringDecoder keyDecoder = new StringDecoder(new VerifiableProperties());
        StringDecoder valueDecoder = new StringDecoder(new VerifiableProperties());

        Map<String, List<KafkaStream<String, String>>> consumerMap =
                consumer.createMessageStreams(topicCountMap,keyDecoder,valueDecoder);
        KafkaStream<String, String> stream = consumerMap.get("test1").get(0);
        ConsumerIterator<String, String> iterator = stream.iterator();
        Map<String,Map<String,Object>> maps;

        while (iterator.hasNext()) {
            //System.out.println(iterator.next().message());
            try {
                maps=new ObjectMapper().readValue(iterator.next().message(), Map.class);
                System.out.println( (Object)(maps.get("xm")) );
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }

    public static void main(String[] args) {
        // TODO Auto-generated method stub
        //System.out.println("请输入一个正整");
        new ceshi().consume();
    }

}