Java KafkaUtils类代码示例

import org.apache.spark.streaming.kafka010.KafkaUtils; //导入依赖的package包/类
@Provides
JavaInputDStream<ConsumerRecord<String, RawRating>> providesKafkaInputStream(JavaStreamingContext streamingContext) {
    Map<String, Object> kafkaParams = new HashedMap();
    kafkaParams.put("bootstrap.servers", "localhost:9092");
    kafkaParams.put("key.deserializer", StringDeserializer.class);
    kafkaParams.put("value.deserializer", JsonDeserializer.class);
    kafkaParams.put("serializedClass", RawRating.class);
    kafkaParams.put("group.id", "rating_stream");
    kafkaParams.put("auto.offset.reset", "latest");
    kafkaParams.put("enable.auto.commit", false);
    Collection<String> topics = Arrays.asList("topicA", "topicB");

    return KafkaUtils.createDirectStream(
            streamingContext,
            LocationStrategies.PreferConsistent(),
            ConsumerStrategies.<String, RawRating>Subscribe(topics, kafkaParams)
    );
}
 

import org.apache.spark.streaming.kafka010.KafkaUtils; //导入依赖的package包/类
public static void main(String[] args) throws InterruptedException {
    Map<String, Object> kafkaParams = new HashMap<>();
    kafkaParams.put("bootstrap.servers", "localhost:9092");
    kafkaParams.put("key.deserializer", StringDeserializer.class);
    kafkaParams.put("value.deserializer", StringDeserializer.class);
    kafkaParams.put("group.id", "use_a_separate_group_id_for_each_stream");
    kafkaParams.put("auto.offset.reset", "latest");
    kafkaParams.put("enable.auto.commit", false);

    Collection<String> topics = Arrays.asList("data-in");

    SparkConf sparkConf = new SparkConf().setAppName("JavaKafkaSpark");
    JavaStreamingContext streamingContext = new JavaStreamingContext(sparkConf, Durations.seconds(5));

    final JavaInputDStream<ConsumerRecord<String, String>> stream =
            KafkaUtils.createDirectStream(
                    streamingContext,
                    LocationStrategies.PreferConsistent(),
                    ConsumerStrategies.<String, String>Subscribe(topics, kafkaParams)
            );

    JavaPairDStream<String, Integer>  countOfMessageKeys = stream
            .map((ConsumerRecord<String, String> record) -> record.key())
            .mapToPair((String s) -> new Tuple2<>(s, 1))
            .reduceByKey((Integer i1, Integer i2)-> i1 + i2);

    countOfMessageKeys.print();

    // Start the computation
    streamingContext.start();
    streamingContext.awaitTermination();
}
 

import org.apache.spark.streaming.kafka010.KafkaUtils; //导入依赖的package包/类
public static void main(String[] args) {
        SparkConf sc = new SparkConf()
                .setMaster("local[2]") // local mode with 2 threads
                .setAppName("RealtimeSpeedCalculator");

        JavaStreamingContext streamingContext = new JavaStreamingContext(sc, new Duration(60 * 1000L));

        // Kafka configuration
        Map<String, Object> kafkaParams = new HashMap();
        kafkaParams.put("bootstrap.servers", "10.128.184.199:9121");
        kafkaParams.put("key.deserializer", StringDeserializer.class);
        kafkaParams.put("value.deserializer", StringDeserializer.class);
        kafkaParams.put("group.id", 0);
        kafkaParams.put("auto.offset.reset", "latest");
        kafkaParams.put("enable.auto.commit", false);

        Collection<String> topics = Arrays.asList("topic-taxi");
        JavaInputDStream<ConsumerRecord<String, String>> stream =
                KafkaUtils.createDirectStream(
                        streamingContext,
                        LocationStrategies.PreferConsistent(),
                        ConsumerStrategies.<String, String>Subscribe(topics, kafkaParams)
                );

        stream.map(record -> {
            System.out.println("#############");
            return record.value();
        }).count();

//        streamingContext.start();
    }
 

import org.apache.spark.streaming.kafka010.KafkaUtils; //导入依赖的package包/类
/**
 *
 * @param <K>
 * @param <V>
 * @return
 */
public <K extends Object, V extends Object> JavaInputDStream<ConsumerRecord<K, V>> createDirectStream() {
  JavaInputDStream<ConsumerRecord<K, V>> directKafkaStream
      = KafkaUtils.
          createDirectStream(jsc, LocationStrategies.PreferConsistent(),
              ConsumerStrategies.Subscribe(topics, kafkaParams));
  return directKafkaStream;
}
 

import org.apache.spark.streaming.kafka010.KafkaUtils; //导入依赖的package包/类
public static void main(String[] args) {
  	//Window Specific property if Hadoop is not instaalled or HADOOP_HOME is not set
 System.setProperty("hadoop.home.dir", "E:\\hadoop");
  	//Logger rootLogger = LogManager.getRootLogger();
 		//rootLogger.setLevel(Level.WARN); 
      SparkConf conf = new SparkConf().setAppName("KafkaExample").setMaster("local[*]");    
      JavaSparkContext sc = new JavaSparkContext(conf);
      JavaStreamingContext streamingContext = new JavaStreamingContext(sc, Durations.minutes(2));
      streamingContext.checkpoint("E:\\hadoop\\checkpoint");
      Logger rootLogger = LogManager.getRootLogger();
 		rootLogger.setLevel(Level.WARN); 
      Map<String, Object> kafkaParams = new HashMap<>();
      kafkaParams.put("bootstrap.servers", "10.0.75.1:9092");
      kafkaParams.put("key.deserializer", StringDeserializer.class);
      kafkaParams.put("value.deserializer", StringDeserializer.class);
      kafkaParams.put("group.id", "use_a_separate_group_id_for_each_strea");
      kafkaParams.put("auto.offset.reset", "latest");
     // kafkaParams.put("enable.auto.commit", false);

      Collection<String> topics = Arrays.asList("mytopic", "anothertopic");

      final JavaInputDStream<ConsumerRecord<String, String>> stream = KafkaUtils.createDirectStream(streamingContext,LocationStrategies.PreferConsistent(),
      				ConsumerStrategies.<String, String>Subscribe(topics, kafkaParams));

      JavaPairDStream<String, String> pairRDD = stream.mapToPair(record-> new Tuple2<>(record.key(), record.value()));
     
      pairRDD.foreachRDD(pRDD-> { pRDD.foreach(tuple-> System.out.println(new Date()+" :: Kafka msg key ::"+tuple._1() +" the val is ::"+tuple._2()));});
     
      JavaDStream<String> tweetRDD = pairRDD.map(x-> x._2()).map(new TweetText());
      
      tweetRDD.foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" :: "+x)));
      
     JavaDStream<String> hashtagRDD = tweetRDD.flatMap(twt-> Arrays.stream(twt.split(" ")).filter(str-> str.contains("#")).collect(Collectors.toList()).iterator() );
 
      hashtagRDD.foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(x)));
      
      JavaPairDStream<String, Long> cntByVal = hashtagRDD.countByValue();
      
      cntByVal.foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" ::The count tag is ::"+x._1() +" and the val is ::"+x._2())));
      
     /* hashtagRDD.window(Durations.seconds(60), Durations.seconds(30))
                .countByValue()
               .foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" ::The window count tag is ::"+x._1() +" and the val is ::"+x._2())));
      
     hashtagRDD.countByValueAndWindow(Durations.seconds(60), Durations.seconds(30))
               .foreachRDD(tRDD -> tRDD.foreach(x->System.out.println("The window&count tag is ::"+x._1() +" and the val is ::"+x._2())));
      */
     hashtagRDD.window(Durations.minutes(8)).countByValue()
     .foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" ::The window count tag is ::"+x._1() +" and the val is ::"+x._2())));
     hashtagRDD.window(Durations.minutes(8),Durations.minutes(2)).countByValue()
     .foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" ::The window count tag is ::"+x._1() +" and the val is ::"+x._2())));
     hashtagRDD.window(Durations.minutes(12),Durations.minutes(8)).countByValue()
     .foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" ::The window count tag is ::"+x._1() +" and the val is ::"+x._2())));
     hashtagRDD.window(Durations.minutes(2),Durations.minutes(2)).countByValue()
     .foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" ::The window count tag is ::"+x._1() +" and the val is ::"+x._2())));
     hashtagRDD.window(Durations.minutes(12),Durations.minutes(12)).countByValue()
     .foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" ::The window count tag is ::"+x._1() +" and the val is ::"+x._2())));
     
     /*hashtagRDD.window(Durations.minutes(5),Durations.minutes(2)).countByValue()
     .foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" ::The window count tag is ::"+x._1() +" and the val is ::"+x._2())));*/
     /* hashtagRDD.window(Durations.minutes(10),Durations.minutes(1)).countByValue()
     .foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" ::The window count tag is ::"+x._1() +" and the val is ::"+x._2())));*/
     
      streamingContext.start();
      try {
	streamingContext.awaitTermination();
} catch (InterruptedException e) {
	// TODO Auto-generated catch block
	e.printStackTrace();
}
  }
 

import org.apache.spark.streaming.kafka010.KafkaUtils; //导入依赖的package包/类
public <K extends Object, V extends Object> JavaRDD<ConsumerRecord<K, V>> createRDD(
    JavaSparkContext jsc,
    OffsetRange[] osr, LocationStrategy ls) {
  return KafkaUtils.createRDD(jsc, kafkaParams, osr, ls);
}
 

import org.apache.spark.streaming.kafka010.KafkaUtils; //导入依赖的package包/类
public void initializeLogIfNecessary(boolean init) {
  KafkaUtils.initializeLogIfNecessary(init);
}
 

import org.apache.spark.streaming.kafka010.KafkaUtils; //导入依赖的package包/类
public boolean isTraceEnabled() {
  return KafkaUtils.isTraceEnabled();
}
 

import org.apache.spark.streaming.kafka010.KafkaUtils; //导入依赖的package包/类
public Logger log() {
  return KafkaUtils.log();
}
 

import org.apache.spark.streaming.kafka010.KafkaUtils; //导入依赖的package包/类
public String logName() {
  return KafkaUtils.logName();
}
 

import org.apache.spark.streaming.kafka010.KafkaUtils; //导入依赖的package包/类
public void logDebug(Function0<String> fun) {
  KafkaUtils.logDebug(fun);
}
 

import org.apache.spark.streaming.kafka010.KafkaUtils; //导入依赖的package包/类
public void logError(Function0<String> fun) {
  KafkaUtils.logError(fun);
}
 

import org.apache.spark.streaming.kafka010.KafkaUtils; //导入依赖的package包/类
public void logInfo(Function0<String> fun) {
  KafkaUtils.logInfo(fun);
}
 

import org.apache.spark.streaming.kafka010.KafkaUtils; //导入依赖的package包/类
public void logTrace(Function0<String> fun) {
  KafkaUtils.logTrace(fun);
}
 

import org.apache.spark.streaming.kafka010.KafkaUtils; //导入依赖的package包/类
public void logWarning(Function0<String> fun) {
  KafkaUtils.logWarning(fun);
}