Java Code Examples for org.apache.spark.streaming.api.java.JavaReceiverInputDStream#flatMap()

public static void main(String[] args) throws Exception {
  
      System.setProperty("hadoop.home.dir", "E:\\hadoop");
	
   SparkConf sparkConf = new SparkConf().setAppName("WordCountSocketEx").setMaster("local[*]");
   JavaStreamingContext streamingContext = new JavaStreamingContext(sparkConf, Durations.seconds(1));
   Logger rootLogger = LogManager.getRootLogger();
 		rootLogger.setLevel(Level.WARN); 
   List<Tuple2<String, Integer>> tuples = Arrays.asList(new Tuple2<>("hello", 10), new Tuple2<>("world", 10));
   JavaPairRDD<String, Integer> initialRDD = streamingContext.sparkContext().parallelizePairs(tuples);
	    

   JavaReceiverInputDStream<String> StreamingLines = streamingContext.socketTextStream( "10.0.75.1", Integer.parseInt("9000"), StorageLevels.MEMORY_AND_DISK_SER);
   
   JavaDStream<String> words = StreamingLines.flatMap( str -> Arrays.asList(str.split(" ")).iterator() );
  
   JavaPairDStream<String, Integer> wordCounts = words.mapToPair(str-> new Tuple2<>(str, 1)).reduceByKey((count1,count2) ->count1+count2 );
  
   wordCounts.print();
   
JavaPairDStream<String, Integer> joinedDstream = wordCounts
		.transformToPair(new Function<JavaPairRDD<String, Integer>, JavaPairRDD<String, Integer>>() {
			@Override
			public JavaPairRDD<String, Integer> call(JavaPairRDD<String, Integer> rdd) throws Exception {
				JavaPairRDD<String, Integer> modRDD = rdd.join(initialRDD).mapToPair(
						new PairFunction<Tuple2<String, Tuple2<Integer, Integer>>, String, Integer>() {
							@Override
							public Tuple2<String, Integer> call(
									Tuple2<String, Tuple2<Integer, Integer>> joinedTuple) throws Exception {
								return new Tuple2<>(joinedTuple._1(),(joinedTuple._2()._1() + joinedTuple._2()._2()));
							}
						});
				return modRDD;
			}
		});

   joinedDstream.print();
   streamingContext.start();
   streamingContext.awaitTermination();
 }
 

public static void main(String[] args) throws Exception {
 System.setProperty("hadoop.home.dir", "E:\\hadoop");

   SparkConf sparkConf = new SparkConf().setAppName("WordCountSocketEx").setMaster("local[*]");
   JavaStreamingContext streamingContext = new JavaStreamingContext(sparkConf, Durations.seconds(1));
   streamingContext.checkpoint("E:\\hadoop\\checkpoint");
// Initial state RDD input to mapWithState
   @SuppressWarnings("unchecked")
   List<Tuple2<String, Integer>> tuples =Arrays.asList(new Tuple2<>("hello", 1), new Tuple2<>("world", 1));
   JavaPairRDD<String, Integer> initialRDD = streamingContext.sparkContext().parallelizePairs(tuples);
   
   JavaReceiverInputDStream<String> StreamingLines = streamingContext.socketTextStream( "10.0.75.1", Integer.parseInt("9000"), StorageLevels.MEMORY_AND_DISK_SER);
   
   JavaDStream<String> words = StreamingLines.flatMap( str -> Arrays.asList(str.split(" ")).iterator() );
  
   JavaPairDStream<String, Integer> wordCounts = words.mapToPair(str-> new Tuple2<>(str, 1)).reduceByKey((count1,count2) ->count1+count2 );
  


  // Update the cumulative count function
  Function3<String, Optional<Integer>, State<Integer>, Tuple2<String, Integer>> mappingFunc =
      new Function3<String, Optional<Integer>, State<Integer>, Tuple2<String, Integer>>() {
        @Override
        public Tuple2<String, Integer> call(String word, Optional<Integer> one,
            State<Integer> state) {
          int sum = one.orElse(0) + (state.exists() ? state.get() : 0);
          Tuple2<String, Integer> output = new Tuple2<>(word, sum);
          state.update(sum);
          return output;
        }
      };

  // DStream made of get cumulative counts that get updated in every batch
  JavaMapWithStateDStream<String, Integer, Integer, Tuple2<String, Integer>> stateDstream = wordCounts.mapWithState(StateSpec.function(mappingFunc).initialState(initialRDD));

  stateDstream.print();
  streamingContext.start();
  streamingContext.awaitTermination();
}
 

public static void main(String[] args) throws Exception {
 
     System.setProperty("hadoop.home.dir", "E:\\hadoop");
	
  SparkConf sparkConf = new SparkConf().setAppName("WordCountSocketEx").setMaster("local[*]");
  JavaStreamingContext streamingContext = new JavaStreamingContext(sparkConf, Durations.seconds(1));
  
  List<Tuple2<String, Integer>> tuples = Arrays.asList(new Tuple2<>("hello", 10), new Tuple2<>("world", 10));
  JavaPairRDD<String, Integer> initialRDD = streamingContext.sparkContext().parallelizePairs(tuples);
    

  JavaReceiverInputDStream<String> StreamingLines = streamingContext.socketTextStream( "10.0.75.1", Integer.parseInt("9000"), StorageLevels.MEMORY_AND_DISK_SER);
  
  JavaDStream<String> words = StreamingLines.flatMap( str -> Arrays.asList(str.split(" ")).iterator() );
 
  JavaPairDStream<String, Integer> wordCounts = words.mapToPair(str-> new Tuple2<>(str, 1)).reduceByKey((count1,count2) ->count1+count2 );
 
  wordCounts.print();
  
JavaPairDStream<String, Integer> joinedDstream = wordCounts.transformToPair(
   new Function<JavaPairRDD<String, Integer>, JavaPairRDD<String, Integer>>() {
	    @Override public JavaPairRDD<String, Integer> call(JavaPairRDD<String, Integer> rdd) throws Exception {
	    	rdd.join(initialRDD).mapToPair(new PairFunction<Tuple2<String,Tuple2<Integer,Integer>>, String, Integer>() {
				@Override
				public Tuple2<String, Integer> call(Tuple2<String, Tuple2<Integer, Integer>> joinedTuple)
						throws Exception {
					// TODO Auto-generated method stub
					return new Tuple2<>( joinedTuple._1(), (joinedTuple._2()._1()+joinedTuple._2()._2()) );
				}
			});
		
		return rdd; 				     
	    }
	  });
 
joinedDstream.print();
  streamingContext.start();
  streamingContext.awaitTermination();
}
 

protected static JavaStreamingContext createContext(String ip, int port, String checkpointDirectory) {
	SparkConf sparkConf = new SparkConf().setAppName("WordCountRecoverableEx").setMaster("local[*]");
	JavaStreamingContext streamingContext = new JavaStreamingContext(sparkConf, Durations.seconds(1));
	streamingContext.checkpoint(checkpointDirectory);
	// Initial state RDD input to mapWithState
	@SuppressWarnings("unchecked")
	List<Tuple2<String, Integer>> tuples = Arrays.asList(new Tuple2<>("hello", 1), new Tuple2<>("world", 1));
	JavaPairRDD<String, Integer> initialRDD = streamingContext.sparkContext().parallelizePairs(tuples);

	JavaReceiverInputDStream<String> StreamingLines = streamingContext.socketTextStream(ip,port, StorageLevels.MEMORY_AND_DISK_SER);

	JavaDStream<String> words = StreamingLines.flatMap(str -> Arrays.asList(str.split(" ")).iterator());

	JavaPairDStream<String, Integer> wordCounts = words.mapToPair(str -> new Tuple2<>(str, 1))
			.reduceByKey((count1, count2) -> count1 + count2);

	// Update the cumulative count function
	Function3<String, Optional<Integer>, State<Integer>, Tuple2<String, Integer>> mappingFunc = new Function3<String, Optional<Integer>, State<Integer>, Tuple2<String, Integer>>() {
		@Override
		public Tuple2<String, Integer> call(String word, Optional<Integer> one, State<Integer> state) {
			int sum = one.orElse(0) + (state.exists() ? state.get() : 0);
			Tuple2<String, Integer> output = new Tuple2<>(word, sum);
			state.update(sum);
			return output;
		}
	};

	// DStream made of get cumulative counts that get updated in every batch
	JavaMapWithStateDStream<String, Integer, Integer, Tuple2<String, Integer>> stateDstream = wordCounts
			.mapWithState(StateSpec.function(mappingFunc).initialState(initialRDD));

	stateDstream.print();
	return streamingContext;
}
 

public static void main(String[] args) throws Exception {
  if (args.length < 2) {
    System.err.println("Usage: JavaCustomReceiver <hostname> <port>");
    System.exit(1);
  }

  StreamingExamples.setStreamingLogLevels();

  // Create the context with a 1 second batch size
  SparkConf sparkConf = new SparkConf().setAppName("JavaCustomReceiver");
  JavaStreamingContext ssc = new JavaStreamingContext(sparkConf, new Duration(1000));

  // Create an input stream with the custom receiver on target ip:port and count the
  // words in input stream of \n delimited text (eg. generated by 'nc')
  JavaReceiverInputDStream<String> lines = ssc.receiverStream(
    new JavaCustomReceiver(args[0], Integer.parseInt(args[1])));
  JavaDStream<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
    @Override
    public Iterator<String> call(String x) {
      return Arrays.asList(SPACE.split(x)).iterator();
    }
  });
  JavaPairDStream<String, Integer> wordCounts = words.mapToPair(
    new PairFunction<String, String, Integer>() {
      @Override public Tuple2<String, Integer> call(String s) {
        return new Tuple2<>(s, 1);
      }
    }).reduceByKey(new Function2<Integer, Integer, Integer>() {
      @Override
      public Integer call(Integer i1, Integer i2) {
        return i1 + i2;
      }
    });

  wordCounts.print();
  ssc.start();
  ssc.awaitTermination();
}
 

public static void main(String[] args) {
    SparkConf sparkConf = new SparkConf().setMaster("local[2]").setAppName("StateLess");

    JavaStreamingContext streamingContext = new JavaStreamingContext(sparkConf, Durations.seconds(1));

    JavaReceiverInputDStream<String> inputDStream = streamingContext.socketTextStream("localhost", 8080);

    JavaDStream<String> dStream = inputDStream.flatMap((FlatMapFunction<String, String>) s -> Arrays.asList(SPACE.split(s)).iterator());

    JavaPairDStream<String, Integer> pairDStream = dStream.mapToPair(new LogTuple());

    JavaPairDStream<String, Integer> result = pairDStream.reduceByKey(new ReduceIsKey());

    //JOIN
    JavaPairDStream<String, Integer> pairDStream1 = dStream.mapToPair(new LogTuple());

    JavaPairDStream<String, Integer> result1 = pairDStream.reduceByKey(new ReduceIsKey());

    JavaPairDStream<String, Tuple2<Integer, Integer>> c = result.join(result);


    result.foreachRDD(rdd -> {
        rdd.foreachPartition(partitionOfRecords -> {
            Connection connection = ConnectionPool.getConnection();
            Tuple2<String, Integer> wordCount;
            while (partitionOfRecords.hasNext()) {
                wordCount = partitionOfRecords.next();
                String sql = "insert into wordcount(word,count) " + "values('" + wordCount._1 + "',"
                        + wordCount._2 + ")";
                Statement stmt = connection.createStatement();
                stmt.executeUpdate(sql);
            }
            ConnectionPool.returnConnection(connection);
        });
    });

    try {
        streamingContext.start();
        streamingContext.awaitTermination();
        streamingContext.close();
    } catch (InterruptedException e) {
        e.printStackTrace();
    }

}
 

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); 
  		
  	 List<Tuple2<String, Integer>> tuples = Arrays.asList(new Tuple2<>("hello", 10), new Tuple2<>("world", 10));
    JavaPairRDD<String, Integer> initialRDD = streamingContext.sparkContext().parallelizePairs(tuples);
		    

    JavaReceiverInputDStream<String> StreamingLines = streamingContext.socketTextStream( "10.0.75.1", Integer.parseInt("9000"), StorageLevels.MEMORY_AND_DISK_SER);
    
    JavaDStream<String> words = StreamingLines.flatMap( str -> Arrays.asList(str.split(" ")).iterator() );
   
    JavaPairDStream<String, Integer> wordCounts = words.mapToPair(str-> new Tuple2<>(str, 1)).reduceByKey((count1,count2) ->count1+count2 );
   
    wordCounts.print();
    wordCounts.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())));
    wordCounts.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())));
    wordCounts.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())));
    wordCounts.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())));
    wordCounts.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())));
      
    //comment these two operation to make it run
    wordCounts.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())));
    wordCounts.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();
	}
}
 

private static JavaStreamingContext createContext(String ip,
                                                  int port,
                                                  String checkpointDirectory,
                                                  String outputPath) {

  // If you do not see this printed, that means the StreamingContext has been loaded
  // from the new checkpoint
  System.out.println("Creating new context");
  final File outputFile = new File(outputPath);
  if (outputFile.exists()) {
    outputFile.delete();
  }
  SparkConf sparkConf = new SparkConf().setAppName("JavaRecoverableNetworkWordCount");
  // Create the context with a 1 second batch size
  JavaStreamingContext ssc = new JavaStreamingContext(sparkConf, Durations.seconds(1));
  ssc.checkpoint(checkpointDirectory);

  // Create a socket stream on target ip:port and count the
  // words in input stream of \n delimited text (eg. generated by 'nc')
  JavaReceiverInputDStream<String> lines = ssc.socketTextStream(ip, port);
  JavaDStream<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
    @Override
    public Iterator<String> call(String x) {
      return Arrays.asList(SPACE.split(x)).iterator();
    }
  });
  JavaPairDStream<String, Integer> wordCounts = words.mapToPair(
    new PairFunction<String, String, Integer>() {
      @Override
      public Tuple2<String, Integer> call(String s) {
        return new Tuple2<>(s, 1);
      }
    }).reduceByKey(new Function2<Integer, Integer, Integer>() {
      @Override
      public Integer call(Integer i1, Integer i2) {
        return i1 + i2;
      }
    });

  wordCounts.foreachRDD(new VoidFunction2<JavaPairRDD<String, Integer>, Time>() {
    @Override
    public void call(JavaPairRDD<String, Integer> rdd, Time time) throws IOException {
      // Get or register the blacklist Broadcast
      final Broadcast<List<String>> blacklist =
          JavaWordBlacklist.getInstance(new JavaSparkContext(rdd.context()));
      // Get or register the droppedWordsCounter Accumulator
      final LongAccumulator droppedWordsCounter =
          JavaDroppedWordsCounter.getInstance(new JavaSparkContext(rdd.context()));
      // Use blacklist to drop words and use droppedWordsCounter to count them
      String counts = rdd.filter(new Function<Tuple2<String, Integer>, Boolean>() {
        @Override
        public Boolean call(Tuple2<String, Integer> wordCount) {
          if (blacklist.value().contains(wordCount._1())) {
            droppedWordsCounter.add(wordCount._2());
            return false;
          } else {
            return true;
          }
        }
      }).collect().toString();
      String output = "Counts at time " + time + " " + counts;
      System.out.println(output);
      System.out.println("Dropped " + droppedWordsCounter.value() + " word(s) totally");
      System.out.println("Appending to " + outputFile.getAbsolutePath());
      Files.append(output + "\n", outputFile, Charset.defaultCharset());
    }
  });

  return ssc;
}
 

public static void main(String[] args) throws Exception {
  if (args.length < 2) {
    System.err.println("Usage: JavaNetworkWordCount <hostname> <port>");
    System.exit(1);
  }

  StreamingExamples.setStreamingLogLevels();

  // Create the context with a 1 second batch size
  SparkConf sparkConf = new SparkConf().setAppName("JavaNetworkWordCount");
  JavaStreamingContext ssc = new JavaStreamingContext(sparkConf, Durations.seconds(1));

  // Create a JavaReceiverInputDStream on target ip:port and count the
  // words in input stream of \n delimited text (eg. generated by 'nc')
  // Note that no duplication in storage level only for running locally.
  // Replication necessary in distributed scenario for fault tolerance.
  JavaReceiverInputDStream<String> lines = ssc.socketTextStream(
          args[0], Integer.parseInt(args[1]), StorageLevels.MEMORY_AND_DISK_SER);
  JavaDStream<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
    @Override
    public Iterator<String> call(String x) {
      return Arrays.asList(SPACE.split(x)).iterator();
    }
  });
  JavaPairDStream<String, Integer> wordCounts = words.mapToPair(
    new PairFunction<String, String, Integer>() {
      @Override
      public Tuple2<String, Integer> call(String s) {
        return new Tuple2<>(s, 1);
      }
    }).reduceByKey(new Function2<Integer, Integer, Integer>() {
      @Override
      public Integer call(Integer i1, Integer i2) {
        return i1 + i2;
      }
    });

  wordCounts.print();
  ssc.start();
  ssc.awaitTermination();
}
 

public static void main(String[] args) throws Exception {
  if (args.length < 2) {
    System.err.println("Usage: JavaNetworkWordCount <hostname> <port>");
    System.exit(1);
  }

  StreamingExamples.setStreamingLogLevels();

  // Create the context with a 1 second batch size
  SparkConf sparkConf = new SparkConf().setAppName("JavaSqlNetworkWordCount");
  JavaStreamingContext ssc = new JavaStreamingContext(sparkConf, Durations.seconds(1));

  // Create a JavaReceiverInputDStream on target ip:port and count the
  // words in input stream of \n delimited text (eg. generated by 'nc')
  // Note that no duplication in storage level only for running locally.
  // Replication necessary in distributed scenario for fault tolerance.
  JavaReceiverInputDStream<String> lines = ssc.socketTextStream(
      args[0], Integer.parseInt(args[1]), StorageLevels.MEMORY_AND_DISK_SER);
  JavaDStream<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
    @Override
    public Iterator<String> call(String x) {
      return Arrays.asList(SPACE.split(x)).iterator();
    }
  });

  // Convert RDDs of the words DStream to DataFrame and run SQL query
  words.foreachRDD(new VoidFunction2<JavaRDD<String>, Time>() {
    @Override
    public void call(JavaRDD<String> rdd, Time time) {
      SparkSession spark = JavaSparkSessionSingleton.getInstance(rdd.context().getConf());

      // Convert JavaRDD[String] to JavaRDD[bean class] to DataFrame
      JavaRDD<JavaRecord> rowRDD = rdd.map(new Function<String, JavaRecord>() {
        @Override
        public JavaRecord call(String word) {
          JavaRecord record = new JavaRecord();
          record.setWord(word);
          return record;
        }
      });
      Dataset<Row> wordsDataFrame = spark.createDataFrame(rowRDD, JavaRecord.class);

      // Creates a temporary view using the DataFrame
      wordsDataFrame.createOrReplaceTempView("words");

      // Do word count on table using SQL and print it
      Dataset<Row> wordCountsDataFrame =
          spark.sql("select word, count(*) as total from words group by word");
      System.out.println("========= " + time + "=========");
      wordCountsDataFrame.show();
    }
  });

  ssc.start();
  ssc.awaitTermination();
}
 

public static void main(String[] args) {
        /**
         * 资源.setMaster("local[2]")必须大于1 一个负责取数据 其他负责计算
         */
//    if (args.length < 2) {
//      System.err.println("Usage: JavaNetworkWordCount <hostname> <port>");
//      System.exit(1);
//    }

        StreamingExamples.setStreamingLogLevels();

        // Create the context with a 1 second batch size
        SparkConf sparkConf = SparkUtils.getLocalSparkConf(JavaNetworkWordCount.class);
        /*
         * 创建该对象类似于spark core中的JavaSparkContext
         * 该对象除了接受SparkConf对象，还接收了一个BatchInterval参数,就算说，每收集多长时间去划分一个人Batch即RDD去执行
         */
        JavaStreamingContext ssc = new JavaStreamingContext(sparkConf, Durations.seconds(2));

        /*
         * 首先创建输入DStream，代表一个数据比如这里从socket或KafKa来持续不断的进入实时数据流
         * 创建一个监听Socket数据量，RDD里面的每一个元素就是一行行的文本
         */
        JavaReceiverInputDStream<String> lines = ssc.socketTextStream("192.168.2.1", 9999, StorageLevels.MEMORY_AND_DISK_SER);
        JavaDStream<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public Iterator<String> call(String x) {
                return Lists.newArrayList(SPACE.split(x)).iterator();
            }
        });
        JavaPairDStream<String, Integer> wordCounts = words.mapToPair(
                new PairFunction<String, String, Integer>() {
                    @Override
                    public Tuple2<String, Integer> call(String s) {
                        return new Tuple2<String, Integer>(s, 1);
                    }
                }).reduceByKey(new Function2<Integer, Integer, Integer>() {
            @Override
            public Integer call(Integer i1, Integer i2) {
                return i1 + i2;
            }
        });

        wordCounts.print();
        ssc.start();
        try {
            ssc.awaitTermination();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }