Java JavaStreamingContext.socketTextStream方法代码示例

import org.apache.spark.streaming.api.java.JavaStreamingContext; //导入方法依赖的package包/类
public static void main(String[] args) throws Exception {
	String master = args[0];
	JavaSparkContext sc = new JavaSparkContext(master, "StreamingLogInput");
   // Create a StreamingContext with a 1 second batch size
   JavaStreamingContext jssc = new JavaStreamingContext(sc, new Duration(1000));
   // Create a DStream from all the input on port 7777
   JavaDStream<String> lines = jssc.socketTextStream("localhost", 7777);
   // Filter our DStream for lines with "error"
   JavaDStream<String> errorLines = lines.filter(new Function<String, Boolean>() {
       public Boolean call(String line) {
         return line.contains("error");
       }});
   // Print out the lines with errors, which causes this DStream to be evaluated
   errorLines.print();
   // start our streaming context and wait for it to "finish"
   jssc.start();
   // Wait for 10 seconds then exit. To run forever call without a timeout
   jssc.awaitTermination(10000);
   // Stop the streaming context
   jssc.stop();
}
 

import org.apache.spark.streaming.api.java.JavaStreamingContext; //导入方法依赖的package包/类
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();
 }
 

import org.apache.spark.streaming.api.java.JavaStreamingContext; //导入方法依赖的package包/类
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();
}
 

import org.apache.spark.streaming.api.java.JavaStreamingContext; //导入方法依赖的package包/类
public static void main(String[] args) throws InterruptedException {

		System.setProperty("hadoop.home.dir", "C:\\softwares\\Winutils");

		SparkSession sparkSession = SparkSession.builder().master("local[*]").appName("Stateful Streaming Example")
				.config("spark.sql.warehouse.dir", "file:////C:/Users/sgulati/spark-warehouse").getOrCreate();

		JavaStreamingContext jssc= new JavaStreamingContext(new JavaSparkContext(sparkSession.sparkContext()),
				Durations.milliseconds(1000));
		JavaReceiverInputDStream<String> inStream = jssc.socketTextStream("10.204.136.223", 9999);
		jssc.checkpoint("C:\\Users\\sgulati\\spark-checkpoint");

		JavaDStream<FlightDetails> flightDetailsStream = inStream.map(x -> {
			ObjectMapper mapper = new ObjectMapper();
			return mapper.readValue(x, FlightDetails.class);
		});
		
		

		JavaPairDStream<String, FlightDetails> flightDetailsPairStream = flightDetailsStream
				.mapToPair(f -> new Tuple2<String, FlightDetails>(f.getFlightId(), f));

		Function3<String, Optional<FlightDetails>, State<List<FlightDetails>>, Tuple2<String, Double>> mappingFunc = (
				flightId, curFlightDetail, state) -> {
			List<FlightDetails> details = state.exists() ? state.get() : new ArrayList<>();

			boolean isLanded = false;

			if (curFlightDetail.isPresent()) {
				details.add(curFlightDetail.get());
				if (curFlightDetail.get().isLanded()) {
					isLanded = true;
				}
			}
			Double avgSpeed = details.stream().mapToDouble(f -> f.getTemperature()).average().orElse(0.0);

			if (isLanded) {
				state.remove();
			} else {
				state.update(details);
			}
			return new Tuple2<String, Double>(flightId, avgSpeed);
		};

		JavaMapWithStateDStream<String, FlightDetails, List<FlightDetails>, Tuple2<String, Double>> streamWithState = flightDetailsPairStream
				.mapWithState(StateSpec.function(mappingFunc).timeout(Durations.minutes(5)));
		
		streamWithState.print();
		jssc.start();
		jssc.awaitTermination();
	}
 

import org.apache.spark.streaming.api.java.JavaStreamingContext; //导入方法依赖的package包/类
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();
}
 

import org.apache.spark.streaming.api.java.JavaStreamingContext; //导入方法依赖的package包/类
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;
}
 

import org.apache.spark.streaming.api.java.JavaStreamingContext; //导入方法依赖的package包/类
@Override
public void connect() throws Exception {

	SparkConf conf = new SparkConf().setMaster(getConfiguration().get("spark.host"))
			.setAppName(getConfiguration().get("spark.appName"));
	jssc = new JavaStreamingContext(conf, Durations.seconds(1));
	jssc.start();

	lines = jssc.socketTextStream("", 1);
}
 

import org.apache.spark.streaming.api.java.JavaStreamingContext; //导入方法依赖的package包/类
@Override
public void connect() throws Exception {

	SparkConf conf = new SparkConf().setMaster(getConfiguration().get("spark.host"))
			.setAppName(getConfiguration().get("spark.appName"));
	jssc = new JavaStreamingContext(conf, Durations.seconds(1));
	jssc.start();

	lines = jssc.socketTextStream("", 1);
	
	redis = new Redis();
}
 

import org.apache.spark.streaming.api.java.JavaStreamingContext; //导入方法依赖的package包/类
public static void main(String[] args) throws Exception {
        SparkConf conf = new SparkConf().setMaster("local[2]").setAppName("SparkJoinTest");
        JavaStreamingContext ssc = new JavaStreamingContext(conf, Durations.seconds(1));
        ssc.checkpoint("checkpoint");

        JavaReceiverInputDStream<String> lines = ssc.socketTextStream("127.0.0.1", 9999);
        JavaPairDStream<String, Long> nameStream = lines.flatMap(new FlatMapFunction<String, String>() {
            public Iterable<String> call(String l) throws Exception {
                return Arrays.asList(l.split(" "));
            }
        }).mapToPair(new PairFunction<String, String, Long>() {
            public Tuple2<String, Long> call(String w) throws Exception {
                return new Tuple2<>(w, 1L);
            }
        }).window(Durations.seconds(30), Durations.seconds(10));

        JavaReceiverInputDStream<String> lines2 = ssc.socketTextStream("127.0.0.1", 9998);
        JavaPairDStream<String, Long> nameAgeStream = lines2.mapToPair(new PairFunction<String, String, Long>() {
            @Override
            public Tuple2<String, Long> call(String s) throws Exception {
                String[] list = s.split(" ");
                String name = list[0];
                long age = 0L;
                if (list.length > 1)
                    age = Long.parseLong(list[1]);
                return new Tuple2<String, Long>(name, age);
            }
        }).window(Durations.seconds(11), Durations.seconds(11));

//        nameStream.print();
//        nameAgeStream.print();
        JavaPairDStream<String, Tuple2<Long, Long>> joinedStream = nameStream.join(nameAgeStream);
        joinedStream.print();

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

import org.apache.spark.streaming.api.java.JavaStreamingContext; //导入方法依赖的package包/类
public static void main(String args[]) {
  if (args.length == 0) {
    System.out
        .println("JavaHBaseBulkPutExample  {master} {host} {post} {tableName} {columnFamily}");
  }

  String master = args[0];
  String host = args[1];
  String port = args[2];
  String tableName = args[3];
  String columnFamily = args[4];

  System.out.println("master:" + master);
  System.out.println("host:" + host);
  System.out.println("port:" + Integer.parseInt(port));
  System.out.println("tableName:" + tableName);
  System.out.println("columnFamily:" + columnFamily);
  
  SparkConf sparkConf = new SparkConf();
  sparkConf.set("spark.cleaner.ttl", "120000");
  
  JavaSparkContext jsc = new JavaSparkContext(master,
      "JavaHBaseBulkPutExample");
  jsc.addJar("SparkHBase.jar");
  
  JavaStreamingContext jssc = new JavaStreamingContext(jsc, new Duration(1000));

  JavaReceiverInputDStream<String> javaDstream = jssc.socketTextStream(host, Integer.parseInt(port));
  
  Configuration conf = HBaseConfiguration.create();
  conf.addResource(new Path("/etc/hbase/conf/core-site.xml"));
  conf.addResource(new Path("/etc/hbase/conf/hbase-site.xml"));

  JavaHBaseContext hbaseContext = new JavaHBaseContext(jsc, conf);

  hbaseContext.streamBulkPut(javaDstream, tableName, new PutFunction(), true);
}
 

import org.apache.spark.streaming.api.java.JavaStreamingContext; //导入方法依赖的package包/类
public static void main(String[] args) {
  if (args.length < 4) {
    System.out.println("JavaHBaseBulkPutExample  " +
            "{host} {port} {tableName}");
    return;
  }

  String host = args[0];
  String port = args[1];
  String tableName = args[2];

  SparkConf sparkConf =
          new SparkConf().setAppName("JavaHBaseStreamingBulkPutExample " +
                  tableName + ":" + port + ":" + tableName);

  JavaSparkContext jsc = new JavaSparkContext(sparkConf);

  try {
    JavaStreamingContext jssc =
            new JavaStreamingContext(jsc, new Duration(1000));

    JavaReceiverInputDStream<String> javaDstream =
            jssc.socketTextStream(host, Integer.parseInt(port));

    Configuration conf = HBaseConfiguration.create();

    JavaHBaseContext hbaseContext = new JavaHBaseContext(jsc, conf);

    hbaseContext.streamBulkPut(javaDstream,
            TableName.valueOf(tableName),
            new PutFunction());
  } finally {
    jsc.stop();
  }
}
 

import org.apache.spark.streaming.api.java.JavaStreamingContext; //导入方法依赖的package包/类
public static void main(String[] args) {
  if (args.length < 3) {
    System.err.println("Usage: NetworkWordCount <master> <hostname> <port>\n" +
        "In local mode, <master> should be 'local[n]' with n > 1");
    System.exit(1);
  }

  // Create the context with a 1 second batch size
  JavaStreamingContext ssc = new JavaStreamingContext(args[0], "NetworkWordCount",
          new Duration(5000), System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR"));

  // Create a NetworkInputDStream on target ip:port and count the
  // words in input stream of \n delimited test (eg. generated by 'nc')
  JavaDStream<String> lines = ssc.socketTextStream(args[1], Integer.parseInt(args[2]));
  
  lines.map(new Function<String, String> () {

@Override
public String call(String arg0) throws Exception {
	System.out.println("arg0" + arg0);
	return arg0;
}}).print();
  
  lines.print();
  ssc.start();


}
 

import org.apache.spark.streaming.api.java.JavaStreamingContext; //导入方法依赖的package包/类
public static void main(String[] args) {

    // Create the context with a 1 second batch size
    SparkConf sparkConf = new SparkConf().setMaster("local[*]").setAppName("Streaming101");
    JavaStreamingContext ssc = new JavaStreamingContext(sparkConf, Durations.seconds(10));


    JavaReceiverInputDStream<String> lines = ssc.socketTextStream("localhost",9999, StorageLevels.MEMORY_AND_DISK_SER);
    JavaDStream<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
      @Override
      public Iterable<String> call(String x) {
    	  System.out.println(x);
    	  return Lists.newArrayList(SPACE.split(x));
      }
    });
    
    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();
    ssc.awaitTermination();
  }
 

import org.apache.spark.streaming.api.java.JavaStreamingContext; //导入方法依赖的package包/类
public static void main(String[] args) throws Exception {

        final String dbUrl = args[0];
        final String hostname = args[1];
        final String port = args[2];
        final String inTargetSchema = args[3];
        final String inTargetTable = args[4];

        SparkConf conf = new SparkConf();

        JavaStreamingContext ssc = new JavaStreamingContext(conf, new Duration(500));
        SpliceSpark.setContext(ssc.sparkContext());

        SparkSession spark = SpliceSpark.getSessionUnsafe();

        JavaReceiverInputDStream<String> stream = ssc.socketTextStream(hostname, Integer.parseInt(port));

        // Create a SplicemachineContext based on the provided DB connection
        SplicemachineContext splicemachineContext = new SplicemachineContext(dbUrl);

        // Set target tablename and schemaname
        final String table = inTargetSchema + "." + inTargetTable;

        stream.foreachRDD((VoidFunction<JavaRDD<String>>) rdd -> {
            JavaRDD<Row> rowRDD = rdd.map((Function<String, Row>) s -> RowFactory.create(s));
            Dataset<Row> df = spark.createDataFrame(rowRDD, splicemachineContext.getSchema(table));

            splicemachineContext.insert(df, table);
        });

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

import org.apache.spark.streaming.api.java.JavaStreamingContext; //导入方法依赖的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); 
  		
  	 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();
	}
}