Package org.apache.spark.streaming.api.java

Examples of org.apache.spark.streaming.api.java.JavaStreamingContext

42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
    }

    StreamingExamples.setStreamingLogLevels();

    // Create the context
    JavaStreamingContext ssc = new JavaStreamingContext(args[0], "QueueStream", new Duration(1000),
            System.getenv("SPARK_HOME"), JavaStreamingContext.jarOfClass(JavaQueueStream.class));

    // Create the queue through which RDDs can be pushed to
    // a QueueInputDStream
    Queue<JavaRDD<Integer>> rddQueue = new LinkedList<JavaRDD<Integer>>();

    // Create and push some RDDs into the queue
    List<Integer> list = Lists.newArrayList();
    for (int i = 0; i < 1000; i++) {
      list.add(i);
    }

    for (int i = 0; i < 30; i++) {
      rddQueue.add(ssc.sparkContext().parallelize(list));
    }

    // Create the QueueInputDStream and use it do some processing
    JavaDStream<Integer> inputStream = ssc.queueStream(rddQueue);
    JavaPairDStream<Integer, Integer> mappedStream = inputStream.mapToPair(
        new PairFunction<Integer, Integer, Integer>() {
          @Override
          public Tuple2<Integer, Integer> call(Integer i) {
            return new Tuple2<Integer, Integer>(i % 10, 1);
          }
        });
    JavaPairDStream<Integer, Integer> reducedStream = mappedStream.reduceByKey(
      new Function2<Integer, Integer, Integer>() {
        @Override
        public Integer call(Integer i1, Integer i2) {
          return i1 + i2;
        }
    });

    reducedStream.print();
    ssc.start();
    ssc.awaitTermination();
  }
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
    }

    StreamingExamples.setStreamingLogLevels();

    // Create the context with a 1 second batch size
    JavaStreamingContext jssc = new JavaStreamingContext(args[0], "KafkaWordCount",
            new Duration(2000), System.getenv("SPARK_HOME"),
            JavaStreamingContext.jarOfClass(JavaKafkaWordCount.class));

    int numThreads = Integer.parseInt(args[4]);
    Map<String, Integer> topicMap = new HashMap<String, Integer>();
    String[] topics = args[3].split(",");
    for (String topic: topics) {
      topicMap.put(topic, numThreads);
    }

    JavaPairDStream<String, String> messages = KafkaUtils.createStream(jssc, args[1], args[2], topicMap);

    JavaDStream<String> lines = messages.map(new Function<Tuple2<String, String>, String>() {
      @Override
      public String call(Tuple2<String, String> tuple2) {
        return tuple2._2();
      }
    });

    JavaDStream<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
      @Override
      public Iterable<String> call(String 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();
    jssc.start();
    jssc.awaitTermination();
  }
View Full Code Here
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
    }

    StreamingExamples.setStreamingLogLevels();

    // Create the context with a 1 second batch size
    JavaStreamingContext ssc = new JavaStreamingContext(args[0], "JavaNetworkWordCount",
            new Duration(1000), System.getenv("SPARK_HOME"),
            JavaStreamingContext.jarOfClass(JavaNetworkWordCount.class));

    // Create a NetworkInputDStream on target ip:port and count the
    // words in input stream of \n delimited text (eg. generated by 'nc')
    JavaDStream<String> lines = ssc.socketTextStream(args[1], Integer.parseInt(args[2]));
    JavaDStream<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
      @Override
      public Iterable<String> call(String 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();
  }
View Full Code Here
27
28
29
30
31
32
33
34
    @Before
    public void setUp() {
        System.clearProperty("spark.driver.port");
        System.setProperty("spark.streaming.clock", "org.apache.spark.streaming.util.ManualClock");
        ssc = new JavaStreamingContext("local[2]", "test", new Duration(1000));
        ssc.checkpoint("checkpoint");
    }
View Full Code Here
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
    assertOrderInvariantEquals(expectedInitial, initialResult);
    Thread.sleep(1000);
    ssc.stop();

    ssc = new JavaStreamingContext(tempDir.getAbsolutePath());
    // Tweak to take into consideration that the last batch before failure
    // will be re-processed after recovery
    List<List<Integer>> finalResult = JavaCheckpointTestUtils.runStreams(ssc, 2, 3);
    assertOrderInvariantEquals(expectedFinal, finalResult.subList(1, 3));
  }
View Full Code Here
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
    server.start();

    final AtomicLong dataCounter = new AtomicLong(0);

    try {
      JavaStreamingContext ssc = new JavaStreamingContext("local[2]", "test", new Duration(200));
      JavaReceiverInputDStream<String> input =
        ssc.receiverStream(new JavaSocketReceiver("localhost", server.port()));
      JavaDStream<String> mapped = input.map(new Function<String, String>() {
        @Override
        public String call(String v1) throws Exception {
          return v1 + ".";
        }
      });
      mapped.foreachRDD(new Function<JavaRDD<String>, Void>() {
        @Override
        public Void call(JavaRDD<String> rdd) throws Exception {
        long count = rdd.count();
        dataCounter.addAndGet(count);
        return null;
        }
      });

      ssc.start();
      long startTime = System.currentTimeMillis();
      long timeout = 10000;

      Thread.sleep(200);
      for (int i = 0; i < 6; i++) {
        server.send("" + i + "\n"); // \n to make sure these are separate lines
        Thread.sleep(100);
      }
      while (dataCounter.get() == 0 && System.currentTimeMillis() - startTime < timeout) {
        Thread.sleep(100);
      }
      ssc.stop();
      assertTrue(dataCounter.get() > 0);
    } finally {
      server.stop();
    }
  }
View Full Code Here
26
27
28
29
30
31
32
33
    protected transient JavaStreamingContext ssc;

    @Before
    public void setUp() {
        System.setProperty("spark.streaming.clock", "org.apache.spark.streaming.util.ManualClock");
        ssc = new JavaStreamingContext("local[2]", "test", new Duration(1000));
        ssc.checkpoint("checkpoint");
    }
View Full Code Here
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
        /* Kinesis checkpoint interval.  Same as batchInterval for this example. */
        Duration checkpointInterval = batchInterval;

        /* Setup the StreamingContext */
        JavaStreamingContext jssc = new JavaStreamingContext(sparkConfig, batchInterval);

        /* Create the same number of Kinesis DStreams/Receivers as Kinesis stream's shards */
        List<JavaDStream<byte[]>> streamsList = new ArrayList<JavaDStream<byte[]>>(numStreams);
        for (int i = 0; i < numStreams; i++) {
          streamsList.add(
            KinesisUtils.createStream(jssc, streamName, endpointUrl, checkpointInterval,
            InitialPositionInStream.LATEST, StorageLevel.MEMORY_AND_DISK_2())
          );
        }

        /* Union all the streams if there is more than 1 stream */
        JavaDStream<byte[]> unionStreams;
        if (streamsList.size() > 1) {
            unionStreams = jssc.union(streamsList.get(0), streamsList.subList(1, streamsList.size()));
        } else {
            /* Otherwise, just use the 1 stream */
            unionStreams = streamsList.get(0);
        }

        /*
         * Split each line of the union'd DStreams into multiple words using flatMap to produce the collection.
         * Convert lines of byte[] to multiple Strings by first converting to String, then splitting on WORD_SEPARATOR.
         */
        JavaDStream<String> words = unionStreams.flatMap(new FlatMapFunction<byte[], String>() {
                @Override
                public Iterable<String> call(byte[] line) {
                    return Lists.newArrayList(WORD_SEPARATOR.split(new String(line)));
                }
            });

        /* Map each word to a (word, 1) tuple, then reduce/aggregate by word. */
        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;
                }
            });

        /* Print the first 10 wordCounts */
        wordCounts.print();

        /* Start the streaming context and await termination */
        jssc.start();
        jssc.awaitTermination();
    }
View Full Code Here
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
    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 a 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 Iterable<String> call(String 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();
  }
View Full Code Here
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
    }

    StreamingExamples.setStreamingLogLevels();
    SparkConf sparkConf = new SparkConf().setAppName("JavaKafkaWordCount");
    // Create the context with a 1 second batch size
    JavaStreamingContext jssc = new JavaStreamingContext(sparkConf, new Duration(2000));

    int numThreads = Integer.parseInt(args[3]);
    Map<String, Integer> topicMap = new HashMap<String, Integer>();
    String[] topics = args[2].split(",");
    for (String topic: topics) {
      topicMap.put(topic, numThreads);
    }

    JavaPairReceiverInputDStream<String, String> messages =
            KafkaUtils.createStream(jssc, args[0], args[1], topicMap);

    JavaDStream<String> lines = messages.map(new Function<Tuple2<String, String>, String>() {
      @Override
      public String call(Tuple2<String, String> tuple2) {
        return tuple2._2();
      }
    });

    JavaDStream<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
      @Override
      public Iterable<String> call(String 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();
    jssc.start();
    jssc.awaitTermination();
  }
View Full Code Here
TOP

Related Classes of org.apache.spark.streaming.api.java.JavaStreamingContext

  • com.cloudera.oryx.lambda.BatchLayer
  • com.cloudera.oryx.lambda.speed.SpeedLayer
  • com.datastax.spark.connector.CassandraJavaUtilTest
  • org.apache.spark.examples.streaming.JavaCustomReceiver
  • org.apache.spark.examples.streaming.JavaKafkaWordCount
  • org.apache.spark.examples.streaming.JavaKinesisWordCountASL
  • org.apache.spark.examples.streaming.JavaNetworkWordCount
  • org.apache.spark.examples.streaming.JavaQueueStream
  • org.apache.spark.streaming.examples.JavaKafkaWordCount
  • org.apache.spark.streaming.examples.JavaNetworkWordCount
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.