public static void main(String[] args) {
SparkConf conf = new SparkConf().setAppName("Example").setMaster("local[2]");
// Create a StreamingContext with a 1-second batch size from a SparkConf
JavaStreamingContext jssc =
new JavaStreamingContext(
conf, Durations.seconds(10)); // Create a DStream from all the input on port 7777
JavaDStream<String> lines = jssc.socketTextStream("localhost", 7777);
// Filter our DStream for lines with "error"
// Split up into words.
final JavaDStream<String> wordDStream =
lines.flatMap(
new FlatMapFunction<String, String>() {
public Iterable<String> call(String x) {
return Arrays.asList(x.split(" "));
}
});
final JavaPairDStream<String, Integer> wordPairDStream =
wordDStream.mapToPair(
new PairFunction<String, String, Integer>() {
@Override
public Tuple2<String, Integer> call(String s) throws Exception {
return new Tuple2<String, Integer>(s, 1);
}
});
final JavaPairDStream<String, Integer> totalWordPairDStream =
wordPairDStream.reduceByKeyAndWindow(
new Function2<Integer, Integer, Integer>() {
@Override
public Integer call(Integer a, Integer b) throws Exception {
return a + b;
}
},
Durations.seconds(30),
Durations.seconds(20));
// totalWordPairDStream.foreach(new Function2<JavaPairRDD<String, Integer>, Time, Void>()
// {
// @Override
// public Void call(JavaPairRDD<String, Integer> wordPairRDD, Time time) throws
// Exception {
//
// final List<Tuple2<String, Integer>> collect = wordPairRDD.collect();
// for (Tuple2<String, Integer> t : collect) {
// System.out.println("the value is t" + t._1() + "," + t._2());
// }
//
// return null;
// }
// });
totalWordPairDStream.print();
// Start our streaming context and wait for it to "finish"
jssc.start();
// Wait for the job to finish
jssc.awaitTermination();
}
public static void main(String[] args) {
SparkConf conf =
new SparkConf()
.setMaster("local[4]")
.setAppName("SparkStreamingPullDataFromFlume for Java");
JavaStreamingContext jsc = new JavaStreamingContext(conf, Durations.seconds(30));
// JavaReceiverInputDStream<SparkFlumeEvent> lines = FlumeUtils.createStream(jsc,"master1",
// 9999); flume push data to Spark Streaming
JavaReceiverInputDStream<SparkFlumeEvent> lines =
FlumeUtils.createPollingStream(
jsc, "master1", 9999); // Spark Streaming pull data from flume
JavaDStream<String> words =
lines.flatMap(
new FlatMapFunction<SparkFlumeEvent, String>() {
private static final long serialVersionUID = 1L;
@Override
public Iterable<String> call(SparkFlumeEvent event) throws Exception {
String line = new String(event.event().getBody().array());
return Arrays.asList(line.split(" "));
}
});
JavaPairDStream<String, Integer> pairs =
words.mapToPair(
new PairFunction<String, String, Integer>() {
private static final long serialVersionUID = 1L;
@Override
public Tuple2<String, Integer> call(String word) throws Exception {
return new Tuple2<String, Integer>(word, 1);
}
});
JavaPairDStream<String, Integer> wordsCount =
pairs.reduceByKey(
new Function2<
Integer, Integer, Integer>() { // 对相同的Key，进行Value的累计（包括Local和Reducer级别同时Reduce）
private static final long serialVersionUID = 1L;
@Override
public Integer call(Integer v1, Integer v2) throws Exception {
return v1 + v2;
}
});
wordsCount.print();
jsc.start();
jsc.awaitTermination();
jsc.close();
}
public static void main(String[] args) throws IOException {
SparkConf conf = new SparkConf().setAppName("faebookStream");
JavaStreamingContext jssc = new JavaStreamingContext(conf, Durations.seconds(15));
JavaDStream<String> stream =
jssc.textFileStream("/Users/sboynenpalli/Desktop/shashankOfficeMackbook/sparkinputfolder");
stream.print(10);
ProcessVideoStreamData processData = new ProcessVideoStreamData();
processData.processData(stream);
jssc.start();
jssc.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);
// Register as table
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 void run() {
System.setProperty("spark.hadoop.dfs.replication", "2");
Logger.getLogger("org").setLevel(Level.OFF);
Logger.getLogger("akka").setLevel(Level.OFF);
SparkConf conf = new SparkConf().setAppName("WindowingKafkaWordCountWithFaultTolerance");
conf.set("spark.master", PropertiesStack.getProperty("spark.master"));
conf.set("spark.executor.memory", PropertiesStack.getProperty("spark.executor.memory"));
conf.set("spark.driver.memory", PropertiesStack.getProperty("spark.driver.memory"));
conf.set(
"spark.driver.maxResultSize", PropertiesStack.getProperty("spark.driver.maxResultSize"));
// .setAppName("WindowingKafkaWordCountWithoutFaultTolerance");
JavaStreamingContext jssc = new JavaStreamingContext(conf, Durations.seconds(10));
HashSet<String> topicsSet = new HashSet<String>(Arrays.asList(PropertiesStack.getKafkaTopic()));
HashMap<String, String> kafkaParams = new HashMap<String, String>();
kafkaParams.put("metadata.broker.list", PropertiesStack.getKafkaBootstrapServers());
kafkaParams.put("zookeeper.connect", PropertiesStack.getZookeeperConnect());
kafkaParams.put("auto.offset.reset", "smallest");
kafkaParams.put("group.id", PropertiesStack.getKafkaGroupId());
kafkaParams.put("auto.commit.enable", "false");
Map<String, Integer> topicMap = new HashMap<String, Integer>();
topicMap.put(PropertiesStack.getKafkaTopic(), 1);
// Map<kafka.common.TopicAndPartition, java.lang.Long> fromOffsets = new HashMap<>();
// fromOffsets.put(new TopicAndPartition(PropertiesStack.getKafkaTopic(),
// 1), 1000L);
// Create direct kafka stream with brokers and topics
// JavaInputDStream<String> messages = KafkaUtils
// .createDirectStream(
// jssc,
// String.class,
// String.class,
// StringDecoder.class,
// StringDecoder.class,
// String.class,
// kafkaParams,
// fromOffsets,
// new Function<kafka.message.MessageAndMetadata<String, String>, String>() {
// @Override
// public String call(
// MessageAndMetadata<String, String> v1)
// throws Exception {
// return v1.message();
// }
// });
JavaPairInputDStream<String, String> messages =
KafkaUtils.createDirectStream(
jssc,
String.class,
String.class,
StringDecoder.class,
StringDecoder.class,
kafkaParams,
topicsSet);
messages.count().print();
// .createStream(jssc, PropertiesStack.getZookeeperConnect(),
// PropertiesStack.getKafkaGroupId(), topicMap);
// Start the computation
jssc.start();
jssc.awaitTermination();
}
public static void main(String[] args) throws Exception {
if (args.length < 2) {
System.err.println(
"Usage: JavaDirectKafkaWordCount <brokers> <topics>\n"
+ " <brokers> is a list of one or more Kafka brokers\n"
+ " <topics> is a list of one or more kafka topics to consume from\n\n");
System.exit(1);
}
String brokers = args[0];
String topics = args[1];
// Create context with a 2 seconds batch interval
SparkConf sparkConf = new SparkConf().setAppName("JavaDirectKafkaWordCount");
JavaStreamingContext jssc = new JavaStreamingContext(sparkConf, Durations.seconds(2));
Set<String> topicsSet = new HashSet<>(Arrays.asList(topics.split(",")));
Map<String, String> kafkaParams = new HashMap<>();
kafkaParams.put("metadata.broker.list", brokers);
// Create direct kafka stream with brokers and topics
JavaPairInputDStream<String, String> messages =
KafkaUtils.createDirectStream(
jssc,
String.class,
String.class,
StringDecoder.class,
StringDecoder.class,
kafkaParams,
topicsSet);
// Get the lines, split them into words, count the words and print
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 Arrays.asList(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<>(s, 1);
}
})
.reduceByKey(
new Function2<Integer, Integer, Integer>() {
@Override
public Integer call(Integer i1, Integer i2) {
return i1 + i2;
}
});
wordCounts.print();
// Start the computation
jssc.start();
jssc.awaitTermination();
}
public static void main(String[] args) {
Logger logger = Logger.getRootLogger();
logger.setLevel(Level.OFF);
String consumerKey = "JqQ1lAWg90PVD9U8XoDWedCm8";
String consumerSecret = "QaUe7V9HuYQvC031MVqpUuuP2OjieI0BBDEHLpFOR221zjQ0xp";
String accessToken = "3299869044-UVd8CwTfnDgcGFGPro2yGXKWhArKtXRxC6iekmH";
String accessTokenSecret = "3XtGQi1naI1V9wCVs2aQgEeVWr65vXDczOwGvqa3iGlEG";
System.setProperty("twitter4j.oauth.consumerKey", consumerKey);
System.setProperty("twitter4j.oauth.consumerSecret", consumerSecret);
System.setProperty("twitter4j.oauth.accessToken", accessToken);
System.setProperty("twitter4j.oauth.accessTokenSecret", accessTokenSecret);
String[] filters = {"bulling", "bullied", "bulling", "bullyed", "bully", "teased"};
SparkConf sparkConf = new SparkConf().setAppName("bullyhunter");
System.out.println("Started bullyhunter...");
JavaStreamingContext sc = new JavaStreamingContext(sparkConf, Durations.seconds(2));
JavaReceiverInputDStream<Status> stream = TwitterUtils.createStream(sc, filters);
JavaDStream<String> text =
stream.map(
new Function<Status, String>() {
public String call(Status status) {
// String msg = status.getText();
// String filtered_msg = Enrichment.filter(msg);
// if (filtered_msg == null) {
// return null;
// }
// TweetRecord tr = new TweetRecord();
// tr.setMsg(filtered_msg);
// //tr.setGeo(status.getGeoLocation().getLatitude());
// String fullName = status.getPlace().getFullName();
// if (fullName == null)
// return null;
// String[] fields = fullName.spilt(DELIMITER);
// tr.setCity(fullName.split());
String msg = status.getText();
double ind = Classification.classifyTweet(msg);
if (ind > 0) {
return status.getText();
} else {
return null;
}
}
});
// text = text.filter(new Function<String, Boolean>() {
// public Boolean call(String msg) {
// boolean containKeyword = false;
// String lowerCase = msg.toLowerCase();
// for (String k : keywords)
// if (lowerCase.contains(k)) {
// containKeyword = true;
// break;
// }
// if (containKeyword == true && lowerCase.contains("bull")
// && !lowerCase.contains("RT")) {
// return true;
// }
// return false;
// }
//
// });
text =
text.filter(
new Function<String, Boolean>() {
public Boolean call(String msg) {
return (msg == null) ? false : true;
}
});
text.print();
sc.start();
sc.awaitTermination();
}