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();
}
