Apache Kafka - Apache Spark ile Twitter Streaming Uygulamasına aşağıdaki adresten ulaşabilirsiniz.
https://github.com/aliturgutbozkurt/kafka-spark-twitter-streaming
https://github.com/aliturgutbozkurt/kafka-spark-twitter-streaming
import org.apache.spark.SparkConf; import org.apache.spark.api.java.JavaRDD; import org.apache.spark.api.java.JavaSparkContext; import scala.Tuple2; import java.util.Arrays; public class Main { public static void main(String[] args) { SparkConf conf = new SparkConf().setAppName("wordCounter").setMaster("local[*]"); JavaSparkContext sc = new JavaSparkContext(conf); JavaRDD<String> inputData = sc.textFile("src/main/resources/input.txt"); inputData.map(value -> value.replaceAll("[^a-zA-z\\s]", "")) .flatMap(value -> Arrays.asList(value.split(" ")).iterator()) .filter(word -> word.length() > 1) .mapToPair(value -> new Tuple2<String,Long>( value, 1L)) .reduceByKey((value1, value2) -> value1 + value2) .mapToPair(value -> new Tuple2<Long,String>(value._2, value._1)).sortByKey(false,1) .foreach(w->System.out.println(w)); sc.close(); } }