package com.digitalpebble.azazello; import org.apache.spark.api.java.*; import org.apache.spark.SparkConf; import org.apache.spark.api.java.function.Function; public class SimpleApp { public static void main(String[] args) { String logFile = args[0]; SparkConf conf = new SparkConf().setAppName("Simple Application"); JavaSparkContext sc = new JavaSparkContext(conf); JavaRDD<String> logData = sc.textFile(logFile); long numAs = logData.filter(new Function<String, Boolean>() { public Boolean call(String s) { return s.contains("a"); } }).count(); long numBs = logData.filter(new Function<String, Boolean>() { public Boolean call(String s) { return s.contains("b"); } }).count(); System.out.println("Lines with a: " + numAs + ", lines with b: " + numBs); } }