1 package au.gov.amsa.spark.ais;
2
3 import org.apache.spark.SparkConf;
4 import org.apache.spark.api.java.JavaRDD;
5 import org.apache.spark.api.java.JavaSparkContext;
6
7 public class SampleApp {
8 public static void main(String[] args) {
9 String logFile = "/var/log/syslog";
10
11 SparkConf conf = new SparkConf().setAppName("Simple Application");
12 conf.setMaster("local");
13 JavaSparkContext sc = new JavaSparkContext(conf);
14 JavaRDD<String> logData = sc.textFile(logFile).cache();
15
16 long numAs = logData.filter(s -> s.contains("a")).count();
17
18 long numZs = logData.filter(s -> s.contains("z")).count();
19
20 System.out.println("Lines with a: " + numAs + ", lines with z: " + numZs);
21 }
22 }