上边的文章介绍的很好,根据自己的需要,做一些修改就可以了,下边是我的代码:
import java.util.List;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
/**
* 在spark的master上执行的命令如下:
* [root@x02 bin]# spark-submit --class com.geo.SparkTest.App --master spark://x02:7077 /root/SparkTest-0.0.1-SNAPSHOT-jar-with-dependencies.jar /wjb/input/imanager.sql
*
*/
public class App
{
public static void main( String[] args )
{
String master="spark://x02:7077";
SparkConf conf = new SparkConf().setAppName("topTest").setMaster(master);
JavaSparkContext sc = new JavaSparkContext(conf);
System.out.println("------------------------------------------------------------");
for (String line : args) {
System.out.println("arg:"+line);
}
System.out.println("------------------------------------------------------------");
JavaRDD<String> lines = sc.textFile(args[0]);
List<String> tops = lines.top(2);
for (String line : tops) {
System.out.println("top:"+line);
}
}
}