java 使用spark_Spark使用小结：Java版Join操作

实现两组数据的Join操作。

第一组：i, i*i

第二组：i, 'a'+i

join之后的结果是：i, i*i, 'a'+i

public class SparkSample {

private static final Pattern SPACE = Pattern.compile(" ");

public static void main(String args[]) {

SparkConf sparkConf = new SparkConf();

sparkConf.setAppName("SparkJavaWordCount");

sparkConf.setMaster("local");

JavaSparkContext context = new JavaSparkContext(sparkConf);

List data = Arrays.asList(1,2,3,4,5);

JavaRDD distData= context.parallelize(data);

JavaPairRDD firstRDD = distData.mapToPair(new PairFunction() {

@Override

public Tuple2 call(Integer integer) throws Exception {

return new Tuple2(integer, integer*integer);

}

});

JavaPairRDD secondRDD = distData.mapToPair(new PairFunction() {

@Override

public Tuple2 call(Integer integer) throws Exception {

return new Tuple2(integer, String.valueOf((char)('a' + integer)));

};

});

JavaPairRDD> joinRDD = firstRDD.join(secondRDD);

JavaRDD result = joinRDD.map(new Function>, String>() {

@Override

public String call(Tuple2> integerTuple2Tuple2) throws Exception {

int key = integerTuple2Tuple2._1();

int value1 = integerTuple2Tuple2._2()._1();

String value2 = integerTuple2Tuple2._2()._2();

return key + " " + value1 + " " + value2;

}

});

List reslist = result.collect();

for(String str : reslist) {

System.out.println(str);

}

context.stop();

}

}