SortByKey用于对pairRDD按照key进行排序,第一个参数可以设置true或者false,默认是true
List<Tuple2<String, Integer>> data = new ArrayList<>();
data.add(new Tuple2<>("A", 10));
data.add(new Tuple2<>("A", 20));
data.add(new Tuple2<>("B", 2));
data.add(new Tuple2<>("B", 3));
data.add(new Tuple2<>("C", 5));
JavaPairRDD<String, Integer> stringIntegerJavaPairRDD = javaSparkContext.parallelizePairs(data);
//升序
System.out.println(stringIntegerJavaPairRDD.sortByKey().collect());
//返回的结果
//[(A,10), (A,20), (B,2), (B,3), (C,5)]
//降序
System.out.println(stringIntegerJavaPairRDD.sortByKey(false).collect());
//返回的结果
//[(C,5), (B,2), (B,3), (A,10), (A,20)]