JavaRDD<String> history_ = sc.emptyRDD();

java.util.Queue<JavaRDD<String> > queue = new LinkedList<JavaRDD<String>>();
queue.add(history_);
JavaDStream<String> history_dstream = ssc.queueStream(queue);

JavaPairDStream<String,ArrayList<String>> history = history_dstream.mapToPair(r -> {
  return new Tuple2< String,ArrayList<String> >(null,null);
});  

 JavaPairInputDStream<String, GenericData.Record> stream_1 =
    KafkaUtils.createDirectStream(ssc, String.class, GenericData.Record.class, StringDecoder.class,
        GenericDataRecordDecoder.class, props, topicsSet_1);

JavaPairInputDStream<String, GenericData.Record> stream_2 =
    KafkaUtils.createDirectStream(ssc, String.class, GenericData.Record.class, StringDecoder.class,
        GenericDataRecordDecoder.class, props, topicsSet_2);

然后进行一些转换并创建类型为的twp dstream data_1和data_2

JavaPairDStream<String, <ArrayList<String>>

并按如下方式进行连接，然后过滤掉那些没有连接键的记录，并将它们保存在历史记录中，以便在下一批中通过与数据\u 1进行联合来使用它

Data_1 = Data_1.union(history);

JavaPairDStream<String, Tuple2<ArrayList<String>, Optional<ArrayList<String>>>> joined =
    Data_1.leftOuterJoin(Data_2).cache();

JavaPairDStream<String, Tuple2<ArrayList<String>, Optional<ArrayList<String>>>> notNULL_join = joined.filter(r -> r._2._2().isPresent());
JavaPairDStream<String, Tuple2<ArrayList<String>, Optional<ArrayList<String>>>> dstream_filtered = joined.filter(r -> !r._2._2().isPresent());

history = dstream_filtered.mapToPair(r -> {
  return new Tuple2<>(r._1,r._2._1);
}).persist;

我在上一步之后获得了历史记录（通过将其保存到hdfs进行检查），但是在执行union时，这个历史记录仍然是成批空的。