Examples with JavaDStream org.apache.spark.streaming.api.java.JavaDStream used on opensource projects

Example 1 with JavaDStream

use of org.apache.spark.streaming.api.java.JavaDStream in project beam by apache.

the class StreamingTransformTranslator method flattenPColl.

private static <T> TransformEvaluator<Flatten.PCollections<T>> flattenPColl() {
    return new TransformEvaluator<Flatten.PCollections<T>>() {

        @SuppressWarnings("unchecked")
        @Override
        public void evaluate(Flatten.PCollections<T> transform, EvaluationContext context) {
            Map<TupleTag<?>, PValue> pcs = context.getInputs(transform);
            // since this is a streaming pipeline, at least one of the PCollections to "flatten" are
            // unbounded, meaning it represents a DStream.
            // So we could end up with an unbounded unified DStream.
            final List<JavaDStream<WindowedValue<T>>> dStreams = new ArrayList<>();
            final List<Integer> streamingSources = new ArrayList<>();
            for (PValue pv : pcs.values()) {
                checkArgument(pv instanceof PCollection, "Flatten had non-PCollection value in input: %s of type %s", pv, pv.getClass().getSimpleName());
                PCollection<T> pcol = (PCollection<T>) pv;
                Dataset dataset = context.borrowDataset(pcol);
                if (dataset instanceof UnboundedDataset) {
                    UnboundedDataset<T> unboundedDataset = (UnboundedDataset<T>) dataset;
                    streamingSources.addAll(unboundedDataset.getStreamSources());
                    dStreams.add(unboundedDataset.getDStream());
                } else {
                    // create a single RDD stream.
                    Queue<JavaRDD<WindowedValue<T>>> q = new LinkedBlockingQueue<>();
                    q.offer(((BoundedDataset) dataset).getRDD());
                    //TODO: this is not recoverable from checkpoint!
                    JavaDStream<WindowedValue<T>> dStream = context.getStreamingContext().queueStream(q);
                    dStreams.add(dStream);
                }
            }
            // start by unifying streams into a single stream.
            JavaDStream<WindowedValue<T>> unifiedStreams = context.getStreamingContext().union(dStreams.remove(0), dStreams);
            context.putDataset(transform, new UnboundedDataset<>(unifiedStreams, streamingSources));
        }

        @Override
        public String toNativeString() {
            return "streamingContext.union(...)";
        }
    };
}

Example 2 with JavaDStream

use of org.apache.spark.streaming.api.java.JavaDStream in project beam by apache.

the class StreamingTransformTranslator method parDo.

private static <InputT, OutputT> TransformEvaluator<ParDo.MultiOutput<InputT, OutputT>> parDo() {
    return new TransformEvaluator<ParDo.MultiOutput<InputT, OutputT>>() {

        public void evaluate(final ParDo.MultiOutput<InputT, OutputT> transform, final EvaluationContext context) {
            final DoFn<InputT, OutputT> doFn = transform.getFn();
            rejectSplittable(doFn);
            rejectStateAndTimers(doFn);
            final SparkRuntimeContext runtimeContext = context.getRuntimeContext();
            final SparkPCollectionView pviews = context.getPViews();
            final WindowingStrategy<?, ?> windowingStrategy = context.getInput(transform).getWindowingStrategy();
            @SuppressWarnings("unchecked") UnboundedDataset<InputT> unboundedDataset = ((UnboundedDataset<InputT>) context.borrowDataset(transform));
            JavaDStream<WindowedValue<InputT>> dStream = unboundedDataset.getDStream();
            final String stepName = context.getCurrentTransform().getFullName();
            JavaPairDStream<TupleTag<?>, WindowedValue<?>> all = dStream.transformToPair(new Function<JavaRDD<WindowedValue<InputT>>, JavaPairRDD<TupleTag<?>, WindowedValue<?>>>() {

                @Override
                public JavaPairRDD<TupleTag<?>, WindowedValue<?>> call(JavaRDD<WindowedValue<InputT>> rdd) throws Exception {
                    final Accumulator<NamedAggregators> aggAccum = AggregatorsAccumulator.getInstance();
                    final Accumulator<MetricsContainerStepMap> metricsAccum = MetricsAccumulator.getInstance();
                    final Map<TupleTag<?>, KV<WindowingStrategy<?, ?>, SideInputBroadcast<?>>> sideInputs = TranslationUtils.getSideInputs(transform.getSideInputs(), JavaSparkContext.fromSparkContext(rdd.context()), pviews);
                    return rdd.mapPartitionsToPair(new MultiDoFnFunction<>(aggAccum, metricsAccum, stepName, doFn, runtimeContext, transform.getMainOutputTag(), transform.getAdditionalOutputTags().getAll(), sideInputs, windowingStrategy, false));
                }
            });
            Map<TupleTag<?>, PValue> outputs = context.getOutputs(transform);
            if (outputs.size() > 1) {
                // cache the DStream if we're going to filter it more than once.
                all.cache();
            }
            for (Map.Entry<TupleTag<?>, PValue> output : outputs.entrySet()) {
                @SuppressWarnings("unchecked") JavaPairDStream<TupleTag<?>, WindowedValue<?>> filtered = all.filter(new TranslationUtils.TupleTagFilter(output.getKey()));
                @SuppressWarnings("unchecked") JavaDStream<WindowedValue<Object>> // Object is the best we can do since different outputs can have different tags
                values = (JavaDStream<WindowedValue<Object>>) (JavaDStream<?>) TranslationUtils.dStreamValues(filtered);
                context.putDataset(output.getValue(), new UnboundedDataset<>(values, unboundedDataset.getStreamSources()));
            }
        }

        @Override
        public String toNativeString() {
            return "mapPartitions(new <fn>())";
        }
    };
}

Example 3 with JavaDStream

use of org.apache.spark.streaming.api.java.JavaDStream in project spark-dataflow by cloudera.

the class StreamingTransformTranslator method window.

private static <T, W extends BoundedWindow> TransformEvaluator<Window.Bound<T>> window() {
    return new TransformEvaluator<Window.Bound<T>>() {

        @Override
        public void evaluate(Window.Bound<T> transform, EvaluationContext context) {
            StreamingEvaluationContext sec = (StreamingEvaluationContext) context;
            //--- first we apply windowing to the stream
            WindowFn<? super T, W> windowFn = WINDOW_FG.get("windowFn", transform);
            @SuppressWarnings("unchecked") JavaDStream<WindowedValue<T>> dStream = (JavaDStream<WindowedValue<T>>) sec.getStream(transform);
            if (windowFn instanceof FixedWindows) {
                Duration windowDuration = Durations.milliseconds(((FixedWindows) windowFn).getSize().getMillis());
                sec.setStream(transform, dStream.window(windowDuration));
            } else if (windowFn instanceof SlidingWindows) {
                Duration windowDuration = Durations.milliseconds(((SlidingWindows) windowFn).getSize().getMillis());
                Duration slideDuration = Durations.milliseconds(((SlidingWindows) windowFn).getPeriod().getMillis());
                sec.setStream(transform, dStream.window(windowDuration, slideDuration));
            }
            //--- then we apply windowing to the elements
            DoFn<T, T> addWindowsDoFn = new AssignWindowsDoFn<>(windowFn);
            DoFnFunction<T, T> dofn = new DoFnFunction<>(addWindowsDoFn, ((StreamingEvaluationContext) context).getRuntimeContext(), null);
            @SuppressWarnings("unchecked") JavaDStreamLike<WindowedValue<T>, ?, JavaRDD<WindowedValue<T>>> dstream = (JavaDStreamLike<WindowedValue<T>, ?, JavaRDD<WindowedValue<T>>>) sec.getStream(transform);
            sec.setStream(transform, dstream.mapPartitions(dofn));
        }
    };
}