Examples with SparkPCollectionView org.apache.beam.runners.spark.translation.SparkPCollectionView used on opensource projects

Example 1 with SparkPCollectionView

use of org.apache.beam.runners.spark.translation.SparkPCollectionView 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>>() {

        @Override
        public void evaluate(final ParDo.MultiOutput<InputT, OutputT> transform, final EvaluationContext context) {
            final DoFn<InputT, OutputT> doFn = transform.getFn();
            checkArgument(!DoFnSignatures.signatureForDoFn(doFn).processElement().isSplittable(), "Splittable DoFn not yet supported in streaming mode: %s", doFn);
            rejectStateAndTimers(doFn);
            final SerializablePipelineOptions options = context.getSerializableOptions();
            final SparkPCollectionView pviews = context.getPViews();
            final WindowingStrategy<?, ?> windowingStrategy = context.getInput(transform).getWindowingStrategy();
            Coder<InputT> inputCoder = (Coder<InputT>) context.getInput(transform).getCoder();
            Map<TupleTag<?>, Coder<?>> outputCoders = context.getOutputCoders();
            @SuppressWarnings("unchecked") UnboundedDataset<InputT> unboundedDataset = (UnboundedDataset<InputT>) context.borrowDataset(transform);
            JavaDStream<WindowedValue<InputT>> dStream = unboundedDataset.getDStream();
            final DoFnSchemaInformation doFnSchemaInformation = ParDoTranslation.getSchemaInformation(context.getCurrentTransform());
            final Map<String, PCollectionView<?>> sideInputMapping = ParDoTranslation.getSideInputMapping(context.getCurrentTransform());
            final String stepName = context.getCurrentTransform().getFullName();
            JavaPairDStream<TupleTag<?>, WindowedValue<?>> all = dStream.transformToPair(rdd -> {
                final MetricsContainerStepMapAccumulator metricsAccum = MetricsAccumulator.getInstance();
                final Map<TupleTag<?>, KV<WindowingStrategy<?, ?>, SideInputBroadcast<?>>> sideInputs = TranslationUtils.getSideInputs(transform.getSideInputs().values(), JavaSparkContext.fromSparkContext(rdd.context()), pviews);
                return rdd.mapPartitionsToPair(new MultiDoFnFunction<>(metricsAccum, stepName, doFn, options, transform.getMainOutputTag(), transform.getAdditionalOutputTags().getAll(), inputCoder, outputCoders, sideInputs, windowingStrategy, false, doFnSchemaInformation, sideInputMapping));
            });
            Map<TupleTag<?>, PCollection<?>> outputs = context.getOutputs(transform);
            if (outputs.size() > 1) {
                // Caching can cause Serialization, we need to code to bytes
                // more details in https://issues.apache.org/jira/browse/BEAM-2669
                Map<TupleTag<?>, Coder<WindowedValue<?>>> coderMap = TranslationUtils.getTupleTagCoders(outputs);
                all = all.mapToPair(TranslationUtils.getTupleTagEncodeFunction(coderMap)).cache().mapToPair(TranslationUtils.getTupleTagDecodeFunction(coderMap));
            }
            for (Map.Entry<TupleTag<?>, PCollection<?>> 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 2 with SparkPCollectionView

use of org.apache.beam.runners.spark.translation.SparkPCollectionView in project beam by apache.

the class StreamingTransformTranslator method combineGrouped.

private static <K, InputT, OutputT> TransformEvaluator<Combine.GroupedValues<K, InputT, OutputT>> combineGrouped() {
    return new TransformEvaluator<Combine.GroupedValues<K, InputT, OutputT>>() {

        @Override
        public void evaluate(final Combine.GroupedValues<K, InputT, OutputT> transform, EvaluationContext context) {
            // get the applied combine function.
            PCollection<? extends KV<K, ? extends Iterable<InputT>>> input = context.getInput(transform);
            final WindowingStrategy<?, ?> windowingStrategy = input.getWindowingStrategy();
            @SuppressWarnings("unchecked") final CombineWithContext.CombineFnWithContext<InputT, ?, OutputT> fn = (CombineWithContext.CombineFnWithContext<InputT, ?, OutputT>) CombineFnUtil.toFnWithContext(transform.getFn());
            @SuppressWarnings("unchecked") UnboundedDataset<KV<K, Iterable<InputT>>> unboundedDataset = (UnboundedDataset<KV<K, Iterable<InputT>>>) context.borrowDataset(transform);
            JavaDStream<WindowedValue<KV<K, Iterable<InputT>>>> dStream = unboundedDataset.getDStream();
            final SerializablePipelineOptions options = context.getSerializableOptions();
            final SparkPCollectionView pviews = context.getPViews();
            JavaDStream<WindowedValue<KV<K, OutputT>>> outStream = dStream.transform(rdd -> {
                SparkCombineFn<KV<K, InputT>, InputT, ?, OutputT> combineFnWithContext = SparkCombineFn.keyed(fn, options, TranslationUtils.getSideInputs(transform.getSideInputs(), new JavaSparkContext(rdd.context()), pviews), windowingStrategy);
                return rdd.map(new TranslationUtils.CombineGroupedValues<>(combineFnWithContext));
            });
            context.putDataset(transform, new UnboundedDataset<>(outStream, unboundedDataset.getStreamSources()));
        }

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