use of org.apache.beam.runners.spark.translation.SparkRuntimeContext in project beam by apache.
the class StreamingTransformTranslator method groupByKey.
private static <K, V, W extends BoundedWindow> TransformEvaluator<GroupByKey<K, V>> groupByKey() {
return new TransformEvaluator<GroupByKey<K, V>>() {
@Override
public void evaluate(GroupByKey<K, V> transform, EvaluationContext context) {
@SuppressWarnings("unchecked") UnboundedDataset<KV<K, V>> inputDataset = (UnboundedDataset<KV<K, V>>) context.borrowDataset(transform);
List<Integer> streamSources = inputDataset.getStreamSources();
JavaDStream<WindowedValue<KV<K, V>>> dStream = inputDataset.getDStream();
@SuppressWarnings("unchecked") final KvCoder<K, V> coder = (KvCoder<K, V>) context.getInput(transform).getCoder();
final SparkRuntimeContext runtimeContext = context.getRuntimeContext();
@SuppressWarnings("unchecked") final WindowingStrategy<?, W> windowingStrategy = (WindowingStrategy<?, W>) context.getInput(transform).getWindowingStrategy();
@SuppressWarnings("unchecked") final WindowFn<Object, W> windowFn = (WindowFn<Object, W>) windowingStrategy.getWindowFn();
//--- coders.
final WindowedValue.WindowedValueCoder<V> wvCoder = WindowedValue.FullWindowedValueCoder.of(coder.getValueCoder(), windowFn.windowCoder());
//--- group by key only.
JavaDStream<WindowedValue<KV<K, Iterable<WindowedValue<V>>>>> groupedByKeyStream = dStream.transform(new Function<JavaRDD<WindowedValue<KV<K, V>>>, JavaRDD<WindowedValue<KV<K, Iterable<WindowedValue<V>>>>>>() {
@Override
public JavaRDD<WindowedValue<KV<K, Iterable<WindowedValue<V>>>>> call(JavaRDD<WindowedValue<KV<K, V>>> rdd) throws Exception {
return GroupCombineFunctions.groupByKeyOnly(rdd, coder.getKeyCoder(), wvCoder);
}
});
//--- now group also by window.
JavaDStream<WindowedValue<KV<K, Iterable<V>>>> outStream = SparkGroupAlsoByWindowViaWindowSet.groupAlsoByWindow(groupedByKeyStream, coder.getKeyCoder(), wvCoder, windowingStrategy, runtimeContext, streamSources);
context.putDataset(transform, new UnboundedDataset<>(outStream, streamSources));
}
@Override
public String toNativeString() {
return "groupByKey()";
}
};
}
use of org.apache.beam.runners.spark.translation.SparkRuntimeContext 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>())";
}
};
}
use of org.apache.beam.runners.spark.translation.SparkRuntimeContext 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 SparkRuntimeContext runtimeContext = context.getRuntimeContext();
final SparkPCollectionView pviews = context.getPViews();
JavaDStream<WindowedValue<KV<K, OutputT>>> outStream = dStream.transform(new Function<JavaRDD<WindowedValue<KV<K, Iterable<InputT>>>>, JavaRDD<WindowedValue<KV<K, OutputT>>>>() {
@Override
public JavaRDD<WindowedValue<KV<K, OutputT>>> call(JavaRDD<WindowedValue<KV<K, Iterable<InputT>>>> rdd) throws Exception {
SparkKeyedCombineFn<K, InputT, ?, OutputT> combineFnWithContext = new SparkKeyedCombineFn<>(fn, runtimeContext, 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>())";
}
};
}
Aggregations