parallel-processing - 是否有一种从Java 8流中提取数据 block 的好方法？

Question

我是ETL流程，正在从Spring Data Repository中检索很多实体。然后，我使用并行流将实体映射到不同的实体。
我既可以使用使用者将这些新实体一个接一个地存储在另一个存储库中，也可以将它们收集到一个列表中并以单个批量操作的形式存储。
前者成本很高，而后者可能超出可用内存。

有没有一种很好的方法来收集流中的一定数量的元素(如limit一样)，消耗该块并继续并行进行直到处理完所有元素？

Answer 1

我使用分块进行批量操作的方法是使用分区分割器包装器，另一个包装器将默认的分割策略(批量大小的算术级数以1024为增量)覆盖为简单的固定批量分割。像这样使用它:

Stream<OriginalType> existingStream = ...;
Stream<List<OriginalType>> partitioned = partition(existingStream, 100, 1);
partitioned.forEach(chunk -> ... process the chunk ...);

这是完整的代码:

import java.util.ArrayList;
import java.util.List;
import java.util.Spliterator;
import java.util.Spliterators.AbstractSpliterator;
import java.util.function.Consumer;
import java.util.stream.Stream;
import java.util.stream.StreamSupport;

public class PartitioningSpliterator<E> extends AbstractSpliterator<List<E>>
{
  private final Spliterator<E> spliterator;
  private final int partitionSize;

  public PartitioningSpliterator(Spliterator<E> toWrap, int partitionSize) {
    super(toWrap.estimateSize(), toWrap.characteristics() | Spliterator.NONNULL);
    if (partitionSize <= 0) throw new IllegalArgumentException(
        "Partition size must be positive, but was " + partitionSize);
    this.spliterator = toWrap;
    this.partitionSize = partitionSize;
  }

  public static <E> Stream<List<E>> partition(Stream<E> in, int size) {
    return StreamSupport.stream(new PartitioningSpliterator(in.spliterator(), size), false);
  }

  public static <E> Stream<List<E>> partition(Stream<E> in, int size, int batchSize) {
    return StreamSupport.stream(
        new FixedBatchSpliterator<>(new PartitioningSpliterator<>(in.spliterator(), size), batchSize), false);
  }

  @Override public boolean tryAdvance(Consumer<? super List<E>> action) {
    final ArrayList<E> partition = new ArrayList<>(partitionSize);
    while (spliterator.tryAdvance(partition::add) 
           && partition.size() < partitionSize);
    if (partition.isEmpty()) return false;
    action.accept(partition);
    return true;
  }

  @Override public long estimateSize() {
    final long est = spliterator.estimateSize();
    return est == Long.MAX_VALUE? est
         : est / partitionSize + (est % partitionSize > 0? 1 : 0);
  }
}

import static java.util.Spliterators.spliterator;

import java.util.Comparator;
import java.util.Spliterator;
import java.util.function.Consumer;

public abstract class FixedBatchSpliteratorBase<T> implements Spliterator<T> {
  private final int batchSize;
  private final int characteristics;
  private long est;

  public FixedBatchSpliteratorBase(int characteristics, int batchSize, long est) {
    characteristics |= ORDERED;
    if ((characteristics & SIZED) != 0) characteristics |= SUBSIZED;
    this.characteristics = characteristics;
    this.batchSize = batchSize;
    this.est = est;
  }
  public FixedBatchSpliteratorBase(int characteristics, int batchSize) {
    this(characteristics, batchSize, Long.MAX_VALUE);
  }
  public FixedBatchSpliteratorBase(int characteristics) {
    this(characteristics, 64, Long.MAX_VALUE);
  }

  @Override public Spliterator<T> trySplit() {
    final HoldingConsumer<T> holder = new HoldingConsumer<>();
    if (!tryAdvance(holder)) return null;
    final Object[] a = new Object[batchSize];
    int j = 0;
    do a[j] = holder.value; while (++j < batchSize && tryAdvance(holder));
    if (est != Long.MAX_VALUE) est -= j;
    return spliterator(a, 0, j, characteristics());
  }
  @Override public Comparator<? super T> getComparator() {
    if (hasCharacteristics(SORTED)) return null;
    throw new IllegalStateException();
  }
  @Override public long estimateSize() { return est; }
  @Override public int characteristics() { return characteristics; }

  static final class HoldingConsumer<T> implements Consumer<T> {
    Object value;
    @Override public void accept(T value) { this.value = value; }
  }
}

import static java.util.stream.StreamSupport.stream;

import java.util.Spliterator;
import java.util.function.Consumer;
import java.util.stream.Stream;

public class FixedBatchSpliterator<T> extends FixedBatchSpliteratorBase<T> {
  private final Spliterator<T> spliterator;

  public FixedBatchSpliterator(Spliterator<T> toWrap, int batchSize, long est) {
    super(toWrap.characteristics(), batchSize, est);
    this.spliterator = toWrap;
  }
  public FixedBatchSpliterator(Spliterator<T> toWrap, int batchSize) {
    this(toWrap, batchSize, toWrap.estimateSize());
  }
  public FixedBatchSpliterator(Spliterator<T> toWrap) {
    this(toWrap, 64, toWrap.estimateSize());
  }

  public static <T> Stream<T> withBatchSize(Stream<T> in, int batchSize) {
    return stream(new FixedBatchSpliterator<>(in.spliterator(), batchSize), true);
  }

  public static <T> FixedBatchSpliterator<T> batchedSpliterator(Spliterator<T> toWrap, int batchSize) {
    return new FixedBatchSpliterator<>(toWrap, batchSize);
  }

  @Override public boolean tryAdvance(Consumer<? super T> action) {
    return spliterator.tryAdvance(action);
  }
  @Override public void forEachRemaining(Consumer<? super T> action) {
    spliterator.forEachRemaining(action);
  }
}