Create batches in linq

Question

Can someone suggest a way to create batches of a certain size in linq?

Ideally I want to be able to perform operations in chunks of some configurable amount.

Answer 1

I wrote a custom IEnumerable implementation that works without linq and guarantees a single enumeration over the data. It also accomplishes all this without requiring backing lists or arrays that cause memory explosions over large data sets.

Here are some basic tests:

    [Fact]
    public void ShouldPartition()
    {
        var ints = new List {0, 1, 2, 3, 4, 5, 6, 7, 8, 9};
        var data = ints.PartitionByMaxGroupSize(3);
        data.Count().Should().Be(4);

        data.Skip(0).First().Count().Should().Be(3);
        data.Skip(0).First().ToList()[0].Should().Be(0);
        data.Skip(0).First().ToList()[1].Should().Be(1);
        data.Skip(0).First().ToList()[2].Should().Be(2);

        data.Skip(1).First().Count().Should().Be(3);
        data.Skip(1).First().ToList()[0].Should().Be(3);
        data.Skip(1).First().ToList()[1].Should().Be(4);
        data.Skip(1).First().ToList()[2].Should().Be(5);

        data.Skip(2).First().Count().Should().Be(3);
        data.Skip(2).First().ToList()[0].Should().Be(6);
        data.Skip(2).First().ToList()[1].Should().Be(7);
        data.Skip(2).First().ToList()[2].Should().Be(8);

        data.Skip(3).First().Count().Should().Be(1);
        data.Skip(3).First().ToList()[0].Should().Be(9);
    }

The Extension Method to partition the data.

/// 

/// A set of extension methods for . 
/// 
public static class EnumerableExtender
{
    /// 

    /// Splits an enumerable into chucks, by a maximum group size.
    /// 
    /// The source to split
    /// The maximum number of items per group.
    /// The type of item to split
    /// A list of lists of the original items.
    public static IEnumerable> PartitionByMaxGroupSize(this IEnumerable source, int maxSize)
    {
        return new SplittingEnumerable(source, maxSize);
    }
}

This is the implementing class

    using System.Collections;
    using System.Collections.Generic;

    internal class SplittingEnumerable : IEnumerable>
    {
        private readonly IEnumerable backing;
        private readonly int maxSize;
        private bool hasCurrent;
        private T lastItem;

        public SplittingEnumerable(IEnumerable backing, int maxSize)
        {
            this.backing = backing;
            this.maxSize = maxSize;
        }

        public IEnumerator> GetEnumerator()
        {
            return new Enumerator(this, this.backing.GetEnumerator());
        }

        IEnumerator IEnumerable.GetEnumerator()
        {
            return this.GetEnumerator();
        }

        private class Enumerator : IEnumerator>
        {
            private readonly SplittingEnumerable parent;
            private readonly IEnumerator backingEnumerator;
            private NextEnumerable current;

            public Enumerator(SplittingEnumerable parent, IEnumerator backingEnumerator)
            {
                this.parent = parent;
                this.backingEnumerator = backingEnumerator;
                this.parent.hasCurrent = this.backingEnumerator.MoveNext();
                if (this.parent.hasCurrent)
                {
                    this.parent.lastItem = this.backingEnumerator.Current;
                }
            }

            public bool MoveNext()
            {
                if (this.current == null)
                {
                    this.current = new NextEnumerable(this.parent, this.backingEnumerator);
                    return true;
                }
                else
                {
                    if (!this.current.IsComplete)
                    {
                        using (var enumerator = this.current.GetEnumerator())
                        {
                            while (enumerator.MoveNext())
                            {
                            }
                        }
                    }
                }

                if (!this.parent.hasCurrent)
                {
                    return false;
                }

                this.current = new NextEnumerable(this.parent, this.backingEnumerator);
                return true;
            }

            public void Reset()
            {
                throw new System.NotImplementedException();
            }

            public IEnumerable Current
            {
                get { return this.current; }
            }

            object IEnumerator.Current
            {
                get { return this.Current; }
            }

            public void Dispose()
            {
            }
        }

        private class NextEnumerable : IEnumerable
        {
            private readonly SplittingEnumerable splitter;
            private readonly IEnumerator backingEnumerator;
            private int currentSize;

            public NextEnumerable(SplittingEnumerable splitter, IEnumerator backingEnumerator)
            {
                this.splitter = splitter;
                this.backingEnumerator = backingEnumerator;
            }

            public bool IsComplete { get; private set; }

            public IEnumerator GetEnumerator()
            {
                return new NextEnumerator(this.splitter, this, this.backingEnumerator);
            }

            IEnumerator IEnumerable.GetEnumerator()
            {
                return this.GetEnumerator();
            }

            private class NextEnumerator : IEnumerator
            {
                private readonly SplittingEnumerable splitter;
                private readonly NextEnumerable parent;
                private readonly IEnumerator enumerator;
                private T currentItem;

                public NextEnumerator(SplittingEnumerable splitter, NextEnumerable parent, IEnumerator enumerator)
                {
                    this.splitter = splitter;
                    this.parent = parent;
                    this.enumerator = enumerator;
                }

                public bool MoveNext()
                {
                    this.parent.currentSize += 1;
                    this.currentItem = this.splitter.lastItem;
                    var hasCcurent = this.splitter.hasCurrent;

                    this.parent.IsComplete = this.parent.currentSize > this.splitter.maxSize;

                    if (this.parent.IsComplete)
                    {
                        return false;
                    }

                    if (hasCcurent)
                    {
                        var result = this.enumerator.MoveNext();

                        this.splitter.lastItem = this.enumerator.Current;
                        this.splitter.hasCurrent = result;
                    }

                    return hasCcurent;
                }

                public void Reset()
                {
                    throw new System.NotImplementedException();
                }

                public T Current
                {
                    get { return this.currentItem; }
                }

                object IEnumerator.Current
                {
                    get { return this.Current; }
                }

                public void Dispose()
                {
                }
            }
        }
    }