Splitting a string into chunks of a certain size

Question

Suppose I had a string:

string str = "1111222233334444"; 

How can I break this string into chunks of some size?

e.g., breaking this into sizes of 4 would return strings:

"1111"
"2222"
"3333"
"4444"

Answer 1

I can't remember who gave me this, but it works great. I speed tested a number of ways to break Enumerable types into groups. The usage would just be like this...

List<string> Divided = Source3.Chunk(24).Select(Piece => string.Concat<char>(Piece)).ToList();

The extention code would look like this...

#region Chunk Logic
private class ChunkedEnumerable<T> : IEnumerable<T>
{
    class ChildEnumerator : IEnumerator<T>
    {
        ChunkedEnumerable<T> parent;
        int position;
        bool done = false;
        T current;


        public ChildEnumerator(ChunkedEnumerable<T> parent)
        {
            this.parent = parent;
            position = -1;
            parent.wrapper.AddRef();
        }

        public T Current
        {
            get
            {
                if (position == -1 || done)
                {
                    throw new InvalidOperationException();
                }
                return current;

            }
        }

        public void Dispose()
        {
            if (!done)
            {
                done = true;
                parent.wrapper.RemoveRef();
            }
        }

        object System.Collections.IEnumerator.Current
        {
            get { return Current; }
        }

        public bool MoveNext()
        {
            position++;

            if (position + 1 > parent.chunkSize)
            {
                done = true;
            }

            if (!done)
            {
                done = !parent.wrapper.Get(position + parent.start, out current);
            }

            return !done;

        }

        public void Reset()
        {
            // per http://msdn.microsoft.com/en-us/library/system.collections.ienumerator.reset.aspx
            throw new NotSupportedException();
        }
    }

    EnumeratorWrapper<T> wrapper;
    int chunkSize;
    int start;

    public ChunkedEnumerable(EnumeratorWrapper<T> wrapper, int chunkSize, int start)
    {
        this.wrapper = wrapper;
        this.chunkSize = chunkSize;
        this.start = start;
    }

    public IEnumerator<T> GetEnumerator()
    {
        return new ChildEnumerator(this);
    }

    System.Collections.IEnumerator System.Collections.IEnumerable.GetEnumerator()
    {
        return GetEnumerator();
    }

}
private class EnumeratorWrapper<T>
{
    public EnumeratorWrapper(IEnumerable<T> source)
    {
        SourceEumerable = source;
    }
    IEnumerable<T> SourceEumerable { get; set; }

    Enumeration currentEnumeration;

    class Enumeration
    {
        public IEnumerator<T> Source { get; set; }
        public int Position { get; set; }
        public bool AtEnd { get; set; }
    }

    public bool Get(int pos, out T item)
    {

        if (currentEnumeration != null && currentEnumeration.Position > pos)
        {
            currentEnumeration.Source.Dispose();
            currentEnumeration = null;
        }

        if (currentEnumeration == null)
        {
            currentEnumeration = new Enumeration { Position = -1, Source = SourceEumerable.GetEnumerator(), AtEnd = false };
        }

        item = default(T);
        if (currentEnumeration.AtEnd)
        {
            return false;
        }

        while (currentEnumeration.Position < pos)
        {
            currentEnumeration.AtEnd = !currentEnumeration.Source.MoveNext();
            currentEnumeration.Position++;

            if (currentEnumeration.AtEnd)
            {
                return false;
            }

        }

        item = currentEnumeration.Source.Current;

        return true;
    }

    int refs = 0;

    // needed for dispose semantics 
    public void AddRef()
    {
        refs++;
    }

    public void RemoveRef()
    {
        refs--;
        if (refs == 0 && currentEnumeration != null)
        {
            var copy = currentEnumeration;
            currentEnumeration = null;
            copy.Source.Dispose();
        }
    }
}
/// <summary>Speed Checked.  Works Great!</summary>
public static IEnumerable<IEnumerable<T>> Chunk<T>(this IEnumerable<T> source, int chunksize)
{
    if (chunksize < 1) throw new InvalidOperationException();

    var wrapper = new EnumeratorWrapper<T>(source);

    int currentPos = 0;
    T ignore;
    try
    {
        wrapper.AddRef();
        while (wrapper.Get(currentPos, out ignore))
        {
            yield return new ChunkedEnumerable<T>(wrapper, chunksize, currentPos);
            currentPos += chunksize;
        }
    }
    finally
    {
        wrapper.RemoveRef();
    }
}
#endregion

Answer 2

This is based on @dove solution but implemented as an extension method.

Benefits:

• Extension method
• Covers corner cases
• Splits string with any chars: numbers, letters, other symbols

Code

public static class EnumerableEx
{    
    public static IEnumerable<string> SplitBy(this string str, int chunkLength)
    {
        if (String.IsNullOrEmpty(str)) throw new ArgumentException();
        if (chunkLength < 1) throw new ArgumentException();

        for (int i = 0; i < str.Length; i += chunkLength)
        {
            if (chunkLength + i > str.Length)
                chunkLength = str.Length - i;

            yield return str.Substring(i, chunkLength);
        }
    }
}

Usage

var result = "bobjoecat".SplitBy(3); // bob, joe, cat

Unit tests removed for brevity (see previous revision)

Answer 3

static IEnumerable<string> Split(string str, double chunkSize)
{
    return Enumerable.Range(0, (int) Math.Ceiling(str.Length/chunkSize))
       .Select(i => new string(str
           .Skip(i * (int)chunkSize)
           .Take((int)chunkSize)
           .ToArray()));
}

and another approach:

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

public class Program
{
    public static void Main()
    {

        var x = "Hello World";
        foreach(var i in x.ChunkString(2)) Console.WriteLine(i);
    }
}

public static class Ext{
    public static IEnumerable<string> ChunkString(this string val, int chunkSize){
        return val.Select((x,i) => new {Index = i, Value = x})
                  .GroupBy(x => x.Index/chunkSize, x => x.Value)
                  .Select(x => string.Join("",x));
    }
}

Answer 4

Personally I prefer my solution :-)

It handles:

• String lengths that are a multiple of the chunk size.
• String lengths that are NOT a multiple of the chunk size.
• String lengths that are smaller than the chunk size.
• NULL and empty strings (throws an exception).
• Chunk sizes smaller than 1 (throws an exception).

It is implemented as a extension method, and it calculates the number of chunks is going to generate beforehand. It checks the last chunk because in case the text length is not a multiple it needs to be shorter. Clean, short, easy to understand... and works!

    public static string[] Split(this string value, int chunkSize)
    {
        if (string.IsNullOrEmpty(value)) throw new ArgumentException("The string cannot be null.");
        if (chunkSize < 1) throw new ArgumentException("The chunk size should be equal or greater than one.");

        int remainder;
        int divResult = Math.DivRem(value.Length, chunkSize, out remainder);

        int numberOfChunks = remainder > 0 ? divResult + 1 : divResult;
        var result = new string[numberOfChunks];

        int i = 0;
        while (i < numberOfChunks - 1)
        {
            result[i] = value.Substring(i * chunkSize, chunkSize);
            i++;
        }

        int lastChunkSize = remainder > 0 ? remainder : chunkSize;
        result[i] = value.Substring(i * chunkSize, lastChunkSize);

        return result;
    }

Answer 5

It's not pretty and it's not fast, but it works, it's a one-liner and it's LINQy:

List<string> a = text.Select((c, i) => new { Char = c, Index = i }).GroupBy(o => o.Index / 4).Select(g => new String(g.Select(o => o.Char).ToArray())).ToList();

Answer 6

You can use morelinq by Jon Skeet. Use Batch like:

string str = "1111222233334444";
int chunkSize = 4;
var chunks = str.Batch(chunkSize).Select(r => new String(r.ToArray()));

This will return 4 chunks for the string "1111222233334444". If the string length is less than or equal to the chunk size Batch will return the string as the only element of IEnumerable<string>

For output:

foreach (var chunk in chunks)
{
    Console.WriteLine(chunk);
}

and it will give:

1111
2222
3333
4444