Replace sequence of bytes in binary file

Question

What is the best method to replace sequence of bytes in binary file to the same length of other bytes? The binary files will be pretty large, about 50 mb and should not be loade

Answer 1

You can use my BinaryUtility to search and replace one or more bytes without loading the entire file into memory like this:

var searchAndReplace = new List>() 
{
    Tuple.Create(
        BitConverter.GetBytes((UInt32)0xDEADBEEF),
        BitConverter.GetBytes((UInt32)0x01234567)),
    Tuple.Create(
        BitConverter.GetBytes((UInt32)0xAABBCCDD),
        BitConverter.GetBytes((UInt16)0xAFFE)),
};
using(var reader =
    new BinaryReader(new FileStream(@"C:\temp\data.bin", FileMode.Open)))
{
    using(var writer =
        new BinaryWriter(new FileStream(@"C:\temp\result.bin", FileMode.Create)))
    {
        BinaryUtility.Replace(reader, writer, searchAndReplace);
    }
}

BinaryUtility code:

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

public static class BinaryUtility
{
    public static IEnumerable GetByteStream(BinaryReader reader)
    {
        const int bufferSize = 1024;
        byte[] buffer;
        do
        {
            buffer = reader.ReadBytes(bufferSize);
            foreach (var d in buffer) { yield return d; }
        } while (bufferSize == buffer.Length);
    }

    public static void Replace(BinaryReader reader, BinaryWriter writer, IEnumerable> searchAndReplace)
    {
        foreach (byte d in Replace(GetByteStream(reader), searchAndReplace)) { writer.Write(d); }
    }

    public static IEnumerable Replace(IEnumerable source, IEnumerable> searchAndReplace)
    {
        foreach (var s in searchAndReplace)
        {
            source = Replace(source, s.Item1, s.Item2);
        }
        return source;
    }

    public static IEnumerable Replace(IEnumerable input, IEnumerable from, IEnumerable to)
    {
        var fromEnumerator = from.GetEnumerator();
        fromEnumerator.MoveNext();
        int match = 0;
        foreach (var data in input)
        {
            if (data == fromEnumerator.Current)
            {
                match++;
                if (fromEnumerator.MoveNext()) { continue; }
                foreach (byte d in to) { yield return d; }
                match = 0;
                fromEnumerator.Reset();
                fromEnumerator.MoveNext();
                continue;
            }
            if (0 != match)
            {
                foreach (byte d in from.Take(match)) { yield return d; }
                match = 0;
                fromEnumerator.Reset();
                fromEnumerator.MoveNext();
            }
            yield return data;
        }
        if (0 != match)
        {
            foreach (byte d in from.Take(match)) { yield return d; }
        }
    }
}