using System;

using System.Linq;

using System.Collections.Generic;

​

public class Program

{

    public static void Main()

    {

        var files = new List<DupInfo>{

            new DupInfo(){FilePath = @"C:\User\FakePath.txt", FileSize = 1321056},

            new DupInfo(){FilePath = @"C:\User\FakePath.txt", FileSize = 120556},

            new DupInfo(){FilePath = @"C:\User\ForPeace.txt", FileSize = 1321056},

            new DupInfo(){FilePath = @"C:\User\RealThing.txt", FileSize = 1321056},

            new DupInfo(){FilePath = @"C:\User\RhymeTime.txt", FileSize = 1321056},

            new DupInfo(){FilePath = @"C:\User\won't match.txt", FileSize = 1321056},

            new DupInfo(){FilePath = @"C:\Other\Ham-n-cheese.txt", FileSize = 653096},

            new DupInfo(){FilePath = @"C:\Other\Hyenas.txt", FileSize = 653096},

            new DupInfo(){FilePath = @"C:\Umbrella\ndsFP.txt", FileSize = 1321056}

        };

        var filesSetsWithPossibleDupes = files.GroupBy(f => f.FileSize)

                                              .Where(grp => grp.Count() > 1);

        var masterDuplicateDict = new Dictionary<DupStats, IEnumerable<DupInfo>>();

        //A dictionary keyed by the basic duplicate stats

        //, and whose value is a collection of the possible duplicates

        foreach (var grp in filesSetsWithPossibleDupes)

        {

            var likelyDuplicates = grp.GroupBy(dup => dup.Checksum)

                                      .Where(g => g.Count() > 1);

            //Same GroupBy logic, but applied to the checksum (instead of file size)

            foreach(var dupGrp in likelyDuplicates)

            {

                //Create the key for the dictionary (your code is likely different)

                var sample = dupGrp.First();

                var key = new DupStats() {FileSize = sample.FileSize, Checksum = sample.Checksum};

                masterDuplicateDict.Add(key, dupGrp);

            }

        }

        foreach (var kvp in masterDuplicateDict) 

        {

            Console.WriteLine("Possible duplicates for  Filesize: {0}, Checksum: {1}", kvp.Key.FileSize, kvp.Key.Checksum);

            foreach(var dup in kvp.Value)

            {

                Console.WriteLine("     Path: {0}", dup.FilePath);

            }

        }

    }

}

​

public class DupInfo

{

    public string FilePath {get; set;}

    public long FileSize {get; set;}

    public int Checksum {get { return CalculateChecksum();}}

    public int MaxFolder {get; set;}

    public int CalculateChecksum()

    {

        //some really complicated, expensive operation

        //really, it just compares the string created from the uppercase characters (via hashcode)

        return new String (FilePath.Where(ch => Char.IsUpper(ch)).ToArray()).GetHashCode();

    }

}

public class DupStats

{

    public long FileSize {get; set;}

    public int Checksum {get; set;}

    public override bool Equals(object other)

    {

        var otherStats = other as DupStats;

        if (otherStats == null)

            return false;

        return otherStats.FileSize == this.FileSize

            && otherStats.Checksum == this.Checksum;

    }

    public override int GetHashCode()

    {

        return this.Checksum;

    }

}