Question

I’m trying to write a program that shows duplicate records to the user to correct the data or remove the duplicate rows. It works, but I had to put a Where clause in my lambda expression to get this working. How can I remove this useless clause?

Where(d => d.Id > 0) at line 22.

public class Person
    {
        public int Id { get; set; }
        public string Name { get; set; }
        public int Age { get; set; }
    }

    public class Program
    {
        static void Main(string[] args)
        {
            List<Person> dt = new List<Person>();
            dt.Add(new Person() { Id = 1, Name = "MICHAEL JACKSON", Age = 50 });
            dt.Add(new Person() { Id = 2, Name = "MICHAEL JACKSON", Age = 51 });
            dt.Add(new Person() { Id = 3, Name = "JOHN LENNON", Age = 40 });
            dt.Add(new Person() { Id = 4, Name = "JOHN LENNON", Age = 41 });
            dt.Add(new Person() { Id = 5, Name = "ELVIS PRESLEY", Age = 42 });

            var duplicates = dt.AsEnumerable().GroupBy(r => r.Name).Where(gr => gr.Count() > 1).ToList();
            if (duplicates.Any())
            {
                var query = duplicates.SelectMany(c => c.Where(d => d.Id > 0)).AsQueryable();

                foreach (var item in query)
                    Console.WriteLine(String.Format("{0} - {1}", item.Name, item.Age));
            }
            else
                Console.WriteLine("No records duplicates.");

            Console.ReadLine();
        }
    }

This is just sample code, my code does a lot of other checks, but if somebody knows how to remove this clause it will be very helpful to me. I think it could impact performance.

Answer 1

This works for me.

            var query = duplicates.SelectMany(c => c).AsQueryable();