Remover duplicados

CSharp · Console

/Program.cs

using System;
using System.Collections.Generic;
using System.Linq;
					
public class Program
{
	public static void Main()
	{
            var person1 = new Person() {id = 1, name = "Bob" };
            var person2 = new Person() {id = 2, name = "Ted" };
            var person3 = new Person() {id = 3, name = "Will_1" };
			var person4 = new Person() {id = 4, name = "Will_2" };

            person1.documents.Add(new IdentificationDocument() { number = "123" });
            person2.documents.Add(new IdentificationDocument() { number = "456" });
            person3.documents.Add(new IdentificationDocument() { number = "789" });
			person3.documents.Add(new IdentificationDocument() { number = "147" });
			person4.documents.Add(new IdentificationDocument() { number = "789" }); //duplicate
			person4.documents.Add(new IdentificationDocument() { number = "147" }); //duplicate
			

            var personList1 = new List<Person>();

            personList1.Add(person1);
            personList1.Add(person2);
			personList1.Add(person3);
			personList1.Add(person4);
		
		
		    //More data for performance test
		    for (int i = 0; i < 20000; i++)
            {
                var personx = new Person() { id = i, name = Guid.NewGuid().ToString() };
                personx.documents.Add(new IdentificationDocument() { number = Guid.NewGuid().ToString() });
                personx.documents.Add(new IdentificationDocument() { number = Guid.NewGuid().ToString() });
                personList1.Add(personx);
            }
		
			var result = new List<Person>();

			foreach (var person in personList1)
			{
    			if (!result.Any(r => r.documents.SelectMany(rd => rd.number)
        			.Intersect(person.documents.SelectMany(pd => pd.number))
        			.Any()))
    			{
        			result.Add(person);
    			}
			}

            result.ForEach(r => Console.WriteLine(r.id + " " +r.name));
		
		//Expected result:
		//1 Bob
		//2 Ted
		//3 Will_1
		
		//Note: Select instead SelectMany works, but is too slow when i have many elements (> 200 thousand)

		
	}
	
	public class Person
    {
		public int id { get; set; }
        public string name { get; set; }
        public List<IdentificationDocument> documents { get; set; }

        public Person()
        {
            documents = new List<IdentificationDocument>();
        }
    }

    public class IdentificationDocument
    {
        public string number { get; set; }
    }
}