I write a faster method for it can make the small one to set. But I test it in some data that some time it's faster that Intersect but some time Intersect fast that my code.
public static bool Contain<T>(List<T> a, List<T> b)
{
if (a.Count <= 10 && b.Count <= 10)
{
return a.Any(b.Contains);
}
if (a.Count > b.Count)
{
return Contain((IEnumerable<T>) b, (IEnumerable<T>) a);
}
return Contain((IEnumerable<T>) a, (IEnumerable<T>) b);
}
public static bool Contain<T>(IEnumerable<T> a, IEnumerable<T> b)
{
HashSet<T> j = new HashSet<T>(a);
return b.Any(j.Contains);
}
The Intersect calls Set that have not check the second size and this is the Intersect's code.
Set<TSource> set = new Set<TSource>(comparer);
foreach (TSource element in second) set.Add(element);
foreach (TSource element in first)
if (set.Remove(element)) yield return element;
The difference in two methods is my method use HashSet and check the count and Intersect use set that is faster than HashSet. We dont warry its performance.
The test :
static void Main(string[] args)
{
var a = Enumerable.Range(0, 100000);
var b = Enumerable.Range(10000000, 1000);
var t = new Stopwatch();
t.Start();
Repeat(()=> { Contain(a, b); });
t.Stop();
Console.WriteLine(t.ElapsedMilliseconds);//490ms
var a1 = Enumerable.Range(0, 100000).ToList();
var a2 = b.ToList();
t.Restart();
Repeat(()=> { Contain(a1, a2); });
t.Stop();
Console.WriteLine(t.ElapsedMilliseconds);//203ms
t.Restart();
Repeat(()=>{ a.Intersect(b).Any(); });
t.Stop();
Console.WriteLine(t.ElapsedMilliseconds);//190ms
t.Restart();
Repeat(()=>{ b.Intersect(a).Any(); });
t.Stop();
Console.WriteLine(t.ElapsedMilliseconds);//497ms
t.Restart();
a.Any(b.Contains);
t.Stop();
Console.WriteLine(t.ElapsedMilliseconds);//600ms
}
private static void Repeat(Action a)
{
for (int i = 0; i < 100; i++)
{
a();
}
}