完整的集Linq到SQL扩展的重复功能检查在MS SQL Server。不使用. tolist()或IEnumerable。这些查询在SQL Server中执行，而不是在内存中。结果只在内存中返回。

public static class Linq2SqlExtensions {

    public class CountOfT<T> {
        public T Key { get; set; }
        public int Count { get; set; }
    }

    public static IQueryable<TKey> Duplicates<TSource, TKey>(this IQueryable<TSource> source, Expression<Func<TSource, TKey>> groupBy)
        => source.GroupBy(groupBy).Where(w => w.Count() > 1).Select(s => s.Key);

    public static IQueryable<TSource> GetDuplicates<TSource, TKey>(this IQueryable<TSource> source, Expression<Func<TSource, TKey>> groupBy)
        => source.GroupBy(groupBy).Where(w => w.Count() > 1).SelectMany(s => s);

    public static IQueryable<CountOfT<TKey>> DuplicatesCounts<TSource, TKey>(this IQueryable<TSource> source, Expression<Func<TSource, TKey>> groupBy)
        => source.GroupBy(groupBy).Where(w => w.Count() > 1).Select(y => new CountOfT<TKey> { Key = y.Key, Count = y.Count() });

    public static IQueryable<Tuple<TKey, int>> DuplicatesCountsAsTuble<TSource, TKey>(this IQueryable<TSource> source, Expression<Func<TSource, TKey>> groupBy)
        => source.GroupBy(groupBy).Where(w => w.Count() > 1).Select(s => Tuple.Create(s.Key, s.Count()));
}

所有的GroupBy答案都是最简单的，但不是最有效的。它们对内存性能尤其不利，因为构建大型内部集合需要分配成本。

一个不错的替代方案是HuBeZa的HashSet。基于添加的方法。它表现得更好。

如果你不关心空值，就我所知，像这样的东西是最有效的(CPU和内存):

public static IEnumerable<TProperty> Duplicates<TSource, TProperty>(
    this IEnumerable<TSource> source,
    Func<TSource, TProperty> duplicateSelector,
    IEqualityComparer<TProperty> comparer = null)
{
    comparer ??= EqualityComparer<TProperty>.Default;

    Dictionary<TProperty, int> counts = new Dictionary<TProperty, int>(comparer);

    foreach (var item in source)
    {
        TProperty property = duplicateSelector(item);
        counts.TryGetValue(property, out int count);

        switch (count)
        {
            case 0:
                counts[property] = ++count;
                break;

            case 1:
                counts[property] = ++count;
                yield return property;
                break;
        }
    }
}

这里的技巧是在重复数达到1时避免额外的查找成本。当然，如果您还想知道每个项重复出现的次数，则可以使用count不断更新字典。对于null，你只需要一些额外的处理，仅此而已。

找出一个枚举对象是否包含任何重复项:

var anyDuplicate = enumerable.GroupBy(x => x.Key).Any(g => g.Count() > 1);

找出一个枚举对象中的所有值是否都是唯一的:

var allUnique = enumerable.GroupBy(x => x.Key).All(g => g.Count() == 1);

Linq查询:

var query = from s2 in (from s in someList group s by new { s.Column1, s.Column2 } into sg select sg) where s2.Count() > 1 select s2;

另一种方法是使用HashSet:

var hash = new HashSet<int>();
var duplicates = list.Where(i => !hash.Add(i));

如果你想在你的重复列表中的唯一值:

var myhash = new HashSet<int>();
var mylist = new List<int>(){1,1,2,2,3,3,3,4,4,4};
var duplicates = mylist.Where(item => !myhash.Add(item)).Distinct().ToList();

下面是与通用扩展方法相同的解决方案:

public static class Extensions
{
  public static IEnumerable<TSource> GetDuplicates<TSource, TKey>(this IEnumerable<TSource> source, Func<TSource, TKey> selector, IEqualityComparer<TKey> comparer)
  {
    var hash = new HashSet<TKey>(comparer);
    return source.Where(item => !hash.Add(selector(item))).ToList();
  }

  public static IEnumerable<TSource> GetDuplicates<TSource>(this IEnumerable<TSource> source, IEqualityComparer<TSource> comparer)
  {
    return source.GetDuplicates(x => x, comparer);      
  }

  public static IEnumerable<TSource> GetDuplicates<TSource, TKey>(this IEnumerable<TSource> source, Func<TSource, TKey> selector)
  {
    return source.GetDuplicates(selector, null);
  }

  public static IEnumerable<TSource> GetDuplicates<TSource>(this IEnumerable<TSource> source)
  {
    return source.GetDuplicates(x => x, null);
  }
}

完整的集Linq到SQL扩展的重复功能检查在MS SQL Server。不使用. tolist()或IEnumerable。这些查询在SQL Server中执行，而不是在内存中。结果只在内存中返回。

public static class Linq2SqlExtensions {

    public class CountOfT<T> {
        public T Key { get; set; }
        public int Count { get; set; }
    }

    public static IQueryable<TKey> Duplicates<TSource, TKey>(this IQueryable<TSource> source, Expression<Func<TSource, TKey>> groupBy)
        => source.GroupBy(groupBy).Where(w => w.Count() > 1).Select(s => s.Key);

    public static IQueryable<TSource> GetDuplicates<TSource, TKey>(this IQueryable<TSource> source, Expression<Func<TSource, TKey>> groupBy)
        => source.GroupBy(groupBy).Where(w => w.Count() > 1).SelectMany(s => s);

    public static IQueryable<CountOfT<TKey>> DuplicatesCounts<TSource, TKey>(this IQueryable<TSource> source, Expression<Func<TSource, TKey>> groupBy)
        => source.GroupBy(groupBy).Where(w => w.Count() > 1).Select(y => new CountOfT<TKey> { Key = y.Key, Count = y.Count() });

    public static IQueryable<Tuple<TKey, int>> DuplicatesCountsAsTuble<TSource, TKey>(this IQueryable<TSource> source, Expression<Func<TSource, TKey>> groupBy)
        => source.GroupBy(groupBy).Where(w => w.Count() > 1).Select(s => Tuple.Create(s.Key, s.Count()));
}