问题
Using LINQ, from a List<int>, how can I retrieve a list that contains entries repeated more than once and their values?
回答1:
The easiest way to solve the problem is to group the elements based on their value, and then pick a representative of the group if there are more than one element in the group. In LINQ, this translates to:
var query = lst.GroupBy(x => x)
.Where(g => g.Count() > 1)
.Select(y => y.Key)
.ToList();
If you want to know how many times the elements are repeated, you can use:
var query = lst.GroupBy(x => x)
.Where(g => g.Count() > 1)
.Select(y => new { Element = y.Key, Counter = y.Count() })
.ToList();
This will return a List of an anonymous type, and each element will have the properties Element and Counter, to retrieve the information you need.
And lastly, if it's a dictionary you are looking for, you can use
var query = lst.GroupBy(x => x)
.Where(g => g.Count() > 1)
.ToDictionary(x => x.Key, y => y.Count());
This will return a dictionary, with your element as key, and the number of times it's repeated as value.
回答2:
Find out if an enumerable contains any duplicate :
var anyDuplicate = enumerable.GroupBy(x => x.Key).Any(g => g.Count() > 1);
Find out if all values in an enumerable are unique :
var allUnique = enumerable.GroupBy(x => x.Key).All(g => g.Count() == 1);
回答3:
Another way is using HashSet:
var hash = new HashSet<int>();
var duplicates = list.Where(i => !hash.Add(i));
If you want unique values in your duplicates list:
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();
Here is the same solution as a generic extension method:
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);
}
}
回答4:
You can do this:
var list = new[] {1,2,3,1,4,2};
var duplicateItems = list.Duplicates();
With these extension methods:
public static class Extensions
{
public static IEnumerable<TSource> Duplicates<TSource, TKey>(this IEnumerable<TSource> source, Func<TSource, TKey> selector)
{
var grouped = source.GroupBy(selector);
var moreThan1 = grouped.Where(i => i.IsMultiple());
return moreThan1.SelectMany(i => i);
}
public static IEnumerable<TSource> Duplicates<TSource, TKey>(this IEnumerable<TSource> source)
{
return source.Duplicates(i => i);
}
public static bool IsMultiple<T>(this IEnumerable<T> source)
{
var enumerator = source.GetEnumerator();
return enumerator.MoveNext() && enumerator.MoveNext();
}
}
Using IsMultiple() in the Duplicates method is faster than Count() because this does not iterate the whole collection.
回答5:
I created a extention to response to this you could includ it in your projects, I think this return the most case when you search for duplicates in List or Linq.
Example:
//Dummy class to compare in list
public class Person
{
public int Id { get; set; }
public string Name { get; set; }
public string Surname { get; set; }
public Person(int id, string name, string surname)
{
this.Id = id;
this.Name = name;
this.Surname = surname;
}
}
//The extention static class
public static class Extention
{
public static IEnumerable<T> getMoreThanOnceRepeated<T>(this IEnumerable<T> extList, Func<T, object> groupProps) where T : class
{ //Return only the second and next reptition
return extList
.GroupBy(groupProps)
.SelectMany(z => z.Skip(1)); //Skip the first occur and return all the others that repeats
}
public static IEnumerable<T> getAllRepeated<T>(this IEnumerable<T> extList, Func<T, object> groupProps) where T : class
{
//Get All the lines that has repeating
return extList
.GroupBy(groupProps)
.Where(z => z.Count() > 1) //Filter only the distinct one
.SelectMany(z => z);//All in where has to be retuned
}
}
//how to use it:
void DuplicateExample()
{
//Populate List
List<Person> PersonsLst = new List<Person>(){
new Person(1,"Ricardo","Figueiredo"), //fist Duplicate to the example
new Person(2,"Ana","Figueiredo"),
new Person(3,"Ricardo","Figueiredo"),//second Duplicate to the example
new Person(4,"Margarida","Figueiredo"),
new Person(5,"Ricardo","Figueiredo")//third Duplicate to the example
};
Console.WriteLine("All:");
PersonsLst.ForEach(z => Console.WriteLine("{0} -> {1} {2}", z.Id, z.Name, z.Surname));
/* OUTPUT:
All:
1 -> Ricardo Figueiredo
2 -> Ana Figueiredo
3 -> Ricardo Figueiredo
4 -> Margarida Figueiredo
5 -> Ricardo Figueiredo
*/
Console.WriteLine("All lines with repeated data");
PersonsLst.getAllRepeated(z => new { z.Name, z.Surname })
.ToList()
.ForEach(z => Console.WriteLine("{0} -> {1} {2}", z.Id, z.Name, z.Surname));
/* OUTPUT:
All lines with repeated data
1 -> Ricardo Figueiredo
3 -> Ricardo Figueiredo
5 -> Ricardo Figueiredo
*/
Console.WriteLine("Only Repeated more than once");
PersonsLst.getMoreThanOnceRepeated(z => new { z.Name, z.Surname })
.ToList()
.ForEach(z => Console.WriteLine("{0} -> {1} {2}", z.Id, z.Name, z.Surname));
/* OUTPUT:
Only Repeated more than once
3 -> Ricardo Figueiredo
5 -> Ricardo Figueiredo
*/
}
回答6:
To find the duplicate values only :
var duplicates = list.GroupBy(x => x.Key).Any(g => g.Count() > 1);
Eg. var list = new[] {1,2,3,1,4,2};
so group by will group the numbers by their keys and will maintain the count(number of times it repeated) with it. After that, we are just checking the values who have repeated more than once.
To find the uniuqe values only :
var unique = list.GroupBy(x => x.Key).All(g => g.Count() == 1);
Eg. var list = new[] {1,2,3,1,4,2};
so group by will group the numbers by their keys and will maintain the count(number of times it repeated) with it. After that, we are just checking the values who have repeated only once means are unique.
回答7:
Complete set of Linq to SQL extensions of Duplicates functions checked in MS SQL Server. Without using .ToList() or IEnumerable. These queries executing in SQL Server rather than in memory.. The results only return at memory.
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()));
}
来源：https://stackoverflow.com/questions/18547354/c-sharp-linq-find-duplicates-in-list