如何通过 Lambda 或 LINQ 从列表中获取不同的实例

Question

I have a class like this:

class MyClass<T> {
    public string value1 { get; set; }
    public T objT { get; set; }
}

and a list of this class. I would like to use .net 3.5 lambda or linq to get a list of MyClass by distinct value1. I guess this is possible and much simpler than the way in .net 2.0 to cache a list like this:

List<MyClass<T>> list; 
...
List<MyClass<T>> listDistinct = new List<MyClass<T>>();
foreach (MyClass<T> instance in list)
{
    // some code to check if listDistinct does contain obj with intance.Value1
    // then listDistinct.Add(instance);
}

What is the lambda or LINQ way to do it?

Answer 1

Both Marc 's and dahlbyk 's answers seem to work very well. I have a much simpler solution though. Instead of using Distinct , you can use GroupBy . It goes like this:

var listDistinct
    = list.GroupBy(
        i => i.value1,
        (key, group) => group.First()
    ).ToArray();

Notice that I've passed two functions to the GroupBy() . The first is a key selector. The second gets only one item from each group. From your question, I assumed First() was the right one. You can write a different one, if you want to. You can try Last() to see what I mean.

I ran a test with the following input:

var list = new [] {
    new { value1 = "ABC", objT = 0 },
    new { value1 = "ABC", objT = 1 },
    new { value1 = "123", objT = 2 },
    new { value1 = "123", objT = 3 },
    new { value1 = "FOO", objT = 4 },
    new { value1 = "BAR", objT = 5 },
    new { value1 = "BAR", objT = 6 },
    new { value1 = "BAR", objT = 7 },
    new { value1 = "UGH", objT = 8 },
};

The result was:

//{ value1 = ABC, objT = 0 }
//{ value1 = 123, objT = 2 }
//{ value1 = FOO, objT = 4 }
//{ value1 = BAR, objT = 5 }
//{ value1 = UGH, objT = 8 }

I haven't tested it for performance. I believe that this solution is probably a little bit slower than one that uses Distinct . Despite this disadvantage, there are two great advantages: simplicity and flexibility. Usually, it's better to favor simplicity over optimization, but it really depends on the problem you're trying to solve.

Answer 2

Hmm... I'd probably write a custom IEqualityComparer<T> so that I can use:

var listDistinct = list.Distinct(comparer).ToList();

and write the comparer via LINQ....

Possibly a bit overkill, but reusable, at least:

Usage first:

static class Program {
    static void Main() {
        var data = new[] {
            new { Foo = 1,Bar = "a"}, new { Foo = 2,Bar = "b"}, new {Foo = 1, Bar = "c"}
        };
        foreach (var item in data.DistinctBy(x => x.Foo))
            Console.WriteLine(item.Bar);
        }
    }
}

With utility methods:

public static class ProjectionComparer
{
    public static IEnumerable<TSource> DistinctBy<TSource,TValue>(
        this IEnumerable<TSource> source,
        Func<TSource, TValue> selector)
    {
        var comparer = ProjectionComparer<TSource>.CompareBy<TValue>(
            selector, EqualityComparer<TValue>.Default);
        return new HashSet<TSource>(source, comparer);
    }
}
public static class ProjectionComparer<TSource>
{
    public static IEqualityComparer<TSource> CompareBy<TValue>(
        Func<TSource, TValue> selector)
    {
        return CompareBy<TValue>(selector, EqualityComparer<TValue>.Default);
    }
    public static IEqualityComparer<TSource> CompareBy<TValue>(
        Func<TSource, TValue> selector,
        IEqualityComparer<TValue> comparer)
    {
        return new ComparerImpl<TValue>(selector, comparer);
    }
    sealed class ComparerImpl<TValue> : IEqualityComparer<TSource>
    {
        private readonly Func<TSource, TValue> selector;
        private readonly IEqualityComparer<TValue> comparer;
        public ComparerImpl(
            Func<TSource, TValue> selector,
            IEqualityComparer<TValue> comparer)
        {
            if (selector == null) throw new ArgumentNullException("selector");
            if (comparer == null) throw new ArgumentNullException("comparer");
            this.selector = selector;
            this.comparer = comparer;
        }

        bool IEqualityComparer<TSource>.Equals(TSource x, TSource y)
        {
            if (x == null && y == null) return true;
            if (x == null || y == null) return false;
            return comparer.Equals(selector(x), selector(y));
        }

        int IEqualityComparer<TSource>.GetHashCode(TSource obj)
        {
            return obj == null ? 0 : comparer.GetHashCode(selector(obj));
        }
    }
}

Answer 3

You can use this extension method:

    IEnumerable<MyClass> distinctList = sourceList.DistinctBy(x => x.value1);

    public static IEnumerable<TSource> DistinctBy<TSource, TKey>(
        this IEnumerable<TSource> source,
        Func<TSource, TKey> keySelector)
    {
        var knownKeys = new HashSet<TKey>();
        return source.Where(element => knownKeys.Add(keySelector(element)));
    }

Answer 4

Check out Enumerable.Distinct() , which can accept an IEqualityComparer:

class MyClassComparer<T> : IEqualityComparer<MyClass<T>>
{
    // Products are equal if their names and product numbers are equal.
    public bool Equals(MyClass<T> x, MyClass<T>y)
    {
        // Check whether the compared objects reference the same data.
        if (Object.ReferenceEquals(x, y)) return true;

        // Check whether any of the compared objects is null.
        if (Object.ReferenceEquals(x, null) || Object.ReferenceEquals(y, null))
            return false;

        // Check whether the products' properties are equal.
        return x.value1 == y.value1;
    }

    // If Equals() returns true for a pair of objects,
    // GetHashCode must return the same value for these objects.

    public int GetHashCode(MyClass<T> x)
    {
        // Check whether the object is null.
        if (Object.ReferenceEquals(x, null)) return 0;

        // Get the hash code for the Name field if it is not null.
        return (x.value1 ?? "").GetHashCode();
    }
}

Your code snippet could look like this:

List<MyClass<T>> list; 
...
List<MyClass<T>> listDistinct = list.Distinct(new MyClassComparer<T>).ToList();

Answer 5

这会更简单...

var distinctList = list.GroupBy(l => l.value1, (key, c) => l.FirstOrDefault());

Answer 6

在 linq 中，这比分组更先进

list.GroupBy(li => li.value, (key, grp) => li.FirstOrDefault());

Answer 7

I took Marc's answer, fixed it to work with TSource being a value type (test for default(TSource) instead of null), cleaned up some redundant type specifications, and wrote some tests for it. Here is what I am using today. Thank you Marc for the great idea and implementation.

public static class LINQExtensions
{
    public static IEnumerable<TSource> DistinctBy<TSource, TValue>(
        this IEnumerable<TSource> source,
        Func<TSource, TValue> selector)
    {
        var comparer = ProjectionComparer<TSource>.CompareBy(
            selector, EqualityComparer<TValue>.Default);
        return new HashSet<TSource>(source, comparer);
    }
}
public static class ProjectionComparer<TSource>
{
    public static IEqualityComparer<TSource> CompareBy<TValue>(
        Func<TSource, TValue> selector)
    {
        return CompareBy(selector, EqualityComparer<TValue>.Default);
    }
    public static IEqualityComparer<TSource> CompareBy<TValue>(
        Func<TSource, TValue> selector,
        IEqualityComparer<TValue> comparer)
    {
        return new ComparerImpl<TValue>(selector, comparer);
    }
    sealed class ComparerImpl<TValue> : IEqualityComparer<TSource>
    {
        private readonly Func<TSource, TValue> _selector;
        private readonly IEqualityComparer<TValue> _comparer;
        public ComparerImpl(
            Func<TSource, TValue> selector,
            IEqualityComparer<TValue> comparer)
        {
            if (selector == null) throw new ArgumentNullException("selector");
            if (comparer == null) throw new ArgumentNullException("comparer");
            _selector = selector;
            _comparer = comparer;
        }

        bool IEqualityComparer<TSource>.Equals(TSource x, TSource y)
        {
            if (x.Equals(default(TSource)) && y.Equals(default(TSource)))
            {
                return true;
            }

            if (x.Equals(default(TSource)) || y.Equals(default(TSource)))
            {
                return false;
            }
            return _comparer.Equals(_selector(x), _selector(y));
        }

        int IEqualityComparer<TSource>.GetHashCode(TSource obj)
        {
            return obj.Equals(default(TSource)) ? 0 : _comparer.GetHashCode(_selector(obj));
        }
    }
}

And the test class:

[TestClass]
public class LINQExtensionsTest
{
    [TestMethod]
    public void DistinctByTestDate()
    {
        var list = Enumerable.Range(0, 200).Select(i => new
        {
            Index = i,
            Date = DateTime.Today.AddDays(i%4)
        }).ToList();

        var distinctList = list.DistinctBy(l => l.Date).ToList();

        Assert.AreEqual(4, distinctList.Count);

        Assert.AreEqual(0, distinctList[0].Index);
        Assert.AreEqual(1, distinctList[1].Index);
        Assert.AreEqual(2, distinctList[2].Index);
        Assert.AreEqual(3, distinctList[3].Index);

        Assert.AreEqual(DateTime.Today, distinctList[0].Date);
        Assert.AreEqual(DateTime.Today.AddDays(1), distinctList[1].Date);
        Assert.AreEqual(DateTime.Today.AddDays(2), distinctList[2].Date);
        Assert.AreEqual(DateTime.Today.AddDays(3), distinctList[3].Date);

        Assert.AreEqual(200, list.Count);
    }

    [TestMethod]
    public void DistinctByTestInt()
    {
        var list = Enumerable.Range(0, 200).Select(i => new
        {
            Index = i % 4,
            Date = DateTime.Today.AddDays(i)
        }).ToList();

        var distinctList = list.DistinctBy(l => l.Index).ToList();

        Assert.AreEqual(4, distinctList.Count);

        Assert.AreEqual(0, distinctList[0].Index);
        Assert.AreEqual(1, distinctList[1].Index);
        Assert.AreEqual(2, distinctList[2].Index);
        Assert.AreEqual(3, distinctList[3].Index);

        Assert.AreEqual(DateTime.Today, distinctList[0].Date);
        Assert.AreEqual(DateTime.Today.AddDays(1), distinctList[1].Date);
        Assert.AreEqual(DateTime.Today.AddDays(2), distinctList[2].Date);
        Assert.AreEqual(DateTime.Today.AddDays(3), distinctList[3].Date);

        Assert.AreEqual(200, list.Count);
    }

    struct EqualityTester
    {
        public readonly int Index;
        public readonly DateTime Date;

        public EqualityTester(int index, DateTime date) : this()
        {
            Index = index;
            Date = date;
        }
    }

    [TestMethod]
    public void TestStruct()
    {
        var list = Enumerable.Range(0, 200)
            .Select(i => new EqualityTester(i, DateTime.Today.AddDays(i%4)))
            .ToList();

        var distinctDateList = list.DistinctBy(e => e.Date).ToList();
        var distinctIntList = list.DistinctBy(e => e.Index).ToList();

        Assert.AreEqual(4, distinctDateList.Count);
        Assert.AreEqual(200, distinctIntList.Count);
    }
}

Answer 8

As of .NET 6 a new DistinctBy operator has been introduced. So now we can write:

var listDistinct = list.DistinctBy(x => x.value1).ToList();

Here's the implementation in the source code if anyone's interested.