如何通过Lambda或LINQ从列表中获取不同的实例

Question

我有一个这样的课程：

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

以及此类的列表。我想使用.net 3.5 lambda或linq来获取不同value1的MyClass列表。我想这可能比在.net 2.0中缓存像这样的列表的方式简单得多：

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);
}

lambda或LINQ的方法是什么？

Answer 1

Marc 和 dahlbyk 的答案似乎都很有效。我有一个更简单的解决方案。您可以使用Distinct，而不是使用GroupBy。它是这样的：

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

请注意，我已将两个函数传递给GroupBy()。第一个是键选择器。第二个只从每个组中获得一个项目。从你的问题来看，我认为First()是正确的。如果你愿意，你可以写一个不同的。您可以尝试Last()查看我的意思。

我使用以下输入进行了测试：

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 },
};

结果是：

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

我没有测试它的性能。我相信这个解决方案可能比使用Distinct的解决方案慢一点。尽管有这个缺点，但有两个很大的优点：简单和灵活。通常，最好是简化优于优化，但它实际上取决于您尝试解决的问题。

Answer 2

嗯......我可能会写一个自定义IEqualityComparer<T>，以便我可以使用：

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

并通过LINQ编写比较器....

可能有点矫枉过正，但可重复使用，至少：

用法优先：

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);
        }
    }
}

使用实用方法：

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

您可以使用此扩展方法：

    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

查看Enumerable.Distinct()，它可以接受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();
    }
}

您的代码段可能如下所示：

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，这更适合群组

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

Answer 7

我接受了Marc的回答，将其修复为使用TSource作为值类型（默认测试（TSource）而不是null），清理了一些冗余类型规范，并为其编写了一些测试。这是我今天使用的。谢谢Marc的好主意和实施。

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));
        }
    }
}

测试类：

[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);
    }
}