[BUG] DistinctBy去重存在问题

[li-zheng-hao]

IEnumerable<int> arr = new List<int>() { 1, 2, 3 };

arr=arr.DistinctByEx(it => it);
arr.Count();
// 迭代无法获取到值
foreach (var i in arr)
{
    Console.Out.WriteLine("i={0}", i);
}
public static class Test
{
    public static IEnumerable<TSource> DistinctByEx<TSource, TKey>(
        this IEnumerable<TSource> source,
        Func<TSource, TKey> keySelector)
    {
        HashSet<TKey> hash = new HashSet<TKey>();
        return source.Where<TSource>((Func<TSource, bool>) (p => hash.Add(keySelector(p))));
    }

}

使用了Count之后无法遍历集合，调试发现在Count内部调用了where的条件判断：

导致foreach遍历时迭代器再次判断where条件时HashSet内部已经有值

建议替换成System.Linq内的官方写法，实测没有问题

public static IEnumerable<TSource> DistinctBy<TSource, TKey>(this IEnumerable<TSource> source, Func<TSource, TKey> keySelector, IEqualityComparer<TKey>? comparer)
{
    if (source is null)
    {
        ThrowHelper.ThrowArgumentNullException(ExceptionArgument.source);
    }
    if (keySelector is null)
    {
        ThrowHelper.ThrowArgumentNullException(ExceptionArgument.keySelector);
    }

    return DistinctByIterator(source, keySelector, comparer);
}

private static IEnumerable<TSource> DistinctByIterator<TSource, TKey>(IEnumerable<TSource> source, Func<TSource, TKey> keySelector, IEqualityComparer<TKey>? comparer)
{
    using IEnumerator<TSource> enumerator = source.GetEnumerator();

    if (enumerator.MoveNext())
    {
        var set = new HashSet<TKey>(DefaultInternalSetCapacity, comparer);
        do
        {
            TSource element = enumerator.Current;
            if (set.Add(keySelector(element)))
            {
                yield return element;
            }
        }
        while (enumerator.MoveNext());
    }
}

[li-zheng-hao]

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

public static IEnumerable<TSource> DistinctBy<TSource, TKey>(this IEnumerable<TSource> source,
    Func<TSource, TKey> keySelector, IEqualityComparer<TKey>? comparer)
{
    if (source == null) throw new ArgumentNullException(nameof(source));
    if (keySelector == null) throw new ArgumentNullException(nameof(keySelector));

    return _(); IEnumerable<TSource> _()
    {
        var knownKeys = new HashSet<TKey>(comparer);
        foreach (var element in source)
        {
            if (knownKeys.Add(keySelector(element)))
                yield return element;
        }
    }
}

这种写法也可以

[ldqk]

已修正