我有一份人们的身份证和名字的名单,还有一份人们的身份证和姓氏的名单。有些人没有名字,有些人没有姓;我想在这两个列表上做一个完整的外部连接。

下面列出:

ID  FirstName
--  ---------
 1  John
 2  Sue

ID  LastName
--  --------
 1  Doe
 3  Smith

应该生产:

ID  FirstName  LastName
--  ---------  --------
 1  John       Doe
 2  Sue
 3             Smith

我已经发现了相当多的解决方案的“LINQ外部连接”,它们看起来都很相似,但似乎真的是离开外部连接。

到目前为止我的尝试是这样的:

private void OuterJoinTest()
{
    List<FirstName> firstNames = new List<FirstName>();
    firstNames.Add(new FirstName { ID = 1, Name = "John" });
    firstNames.Add(new FirstName { ID = 2, Name = "Sue" });

    List<LastName> lastNames = new List<LastName>();
    lastNames.Add(new LastName { ID = 1, Name = "Doe" });
    lastNames.Add(new LastName { ID = 3, Name = "Smith" });

    var outerJoin = from first in firstNames
        join last in lastNames
        on first.ID equals last.ID
        into temp
        from last in temp.DefaultIfEmpty()
        select new
        {
            id = first != null ? first.ID : last.ID,
            firstname = first != null ? first.Name : string.Empty,
            surname = last != null ? last.Name : string.Empty
        };
    }
}

public class FirstName
{
    public int ID;
    
    public string Name;
}
    
public class LastName
{
    public int ID;
    
    public string Name;
}

但结果是:

ID  FirstName  LastName
--  ---------  --------
 1  John       Doe
 2  Sue

我做错了什么?


当前回答

我不知道这是否适用于所有情况,但从逻辑上讲,这似乎是正确的。其思想是取一个左外连接和一个右外连接,然后取结果的并集。

var firstNames = new[]
{
    new { ID = 1, Name = "John" },
    new { ID = 2, Name = "Sue" },
};
var lastNames = new[]
{
    new { ID = 1, Name = "Doe" },
    new { ID = 3, Name = "Smith" },
};
var leftOuterJoin =
    from first in firstNames
    join last in lastNames on first.ID equals last.ID into temp
    from last in temp.DefaultIfEmpty()
    select new
    {
        first.ID,
        FirstName = first.Name,
        LastName = last?.Name,
    };
var rightOuterJoin =
    from last in lastNames
    join first in firstNames on last.ID equals first.ID into temp
    from first in temp.DefaultIfEmpty()
    select new
    {
        last.ID,
        FirstName = first?.Name,
        LastName = last.Name,
    };
var fullOuterJoin = leftOuterJoin.Union(rightOuterJoin);

这就像写的一样,因为它是在LINQ to Objects中。如果LINQ to SQL或其他,查询处理器可能不支持安全导航或其他操作。你必须使用条件操作符有条件地获取值。

也就是说,

var leftOuterJoin =
    from first in firstNames
    join last in lastNames on first.ID equals last.ID into temp
    from last in temp.DefaultIfEmpty()
    select new
    {
        first.ID,
        FirstName = first.Name,
        LastName = last != null ? last.Name : default,
    };

其他回答

正如您所发现的,Linq没有“外部连接”结构。您所能得到的最接近的是使用您所声明的查询的左外连接。为此,你可以添加任何没有在join中表示的姓氏列表元素:

outerJoin = outerJoin.Concat(lastNames.Select(l=>new
                            {
                                id = l.ID,
                                firstname = String.Empty,
                                surname = l.Name
                            }).Where(l=>!outerJoin.Any(o=>o.id == l.id)));

我不知道这是否适用于所有情况,但从逻辑上讲,这似乎是正确的。其思想是取一个左外连接和一个右外连接,然后取结果的并集。

var firstNames = new[]
{
    new { ID = 1, Name = "John" },
    new { ID = 2, Name = "Sue" },
};
var lastNames = new[]
{
    new { ID = 1, Name = "Doe" },
    new { ID = 3, Name = "Smith" },
};
var leftOuterJoin =
    from first in firstNames
    join last in lastNames on first.ID equals last.ID into temp
    from last in temp.DefaultIfEmpty()
    select new
    {
        first.ID,
        FirstName = first.Name,
        LastName = last?.Name,
    };
var rightOuterJoin =
    from last in lastNames
    join first in firstNames on last.ID equals first.ID into temp
    from first in temp.DefaultIfEmpty()
    select new
    {
        last.ID,
        FirstName = first?.Name,
        LastName = last.Name,
    };
var fullOuterJoin = leftOuterJoin.Union(rightOuterJoin);

这就像写的一样,因为它是在LINQ to Objects中。如果LINQ to SQL或其他,查询处理器可能不支持安全导航或其他操作。你必须使用条件操作符有条件地获取值。

也就是说,

var leftOuterJoin =
    from first in firstNames
    join last in lastNames on first.ID equals last.ID into temp
    from last in temp.DefaultIfEmpty()
    select new
    {
        first.ID,
        FirstName = first.Name,
        LastName = last != null ? last.Name : default,
    };

我大约在6年前为一个应用程序编写了这个扩展类,并且从那时起一直在许多解决方案中使用它,没有任何问题。希望能有所帮助。

编辑:我注意到有些人可能不知道如何使用扩展类。

要使用此扩展类,只需在类中添加以下行引用其名称空间 使用joinext;

^这应该允许你在任何你碰巧使用的IEnumerable对象集合上看到扩展函数的智能感知。

希望这能有所帮助。如果仍然不清楚,请告诉我,我希望写一个关于如何使用它的示例。

下面是这个类:

namespace joinext
{    
public static class JoinExtensions
    {
        public static IEnumerable<TResult> FullOuterJoin<TOuter, TInner, TKey, TResult>(
            this IEnumerable<TOuter> outer,
            IEnumerable<TInner> inner,
            Func<TOuter, TKey> outerKeySelector,
            Func<TInner, TKey> innerKeySelector,
            Func<TOuter, TInner, TResult> resultSelector)
            where TInner : class
            where TOuter : class
        {
            var innerLookup = inner.ToLookup(innerKeySelector);
            var outerLookup = outer.ToLookup(outerKeySelector);

            var innerJoinItems = inner
                .Where(innerItem => !outerLookup.Contains(innerKeySelector(innerItem)))
                .Select(innerItem => resultSelector(null, innerItem));

            return outer
                .SelectMany(outerItem =>
                {
                    var innerItems = innerLookup[outerKeySelector(outerItem)];

                    return innerItems.Any() ? innerItems : new TInner[] { null };
                }, resultSelector)
                .Concat(innerJoinItems);
        }


        public static IEnumerable<TResult> LeftJoin<TOuter, TInner, TKey, TResult>(
            this IEnumerable<TOuter> outer,
            IEnumerable<TInner> inner,
            Func<TOuter, TKey> outerKeySelector,
            Func<TInner, TKey> innerKeySelector,
            Func<TOuter, TInner, TResult> resultSelector)
        {
            return outer.GroupJoin(
                inner,
                outerKeySelector,
                innerKeySelector,
                (o, i) =>
                    new { o = o, i = i.DefaultIfEmpty() })
                    .SelectMany(m => m.i.Select(inn =>
                        resultSelector(m.o, inn)
                        ));

        }



        public static IEnumerable<TResult> RightJoin<TOuter, TInner, TKey, TResult>(
            this IEnumerable<TOuter> outer,
            IEnumerable<TInner> inner,
            Func<TOuter, TKey> outerKeySelector,
            Func<TInner, TKey> innerKeySelector,
            Func<TOuter, TInner, TResult> resultSelector)
        {
            return inner.GroupJoin(
                outer,
                innerKeySelector,
                outerKeySelector,
                (i, o) =>
                    new { i = i, o = o.DefaultIfEmpty() })
                    .SelectMany(m => m.o.Select(outt =>
                        resultSelector(outt, m.i)
                        ));

        }

    }
}

我决定把这个作为一个单独的答案,因为我不确定它是否经过了足够的测试。这是FullOuterJoin方法的重新实现,基本上使用了简化的、定制的LINQKit Invoke/Expand for Expression版本,以便它可以在实体框架中工作。没有太多的解释,因为这和我之前的答案几乎一样。

public static class Ext {
    private static Expression<Func<TP, TC, TResult>> CastSMBody<TP, TC, TResult>(LambdaExpression ex, TP unusedP, TC unusedC, TResult unusedRes) => (Expression<Func<TP, TC, TResult>>)ex;

    public static IQueryable<TResult> LeftOuterJoin<TLeft, TRight, TKey, TResult>(
        this IQueryable<TLeft> leftItems,
        IQueryable<TRight> rightItems,
        Expression<Func<TLeft, TKey>> leftKeySelector,
        Expression<Func<TRight, TKey>> rightKeySelector,
        Expression<Func<TLeft, TRight, TResult>> resultSelector) {

        // (lrg,r) => resultSelector(lrg.left, r)
        var sampleAnonLR = new { left = default(TLeft), rightg = default(IEnumerable<TRight>) };
        var parmP = Expression.Parameter(sampleAnonLR.GetType(), "lrg");
        var parmC = Expression.Parameter(typeof(TRight), "r");
        var argLeft = Expression.PropertyOrField(parmP, "left");
        var newleftrs = CastSMBody(Expression.Lambda(resultSelector.Apply(argLeft, parmC), parmP, parmC), sampleAnonLR, default(TRight), default(TResult));

        return leftItems.GroupJoin(rightItems, leftKeySelector, rightKeySelector, (left, rightg) => new { left, rightg }).SelectMany(r => r.rightg.DefaultIfEmpty(), newleftrs);
    }

    public static IQueryable<TResult> RightOuterJoin<TLeft, TRight, TKey, TResult>(
        this IQueryable<TLeft> leftItems,
        IQueryable<TRight> rightItems,
        Expression<Func<TLeft, TKey>> leftKeySelector,
        Expression<Func<TRight, TKey>> rightKeySelector,
        Expression<Func<TLeft, TRight, TResult>> resultSelector) {

        // (lgr,l) => resultSelector(l, lgr.right)
        var sampleAnonLR = new { leftg = default(IEnumerable<TLeft>), right = default(TRight) };
        var parmP = Expression.Parameter(sampleAnonLR.GetType(), "lgr");
        var parmC = Expression.Parameter(typeof(TLeft), "l");
        var argRight = Expression.PropertyOrField(parmP, "right");
        var newrightrs = CastSMBody(Expression.Lambda(resultSelector.Apply(parmC, argRight), parmP, parmC), sampleAnonLR, default(TLeft), default(TResult));

        return rightItems.GroupJoin(leftItems, rightKeySelector, leftKeySelector, (right, leftg) => new { leftg, right })
                         .SelectMany(l => l.leftg.DefaultIfEmpty(), newrightrs);
    }

    private static Expression<Func<TParm, TResult>> CastSBody<TParm, TResult>(LambdaExpression ex, TParm unusedP, TResult unusedRes) => (Expression<Func<TParm, TResult>>)ex;

    public static IQueryable<TResult> RightAntiSemiJoin<TLeft, TRight, TKey, TResult>(
        this IQueryable<TLeft> leftItems,
        IQueryable<TRight> rightItems,
        Expression<Func<TLeft, TKey>> leftKeySelector,
        Expression<Func<TRight, TKey>> rightKeySelector,
        Expression<Func<TLeft, TRight, TResult>> resultSelector) where TLeft : class where TRight : class where TResult : class {

        // newrightrs = lgr => resultSelector(default(TLeft), lgr.right)
        var sampleAnonLgR = new { leftg = (IEnumerable<TLeft>)null, right = default(TRight) };
        var parmLgR = Expression.Parameter(sampleAnonLgR.GetType(), "lgr");
        var argLeft = Expression.Constant(default(TLeft), typeof(TLeft));
        var argRight = Expression.PropertyOrField(parmLgR, "right");
        var newrightrs = CastSBody(Expression.Lambda(resultSelector.Apply(argLeft, argRight), parmLgR), sampleAnonLgR, default(TResult));

        return rightItems.GroupJoin(leftItems, rightKeySelector, leftKeySelector, (right, leftg) => new { leftg, right }).Where(lgr => !lgr.leftg.Any()).Select(newrightrs);
    }

    public static IQueryable<TResult> FullOuterJoin<TLeft, TRight, TKey, TResult>(
        this IQueryable<TLeft> leftItems,
        IQueryable<TRight> rightItems,
        Expression<Func<TLeft, TKey>> leftKeySelector,
        Expression<Func<TRight, TKey>> rightKeySelector,
        Expression<Func<TLeft, TRight, TResult>> resultSelector)  where TLeft : class where TRight : class where TResult : class {

        return leftItems.LeftOuterJoin(rightItems, leftKeySelector, rightKeySelector, resultSelector).Concat(leftItems.RightAntiSemiJoin(rightItems, leftKeySelector, rightKeySelector, resultSelector));
    }

    public static Expression Apply(this LambdaExpression e, params Expression[] args) {
        var b = e.Body;

        foreach (var pa in e.Parameters.Cast<ParameterExpression>().Zip(args, (p, a) => (p, a))) {
            b = b.Replace(pa.p, pa.a);
        }

        return b.PropagateNull();
    }

    public static Expression Replace(this Expression orig, Expression from, Expression to) => new ReplaceVisitor(from, to).Visit(orig);
    public class ReplaceVisitor : System.Linq.Expressions.ExpressionVisitor {
        public readonly Expression from;
        public readonly Expression to;

        public ReplaceVisitor(Expression _from, Expression _to) {
            from = _from;
            to = _to;
        }

        public override Expression Visit(Expression node) => node == from ? to : base.Visit(node);
    }

    public static Expression PropagateNull(this Expression orig) => new NullVisitor().Visit(orig);
    public class NullVisitor : System.Linq.Expressions.ExpressionVisitor {
        public override Expression Visit(Expression node) {
            if (node is MemberExpression nme && nme.Expression is ConstantExpression nce && nce.Value == null)
                return Expression.Constant(null, nce.Type.GetMember(nme.Member.Name).Single().GetMemberType());
            else
                return base.Visit(node);
        }
    }

    public static Type GetMemberType(this MemberInfo member) {
        switch (member) {
            case FieldInfo mfi:
                return mfi.FieldType;
            case PropertyInfo mpi:
                return mpi.PropertyType;
            case EventInfo mei:
                return mei.EventHandlerType;
            default:
                throw new ArgumentException("MemberInfo must be if type FieldInfo, PropertyInfo or EventInfo", nameof(member));
        }
    }
}

更新1:提供一个真正通用的扩展方法FullOuterJoin 更新2:可选地接受键类型的自定义IEqualityComparer 更新3:这个实现最近已经成为MoreLinq的一部分-谢谢大家!

编辑新增FullOuterGroupJoin (ideone)。我重用了GetOuter<>实现,使它的性能比它可能的要低一些,但我现在的目标是“高级”代码,而不是前沿优化。

请登录http://ideone.com/O36nWc观看直播

static void Main(string[] args)
{
    var ax = new[] { 
        new { id = 1, name = "John" },
        new { id = 2, name = "Sue" } };
    var bx = new[] { 
        new { id = 1, surname = "Doe" },
        new { id = 3, surname = "Smith" } };

    ax.FullOuterJoin(bx, a => a.id, b => b.id, (a, b, id) => new {a, b})
        .ToList().ForEach(Console.WriteLine);
}

打印输出:

{ a = { id = 1, name = John }, b = { id = 1, surname = Doe } }
{ a = { id = 2, name = Sue }, b =  }
{ a = , b = { id = 3, surname = Smith } }

您还可以提供默认值:http://ideone.com/kG4kqO

    ax.FullOuterJoin(
            bx, a => a.id, b => b.id, 
            (a, b, id) => new { a.name, b.surname },
            new { id = -1, name    = "(no firstname)" },
            new { id = -2, surname = "(no surname)" }
        )

印刷:

{ name = John, surname = Doe }
{ name = Sue, surname = (no surname) }
{ name = (no firstname), surname = Smith }

使用术语的解释:

连接是一个借用自关系数据库设计的术语:

只要b中有对应键的元素,连接就会重复A中的元素(即:如果b为空,则什么都没有)。数据库行话称之为内部连接(equi)。 外部连接包括没有对应的元素 元素存在于b中(即:如果b为空则结果为偶数)。这通常称为左连接。 一个完整的外部连接包括来自A和b的记录,如果另一个中不存在相应的元素。(即,如果a为空,则结果为偶数)

在RDBMS中不常见的是组连接[1]:

组连接与上面描述的相同,但它不是为多个对应的b重复A中的元素,而是用对应的键对记录进行分组。当您希望根据公共键枚举“已连接”记录时,这通常更方便。

另请参阅GroupJoin,其中还包含一些一般的背景说明。


[1](我相信Oracle和MSSQL对此有专有扩展)

完整代码

一个通用的“drop-in”扩展类

internal static class MyExtensions
{
    internal static IEnumerable<TResult> FullOuterGroupJoin<TA, TB, TKey, TResult>(
        this IEnumerable<TA> a,
        IEnumerable<TB> b,
        Func<TA, TKey> selectKeyA, 
        Func<TB, TKey> selectKeyB,
        Func<IEnumerable<TA>, IEnumerable<TB>, TKey, TResult> projection,
        IEqualityComparer<TKey> cmp = null)
    {
        cmp = cmp?? EqualityComparer<TKey>.Default;
        var alookup = a.ToLookup(selectKeyA, cmp);
        var blookup = b.ToLookup(selectKeyB, cmp);

        var keys = new HashSet<TKey>(alookup.Select(p => p.Key), cmp);
        keys.UnionWith(blookup.Select(p => p.Key));

        var join = from key in keys
                   let xa = alookup[key]
                   let xb = blookup[key]
                   select projection(xa, xb, key);

        return join;
    }

    internal static IEnumerable<TResult> FullOuterJoin<TA, TB, TKey, TResult>(
        this IEnumerable<TA> a,
        IEnumerable<TB> b,
        Func<TA, TKey> selectKeyA, 
        Func<TB, TKey> selectKeyB,
        Func<TA, TB, TKey, TResult> projection,
        TA defaultA = default(TA), 
        TB defaultB = default(TB),
        IEqualityComparer<TKey> cmp = null)
    {
        cmp = cmp?? EqualityComparer<TKey>.Default;
        var alookup = a.ToLookup(selectKeyA, cmp);
        var blookup = b.ToLookup(selectKeyB, cmp);

        var keys = new HashSet<TKey>(alookup.Select(p => p.Key), cmp);
        keys.UnionWith(blookup.Select(p => p.Key));

        var join = from key in keys
                   from xa in alookup[key].DefaultIfEmpty(defaultA)
                   from xb in blookup[key].DefaultIfEmpty(defaultB)
                   select projection(xa, xb, key);

        return join;
    }
}