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

我认为其中大部分都存在问题,包括公认的答案,因为它们与Linq相比IQueryable工作不太好,要么是由于做了太多的服务器往返和太多的数据返回,要么是做了太多的客户端执行。

对于IEnumerable,我不喜欢Sehe的答案或类似的答案,因为它占用了过多的内存(一个简单的10000000两个列表测试在我的32GB机器上运行Linqpad内存)。

另外,其他大多数方法实际上并没有实现正确的Full Outer Join,因为它们使用的是带有右连接的Union,而不是带有右反半连接的Concat,这不仅消除了结果中重复的内部连接行,而且消除了最初存在于左或右数据中的任何正确的副本。

所以这里是我的扩展,处理所有这些问题,生成SQL以及直接实现LINQ到SQL的连接,在服务器上执行,比其他枚举对象更快,内存更少:

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

        return from left in leftItems
               join right in rightItems on leftKeySelector(left) equals rightKeySelector(right) into temp
               from right in temp.DefaultIfEmpty()
               select resultSelector(left, right);
    }

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

        return from right in rightItems
               join left in leftItems on rightKeySelector(right) equals leftKeySelector(left) into temp
               from left in temp.DefaultIfEmpty()
               select resultSelector(left, right);
    }

    public static IEnumerable<TResult> FullOuterJoinDistinct<TLeft, TRight, TKey, TResult>(
        this IEnumerable<TLeft> leftItems,
        IEnumerable<TRight> rightItems,
        Func<TLeft, TKey> leftKeySelector,
        Func<TRight, TKey> rightKeySelector,
        Func<TLeft, TRight, TResult> resultSelector) {

        return leftItems.LeftOuterJoin(rightItems, leftKeySelector, rightKeySelector, resultSelector).Union(leftItems.RightOuterJoin(rightItems, leftKeySelector, rightKeySelector, resultSelector));
    }

    public static IEnumerable<TResult> RightAntiSemiJoin<TLeft, TRight, TKey, TResult>(
        this IEnumerable<TLeft> leftItems,
        IEnumerable<TRight> rightItems,
        Func<TLeft, TKey> leftKeySelector,
        Func<TRight, TKey> rightKeySelector,
        Func<TLeft, TRight, TResult> resultSelector) {

        var hashLK = new HashSet<TKey>(from l in leftItems select leftKeySelector(l));
        return rightItems.Where(r => !hashLK.Contains(rightKeySelector(r))).Select(r => resultSelector(default(TLeft),r));
    }

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

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

    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) {

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

        return leftItems.AsQueryable().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) {

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

    public static IQueryable<TResult> FullOuterJoinDistinct<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) {

        return leftItems.LeftOuterJoin(rightItems, leftKeySelector, rightKeySelector, resultSelector).Union(leftItems.RightOuterJoin(rightItems, leftKeySelector, rightKeySelector, resultSelector));
    }

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

        var sampleAnonLgR = new { leftg = default(IEnumerable<TLeft>), 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(Expression.Invoke(resultSelector, 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) {

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

右反半连接(Right Anti-Semi-Join)之间的差异在Linq to Objects或源代码中大多是没有意义的,但在最终的答案中,在服务器(SQL)端产生了差异,删除了一个不必要的连接。

手动编码Expression来处理将Expression<Func<>>合并到lambda中,可以使用LinqKit进行改进,但如果语言/编译器为此添加了一些帮助,那就更好了。为了完整起见,包括了fullouterjo模糊不清和RightOuterJoin函数,但我还没有重新实现FullOuterGroupJoin。

我为IEnumerable编写了另一个完整的外部连接版本,用于键是可排序的情况,这比组合左外部连接和右反半连接快50%左右,至少在小型集合上是这样。它只对每个集合进行一次排序。

我还为使用EF的版本添加了另一个答案,即用自定义展开替换Invoke。

其他回答

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)
                        ));

        }

    }
}

两个或多个表的完全外部连接: 首先提取要连接的列。

var DatesA = from A in db.T1 select A.Date; 
var DatesB = from B in db.T2 select B.Date; 
var DatesC = from C in db.T3 select C.Date;            

var Dates = DatesA.Union(DatesB).Union(DatesC); 

然后在提取的列和主表之间使用左外连接。

var Full_Outer_Join =

(from A in Dates
join B in db.T1
on A equals B.Date into AB 

from ab in AB.DefaultIfEmpty()
join C in db.T2
on A equals C.Date into ABC 

from abc in ABC.DefaultIfEmpty()
join D in db.T3
on A equals D.Date into ABCD

from abcd in ABCD.DefaultIfEmpty() 
select new { A, ab, abc, abcd })
.AsEnumerable();

在两个输入上执行内存流枚举,并为每一行调用选择器。如果在当前迭代中没有相关性,则选择器参数之一将为空。

例子:

   var result = left.FullOuterJoin(
         right, 
         x=>left.Key, 
         x=>right.Key, 
         (l,r) => new { LeftKey = l?.Key, RightKey=r?.Key });

Requires an IComparer for the correlation type, uses the Comparer.Default if not provided. Requires that 'OrderBy' is applied to the input enumerables /// <summary> /// Performs a full outer join on two <see cref="IEnumerable{T}" />. /// </summary> /// <typeparam name="TLeft"></typeparam> /// <typeparam name="TValue"></typeparam> /// <typeparam name="TRight"></typeparam> /// <typeparam name="TResult"></typeparam> /// <param name="left"></param> /// <param name="right"></param> /// <param name="leftKeySelector"></param> /// <param name="rightKeySelector"></param> /// <param name="selector">Expression defining result type</param> /// <param name="keyComparer">A comparer if there is no default for the type</param> /// <returns></returns> [System.Diagnostics.DebuggerStepThrough] public static IEnumerable<TResult> FullOuterJoin<TLeft, TRight, TValue, TResult>( this IEnumerable<TLeft> left, IEnumerable<TRight> right, Func<TLeft, TValue> leftKeySelector, Func<TRight, TValue> rightKeySelector, Func<TLeft, TRight, TResult> selector, IComparer<TValue> keyComparer = null) where TLeft: class where TRight: class where TValue : IComparable { keyComparer = keyComparer ?? Comparer<TValue>.Default; using (var enumLeft = left.OrderBy(leftKeySelector).GetEnumerator()) using (var enumRight = right.OrderBy(rightKeySelector).GetEnumerator()) { var hasLeft = enumLeft.MoveNext(); var hasRight = enumRight.MoveNext(); while (hasLeft || hasRight) { var currentLeft = enumLeft.Current; var valueLeft = hasLeft ? leftKeySelector(currentLeft) : default(TValue); var currentRight = enumRight.Current; var valueRight = hasRight ? rightKeySelector(currentRight) : default(TValue); int compare = !hasLeft ? 1 : !hasRight ? -1 : keyComparer.Compare(valueLeft, valueRight); switch (compare) { case 0: // The selector matches. An inner join is achieved yield return selector(currentLeft, currentRight); hasLeft = enumLeft.MoveNext(); hasRight = enumRight.MoveNext(); break; case -1: yield return selector(currentLeft, default(TRight)); hasLeft = enumLeft.MoveNext(); break; case 1: yield return selector(default(TLeft), currentRight); hasRight = enumRight.MoveNext(); break; } } } }

下面是一个扩展方法:

public static IEnumerable<KeyValuePair<TLeft, TRight>> FullOuterJoin<TLeft, TRight>(this IEnumerable<TLeft> leftItems, Func<TLeft, object> leftIdSelector, IEnumerable<TRight> rightItems, Func<TRight, object> rightIdSelector)
{
    var leftOuterJoin = from left in leftItems
        join right in rightItems on leftIdSelector(left) equals rightIdSelector(right) into temp
        from right in temp.DefaultIfEmpty()
        select new { left, right };

    var rightOuterJoin = from right in rightItems
        join left in leftItems on rightIdSelector(right) equals leftIdSelector(left) into temp
        from left in temp.DefaultIfEmpty()
        select new { left, right };

    var fullOuterJoin = leftOuterJoin.Union(rightOuterJoin);

    return fullOuterJoin.Select(x => new KeyValuePair<TLeft, TRight>(x.left, x.right));
}

这是另一个完整的外部连接

由于对其他命题的简单性和可读性不太满意,我最后得出了这样的结论:

它没有快速的自命(在2020m CPU上加入1000 * 1000大约800毫秒:2.4ghz / 2核)。对我来说,它只是一个紧凑而随意的完全外部连接。

它的工作原理与SQL FULL OUTER JOIN相同(重复保存)

欢呼;-)

using System;
using System.Collections.Generic;
using System.Linq;
namespace NS
{
public static class DataReunion
{
    public static List<Tuple<T1, T2>> FullJoin<T1, T2, TKey>(List<T1> List1, Func<T1, TKey> KeyFunc1, List<T2> List2, Func<T2, TKey> KeyFunc2)
    {
        List<Tuple<T1, T2>> result = new List<Tuple<T1, T2>>();

        Tuple<TKey, T1>[] identifiedList1 = List1.Select(_ => Tuple.Create(KeyFunc1(_), _)).OrderBy(_ => _.Item1).ToArray();
        Tuple<TKey, T2>[] identifiedList2 = List2.Select(_ => Tuple.Create(KeyFunc2(_), _)).OrderBy(_ => _.Item1).ToArray();

        identifiedList1.Where(_ => !identifiedList2.Select(__ => __.Item1).Contains(_.Item1)).ToList().ForEach(_ => {
            result.Add(Tuple.Create<T1, T2>(_.Item2, default(T2)));
        });

        result.AddRange(
            identifiedList1.Join(identifiedList2, left => left.Item1, right => right.Item1, (left, right) => Tuple.Create<T1, T2>(left.Item2, right.Item2)).ToList()
        );

        identifiedList2.Where(_ => !identifiedList1.Select(__ => __.Item1).Contains(_.Item1)).ToList().ForEach(_ => {
            result.Add(Tuple.Create<T1, T2>(default(T1), _.Item2));
        });

        return result;
    }
}
}

这个想法是

基于提供的关键函数生成器构建id 处理仅剩下的项 流程内部连接 只处理正确的项目

下面是一个与之相关的简单测试:

在结束处放置断点,以手动验证它的行为是否符合预期

using System;
using System.Collections.Generic;
using Microsoft.VisualStudio.TestTools.UnitTesting;
using Newtonsoft.Json;
using Newtonsoft.Json.Linq;
using NS;

namespace Tests
{
[TestClass]
public class DataReunionTest
{
    [TestMethod]
    public void Test()
    {
        List<Tuple<Int32, Int32, String>> A = new List<Tuple<Int32, Int32, String>>();
        List<Tuple<Int32, Int32, String>> B = new List<Tuple<Int32, Int32, String>>();

        Random rnd = new Random();

        /* Comment the testing block you do not want to run
        /* Solution to test a wide range of keys*/

        for (int i = 0; i < 500; i += 1)
        {
            A.Add(Tuple.Create(rnd.Next(1, 101), rnd.Next(1, 101), "A"));
            B.Add(Tuple.Create(rnd.Next(1, 101), rnd.Next(1, 101), "B"));
        }

        /* Solution for essential testing*/

        A.Add(Tuple.Create(1, 2, "B11"));
        A.Add(Tuple.Create(1, 2, "B12"));
        A.Add(Tuple.Create(1, 3, "C11"));
        A.Add(Tuple.Create(1, 3, "C12"));
        A.Add(Tuple.Create(1, 3, "C13"));
        A.Add(Tuple.Create(1, 4, "D1"));

        B.Add(Tuple.Create(1, 1, "A21"));
        B.Add(Tuple.Create(1, 1, "A22"));
        B.Add(Tuple.Create(1, 1, "A23"));
        B.Add(Tuple.Create(1, 2, "B21"));
        B.Add(Tuple.Create(1, 2, "B22"));
        B.Add(Tuple.Create(1, 2, "B23"));
        B.Add(Tuple.Create(1, 3, "C2"));
        B.Add(Tuple.Create(1, 5, "E2"));

        Func<Tuple<Int32, Int32, String>, Tuple<Int32, Int32>> key = (_) => Tuple.Create(_.Item1, _.Item2);

        var watch = System.Diagnostics.Stopwatch.StartNew();
        var res = DataReunion.FullJoin(A, key, B, key);
        watch.Stop();
        var elapsedMs = watch.ElapsedMilliseconds;
        String aser = JToken.FromObject(res).ToString(Formatting.Indented);
        Console.Write(elapsedMs);
    }
}

}