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。
