Question

我试图在动态数量的列上加入两个DataTable。我已经得到了下面的代码。问题是连接的ON语句。如何根据列表中的列名和＃34; joinColumnNames＆＃34;来创建此动态。

我在想我需要构建某种表达式树，但是我找不到任何关于如何使用多个连接列以及没有属性的DataRow对象的示例每一栏。

private DataTable Join(List<string> joinColumnNames, DataTable pullX, DataTable pullY)
{
    DataTable joinedTable = new DataTable();

    // Add all the columns from pullX
    foreach (string colName in joinColumnNames)
    {
        joinedTable.Columns.Add(pullX.Columns[colName]);
    }
    // Add unique columns from PullY
    foreach (DataColumn col in pullY.Columns)
    {
        if (!joinedTable.Columns.Contains((col.ColumnName)))
        {
            joinedTable.Columns.Add(col);
        }
    }

    var Join = (from PX in pullX.AsEnumerable()
                join PY in pullY.AsEnumerable() on 
                // This must be dynamic and join on every column mentioned in joinColumnNames
                new { A = PX[joinColumnNames[0]], B = PX[joinColumnNames[1]] } equals new { A = PY[joinColumnNames[0]], B = PY[joinColumnNames[1]] } 
                into Outer
                from PY in Outer.DefaultIfEmpty<DataRow>(pullY.NewRow())
                select new { PX, PY });

    foreach (var item in Join)
    {
        DataRow newRow = joinedTable.NewRow();
        foreach (DataColumn col in joinedTable.Columns)
        {
            var pullXValue = item.PX.Table.Columns.Contains(col.ColumnName) ? item.PX[col.ColumnName] : string.Empty;
            var pullYValue = item.PY.Table.Columns.Contains(col.ColumnName) ? item.PY[col.ColumnName] : string.Empty;
            newRow[col.ColumnName] = (pullXValue == null || string.IsNullOrEmpty(pullXValue.ToString())) ? pullYValue : pullXValue;
        }
        joinedTable.Rows.Add(newRow);
    }

    return joinedTable;
}

使用3个连接列（Country，Company和DateId）添加一个显示输入/输出的特定示例：

拉X：

Country        Company       DateId    Sales
United States  Test1 Ltd    20160722    $25 

Canada         Test3 Ltd    20160723    $30 

Italy          Test4 Ltd    20160724    $40 

India          Test2 Ltd    20160725    $35

拉Y：

Country        Company       DateId    Downloads
United States  Test1 Ltd    20160722    500 

Mexico         Test2 Ltd    20160723    300 

Italy          Test4 Ltd    20160724    900

结果：

Country        Company       DateId    Sales    Downloads
United States  Test1 Ltd    20160722    $25      500 

Canada         Test3 Ltd    20160723    $30  

Mexico         Test2 Ltd    20160723                300 

Italy          Test4 Ltd    20160724    $40      900 

India          Test2 Ltd    20160725    $35

Answer 1

由于您使用的是LINQ to Objects，因此无需使用表达式树。您可以使用自定义相等比较器解决问题。

创建一个相等比较器，它可以根据特定列的值比较两个DataRow对象之间的相等性。这是一个例子：

public class MyEqualityComparer : IEqualityComparer<DataRow>
{
    private readonly string[] columnNames;

    public MyEqualityComparer(string[] columnNames)
    {
        this.columnNames = columnNames;
    }

    public bool Equals(DataRow x, DataRow y)
    {
        return columnNames.All(cn => x[cn].Equals(y[cn]));
    }

    public int GetHashCode(DataRow obj)
    {
        unchecked
        {
            int hash = 19;
            foreach (var value in columnNames.Select(cn => obj[cn]))
            {
                hash = hash * 31 + value.GetHashCode();
            }
            return hash;
        }
    }
}

然后你可以用它来做这样的连接：

public class TwoRows
{
    public DataRow Row1 { get; set; }
    public DataRow Row2 { get; set; }
}

private static List<TwoRows> LeftOuterJoin(
    List<string> joinColumnNames,
    DataTable leftTable,
    DataTable rightTable)
{
    return leftTable
        .AsEnumerable()
        .GroupJoin(
            rightTable.AsEnumerable(),
            l => l,
            r => r,
            (l, rlist) => new {LeftValue = l, RightValues = rlist},
            new MyEqualityComparer(joinColumnNames.ToArray()))
        .SelectMany(
            x => x.RightValues.DefaultIfEmpty(rightTable.NewRow()),
            (x, y) => new TwoRows {Row1 = x.LeftValue, Row2 = y})
        .ToList();
}

请注意我使用的是方法语法，因为我不认为你可以使用自定义相等比较器。

请注意，该方法执行左外连接，而不是完整外连接。根据您提供的示例，您似乎需要完整的外部联接。为此，您需要执行两个左外连接（请参阅此answer）。以下是完整方法的样子：

private static DataTable FullOuterJoin(
    List<string> joinColumnNames,
    DataTable pullX,
    DataTable pullY)
{
    var pullYOtherColumns =
        pullY.Columns
            .Cast<DataColumn>()
            .Where(x => !joinColumnNames.Contains(x.ColumnName))
            .ToList();

    var allColumns = 
        pullX.Columns
            .Cast<DataColumn>()
            .Concat(pullYOtherColumns)
            .ToArray();

    var allColumnsClone =
        allColumns
            .Select(x => new DataColumn(x.ColumnName, x.DataType))
            .ToArray();

    DataTable joinedTable = new DataTable();

    joinedTable.Columns.AddRange(allColumnsClone);

    var first =
        LeftOuterJoin(joinColumnNames, pullX, pullY);

    var resultRows = new List<DataRow>();

    foreach (var item in first)
    {
        DataRow newRow = joinedTable.NewRow();
        foreach (DataColumn col in joinedTable.Columns)
        {
            var value = pullX.Columns.Contains(col.ColumnName)
                ? item.Row1[col.ColumnName]
                : item.Row2[col.ColumnName];

            newRow[col.ColumnName] = value;
        }
        resultRows.Add(newRow);
    }

    var second =
        LeftOuterJoin(joinColumnNames, pullY, pullX);

    foreach (var item in second)
    {
        DataRow newRow = joinedTable.NewRow();
        foreach (DataColumn col in joinedTable.Columns)
        {
            var value = pullY.Columns.Contains(col.ColumnName)
                ? item.Row1[col.ColumnName]
                : item.Row2[col.ColumnName];

            newRow[col.ColumnName] = value;
        }
        resultRows.Add(newRow);
    }

    var uniqueRows =
        resultRows
            .Distinct(
                new MyEqualityComparer(
                    joinedTable.Columns
                        .Cast<DataColumn>()
                        .Select(x => x.ColumnName)
                        .ToArray()));

    foreach (var uniqueRow in uniqueRows)
        joinedTable.Rows.Add(uniqueRow);


    return joinedTable;
}

还请注意我如何克隆列。您不能在两个表中使用相同的列对象。

Answer 2

var Join = 
    from PX in pullX.AsEnumerable()
    join PY in pullY.AsEnumerable()
    on     string.Join("\0", joinColumnNames.Select(c => PX[c]))
    equals string.Join("\0", joinColumnNames.Select(c => PY[c]))
    into Outer
    from PY in Outer.DefaultIfEmpty<DataRow>(pullY.NewRow())
    select new { PX, PY };

另一种方法是在DataTable中同时使用DataSet并使用DataRelation How To: Use DataRelation to perform a join on two DataTables in a DataSet?

在动态列数上加入2个DataTable

2 个答案: