37


16

Open XMLを使用したC#でのExcelからDataTableへ

Visual Studio 2008を使用していますが、Open XML SDK 2.0を使用してExcelシートから「DataTable」を作成する必要があります。 シートの最初の行でDataTable列を使用して作成し、残りの値でそれを完了する必要があります。

これを行うのに役立つサンプルコードやリンクはありますか?

6 Answer


60


これはあなたが求めていることをするはずだと思います。 他の関数は、文字列を共有している場合に対処するためのものです。これは、列ヘッダーで行うと仮定しています。 これが完璧かどうかはわかりませんが、役に立つと思います。

static void Main(string[] args)
{
    DataTable dt = new DataTable();

    using (SpreadsheetDocument spreadSheetDocument = SpreadsheetDocument.Open(@"..\..\example.xlsx", false))
    {

        WorkbookPart workbookPart = spreadSheetDocument.WorkbookPart;
        IEnumerable sheets = spreadSheetDocument.WorkbookPart.Workbook.GetFirstChild().Elements();
        string relationshipId = sheets.First().Id.Value;
        WorksheetPart worksheetPart = (WorksheetPart)spreadSheetDocument.WorkbookPart.GetPartById(relationshipId);
        Worksheet workSheet = worksheetPart.Worksheet;
        SheetData sheetData = workSheet.GetFirstChild();
        IEnumerable rows = sheetData.Descendants();

        foreach (Cell cell in rows.ElementAt(0))
        {
            dt.Columns.Add(GetCellValue(spreadSheetDocument, cell));
        }

        foreach (Row row in rows) //this will also include your header row...
        {
            DataRow tempRow = dt.NewRow();

            for (int i = 0; i < row.Descendants().Count(); i++)
            {
                tempRow[i] = GetCellValue(spreadSheetDocument, row.Descendants().ElementAt(i-1));
            }

            dt.Rows.Add(tempRow);
        }

    }
    dt.Rows.RemoveAt(0); //...so i'm taking it out here.

}


public static string GetCellValue(SpreadsheetDocument document, Cell cell)
{
    SharedStringTablePart stringTablePart = document.WorkbookPart.SharedStringTablePart;
    string value = cell.CellValue.InnerXml;

    if (cell.DataType != null && cell.DataType.Value == CellValues.SharedString)
    {
        return stringTablePart.SharedStringTable.ChildElements[Int32.Parse(value)].InnerText;
    }
    else
    {
        return value;
    }
}


14


こんにちは上記のコードは1つの変更を除いて正常に動作しています

以下のコード行を置き換えます

tempRow[i] = GetCellValue(spreadSheetDocument, row.Descendants().ElementAt(i-1));

with

tempRow[i] = GetCellValue(spreadSheetDocument, row.Descendants().ElementAt(i));

(i-1)を使用すると、例外がスローされます。

specified argument was out of the range of valid values. parameter name index.


2


 Public Shared Function ExcelToDataTable(filename As String) As DataTable
        Try

            Dim dt As New DataTable()

            Using doc As SpreadsheetDocument = SpreadsheetDocument.Open(filename, False)

                Dim workbookPart As WorkbookPart = doc.WorkbookPart
                Dim sheets As IEnumerable(Of Sheet) = doc.WorkbookPart.Workbook.GetFirstChild(Of Sheets)().Elements(Of Sheet)()
                Dim relationshipId As String = sheets.First().Id.Value
                Dim worksheetPart As WorksheetPart = DirectCast(doc.WorkbookPart.GetPartById(relationshipId), WorksheetPart)
                Dim workSheet As Worksheet = worksheetPart.Worksheet
                Dim sheetData As SheetData = workSheet.GetFirstChild(Of SheetData)()
                Dim rows As IEnumerable(Of Row) = sheetData.Descendants(Of Row)()

                For Each cell As Cell In rows.ElementAt(0)
                    dt.Columns.Add(GetCellValue(doc, cell))
                Next

                For Each row As Row In rows
                    'this will also include your header row...
                    Dim tempRow As DataRow = dt.NewRow()

                    For i As Integer = 0 To row.Descendants(Of Cell)().Count() - 1
                        tempRow(i) = GetCellValue(doc, row.Descendants(Of Cell)().ElementAt(i))
                    Next

                    dt.Rows.Add(tempRow)
                Next
            End Using

            dt.Rows.RemoveAt(0)

            Return dt

        Catch ex As Exception
            Throw ex
        End Try
    End Function


    Public Shared Function GetCellValue(document As SpreadsheetDocument, cell As Cell) As String
        Try

            If IsNothing(cell.CellValue) Then
                Return ""
            End If

            Dim value As String = cell.CellValue.InnerXml

            If cell.DataType IsNot Nothing AndAlso cell.DataType.Value = CellValues.SharedString Then
                Dim stringTablePart As SharedStringTablePart = document.WorkbookPart.SharedStringTablePart
                Return stringTablePart.SharedStringTable.ChildElements(Int32.Parse(value)).InnerText
            Else
                Return value
            End If

        Catch ex As Exception
            Return ""
        End Try
    End Function


2


このソリューションは、空のセルのないスプレッドシートで機能します。

空のセルを処理するには、次の行を置き換える必要があります。

tempRow[i] = GetCellValue(spreadSheetDocument, row.Descendants().ElementAt(i-1));

このようなもので:

Cell cell = row.Descendants().ElementAt(i);
int index = CellReferenceToIndex(cell);
tempRow[index] = GetCellValue(spreadSheetDocument, cell);

そして、このメソッドを追加します:

private static int CellReferenceToIndex(Cell cell)
{
    int index = 0;
    string reference = cell.CellReference.ToString().ToUpper();
    foreach (char ch in reference)
    {
        if (Char.IsLetter(ch))
        {
            int value = (int)ch - (int)'A';
            index = (index == 0) ? value : ((index + 1) * 26) + value;
        }
        else
            return index;
    }
    return index;
}


0


これは、空のセルも考慮される私の完全なソリューションです。

public static class ExcelHelper
        {
            //To get the value of the cell, even it's empty. Unable to use loop by index
            private static string GetCellValue(WorkbookPart wbPart, List theCells, string cellColumnReference)
            {
                Cell theCell = null;
                string value = "";
                foreach (Cell cell in theCells)
                {
                    if (cell.CellReference.Value.StartsWith(cellColumnReference))
                    {
                        theCell = cell;
                        break;
                    }
                }
                if (theCell != null)
                {
                    value = theCell.InnerText;
                    // If the cell represents an integer number, you are done.
                    // For dates, this code returns the serialized value that represents the date. The code handles strings and
                    // Booleans individually. For shared strings, the code looks up the corresponding value in the shared string table. For Booleans, the code converts the value into the words TRUE or FALSE.
                    if (theCell.DataType != null)
                    {
                        switch (theCell.DataType.Value)
                        {
                            case CellValues.SharedString:
                                // For shared strings, look up the value in the shared strings table.
                                var stringTable = wbPart.GetPartsOfType().FirstOrDefault();
                                // If the shared string table is missing, something is wrong. Return the index that is in the cell. Otherwise, look up the correct text in the table.
                                if (stringTable != null)
                                {
                                    value = stringTable.SharedStringTable.ElementAt(int.Parse(value)).InnerText;
                                }
                                break;
                            case CellValues.Boolean:
                                switch (value)
                                {
                                    case "0":
                                        value = "FALSE";
                                        break;
                                    default:
                                        value = "TRUE";
                                        break;
                                }
                                break;
                        }
                    }
                }
                return value;
            }

            private static string GetCellValue(WorkbookPart wbPart, List theCells, int index)
            {
                return GetCellValue(wbPart, theCells, GetExcelColumnName(index));
            }

            private static string GetExcelColumnName(int columnNumber)
            {
                int dividend = columnNumber;
                string columnName = String.Empty;
                int modulo;
                while (dividend > 0)
                {
                    modulo = (dividend - 1) % 26;
                    columnName = Convert.ToChar(65 + modulo).ToString() + columnName;
                    dividend = (int)((dividend - modulo) / 26);
                }
                return columnName;
            }

            //Only xlsx files
            public static DataTable GetDataTableFromExcelFile(string filePath, string sheetName = "")
            {
                DataTable dt = new DataTable();
                try
                {
                    using (SpreadsheetDocument document = SpreadsheetDocument.Open(filePath, false))
                    {
                        WorkbookPart wbPart = document.WorkbookPart;
                        IEnumerable sheets = document.WorkbookPart.Workbook.GetFirstChild().Elements();
                        string sheetId = sheetName != "" ? sheets.Where(q => q.Name == sheetName).First().Id.Value : sheets.First().Id.Value;
                        WorksheetPart wsPart = (WorksheetPart)wbPart.GetPartById(sheetId);
                        SheetData sheetdata = wsPart.Worksheet.Elements().FirstOrDefault();
                        int totalHeaderCount = sheetdata.Descendants().ElementAt(0).Descendants().Count();
                        //Get the header
                        for (int i = 1; i <= totalHeaderCount; i++)
                        {
                            dt.Columns.Add(GetCellValue(wbPart, sheetdata.Descendants().ElementAt(0).Elements().ToList(), i));
                        }
                        foreach (Row r in sheetdata.Descendants())
                        {
                            if (r.RowIndex > 1)
                            {
                                DataRow tempRow = dt.NewRow();

                                //Always get from the header count, because the index of the row changes where empty cell is not counted
                                for (int i = 1; i <= totalHeaderCount; i++)
                                {
                                    tempRow[i - 1] = GetCellValue(wbPart, r.Elements().ToList(), i);
                                }
                                dt.Rows.Add(tempRow);
                            }
                        }
                    }
                }
                catch (Exception ex)
                {

                }
                return dt;
            }
        }


-1


行の値がnullまたは空の場合、値の取得は正しく動作しません。

正常に機能している場合、すべての列にデータが入力されます。 しかし、おそらくすべての行ではない