使用 OpenXML sdk 读取 excel 文件时遇到问题

Question

我有一个从 excel 文件中读取并将结果存储在 DataSet 中的函数。我有另一个写入 excel 文件的函数。当我尝试从常规的人工生成的 excel 文件中读取时，excel 读取函数返回空白 DataSet，但是当我从写入函数生成的 excel 文件中读取时，它工作得非常好。然后，即使我只是复制并粘贴函数生成的 excel 文件的内容，该函数也无法在常规生成的 excel 文件上工作。我终于找到了它，但我不知道从哪里开始。我的代码有问题吗？

这里是excel生成函数：

public static Boolean writeToExcel(string fileName, DataSet data)
{
    Boolean answer = false;
    using (SpreadsheetDocument excelDoc = SpreadsheetDocument.Create(tempPath + fileName, SpreadsheetDocumentType.Workbook))
    {
        WorkbookPart workbookPart = excelDoc.AddWorkbookPart();
        workbookPart.Workbook = new Workbook();
        WorksheetPart worksheetPart = workbookPart.AddNewPart<WorksheetPart>();
        Sheets sheets = excelDoc.WorkbookPart.Workbook.AppendChild<Sheets>(new Sheets());
        Sheet sheet = new Sheet()
        {
            Id = excelDoc.WorkbookPart.GetIdOfPart(worksheetPart),
            SheetId = 1,
            Name = "Page1"
        };

        sheets.Append(sheet);

        CreateWorkSheet(worksheetPart, data);
        answer = true;
    }

    return answer;
}

private static void CreateWorkSheet(WorksheetPart worksheetPart, DataSet data)
{
    Worksheet worksheet = new Worksheet();
    SheetData sheetData = new SheetData();
    UInt32Value currRowIndex = 1U;
    int colIndex = 0;
    Row excelRow;
    DataTable table = data.Tables[0];

    for (int rowIndex = -1; rowIndex < table.Rows.Count; rowIndex++)
    {
        excelRow = new Row();
        excelRow.RowIndex = currRowIndex++;
        for (colIndex = 0; colIndex < table.Columns.Count; colIndex++)
        {
            Cell cell = new Cell()
            {
                CellReference = Convert.ToString(Convert.ToChar(65 + colIndex)),
                DataType = CellValues.String
            };

            CellValue cellValue = new CellValue();

            if (rowIndex == -1)
            {
                cellValue.Text = table.Columns[colIndex].ColumnName.ToString();
            }
            else
            {
                cellValue.Text = (table.Rows[rowIndex].ItemArray[colIndex].ToString() != "") ? table.Rows[rowIndex].ItemArray[colIndex].ToString() : "*";
            }

            cell.Append(cellValue);
            excelRow.Append(cell);
        }

        sheetData.Append(excelRow);
    }

    SheetFormatProperties formattingProps = new SheetFormatProperties()
    {
        DefaultColumnWidth = 20D,
        DefaultRowHeight = 20D
    };

    worksheet.Append(formattingProps);
    worksheet.Append(sheetData);
    worksheetPart.Worksheet = worksheet;
}

而读取功能如下：

public static void readInventoryExcel(string fileName, ref DataSet set)
{
    using (SpreadsheetDocument spreadsheetDocument = SpreadsheetDocument.Open(fileName, false))
    {
        WorkbookPart workbookPart = spreadsheetDocument.WorkbookPart;
        WorksheetPart worksheetPart = workbookPart.WorksheetParts.First();
        SheetData sheetData = worksheetPart.Worksheet.Elements<SheetData>().First();
        int count = -1;
        foreach (Row r in sheetData.Elements<Row>())
        {
            if (count >= 0)
            {
                DataRow row = set.Tables[0].NewRow();
                row["SerialNumber"]         = r.ChildElements[1].InnerXml;
                row["PartNumber"]           = r.ChildElements[2].InnerXml;
                row["EntryDate"]            = r.ChildElements[3].InnerXml;
                row["RetirementDate"]       = r.ChildElements[4].InnerXml;
                row["ReasonForReplacement"] = r.ChildElements[5].InnerXml;
                row["RetirementTech"]       = r.ChildElements[6].InnerXml;
                row["IncludeInMaintenance"] = r.ChildElements[7].InnerXml;
                row["MaintenanceTech"]      = r.ChildElements[8].InnerXml;
                row["Comment"]              = r.ChildElements[9].InnerXml;
                row["Station"]              = r.ChildElements[10].InnerXml;
                row["LocationStatus"]       = r.ChildElements[11].InnerXml;
                row["AssetName"]            = r.ChildElements[12].InnerXml;
                row["InventoryType"]        = r.ChildElements[13].InnerXml;
                row["Description"]          = r.ChildElements[14].InnerXml;
                set.Tables[0].Rows.Add(row);
            }
            count++;
        }
    }
}

Answer 1

我认为这是因为您只有一张工作表而 Excel 有三张。我不确定，但我认为床单是按相反的顺序返回的，所以你应该换行：

WorksheetPart worksheetPart = workbookPart.WorksheetParts.First();

到

WorksheetPart worksheetPart = workbookPart.WorksheetParts.Last();

如果您可以通过工作表名称识别WorksheetPart，则搜索它可能会更安全。您需要先找到Sheet，然后使用该ID 找到SheetPart：

private WorksheetPart GetWorksheetPartBySheetName(WorkbookPart workbookPart, string sheetName)
{
    //find the sheet first.
    IEnumerable<Sheet> sheets = workbookPart.Workbook.GetFirstChild<Sheets>().Elements<Sheet>().Where(s => s.Name == sheetName);

    if (sheets.Count() > 0)
    {
        string relationshipId = sheets.First().Id.Value;
        WorksheetPart worksheetPart = (WorksheetPart)workbookPart.GetPartById(relationshipId);
        return worksheetPart;
    }

    return null;
}

然后您可以使用：

WorksheetPart worksheetPart = GetWorksheetPartBySheetName(workbookPart, "Sheet1");

在查看您的代码时，我还注意到了一些您可能（或可能不！）感兴趣的事情：

在您的代码中，您只是在阅读 InnerXml，所以这对您来说可能无关紧要，但 Excel 存储字符串的方式与您编写它们的方式不同，因此读取 Excel 生成的文件可能无法为您提供您期望的值.在您的示例中，您将字符串直接写入单元格，如下所示：

但 Excel 使用 SharedStrings 概念，其中所有字符串都写入名为 sharedStrings.xml 的单独 XML 文件。该文件包含 Excel 文件中使用的字符串和引用，它的 that 值存储在工作表 XML 的单元格值中。

sharedString.xml 如下所示：

然后细胞看起来像这样：

<v> 元素中的47 是对第 47 个共享字符串的引用。请注意，生成的 XML 中的类型（t 属性）是 str，但 Excel 生成的文件中的类型是 s。这表示你的是内联字符串，而他们的是共享字符串。

您可以像阅读任何其他部分一样阅读 SharedStrings：

var stringTable = workbookPart.GetPartsOfType<SharedStringTablePart>().FirstOrDefault();

if (stringTable != null)
{
    sharedString = stringTable.SharedStringTable.ElementAt(int.Parse(value)).InnerText;
}

其次，如果您查看代码生成的单元格引用和 Excel 生成的单元格引用，您会发现您只输出列而不是行（例如，您输出 A 而不是 A1）。要解决此问题，您应该更改行：

CellReference = Convert.ToString(Convert.ToChar(65 + colIndex)),

到

CellReference = Convert.ToString(Convert.ToChar(65 + colIndex) + rowIndex.ToString()),

希望对你有帮助。

Answer 2

不久前我在尝试对 Word 文档执行此操作时遇到了类似的问题（程序生成的工作正常，但人工生成的却不行）。我发现这个工具非常有用：

http://www.microsoft.com/en-us/download/details.aspx?id=30425

基本上，它会查看文件并向您显示 Microsoft 为读取它而生成的代码，以及文件本身的 xml 结构。像往常一样，Microsoft 产品有很多菜单，而且不是很直观，但是在单击一下之后，您将能够准确地看到任何两个文件的情况。我建议您打开一个工作的 excel 文件和一个不工作的文件并比较差异，看看是什么导致了您的问题。

Answer 3

下面是我用来将特定工作表中的 Excel 文件读取到 DataTable 的 OpenXML 代码。

首先，你会这样称呼它：

DataTable dt = OpenXMLHelper.ExcelWorksheetToDataTable("C:\\SQL Server\\SomeExcelFile.xlsx", "Mikes Worksheet");

这是代码：

    public class OpenXMLHelper
    {
        public static DataTable ExcelWorksheetToDataTable(string pathFilename, string worksheetName)
        {
            DataTable dt = new DataTable(worksheetName);

            using (SpreadsheetDocument document = SpreadsheetDocument.Open(pathFilename, false))
            {
                // Find the sheet with the supplied name, and then use that 
                // Sheet object to retrieve a reference to the first worksheet.
                Sheet theSheet = document.WorkbookPart.Workbook.Descendants<Sheet>().Where(s => s.Name == worksheetName).FirstOrDefault();
                if (theSheet == null)
                    throw new Exception("Couldn't find the worksheet: " + worksheetName);

                // Retrieve a reference to the worksheet part.
                WorksheetPart wsPart = (WorksheetPart)(document.WorkbookPart.GetPartById(theSheet.Id));
                Worksheet workSheet = wsPart.Worksheet;

                string dimensions = workSheet.SheetDimension.Reference.InnerText;       //  Get the dimensions of this worksheet, eg "B2:F4"

                int numOfColumns = 0;
                int numOfRows = 0;
                CalculateDataTableSize(dimensions, ref numOfColumns, ref numOfRows);
                System.Diagnostics.Trace.WriteLine(string.Format("The worksheet \"{0}\" has dimensions \"{1}\", so we need a DataTable of size {2}x{3}.", worksheetName, dimensions, numOfColumns, numOfRows));

                SheetData sheetData = workSheet.GetFirstChild<SheetData>();
                IEnumerable<Row> rows = sheetData.Descendants<Row>();

                string[,] cellValues = new string[numOfColumns, numOfRows];

                int colInx = 0;
                int rowInx = 0;
                string value = "";
                SharedStringTablePart stringTablePart = document.WorkbookPart.SharedStringTablePart;

                //  Iterate through each row of OpenXML data
                foreach (Row row in rows)
                {
                    for (int i = 0; i < row.Descendants<Cell>().Count(); i++)
                    {
                        //  *DON'T* assume there's going to be one XML element for each item in each row...
                        Cell cell = row.Descendants<Cell>().ElementAt(i);
                        if (cell.CellValue == null || cell.CellReference == null)
                            continue;                       //  eg when an Excel cell contains a blank string

                        //  Convert this Excel cell's CellAddress into a 0-based offset into our array (eg "G13" -> [6, 12])
                        colInx = GetColumnIndexByName(cell.CellReference);             //  eg "C" -> 2  (0-based)
                        rowInx = GetRowIndexFromCellAddress(cell.CellReference)-1;     //  Needs to be 0-based  

                        //  Fetch the value in this cell
                        value = cell.CellValue.InnerXml;
                        if (cell.DataType != null && cell.DataType.Value == CellValues.SharedString)
                        {
                            value = stringTablePart.SharedStringTable.ChildElements[Int32.Parse(value)].InnerText;
                        }

                        cellValues[colInx, rowInx] = value;
                    }
                    dt.Rows.Add(dataRow);
                }

                //  Copy the array of strings into a DataTable
                for (int col = 0; col < numOfColumns; col++)
                    dt.Columns.Add("Column_" + col.ToString());

                for (int row = 0; row < numOfRows; row++)
                {
                    DataRow dataRow = dt.NewRow();
                    for (int col = 0; col < numOfColumns; col++)
                    {
                        dataRow.SetField(col, cellValues[col, row]);
                    }
                    dt.Rows.Add(dataRow);
                }

#if DEBUG
                //  Write out the contents of our DataTable to the Output window (for debugging)
                string str = "";
                for (rowInx = 0; rowInx < maxNumOfRows; rowInx++)
                {
                    for (colInx = 0; colInx < maxNumOfColumns; colInx++)
                    {
                        object val = dt.Rows[rowInx].ItemArray[colInx];
                        str += (val == null) ? "" : val.ToString();
                        str += "\t";
                    }
                    str += "\n";
                }
                System.Diagnostics.Trace.WriteLine(str);
#endif
                return dt;
            }
        }

        private static void CalculateDataTableSize(string dimensions, ref int numOfColumns, ref int numOfRows)
        {
            //  How many columns & rows of data does this Worksheet contain ?  
            //  We'll read in the Dimensions string from the Excel file, and calculate the size based on that.
            //      eg "B1:F4" -> we'll need 6 columns and 4 rows.
            //
            //  (We deliberately ignore the top-left cell address, and just use the bottom-right cell address.)
            try
            {
                string[] parts = dimensions.Split(':');     // eg "B1:F4" 
                if (parts.Length != 2)
                    throw new Exception("Couldn't find exactly *two* CellAddresses in the dimension");

                numOfColumns = 1 + GetColumnIndexByName(parts[1]);     //  A=1, B=2, C=3  (1-based value), so F4 would return 6 columns
                numOfRows = GetRowIndexFromCellAddress(parts[1]);
            }
            catch
            {
                throw new Exception("Could not calculate maximum DataTable size from the worksheet dimension: " + dimensions);
            }
        }

        public static int GetRowIndexFromCellAddress(string cellAddress)
        {
            //  Convert an Excel CellReference column into a 1-based row index
            //  eg "D42"  ->  42
            //     "F123" ->  123
            string rowNumber = System.Text.RegularExpressions.Regex.Replace(cellAddress, "[^0-9 _]", "");
            return int.Parse(rowNumber);
        }

        public static int GetColumnIndexByName(string cellAddress)
        {
            //  Convert an Excel CellReference column into a 0-based column index
            //  eg "D42" ->  3
            //     "F123" -> 5
            var columnName = System.Text.RegularExpressions.Regex.Replace(cellAddress, "[^A-Z_]", "");
            int number = 0, pow = 1;
            for (int i = columnName.Length - 1; i >= 0; i--)
            {
                number += (columnName[i] - 'A' + 1) * pow;
                pow *= 26;
            }
            return number - 1;
        }
    }

顺便提一下，我们公司的一些 Excel 工作表顶部有一个或多个空白行。奇怪的是，这会阻止其他一些 OpenXML 库正确读取此类工作表。

这段代码特意为工作表中的每个单元格创建了一个DataTable，即使是顶部的空白单元格也是如此。