reading Excel Open XML is ignoring blank cells

Question

I am using the accepted solution here to convert an excel sheet into a datatable. This works fine if I have \"perfect\" data but if I have a blank cell in the middle of my

Answer 1

Okay, I'm not exactly an expert on this but the other answers do seem like over kill to me so here's my solution:

// Loop through each row in the spreadsheet, skipping the header row
foreach (var row in sheetData.Elements<Row>().Skip(1))
{
    var i = 0;
    string[] letters = new string[15] {"A", "B", "C", "D", "E", "F", "G", "H", "I", "J", "K", "L", "M", "N", "O" };

    List<String> cellsList = new List<string>();
    foreach (var cell in row.Elements<Cell>().ToArray())
    {
        while (cell.CellReference.ToString()[0] != Convert.ToChar(letters[i]))
        {//accounts for multiple consecutive blank cells
            cellsList.Add("");
            i++;
        }
        cellsList.Add(cell.CellValue.Text);
        i++;
    }

    string[] cells = cellsList.ToArray();

    foreach(var cell in cellsList)
    {
        //display contents of cell, depending on the datatype you may need to call each of the cells manually
    }
}

Hope someone finds this useful!

Answer 2

You can use this function to extract a cell from a row passing the header index:

public static Cell GetCellFromRow(Row r ,int headerIdx) {
        string cellname = GetNthColumnName(headerIdx) + r.RowIndex.ToString();
        IEnumerable<Cell> cells = r.Elements<Cell>().Where(x=> x.CellReference == cellname);
        if (cells.Count() > 0)
        {
            return cells.First();
        }
        else {
            return null;
        }
}
public static string GetNthColumnName(int n)
    {
        string name = "";
        while (n > 0)
        {
            n--;
            name = (char)('A' + n % 26) + name;
            n /= 26;
        }
        return name;
    }

Answer 3

With apologies for posting yet another answer to this question, here's the code I used.

I was having problems with OpenXML not working properly if a worksheet had a blank row at the top. It would sometimes just return a DataTable with 0 rows and 0 columns in it. The code below copes with this, and all other worksheets.

Here's how you would call my code. Just pass in a filename and the name of the Worksheet to read in:

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

And here's the code itself:

    public class OpenXMLHelper
    {
        //  A helper function to open an Excel file using OpenXML, and return a DataTable containing all the data from one
        //  of the worksheets.
        //
        //  We've had lots of problems reading in Excel data using OLEDB (eg the ACE drivers no longer being present on new servers,
        //  OLEDB not working due to security issues, and blatantly ignoring blank rows at the top of worksheets), so this is a more 
        //  stable method of reading in the data.
        //
        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, and store each cell's value in the appropriate slot in our [,] string array.
                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 column 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;
                    }
                }

                //  Copy the array of strings into a DataTable.
                //  We don't (currently) make any attempt to work out which columns should be numeric, rather than string.
                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;
        }
    }

Answer 4

The letter code is a base 26 encoding so this should work to convert it into an offset.

// Converts letter code (i.e. AA) to an offset
public int offset( string code)
{
    var offset = 0;
    var byte_array = Encoding.ASCII.GetBytes( code ).Reverse().ToArray();
    for( var i = 0; i < byte_array.Length; i++ )
    {
        offset += (byte_array[i] - 65 + 1) * Convert.ToInt32(Math.Pow(26.0, Convert.ToDouble(i)));
    }
    return offset - 1;
}

Answer 5

Here's a slightly modified version of Waylon's answer which also relied on other answers. It encapsulates his method in a class.

I changed

IEnumerator<Cell> GetEnumerator()

to

IEnumerable<Cell> GetRowCells(Row row)

Here's the class, you don't need to instantiate it, it just serves as an utility class:

public class SpreedsheetHelper
{
    ///<summary>returns an empty cell when a blank cell is encountered
    ///</summary>
    public static IEnumerable<Cell> GetRowCells(Row row)
    {
        int currentCount = 0;

        foreach (DocumentFormat.OpenXml.Spreadsheet.Cell cell in
            row.Descendants<DocumentFormat.OpenXml.Spreadsheet.Cell>())
        {
            string columnName = GetColumnName(cell.CellReference);

            int currentColumnIndex = ConvertColumnNameToNumber(columnName);

            for (; currentCount < currentColumnIndex; currentCount++)
            {
                yield return new DocumentFormat.OpenXml.Spreadsheet.Cell();
            }

            yield return cell;
            currentCount++;
        }
    }

    /// <summary>
    /// Given a cell name, parses the specified cell to get the column name.
    /// </summary>
    /// <param name="cellReference">Address of the cell (ie. B2)</param>
    /// <returns>Column Name (ie. B)</returns>
    public static string GetColumnName(string cellReference)
    {
        // Match the column name portion of the cell name.
        var regex = new System.Text.RegularExpressions.Regex("[A-Za-z]+");
        var match = regex.Match(cellReference);

        return match.Value;
    }

    /// <summary>
    /// Given just the column name (no row index),
    /// it will return the zero based column index.
    /// </summary>
    /// <param name="columnName">Column Name (ie. A or AB)</param>
    /// <returns>Zero based index if the conversion was successful</returns>
    /// <exception cref="ArgumentException">thrown if the given string
    /// contains characters other than uppercase letters</exception>
    public static int ConvertColumnNameToNumber(string columnName)
    {
        var alpha = new System.Text.RegularExpressions.Regex("^[A-Z]+$");
        if (!alpha.IsMatch(columnName)) throw new ArgumentException();

        char[] colLetters = columnName.ToCharArray();
        Array.Reverse(colLetters);

        int convertedValue = 0;
        for (int i = 0; i < colLetters.Length; i++)
        {
            char letter = colLetters[i];
            int current = i == 0 ? letter - 65 : letter - 64; // ASCII 'A' = 65
            convertedValue += current * (int)Math.Pow(26, i);
        }

        return convertedValue;
    }
}

Now you're able to get all rows' cells in this way:

// skip the part that retrieves the worksheet sheetData
IEnumerable<Row> rows = sheetData.Descendants<Row>();
foreach(Row row in rows)
{
    IEnumerable<Cell> cells = SpreedsheetHelper.GetRowCells(row);
    foreach (Cell cell in cells)
    {
         // skip part that reads the text according to the cell-type
    }
}

It will contain all cells even if they are empty.

Answer 6

See my implementation:

  Row[] rows = worksheet.GetFirstChild<SheetData>()
                .Elements<Row>()
                .ToArray();

  string[] columnNames = rows.First()
                .Elements<Cell>()
                .Select(cell => GetCellValue(cell, document))
                .ToArray();

  HeaderLetters = ExcelHeaderHelper.GetHeaderLetters((uint)columnNames.Count());

  if (columnNames.Count() != HeaderLetters.Count())
  {
       throw new ArgumentException("HeaderLetters");
  }

  IEnumerable<List<string>> cellValues = GetCellValues(rows.Skip(1), columnNames.Count(), document);

//Here you can enumerate through the cell values, based on the cell index the column names can be retrieved.

HeaderLetters are collected using this class:

    private static class ExcelHeaderHelper
    {
        public static string[] GetHeaderLetters(uint max)
        {
            var result = new List<string>();
            int i = 0;
            var columnPrefix = new Queue<string>();
            string prefix = null;
            int prevRoundNo = 0;
            uint maxPrefix = max / 26;

            while (i < max)
            {
                int roundNo = i / 26;
                if (prevRoundNo < roundNo)
                {
                    prefix = columnPrefix.Dequeue();
                    prevRoundNo = roundNo;
                }
                string item = prefix + ((char)(65 + (i % 26))).ToString(CultureInfo.InvariantCulture);
                if (i <= maxPrefix)
                {
                    columnPrefix.Enqueue(item);
                }
                result.Add(item);
                i++;
            }
            return result.ToArray();
        }
    }

And the helper methods are:

    private static IEnumerable<List<string>> GetCellValues(IEnumerable<Row> rows, int columnCount, SpreadsheetDocument document)
    {
        var result = new List<List<string>>();
        foreach (var row in rows)
        {
            List<string> cellValues = new List<string>();
            var actualCells = row.Elements<Cell>().ToArray();

            int j = 0;
            for (int i = 0; i < columnCount; i++)
            {
                if (actualCells.Count() <= j || !actualCells[j].CellReference.ToString().StartsWith(HeaderLetters[i]))
                {
                    cellValues.Add(null);
                }
                else
                {
                    cellValues.Add(GetCellValue(actualCells[j], document));
                    j++;
                }
            }
            result.Add(cellValues);
        }
        return result;
    }


private static string GetCellValue(Cell cell, SpreadsheetDocument document)
{
    bool sstIndexedcell = GetCellType(cell);
    return sstIndexedcell
        ? GetSharedStringItemById(document.WorkbookPart, Convert.ToInt32(cell.InnerText))
        : cell.InnerText;
}

private static bool GetCellType(Cell cell)
{
    return cell.DataType != null && cell.DataType == CellValues.SharedString;
}

private static string GetSharedStringItemById(WorkbookPart workbookPart, int id)
{
    return workbookPart.SharedStringTablePart.SharedStringTable.Elements<SharedStringItem>().ElementAt(id).InnerText;
}

The solution deals with shared cell items (SST indexed cells).