EPPlus - Read Excel Table

Question

Using EPPlus, I want to read an excel table, then store all the contents from each column into its corresponding List. I want it to recognize the table's heading and categorize the contents based on that.

For example, if my excel table is as below:

Id    Name     Gender
 1    John     Male
 2    Maria    Female
 3    Daniel   Unknown

I want the data to store in List<ExcelData> where

public class ExcelData
{
    public string Id { get; set; }
    public string Name { get; set; }
    public string Gender { get; set; }
}

So that I can call out the contents using the heading name. For example, when I do this:

foreach (var data in ThatList)
{
     Console.WriteLine(data.Id + data.Name + data.Gender);
}

It will give me this output:

1JohnMale
2MariaFemale
3DanielUnknown

---

This is really all I got:

var package = new ExcelPackage(new FileInfo(@"C:\ExcelFile.xlsx"));
ExcelWorksheet sheet = package.Workbook.Worksheets[1];

var table = sheet.Tables.First();

table.Columns.Something //I guess I can use this to do what I want

Please help :( I have spent long hours searching for sample code regarding this so that I can learn from it but to no avail. I also understand ExcelToLinQ is managed to do that but it can't recognize table.

Solution 1

There is no native but what if you use what I put in this post:

How to parse excel rows back to types using EPPlus

If you want to point it at a table only it will need to be modified. Something like this should do it:

public static IEnumerable<T> ConvertTableToObjects<T>(this ExcelTable table) where T : new()
{
    //DateTime Conversion
    var convertDateTime = new Func<double, DateTime>(excelDate =>
    {
        if (excelDate < 1)
            throw new ArgumentException("Excel dates cannot be smaller than 0.");

        var dateOfReference = new DateTime(1900, 1, 1);

        if (excelDate > 60d)
            excelDate = excelDate - 2;
        else
            excelDate = excelDate - 1;
        return dateOfReference.AddDays(excelDate);
    });

    //Get the properties of T
    var tprops = (new T())
        .GetType()
        .GetProperties()
        .ToList();

    //Get the cells based on the table address
    var start = table.Address.Start;
    var end = table.Address.End;
    var cells = new List<ExcelRangeBase>();

    //Have to use for loops insteadof worksheet.Cells to protect against empties
    for (var r = start.Row; r <= end.Row; r++)
        for (var c = start.Column; c <= end.Column; c++)
            cells.Add(table.WorkSheet.Cells[r, c]);

    var groups = cells
        .GroupBy(cell => cell.Start.Row)
        .ToList();

    //Assume the second row represents column data types (big assumption!)
    var types = groups
        .Skip(1)
        .First()
        .Select(rcell => rcell.Value.GetType())
        .ToList();

    //Assume first row has the column names
    var colnames = groups
        .First()
        .Select((hcell, idx) => new { Name = hcell.Value.ToString(), index = idx })
        .Where(o => tprops.Select(p => p.Name).Contains(o.Name))
        .ToList();

    //Everything after the header is data
    var rowvalues = groups
        .Skip(1) //Exclude header
        .Select(cg => cg.Select(c => c.Value).ToList());

    //Create the collection container
    var collection = rowvalues
        .Select(row =>
        {
            var tnew = new T();
            colnames.ForEach(colname =>
            {
                //This is the real wrinkle to using reflection - Excel stores all numbers as double including int
                var val = row[colname.index];
                var type = types[colname.index];
                var prop = tprops.First(p => p.Name == colname.Name);

                //If it is numeric it is a double since that is how excel stores all numbers
                if (type == typeof(double))
                {
                    if (!string.IsNullOrWhiteSpace(val?.ToString()))
                    {
                        //Unbox it
                        var unboxedVal = (double)val;

                        //FAR FROM A COMPLETE LIST!!!
                        if (prop.PropertyType == typeof(Int32))
                            prop.SetValue(tnew, (int)unboxedVal);
                        else if (prop.PropertyType == typeof(double))
                            prop.SetValue(tnew, unboxedVal);
                        else if (prop.PropertyType == typeof(DateTime))
                            prop.SetValue(tnew, convertDateTime(unboxedVal));
                        else
                            throw new NotImplementedException(String.Format("Type '{0}' not implemented yet!", prop.PropertyType.Name));
                    }
                }
                else
                {
                    //Its a string
                    prop.SetValue(tnew, val);
                }
            });

            return tnew;
        });


    //Send it back
    return collection;
}

Here is a test method:

[TestMethod]
public void Table_To_Object_Test()
{
    //Create a test file
    var fi = new FileInfo(@"c:\temp\Table_To_Object.xlsx");

    using (var package = new ExcelPackage(fi))
    {
        var workbook = package.Workbook;
        var worksheet = workbook.Worksheets.First();
        var ThatList = worksheet.Tables.First().ConvertTableToObjects<ExcelData>();
        foreach (var data in ThatList)
        {
            Console.WriteLine(data.Id + data.Name + data.Gender);
        }

        package.Save();
    }
}

Gave this in the console:

1JohnMale
2MariaFemale
3DanielUnknown

Just be careful if you Id field is an number or string in excel since the class is expecting a string.

Solution 2

Not sure why but none of the above solution work for me. So sharing what worked:

public void readXLS(string FilePath)
{
    FileInfo existingFile = new FileInfo(FilePath);
    using (ExcelPackage package = new ExcelPackage(existingFile))
    {
        //get the first worksheet in the workbook
        ExcelWorksheet worksheet = package.Workbook.Worksheets[1];
        int colCount = worksheet.Dimension.End.Column;  //get Column Count
        int rowCount = worksheet.Dimension.End.Row;     //get row count
        for (int row = 1; row <= rowCount; row++)
        {
            for (int col = 1; col <= colCount; col++)
            {
                Console.WriteLine(" Row:" + row + " column:" + col + " Value:" + worksheet.Cells[row, col].Value?.ToString().Trim());
            }
        }
    }
}

Solution 3

This is my working version. Note that the resolvers code is not shown but are a spin on my implementation which allows columns to be resolved even though they are named slightly differently in each worksheet.

public static IEnumerable<T> ToArray<T>(this ExcelWorksheet worksheet, List<PropertyNameResolver> resolvers) where T : new()
{

  // List of all the column names
  var header = worksheet.Cells.GroupBy(cell => cell.Start.Row).First();

  // Get the properties from the type your are populating
  var properties = typeof(T).GetProperties().ToList();


  var start = worksheet.Dimension.Start;
  var end = worksheet.Dimension.End;

  // Resulting list
  var list = new List<T>();

  // Iterate the rows starting at row 2 (ie start.Row + 1)
  for (int row = start.Row + 1; row <= end.Row; row++)
  {
    var instance = new T();
    for (int col = start.Column; col <= end.Column; col++)
    {
      object value = worksheet.Cells[row, col].Text;

      // Get the column name zero based (ie col -1)
      var column = (string)header.Skip(col - 1).First().Value;

      // Gets the corresponding property to set
      var property = properties.Property(resolvers, column);

      try
      {
        var propertyName = property.PropertyType.IsGenericType
          ? property.PropertyType.GetGenericArguments().First().FullName
          : property.PropertyType.FullName;


        // Implement setter code as needed. 
        switch (propertyName)
        {
          case "System.String":
            property.SetValue(instance, Convert.ToString(value));
            break;
          case "System.Int32":
            property.SetValue(instance, Convert.ToInt32(value));
            break;
          case "System.DateTime":
            if (DateTime.TryParse((string) value, out var date))
            {
              property.SetValue(instance, date);
            }
            property.SetValue(instance, FromExcelSerialDate(Convert.ToInt32(value)));
            break;
          case "System.Boolean":
            property.SetValue(instance, (int)value == 1);
            break;
        }
      }
      catch (Exception e)
      {
        // instance property is empty because there was a problem.
      }

    } 
    list.Add(instance);
  }
  return list;
}

// Utility function taken from the above post's inline function.
public static DateTime FromExcelSerialDate(int excelDate)
{
  if (excelDate < 1)
    throw new ArgumentException("Excel dates cannot be smaller than 0.");

  var dateOfReference = new DateTime(1900, 1, 1);

  if (excelDate > 60d)
    excelDate = excelDate - 2;
  else
    excelDate = excelDate - 1;
  return dateOfReference.AddDays(excelDate);
}

Solution 4

Below code will read excel data into a datatable, which is converted to list of datarows.

if (FileUpload1.HasFile)
{
    if (Path.GetExtension(FileUpload1.FileName) == ".xlsx")
    {
        Stream fs = FileUpload1.FileContent;
        ExcelPackage package = new ExcelPackage(fs);
        DataTable dt = new DataTable();
        dt= package.ToDataTable();
        List<DataRow> listOfRows = new List<DataRow>();
        listOfRows = dt.AsEnumerable().ToList();

    }
}

using OfficeOpenXml;
using System.Data;
using System.Linq;

 public static class ExcelPackageExtensions
    {
        public static DataTable ToDataTable(this ExcelPackage package)
        {
            ExcelWorksheet workSheet = package.Workbook.Worksheets.First();
            DataTable table = new DataTable();
            foreach (var firstRowCell in workSheet.Cells[1, 1, 1, workSheet.Dimension.End.Column])
            {
                table.Columns.Add(firstRowCell.Text);
            }

            for (var rowNumber = 2; rowNumber <= workSheet.Dimension.End.Row; rowNumber++)
            {
                var row = workSheet.Cells[rowNumber, 1, rowNumber, workSheet.Dimension.End.Column];
                var newRow = table.NewRow();
                foreach (var cell in row)
                {
                    newRow[cell.Start.Column - 1] = cell.Text;
                }
                table.Rows.Add(newRow);
            }
            return table;
        }

    }

Solution 5

Yet another way to do it.

I used Ernie S solution but it didn't work if I had empty cells in the first data row (it wasn't able to guess the data type from it).
So instead of getting a data type from Excel table I get it from the T parameter class properties using reflection.

/// <summary>
///     Converts table to list of T objects
/// </summary>
/// <typeparam name="T">The type to return</typeparam>
/// <param name="table">Data source</param>
/// <returns>List of T objects</returns>
public static IEnumerable<T> ConvertToObjects<T>(this ExcelTable table) where T : new()
{
    ExcelCellAddress start = table.Address.Start;
    ExcelCellAddress end = table.Address.End;
    List<ExcelRange> cells = new();

    for (int r = start.Row; r <= end.Row; r++)
        for (int c = start.Column; c <= end.Column; c++)
            cells.Add(table.WorkSheet.Cells[r, c]);

    List<IGrouping<int, ExcelRange>> allRows = cells
        .GroupBy(cell => cell.Start.Row)
        .OrderBy(cell => cell.Key)
        .ToList();

    IEnumerable<PropertyInfo> typeProperties = typeof(T).GetProperties();

    IGrouping<int, ExcelRangeBase> header = allRows.First();

    Dictionary<PropertyInfo, int> columns = new();

    foreach (ExcelRangeBase col in header)
    {
        string propName = col.GetValue<string>();
        PropertyInfo propInfo = typeProperties.FirstOrDefault(x => x.Name.Equals(propName));
        if (propInfo != null)
        {
            columns.Add(propInfo, col.Start.Column);
        }                    
    }

    IEnumerable<IGrouping<int, ExcelRangeBase>> rows = allRows.Skip(1);

    List<T> objects = new();

    foreach (IGrouping<int, ExcelRangeBase> row in rows)
    {
        T obj = new();
        foreach (KeyValuePair<PropertyInfo, int> colInfo in columns)
        {
            ExcelRangeBase col = row.First(x => x.Start.Column == colInfo.Value);

            if (col.Value == null)
                continue;

            object value = Convert.ChangeType(col.Value, Nullable.GetUnderlyingType(colInfo.Key.PropertyType) ?? colInfo.Key.PropertyType);
            colInfo.Key.SetValue(obj, value);
        }
        objects.Add(obj);
    }

    return objects;
}

View more solutions