如何使用 EPPlus 将 excel 行解析回类型

Question

EPPlus 有一个方便的 LoadFromCollection<T> 方法可以将我自己类型的数据获取到工作表中。

例如，如果我有 class:

public class Customer
{
    public int Id { get; set; }
    public string Firstname { get; set; }
    public string Surname { get; set; }
    public DateTime Birthdate { get; set; }
}

然后是下面的代码：

var package = new ExcelPackage();
var sheet = package.Workbook.Worksheets.Add("Customers");
var customers = new List<Customer>{
    new Customer{
        Id = 1,
        Firstname = "John",
        Surname = "Doe",
        Birthdate = new DateTime(2000, 1, 1)
    },
    new Customer{
        Id = 2,
        Firstname = "Mary",
        Surname = "Moe",
        Birthdate = new DateTime(2001, 2, 2)
    }
};
sheet.Cells[1, 1].LoadFromCollection(customers);
package.Save();

...将向名为 "Customers".

的工作表中添加 2 行

我的问题是是否有一个方便的对应方可以将 excel 中的行（例如在进行了一些修改之后）提取回我的类型。

类似于：

var package = new ExcelPackage(inputStream);
var customers = sheet.Dimension.SaveToCollection<Customer>() ??

我有

一直在查看 EPPlus 代码库
搜索了任何 saving 个问题
搜索了任何 parsing 个问题
看到this关于阅读单细胞的问题

...但没有发现如何简单地将行解析为我的类型。

Answer 1

不幸的是，EPPlus 本身没有这样的方法。这是一个棘手的问题，因为如果你真的希望它是通用的，你将不得不使用反射。由于 Excel 将所有数字和日期存储为双精度，因此您必须处理大量的拆箱和类型检查。

这是我一直在努力的事情。它是一种扩展方法，将通过 Generics 完成。它可以工作，但只能在有限的测试下使用，因此请确保您自己检查一下。我不能保证它是最优化的（迄今为止），但在他看来它相当不错。你会像这样使用它：

IEnumerable<TestObject> newcollection = worksheet.ConvertSheetToObjects<TestObject>();

分机：

public static IEnumerable<T> ConvertSheetToObjects<T>(this ExcelWorksheet worksheet) 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();

    //Cells only contains references to cells with actual data
    var groups = worksheet.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))
                {
                    //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;
}

一个完整的例子：

[TestMethod]
public void Read_To_Collection_Test()
{   
    //A collection to Test
    var objectcollection = new List<TestObject>();

    for (var i = 0; i < 10; i++)
        objectcollection.Add(new TestObject {Col1 = i, Col2 = i*10, Col3 = Path.GetRandomFileName(), Col4 = DateTime.Now.AddDays(i)});

    //Create a test file to convert back
    byte[] bytes;
    using (var pck = new ExcelPackage())
    {
        //Load the random data
        var workbook = pck.Workbook;
        var worksheet = workbook.Worksheets.Add("data");
        worksheet.Cells.LoadFromCollection(objectcollection, true);
        bytes = pck.GetAsByteArray();
    }


    //*********************************
    //Convert from excel to a collection
    using (var pck = new ExcelPackage(new MemoryStream(bytes)))
    {
        var workbook = pck.Workbook;
        var worksheet = workbook.Worksheets["data"];

        var newcollection = worksheet.ConvertSheetToObjects<TestObject>();
        newcollection.ToList().ForEach(to => Console.WriteLine("{{ Col1:{0}, Col2: {1}, Col3: \"{2}\", Col4: {3} }}", to.Col1, to.Col2, to.Col3, to.Col4.ToShortDateString()));
    }
}

//test object class
public class TestObject
{
    public int Col1 { get; set; }
    public int Col2 { get; set; }
    public string Col3 { get; set; }
    public DateTime Col4 { get; set; }
}

控制台输出：

{ Col1:0, Col2: 0, Col3: "wrulvxbx.wdv", Col4: 10/30/2015 }
{ Col1:1, Col2: 10, Col3: "wflh34yu.0pu", Col4: 10/31/2015 }
{ Col1:2, Col2: 20, Col3: "ps0f1jg0.121", Col4: 11/1/2015 }
{ Col1:3, Col2: 30, Col3: "skoc2gx1.2xs", Col4: 11/2/2015 }
{ Col1:4, Col2: 40, Col3: "urs3jnbb.ob1", Col4: 11/3/2015 }
{ Col1:5, Col2: 50, Col3: "m4l2fese.4yz", Col4: 11/4/2015 }
{ Col1:6, Col2: 60, Col3: "v3dselpn.rqq", Col4: 11/5/2015 }
{ Col1:7, Col2: 70, Col3: "v2ggbaar.r31", Col4: 11/6/2015 }
{ Col1:8, Col2: 80, Col3: "da4vd35p.msl", Col4: 11/7/2015 }
{ Col1:9, Col2: 90, Col3: "v5dtpuad.2ao", Col4: 11/8/2015 }

Answer 2

受上述启发，我采取了稍微不同的路线。

我创建了一个属性并将每个属性映射到一个列。
我使用 DTO 类型来定义我期望每一列的内容
允许不需要列
使用 EPPlus 转换类型

通过这样做，我可以使用传统的模型验证，并接受对列 headers

的更改

-- 用法：

using(FileStream fileStream = new FileStream(_fileName, FileMode.Open)){
      ExcelPackage excel = new ExcelPackage(fileStream);
      var workSheet = excel.Workbook.Worksheets[RESOURCES_WORKSHEET];

      IEnumerable<ExcelResourceDto> newcollection = workSheet.ConvertSheetToObjects<ExcelResourceDto>();
      newcollection.ToList().ForEach(x => Console.WriteLine(x.Title));
 }

Dto 映射到 excel

public class ExcelResourceDto
{
    [Column(1)]
    [Required]
    public string Title { get; set; }

    [Column(2)]
    [Required]
    public string SearchTags { get; set; }
}

这是属性定义

[AttributeUsage(AttributeTargets.All)]
public class Column : System.Attribute
{
    public int ColumnIndex { get; set; }


    public Column(int column) 
    {
        ColumnIndex = column;
    }
}

扩展 class 处理映射行到 DTO

public static class EPPLusExtensions
{
   public static IEnumerable<T> ConvertSheetToObjects<T>(this ExcelWorksheet worksheet) where T : new()
    {

        Func<CustomAttributeData, bool> columnOnly = y => y.AttributeType == typeof(Column);

        var columns = typeof(T)
                .GetProperties()
                .Where(x => x.CustomAttributes.Any(columnOnly))
        .Select(p => new
        {
            Property = p,
            Column = p.GetCustomAttributes<Column>().First().ColumnIndex //safe because if where above
        }).ToList();


        var rows= worksheet.Cells
            .Select(cell => cell.Start.Row)
            .Distinct()
            .OrderBy(x=>x);


        //Create the collection container
        var collection = rows.Skip(1)
            .Select(row =>
            {
                var tnew = new T();
                columns.ForEach(col =>
                {
                    //This is the real wrinkle to using reflection - Excel stores all numbers as double including int
                    var val = worksheet.Cells[row, col.Column];
                    //If it is numeric it is a double since that is how excel stores all numbers
                    if (val.Value == null)
                    {
                        col.Property.SetValue(tnew, null);
                        return;
                    }
                    if (col.Property.PropertyType == typeof(Int32))
                    {
                        col.Property.SetValue(tnew, val.GetValue<int>());
                        return;
                    }
                    if (col.Property.PropertyType == typeof(double))
                    {
                        col.Property.SetValue(tnew, val.GetValue<double>());
                        return;
                    }
                    if (col.Property.PropertyType == typeof(DateTime))
                    {
                        col.Property.SetValue(tnew, val.GetValue<DateTime>());
                        return;
                    }
                    //Its a string
                    col.Property.SetValue(tnew, val.GetValue<string>());
                });

                return tnew;
            });


        //Send it back
        return collection;
    }
}

如何使用 EPPlus 将 excel 行解析回类型

How to parse excel rows back to types using EPPlus

c#

epplus