Related
I have a requirement where-in I have to fill dataTable from a sheet of Microsoft excel.
The sheet may have lots of data so the requirement is that when a foreach loop is iterated over the data table which is supposed to hold the data from Microsoft excel sheet should fill the table on demand.
Meaning if there are 1000000 records in the sheet the data table should fetch data in batches of 100 depending on the current position of the foreach current item in the loop.
Any pointer or suggestion will be appreciated.
I would suggest you to use OpenXML to parse and read your excel data from file.
This will also allow you to read out specific sections/regions from your workbook.
You will find more information and also an example at this link:
Microsoft Docs - Parse and read a large spreadsheet document (Open XML SDK)
This will be more efficiently and easier to develop than use the official microsoft office excel interop.
**I am not near a PC with Visual stuido, so this code is untested, and may have syntax errors until I can test it later.
It will still give you the main idea of what needs to be done.
private void ExcelDataPages(int firstRecord, int numberOfRecords)
{
Excel.Application dataApp = new Excel.Application();
Excel.Workbook dataWorkbook = new Excel.Workbook();
int x = 0;
dataWorkbook.DisplayAlerts = false;
dataWorkbook.Visible = false;
dataWorkbook.AutomationSecurity = Microsoft.Office.Core.MsoAutomationSecurity.msoAutomationSecurityLow;
dataWorkbook = dataApp.Open(#"C:\Test\YourWorkbook.xlsx");
try
{
Excel.Worksheet dataSheet = dataWorkbook.Sheet("Name of Sheet");
while (x < numberOfRecords)
{
Range currentRange = dataSheet.Rows[firstRecord + x]; //For all columns in row
foreach (Range r in currentRange.Cells) //currentRange represents all the columns in the row
{
// do what you need to with the Data here.
}
x++;
}
}
catch (Exception ex)
{
//Enter in Error handling
}
dataWorkbook.Close(false); //Depending on how quick you will access the next batch of data, you may not want to close the Workbook, reducing load time each time. This may also mean you need to move the open of the workbook to a higher level in your class, or if this is the main process of the app, make it static, stopping the garbage collector from destroying the connection.
dataApp.Quit();
}
Give the following a try--it uses NuGet package DocumentFormat.OpenXml The code is from Using OpenXmlReader. However, I modified it to add data to a DataTable. Since you're reading data from the same Excel file multiple times, it's faster to open the Excel file once using an instance of SpreadSheetDocument and dispose of it when finished. Since the instance of SpreedSheetDocument needs to be disposed of before your application exits, IDisposable is used.
Where it says "ToDo", you'll need to replace the code that creates the DataTable columns with your own code to create the correct columns for your project.
I tested the code below with an Excel file containing approximately 15,000 rows. When reading 100 rows at a time, the first read took approximately 500 ms - 800 ms, whereas subsequent reads took approximately 100 ms - 400 ms.
Create a class (name: HelperOpenXml)
HelperOpenXml.cs
using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Threading.Tasks;
using DocumentFormat.OpenXml;
using DocumentFormat.OpenXml.Packaging;
using DocumentFormat.OpenXml.Spreadsheet;
using System.Data;
using System.Diagnostics;
namespace ExcelReadSpecifiedRowsUsingOpenXml
{
public class HelperOpenXml : IDisposable
{
public string Filename { get; private set; } = string.Empty;
public int RowCount { get; private set; } = 0;
private SpreadsheetDocument spreadsheetDocument = null;
private DataTable dt = null;
public HelperOpenXml(string filename)
{
this.Filename = filename;
}
public void Dispose()
{
if (spreadsheetDocument != null)
{
try
{
spreadsheetDocument.Dispose();
dt.Clear();
}
catch(Exception ex)
{
throw ex;
}
}
}
public DataTable GetRowsSax(int startRow, int endRow, bool firstRowIsHeader = false)
{
int startIndex = startRow;
int endIndex = endRow;
if (firstRowIsHeader)
{
//if first row is header, increment by 1
startIndex = startRow + 1;
endIndex = endRow + 1;
}
if (spreadsheetDocument == null)
{
//create new instance
spreadsheetDocument = SpreadsheetDocument.Open(Filename, false);
//create new instance
dt = new DataTable();
//ToDo: replace 'dt.Columns.Add(...)' below with your code to create the DataTable columns
//add columns to DataTable
dt.Columns.Add("A");
dt.Columns.Add("B");
dt.Columns.Add("C");
dt.Columns.Add("D");
dt.Columns.Add("E");
dt.Columns.Add("F");
dt.Columns.Add("G");
dt.Columns.Add("H");
dt.Columns.Add("I");
dt.Columns.Add("J");
dt.Columns.Add("K");
}
else
{
//remove existing data from DataTable
dt.Rows.Clear();
}
WorkbookPart workbookPart = spreadsheetDocument.WorkbookPart;
int numWorkSheetParts = 0;
foreach (WorksheetPart worksheetPart in workbookPart.WorksheetParts)
{
using (OpenXmlReader reader = OpenXmlReader.Create(worksheetPart))
{
int rowIndex = 0;
//use the reader to read the XML
while (reader.Read())
{
if (reader.ElementType == typeof(Row))
{
reader.ReadFirstChild();
List<string> cValues = new List<string>();
int colIndex = 0;
do
{
//only get data from desired rows
if ((rowIndex > 0 && rowIndex >= startIndex && rowIndex <= endIndex) ||
(rowIndex == 0 && !firstRowIsHeader && rowIndex >= startIndex && rowIndex <= endIndex))
{
if (reader.ElementType == typeof(Cell))
{
Cell c = (Cell)reader.LoadCurrentElement();
string cellRef = c.CellReference; //ex: A1, B1, ..., A2, B2
string cellValue = string.Empty;
//string/text data is stored in SharedString
if (c.DataType != null && c.DataType == CellValues.SharedString)
{
SharedStringItem ssi = workbookPart.SharedStringTablePart.SharedStringTable.Elements<SharedStringItem>().ElementAt(int.Parse(c.CellValue.InnerText));
cellValue = ssi.Text.Text;
}
else
{
cellValue = c.CellValue.InnerText;
}
//Debug.WriteLine("{0}: {1} ", c.CellReference, cellValue);
//add value to List which is used to add a row to the DataTable
cValues.Add(cellValue);
}
}
colIndex += 1; //increment
} while (reader.ReadNextSibling());
if (cValues.Count > 0)
{
//if List contains data, use it to add row to DataTable
dt.Rows.Add(cValues.ToArray());
}
rowIndex += 1; //increment
if (rowIndex > endIndex)
{
break; //exit loop
}
}
}
}
numWorkSheetParts += 1; //increment
}
DisplayDataTableData(dt); //display data in DataTable
return dt;
}
private void DisplayDataTableData(DataTable dt)
{
foreach (DataColumn dc in dt.Columns)
{
Debug.WriteLine("colName: " + dc.ColumnName);
}
foreach (DataRow r in dt.Rows)
{
Debug.WriteLine(r[0].ToString() + " " + r[1].ToString());
}
}
}
}
Usage:
private string excelFilename = #"C:\Temp\Test.xlsx";
private HelperOpenXml helperOpenXml = null;
...
private void GetData(int startIndex, int endIndex, bool firstRowIsHeader)
{
helperOpenXml.GetRowsSax(startIndex, endIndex, firstRowIsHeader);
}
Note: Make sure to call Dispose() (ex: helperOpenXml.Dispose();) before your application exits.
Update:
OpenXML stores dates as the number of days since 01 Jan 1900. For dates prior to 01 Jan 1900, they are stored in SharedString. For more info see Reading a date from xlsx using open xml sdk
Here's a code snippet:
Cell c = (Cell)reader.LoadCurrentElement();
...
string cellValue = string.Empty
...
cellValue = c.CellValue.InnerText;
double dateCellValue = 0;
Double.TryParse(cellValue, out dateCellValue);
DateTime dt = DateTime.FromOADate(dateCellValue);
cellValue = dt.ToString("yyyy/MM/dd");
Another simple alternative is this: Take a look at the NUGET package ExcelDataReader, with additional information on
https://github.com/ExcelDataReader/ExcelDataReader
Usage example:
[Fact]
void Test_ExcelDataReader()
{
System.Text.Encoding.RegisterProvider(System.Text.CodePagesEncodingProvider.Instance);
var scriptPath = Path.GetDirectoryName(Util.CurrentQueryPath); // LinqPad script path
var filePath = $#"{scriptPath}\TestExcel.xlsx";
using (var stream = File.Open(filePath, FileMode.Open, FileAccess.Read))
{
// Auto-detect format, supports:
// - Binary Excel files (2.0-2003 format; *.xls)
// - OpenXml Excel files (2007 format; *.xlsx, *.xlsb)
using (var reader = ExcelDataReader.ExcelReaderFactory.CreateReader(stream))
{
var result = reader.AsDataSet();
// The result of each spreadsheet is in result.Tables
var t0 = result.Tables[0];
Assert.True(t0.Rows[0][0].Dump("R0C0").ToString()=="Hello", "Expected 'Hello'");
Assert.True(t0.Rows[0][1].Dump("R0C1").ToString()=="World!", "Expected 'World!'");
} // using
} // using
} // fact
Before you start reading, you need to set and encoding provider as follows:
System.Text.Encoding.RegisterProvider(
System.Text.CodePagesEncodingProvider.Instance);
The cells are addressed the following way:
var t0 = result.Tables[0]; // table 0 is the first worksheet
var cell = t0.Rows[0][0]; // on table t0, read cell row 0 column 0
And you can easily loop through the rows and columns in a for loop as follows:
for (int r = 0; r < t0.Rows.Count; r++)
{
var row = t0.Rows[r];
var columns = row.ItemArray;
for (int c = 0; c < columns.Length; c++)
{
var cell = columns[c];
cell.Dump();
}
}
I use this code with EPPlus DLL, Don't forget to add reference. But should check to match with your requirement.
public DataTable ReadExcelDatatable(bool hasHeader = true)
{
using (var pck = new OfficeOpenXml.ExcelPackage())
{
using (var stream = File.OpenRead(this._fullPath))
{
pck.Load(stream);
}
var ws = pck.Workbook.Worksheets.First();
DataTable tbl = new DataTable();
int i = 1;
foreach (var firstRowCell in ws.Cells[1, 1, 1, ws.Dimension.End.Column])
{
//table head
tbl.Columns.Add(hasHeader ? firstRowCell.Text : string.Format("Column {0}", firstRowCell.Start.Column));
tbl.Columns.Add(_tableHead[i]);
i++;
}
var startRow = hasHeader ? 2 : 1;
for (int rowNum = startRow; rowNum <= ws.Dimension.End.Row; rowNum++)
{
var wsRow = ws.Cells[rowNum, 1, rowNum, ws.Dimension.End.Column];
DataRow row = tbl.Rows.Add();
foreach (var cell in wsRow)
{
row[cell.Start.Column - 1] = cell.Text;
}
}
return tbl;
}
}
I'm going to give you a different answer. If the performance is bad loading a million rows into a DataTable resort to using a Driver to load the data: How to open a huge excel file efficiently
DataSet excelDataSet = new DataSet();
string filePath = #"c:\temp\BigBook.xlsx";
// For .XLSXs we use =Microsoft.ACE.OLEDB.12.0;, for .XLS we'd use Microsoft.Jet.OLEDB.4.0; with "';Extended Properties=\"Excel 8.0;HDR=YES;\"";
string connectionString = "Provider=Microsoft.ACE.OLEDB.12.0;Data Source='" + filePath + "';Extended Properties=\"Excel 12.0;HDR=YES;\"";
using (OleDbConnection conn = new OleDbConnection(connectionString))
{
conn.Open();
OleDbDataAdapter objDA = new System.Data.OleDb.OleDbDataAdapter
("select * from [Sheet1$]", conn);
objDA.Fill(excelDataSet);
//dataGridView1.DataSource = excelDataSet.Tables[0];
}
Next filter the DataSet's DataTable using a DataView. Using a DataView's RowFilter property you can specify subsets of rows based on their column values.
DataView prodView = new DataView(excelDataSet.Tables[0],
"UnitsInStock <= ReorderLevel",
"SupplierID, ProductName",
DataViewRowState.CurrentRows);
Ref: https://www.c-sharpcorner.com/article/dataview-in-C-Sharp/
Or you could use the DataTables' DefaultView RowFilter directly:
excelDataSet.Tables[0].DefaultView.RowFilter = "Amount >= 5000 and Amount <= 5999 and Name = 'StackOverflow'";
I want to implement openXml sdk 2.5 into my project. I do everything in this link
using DocumentFormat.OpenXml;
using DocumentFormat.OpenXml.Packaging;
using DocumentFormat.OpenXml.Spreadsheet;
using System.IO.Packaging;
static void Main(string[] args)
{
String fileName = #"C:\OPENXML\BigData.xlsx";
// Comment one of the following lines to test the method separately.
ReadExcelFileDOM(fileName); // DOM
//ReadExcelFileSAX(fileName); // SAX
}
// The DOM approach.
// Note that the code below works only for cells that contain numeric values.
//
static void ReadExcelFileDOM(string fileName)
{
using (SpreadsheetDocument spreadsheetDocument = SpreadsheetDocument.Open(fileName, false))
{
WorkbookPart workbookPart = spreadsheetDocument.WorkbookPart;
WorksheetPart worksheetPart = workbookPart.WorksheetParts.First();
SheetData sheetData = worksheetPart.Worksheet.Elements<SheetData>().First();
string text;
int rowCount= sheetData.Elements<Row>().Count();
foreach (Row r in sheetData.Elements<Row>())
{
foreach (Cell c in r.Elements<Cell>())
{
text = c.CellValue.Text;
Console.Write(text + " ");
}
}
Console.WriteLine();
Console.ReadKey();
}
}
But i am not getting any row. It hasn't entered loop. Note: I also set up openXml sdk 2.5 my computer
And I find below code this is work for numeric value.For string value it writes 0 1 2 ...
private static void Main(string[] args)
{
var filePath = #"C:/OPENXML/BigData.xlsx";
using (var document = SpreadsheetDocument.Open(filePath, false))
{
var workbookPart = document.WorkbookPart;
var workbook = workbookPart.Workbook;
var sheets = workbook.Descendants<Sheet>();
foreach (var sheet in sheets)
{
var worksheetPart = (WorksheetPart)workbookPart.GetPartById(sheet.Id);
var sharedStringPart = workbookPart.SharedStringTablePart;
//var values = sharedStringPart.SharedStringTable.Elements<SharedStringItem>().ToArray();
string text;
var rows = worksheetPart.Worksheet.Descendants<Row>();
foreach (var row in rows)
{
Console.WriteLine();
int count = row.Elements<Cell>().Count();
foreach (Cell c in row.Elements<Cell>())
{
text = c.CellValue.InnerText;
Console.Write(text + " ");
}
}
}
}
Console.ReadLine();
}
Your approach seemed to work ok for me - in that it did "enter the loop".
Nevertheless you could also try something like the following:
void Main()
{
string fileName = #"c:\path\to\my\file.xlsx";
using (FileStream fs = new FileStream(fileName, FileMode.Open, FileAccess.Read, FileShare.ReadWrite))
{
using (SpreadsheetDocument doc = SpreadsheetDocument.Open(fs, false))
{
WorkbookPart workbookPart = doc.WorkbookPart;
SharedStringTablePart sstpart = workbookPart.GetPartsOfType<SharedStringTablePart>().First();
SharedStringTable sst = sstpart.SharedStringTable;
WorksheetPart worksheetPart = workbookPart.WorksheetParts.First();
Worksheet sheet = worksheetPart.Worksheet;
var cells = sheet.Descendants<Cell>();
var rows = sheet.Descendants<Row>();
Console.WriteLine("Row count = {0}", rows.LongCount());
Console.WriteLine("Cell count = {0}", cells.LongCount());
// One way: go through each cell in the sheet
foreach (Cell cell in cells)
{
if ((cell.DataType != null) && (cell.DataType == CellValues.SharedString))
{
int ssid = int.Parse(cell.CellValue.Text);
string str = sst.ChildElements[ssid].InnerText;
Console.WriteLine("Shared string {0}: {1}", ssid, str);
}
else if (cell.CellValue != null)
{
Console.WriteLine("Cell contents: {0}", cell.CellValue.Text);
}
}
// Or... via each row
foreach (Row row in rows)
{
foreach (Cell c in row.Elements<Cell>())
{
if ((c.DataType != null) && (c.DataType == CellValues.SharedString))
{
int ssid = int.Parse(c.CellValue.Text);
string str = sst.ChildElements[ssid].InnerText;
Console.WriteLine("Shared string {0}: {1}", ssid, str);
}
else if (c.CellValue != null)
{
Console.WriteLine("Cell contents: {0}", c.CellValue.Text);
}
}
}
}
}
}
I used the filestream approach to open the workbook because this allows you to open it with shared access - so that you can have the workbook open in Excel at the same time. The Spreadsheet.Open(... method won't work if the workbook is open elsewhere.
Perhaps that is why your code didn't work.
Note, also, the use of the SharedStringTable to get the cell text where appropriate.
EDIT 2018-07-11:
Since this post is still getting votes I should also point out that in many cases it may be a lot easier to use ClosedXML to manipulate/read/edit your workbooks. The documentation examples are pretty user friendly and the coding is, in my limited experience, much more straight forward. Just be aware that it does not (yet) implement all the Excel functions (for example INDEX and MATCH) which may or may not be an issue. [Not that I would want to be trying to deal with INDEX and MATCH in OpenXML anyway.]
I had the same issue as the OP, and the answer above did not work for me.
I think this is the issue: when you create a document in Excel (not programmatically), you have 3 sheets by default and the WorksheetParts that has the row data for Sheet1 is the last WorksheetParts element, not the first.
I figured this out by putting a watch for document.WorkbookPart.WorksheetParts in Visual Studio, expanding Results, then looking at all of the sub elements until I found a SheetData object where HasChildren = true.
Try this:
// open the document read-only
SpreadSheetDocument document = SpreadsheetDocument.Open(filePath, false);
SharedStringTable sharedStringTable = document.WorkbookPart.SharedStringTablePart.SharedStringTable;
string cellValue = null;
foreach (WorksheetPart worksheetPart in document.WorkbookPart.WorksheetParts)
{
foreach (SheetData sheetData in worksheetPart.Worksheet.Elements<SheetData>())
{
if (sheetData.HasChildren)
{
foreach (Row row in sheetData.Elements<Row>())
{
foreach (Cell cell in row.Elements<Cell>())
{
cellValue = cell.InnerText;
if (cell.DataType == CellValues.SharedString)
{
Console.WriteLine("cell val: " + sharedStringTable.ElementAt(Int32.Parse(cellValue)).InnerText);
}
else
{
Console.WriteLine("cell val: " + cellValue);
}
}
}
}
}
}
document.Close();
Read Large Excel :
openxml has two approaches of DOM and SAX to read an excel. the DOM one consume more RAM resource since it loads the whole xml content(Excel file) in Memory but its strong typed approach.
SAX in other hand is event base parse. more here
so if you are facing large excel file its better to use SAX.
the below code sample uses SAX approach and also handle two important scenario in excel file reading.
open xml skips the empty cells so your dataset faces displacement and wrong index.
you need to skip the empty rows also.
this function returns the exact actual index of the cell at the time and handle the first scenario.
from here
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;
}
code to read excel sax approach.
//i want to import excel to data table
dt = new DataTable();
using (SpreadsheetDocument document = SpreadsheetDocument.Open(path, false))
{
WorkbookPart workbookPart = document.WorkbookPart;
WorksheetPart worksheetPart = workbookPart.WorksheetParts.First();
OpenXmlReader reader = OpenXmlReader.Create(worksheetPart);
//row counter
int rcnt = 0;
while (reader.Read())
{
//find xml row element type
//to understand the element type you can change your excel file eg : test.xlsx to test.zip
//and inside that you may observe the elements in xl/worksheets/sheet.xml
//that helps to understand openxml better
if (reader.ElementType == typeof(Row))
{
//create data table row type to be populated by cells of this row
DataRow tempRow = dt.NewRow();
//***** HANDLE THE SECOND SENARIO*****
//if row has attribute means it is not a empty row
if (reader.HasAttributes)
{
//read the child of row element which is cells
//here first element
reader.ReadFirstChild();
do
{
//find xml cell element type
if (reader.ElementType == typeof(Cell))
{
Cell c = (Cell)reader.LoadCurrentElement();
string cellValue;
int actualCellIndex = CellReferenceToIndex(c);
if (c.DataType != null && c.DataType == CellValues.SharedString)
{
SharedStringItem ssi = workbookPart.SharedStringTablePart.SharedStringTable.Elements<SharedStringItem>().ElementAt(int.Parse(c.CellValue.InnerText));
cellValue = ssi.Text.Text;
}
else
{
cellValue = c.CellValue.InnerText;
}
//if row index is 0 its header so columns headers are added & also can do some headers check incase
if (rcnt == 0)
{
dt.Columns.Add(cellValue);
}
else
{
// instead of tempRow[c.CellReference] = cellValue;
tempRow[actualCellIndex] = cellValue;
}
}
}
while (reader.ReadNextSibling());
//if its not the header row so append rowdata to the datatable
if (rcnt != 0)
{
dt.Rows.Add(tempRow);
}
rcnt++;
}
}
}
}
Everything is explained in the accepted answer.
Here is just an extension method to solve the problem
public static string GetCellText(this Cell cell, in SharedStringTable sst)
{
if (cell.CellValue is null)
return string.Empty;
if ((cell.DataType is not null) &&
(cell.DataType == CellValues.SharedString))
{
int ssid = int.Parse(cell.CellValue.Text);
return sst.ChildElements[ssid].InnerText;
}
return cell.CellValue.Text;
}
My sample Code is below using the NPOI.dll. I can read the EXCEL File (i.e. Excel would be stored in the system like D:/Jamal/Test.xls. Then the dll is easily reading the content, but I need to read the uploaded Excel file without storing it in any place before.The HTTPPOSTEDFILEBASE excelfile has the value for the Excel file but I need to know how to read it using NPOI dlls
public List<string> SendInvitesExcelFile1(List<String> CorrectMailIDs,
ListInvites Invites, HttpPostedFileBase excelfile)
{
List<string> mailids = new List<string>();
//string filename = (excelfile.FileName).ToString();
HSSFWorkbook hssfwb;
// using (FileStream file = new FileStream(#"D:\test.xls", FileMode.Open, FileAccess.Read))
using (FileStream file = new FileStream(excelFile.FileName, FileMode.Open, FileAccess.Read))
{
hssfwb = new HSSFWorkbook(file);
}
Sheet sheet = hssfwb.GetSheet("sheet1");
for (int row = 0; row <= sheet.LastRowNum; row++)
{
if (sheet.GetRow(row) != null) //null is when the row only contains empty cells
{
mailids.Add(sheet.GetRow(row).GetCell(0).ToString());
}
}
return mailids;
I came across the same problem and I solved it using Inpustream. I am pasting the code for your reference.
[HttpPost]
public DataTable PostValues(HttpPostedFileBase file)
{
ISheet sheet;
string filename = Path.GetFileName(Server.MapPath(file.FileName));
var fileExt = Path.GetExtension(filename);
if (fileExt == ".xls")
{
HSSFWorkbook hssfwb = new HSSFWorkbook(file.InputStream);
sheet = hssfwb.GetSheetAt(0);
}
else
{
XSSFWorkbook hssfwb = new XSSFWorkbook(file.InputStream);
sheet = hssfwb.GetSheetAt(0);
}
DataTable table = new DataTable();
IRow headerRow = sheet.GetRow(0);
int cellCount = headerRow.LastCellNum;
for (int i = headerRow.FirstCellNum; i < cellCount; i++)
{
DataColumn column = new DataColumn(headerRow.GetCell(i).StringCellValue);
table.Columns.Add(column);
}
int rowCount = sheet.LastRowNum;
for (int i = (sheet.FirstRowNum); i < sheet.LastRowNum; i++)
{
IRow row = sheet.GetRow(i);
DataRow dataRow = table.NewRow();
for (int j = row.FirstCellNum; j < cellCount; j++)
{
if (row.GetCell(j) != null)
{
dataRow[j] = row.GetCell(j).ToString();
}
}
table.Rows.Add(dataRow);
}
return table;
}
You can use a MemoryStream as well, so you should be able to get the byte array repsonse and open the spreadsheet. I'm unsure if the WorkbookFactory will detect the file type from the MemoryStream, so you may need to instruct the users to use the format that you require.
Here is how I use a MemoryStream to return a xls from a dot net core controller without ever storing it as a file.
IWorkbook wb = new HSSFWorkbook();
//Edit workbook object here
MemoryStream m = new MemoryStream();
wb.Write(m);
var byteArray = m.ToArray();
return new FileContentResult(byteArray, "application/vnd.ms-excel");
I know that there are different ways to read an Excel file:
Iterop
Oledb
Open Xml SDK
Compatibility is not a question because the program will be executed in a controlled environment.
My Requirement :
Read a file to a DataTable / CUstom Entities (I don't know how to make dynamic properties/fields to an object[column names will be variating in an Excel file])
Use DataTable/Custom Entities to perform some operations using its data.
Update DataTable with the results of the operations
Write it back to excel file.
Which would be simpler.
Also if possible advice me on custom Entities (adding properties/fields to an object dynamically)
Take a look at Linq-to-Excel. It's pretty neat.
var book = new LinqToExcel.ExcelQueryFactory(#"File.xlsx");
var query =
from row in book.Worksheet("Stock Entry")
let item = new
{
Code = row["Code"].Cast<string>(),
Supplier = row["Supplier"].Cast<string>(),
Ref = row["Ref"].Cast<string>(),
}
where item.Supplier == "Walmart"
select item;
It also allows for strongly-typed row access too.
I realize this question was asked nearly 7 years ago but it's still a top Google search result for certain keywords regarding importing excel data with C#, so I wanted to provide an alternative based on some recent tech developments.
Importing Excel data has become such a common task to my everyday duties, that I've streamlined the process and documented the method on my blog: best way to read excel file in c#.
I use NPOI because it can read/write Excel files without Microsoft Office installed and it doesn't use COM+ or any interops. That means it can work in the cloud!
But the real magic comes from pairing up with NPOI Mapper from Donny Tian because it allows me to map the Excel columns to properties in my C# classes without writing any code. It's beautiful.
Here is the basic idea:
I create a .net class that matches/maps the Excel columns I'm interested in:
class CustomExcelFormat
{
[Column("District")]
public int District { get; set; }
[Column("DM")]
public string FullName { get; set; }
[Column("Email Address")]
public string EmailAddress { get; set; }
[Column("Username")]
public string Username { get; set; }
public string FirstName
{
get
{
return Username.Split('.')[0];
}
}
public string LastName
{
get
{
return Username.Split('.')[1];
}
}
}
Notice, it allows me to map based on column name if I want to!
Then when I process the excel file all I need to do is something like this:
public void Execute(string localPath, int sheetIndex)
{
IWorkbook workbook;
using (FileStream file = new FileStream(localPath, FileMode.Open, FileAccess.Read))
{
workbook = WorkbookFactory.Create(file);
}
var importer = new Mapper(workbook);
var items = importer.Take<CustomExcelFormat>(sheetIndex);
foreach(var item in items)
{
var row = item.Value;
if (string.IsNullOrEmpty(row.EmailAddress))
continue;
UpdateUser(row);
}
DataContext.SaveChanges();
}
Now, admittedly, my code does not modify the Excel file itself. I am instead saving the data to a database using Entity Framework (that's why you see "UpdateUser" and "SaveChanges" in my example). But there is already a good discussion on SO about how to save/modify a file using NPOI.
Using OLE Query, it's quite simple (e.g. sheetName is Sheet1):
DataTable LoadWorksheetInDataTable(string fileName, string sheetName)
{
DataTable sheetData = new DataTable();
using (OleDbConnection conn = this.returnConnection(fileName))
{
conn.Open();
// retrieve the data using data adapter
OleDbDataAdapter sheetAdapter = new OleDbDataAdapter("select * from [" + sheetName + "$]", conn);
sheetAdapter.Fill(sheetData);
conn.Close();
}
return sheetData;
}
private OleDbConnection returnConnection(string fileName)
{
return new OleDbConnection("Provider=Microsoft.Jet.OLEDB.4.0;Data Source=" + fileName + "; Jet OLEDB:Engine Type=5;Extended Properties=\"Excel 8.0;\"");
}
For newer Excel versions:
return new OleDbConnection("Provider=Microsoft.ACE.OLEDB.12.0;Data Source=" + fileName + ";Extended Properties=Excel 12.0;");
You can also use Excel Data Reader an open source project on CodePlex. Its works really well to export data from Excel sheets.
The sample code given on the link specified:
FileStream stream = File.Open(filePath, FileMode.Open, FileAccess.Read);
//1. Reading from a binary Excel file ('97-2003 format; *.xls)
IExcelDataReader excelReader = ExcelReaderFactory.CreateBinaryReader(stream);
//...
//2. Reading from a OpenXml Excel file (2007 format; *.xlsx)
IExcelDataReader excelReader = ExcelReaderFactory.CreateOpenXmlReader(stream);
//...
//3. DataSet - The result of each spreadsheet will be created in the result.Tables
DataSet result = excelReader.AsDataSet();
//...
//4. DataSet - Create column names from first row
excelReader.IsFirstRowAsColumnNames = true;
DataSet result = excelReader.AsDataSet();
//5. Data Reader methods
while (excelReader.Read())
{
//excelReader.GetInt32(0);
}
//6. Free resources (IExcelDataReader is IDisposable)
excelReader.Close();
Reference: How do I import from Excel to a DataSet using Microsoft.Office.Interop.Excel?
Try to use this free way to this, https://freenetexcel.codeplex.com
Workbook workbook = new Workbook();
workbook.LoadFromFile(#"..\..\parts.xls",ExcelVersion.Version97to2003);
//Initialize worksheet
Worksheet sheet = workbook.Worksheets[0];
DataTable dataTable = sheet.ExportDataTable();
If you can restrict it to just (Open Office XML format) *.xlsx files, then probably the most popular library would be EPPLus.
Bonus is, there are no other dependencies. Just install using nuget:
Install-Package EPPlus
Try to use Aspose.cells library (not free, but trial is enough to read), it is quite good
Install-package Aspose.cells
There is sample code:
using Aspose.Cells;
using System;
namespace ExcelReader
{
class Program
{
static void Main(string[] args)
{
// Replace path for your file
readXLS(#"C:\MyExcelFile.xls"); // or "*.xlsx"
Console.ReadKey();
}
public static void readXLS(string PathToMyExcel)
{
//Open your template file.
Workbook wb = new Workbook(PathToMyExcel);
//Get the first worksheet.
Worksheet worksheet = wb.Worksheets[0];
//Get cells
Cells cells = worksheet.Cells;
// Get row and column count
int rowCount = cells.MaxDataRow;
int columnCount = cells.MaxDataColumn;
// Current cell value
string strCell = "";
Console.WriteLine(String.Format("rowCount={0}, columnCount={1}", rowCount, columnCount));
for (int row = 0; row <= rowCount; row++) // Numeration starts from 0 to MaxDataRow
{
for (int column = 0; column <= columnCount; column++) // Numeration starts from 0 to MaxDataColumn
{
strCell = "";
strCell = Convert.ToString(cells[row, column].Value);
if (String.IsNullOrEmpty(strCell))
{
continue;
}
else
{
// Do your staff here
Console.WriteLine(strCell);
}
}
}
}
}
}
Read from excel, modify and write back
/// <summary>
/// /Reads an excel file and converts it into dataset with each sheet as each table of the dataset
/// </summary>
/// <param name="filename"></param>
/// <param name="headers">If set to true the first row will be considered as headers</param>
/// <returns></returns>
public DataSet Import(string filename, bool headers = true)
{
var _xl = new Excel.Application();
var wb = _xl.Workbooks.Open(filename);
var sheets = wb.Sheets;
DataSet dataSet = null;
if (sheets != null && sheets.Count != 0)
{
dataSet = new DataSet();
foreach (var item in sheets)
{
var sheet = (Excel.Worksheet)item;
DataTable dt = null;
if (sheet != null)
{
dt = new DataTable();
var ColumnCount = ((Excel.Range)sheet.UsedRange.Rows[1, Type.Missing]).Columns.Count;
var rowCount = ((Excel.Range)sheet.UsedRange.Columns[1, Type.Missing]).Rows.Count;
for (int j = 0; j < ColumnCount; j++)
{
var cell = (Excel.Range)sheet.Cells[1, j + 1];
var column = new DataColumn(headers ? cell.Value : string.Empty);
dt.Columns.Add(column);
}
for (int i = 0; i < rowCount; i++)
{
var r = dt.NewRow();
for (int j = 0; j < ColumnCount; j++)
{
var cell = (Excel.Range)sheet.Cells[i + 1 + (headers ? 1 : 0), j + 1];
r[j] = cell.Value;
}
dt.Rows.Add(r);
}
}
dataSet.Tables.Add(dt);
}
}
_xl.Quit();
return dataSet;
}
public string Export(DataTable dt, bool headers = false)
{
var wb = _xl.Workbooks.Add();
var sheet = (Excel.Worksheet)wb.ActiveSheet;
//process columns
for (int i = 0; i < dt.Columns.Count; i++)
{
var col = dt.Columns[i];
//added columns to the top of sheet
var currentCell = (Excel.Range)sheet.Cells[1, i + 1];
currentCell.Value = col.ToString();
currentCell.Font.Bold = true;
//process rows
for (int j = 0; j < dt.Rows.Count; j++)
{
var row = dt.Rows[j];
//added rows to sheet
var cell = (Excel.Range)sheet.Cells[j + 1 + 1, i + 1];
cell.Value = row[i];
}
currentCell.EntireColumn.AutoFit();
}
var fileName="{somepath/somefile.xlsx}";
wb.SaveCopyAs(fileName);
_xl.Quit();
return fileName;
}
I used Office's NuGet Package: DocumentFormat.OpenXml and pieced together the code from that component's doc site.
With the below helper code, was similar in complexity to my other CSV file format parsing in that project...
public static async Task ImportXLSX(Stream stream, string sheetName) {
{
// This was necessary for my Blazor project, which used a BrowserFileStream object
MemoryStream ms = new MemoryStream();
await stream.CopyToAsync(ms);
using (var document = SpreadsheetDocument.Open(ms, false))
{
// Retrieve a reference to the workbook part.
WorkbookPart wbPart = document.WorkbookPart;
// Find the sheet with the supplied name, and then use that
// Sheet object to retrieve a reference to the first worksheet.
Sheet theSheet = wbPart?.Workbook.Descendants<Sheet>().Where(s => s?.Name == sheetName).FirstOrDefault();
// Throw an exception if there is no sheet.
if (theSheet == null)
{
throw new ArgumentException("sheetName");
}
WorksheetPart wsPart = (WorksheetPart)(wbPart.GetPartById(theSheet.Id));
// For shared strings, look up the value in the
// shared strings table.
var stringTable =
wbPart.GetPartsOfType<SharedStringTablePart>()
.FirstOrDefault();
// I needed to grab 4 cells from each row
// Starting at row 11, until the cell in column A is blank
int row = 11;
while (true) {
var accountNameCell = GetCell(wsPart, "A" + row.ToString());
var accountName = GetValue(accountNameCell, stringTable);
if (string.IsNullOrEmpty(accountName)) {
break;
}
var investmentNameCell = GetCell(wsPart, "B" + row.ToString());
var investmentName = GetValue(investmentNameCell, stringTable);
var symbolCell = GetCell(wsPart, "D" + row.ToString());
var symbol = GetValue(symbolCell, stringTable);
var marketValue = GetCell(wsPart, "J" + row.ToString()).InnerText;
// DO STUFF with data
row++;
}
}
}
private static string? GetValue(Cell cell, SharedStringTablePart stringTable) {
try {
return stringTable.SharedStringTable.ElementAt(int.Parse(cell.InnerText)).InnerText;
} catch (Exception) {
return null;
}
}
private static Cell GetCell(WorksheetPart wsPart, string cellReference) {
return wsPart.Worksheet.Descendants<Cell>().Where(c => c.CellReference.Value == cellReference)?.FirstOrDefault();
}
I am using NPOI to work with Excel in C#. But there is no full documentation how to work with it. I need to copy some range to another worksheet. Does anybody know, how to do this? Maybe you are using another dll(not interop) to provide such functionality. If so, please tell me.
In excel everything is very simple:
Worksheets(2).rows(2).copy newsheet.Range("A1")
Thanks for your answer!
NPOI doesn't support this out of the box but the implementation is straightforward.
Two functions are of interest here: CopyColumn() and CopyRange().
CopyRangeExample() opens a workbook, creates a new output sheet and copies cells (data and style) from one sheet to another.
void CopyRangeExample()
{
var workbook = OpenWorkbook("test.xlsx");
var destinationSheetName = "destination" + (workbook.NumberOfSheets + 1).ToString();
workbook.CreateSheet(destinationSheetName);
ISheet sourceSheet = workbook.GetSheet("source");
ISheet destinationSheet = workbook.GetSheet(destinationSheetName);
CopyColumn("I", sourceSheet, destinationSheet);
CopyRange(CellRangeAddress.ValueOf("C6:E15"), sourceSheet, destinationSheet);
SaveWorkbook(workbook, "test.xlsx");
}
And the rest of the code:
void CopyRange(CellRangeAddress range, ISheet sourceSheet, ISheet destinationSheet)
{
for (var rowNum = range.FirstRow; rowNum <= range.LastRow; rowNum++)
{
IRow sourceRow = sourceSheet.GetRow(rowNum);
if (destinationSheet.GetRow(rowNum)==null)
destinationSheet.CreateRow(rowNum);
if (sourceRow != null)
{
IRow destinationRow = destinationSheet.GetRow(rowNum);
for (var col = range.FirstColumn; col < sourceRow.LastCellNum && col<=range.LastColumn; col++)
{
destinationRow.CreateCell(col);
CopyCell(sourceRow.GetCell(col), destinationRow.GetCell(col));
}
}
}
}
void CopyColumn(string column, ISheet sourceSheet, ISheet destinationSheet)
{
int columnNum = CellReference.ConvertColStringToIndex(column);
var range = new CellRangeAddress(0, sourceSheet.LastRowNum, columnNum, columnNum);
CopyRange(range, sourceSheet, destinationSheet);
}
void CopyCell(ICell source, ICell destination)
{
if (destination != null && source != null)
{
//you can comment these out if you don't want to copy the style ...
destination.CellComment = source.CellComment;
destination.CellStyle = source.CellStyle;
destination.Hyperlink = source.Hyperlink;
switch (source.CellType)
{
case CellType.Formula:
destination.CellFormula = source.CellFormula; break;
case CellType.Numeric:
destination.SetCellValue(source.NumericCellValue); break;
case CellType.String:
destination.SetCellValue(source.StringCellValue); break;
}
}
}
IWorkbook OpenWorkbook(string path)
{
IWorkbook workbook;
using (FileStream fileStream = new FileStream(path, FileMode.Open, FileAccess.Read))
{
workbook = WorkbookFactory.Create(fileStream);
}
return workbook;
}
void SaveWorkbook(IWorkbook workbook, string path)
{
using (var fileStream = new FileStream(path, FileMode.Create, FileAccess.Write))
{
workbook.Write(fileStream);
}
}
Just remember to include NPOI and System.IO in your project:
using NPOI.SS.UserModel;
using NPOI.SS.Util;
using System.IO;