I need to export lots of data from database table to excel (xls/xlsx) file. It could be easily 10million rows and more.
I need open source solution which does not require Office to be installed (SpreadsheetGear and interop solutions will not work for me).
I am checking two libraries: OpenXML SDK and EPPlus.
For OpenXML SDK I found this method:
private static void Write(string fileName, int numRows, int numCols)
{
using (var spreadsheetDocument = SpreadsheetDocument.Open(fileName, true))
{
WorkbookPart workbookPart = spreadsheetDocument.WorkbookPart;
WorksheetPart worksheetPart = workbookPart.WorksheetParts.First();
string origninalSheetId = workbookPart.GetIdOfPart(worksheetPart);
WorksheetPart replacementPart = workbookPart.AddNewPart<WorksheetPart>();
string replacementPartId = workbookPart.GetIdOfPart(replacementPart);
using (OpenXmlReader reader = OpenXmlReader.Create(worksheetPart))
{
using (OpenXmlWriter writer = OpenXmlWriter.Create(replacementPart))
{
Row row = new Row();
Cell cell = new Cell();
//CellFormula cellFormula = new CellFormula();
//cellFormula.CalculateCell = true;
//cellFormula.Text = "RAND()";
//cell.Append(cellFormula);
CellValue cellValue = new CellValue("val val");
cell.Append(cellValue);
while (reader.Read())
{
if (reader.ElementType == typeof(SheetData))
{
if (reader.IsEndElement)
continue;
writer.WriteStartElement(new SheetData());
for (int rowNumber = 0; rowNumber < numRows; rowNumber++)
{
writer.WriteStartElement(row);
for (int col = 0; col < numCols; col++)
{
writer.WriteElement(cell);
}
writer.WriteEndElement();
}
writer.WriteEndElement();
}
else
{
if (reader.IsStartElement)
{
writer.WriteStartElement(reader);
}
else if (reader.IsEndElement)
{
writer.WriteEndElement();
}
}
}
}
}
Sheet sheet = workbookPart.Workbook.Descendants<Sheet>().First(s => s.Id.Value.Equals(origninalSheetId));
sheet.Id.Value = replacementPartId;
workbookPart.DeletePart(worksheetPart);
}
}
But it throws Out of memory
exception.
I need batch oriented
approach and to be able to append
data to the end of excel document.
Unfortunately I did not find how to append rows with OpenXML SDK
.
Also, I checked EPPlus soluion with LoadFromCollection
method.
It does support IDataReader
with LoadFromDataReader
but I dont have datareader at that point in code.
The question: is there a way to append data to existing sheet xls/xlsx file with kind of writer? Like OpenXMLWrite
r in OpenXML SDK
.
UPD. Excel clearly does not support 10 million rows. Lets stick with 1m rows and lost of columns without out of memory exception.
UPD. Added EPPlus sample. 200k rows exports in 6 minutes and takes up to 1GB of RAM.
private const string TempFile = @"C:\Users\vnechyp\Desktop\temp.xlsx";
private static void EPPlusExport()
{
var random = new Random();
var dt = new System.Data.DataTable();
for (int i = 0; i < 15; i++)
{
dt.Columns.Add($"column_{i}");
}
var values = Enumerable.Range(0, 15).Select(val => random.Next().ToString()).ToArray();
for (int i = 0; i < 10000; i++)
{
dt.Rows.Add(values);
}
using (ExcelPackage excelPackage = new ExcelPackage())
{
var workSheet = excelPackage.Workbook.Worksheets.Add("sheet");
workSheet.Cells[1, 1].LoadFromDataTable(dt, true);
excelPackage.SaveAs(new FileInfo(TempFile));
}
for (int i = 1; i < 50; i++)
{
Console.WriteLine($"Iteration: {i}");
var updateRow = i*10000;
Console.WriteLine($"Rows: {updateRow}");
FileInfo existingFile = new FileInfo(TempFile);
using (ExcelPackage excelPackage = new ExcelPackage(existingFile))
{
// get the first worksheet in the workbook
ExcelWorksheet worksheet = excelPackage.Workbook.Worksheets[1];
worksheet.Cells[updateRow, 1].LoadFromDataTable(dt, true);
excelPackage.SaveAs(new FileInfo(TempFile));
}
}
}