我尝试使用脚本任务将数据导出到Excel,因为我生成的某些报告只包含太多列以继续使用模板文件。
关于使用模板最烦人的部分是:如果像列标题这样简单的内容发生变化,元数据就会变得紧张,迫使我重新创建我的DataFlow。因为我使用OLE DB源,我需要使用数据转换任务在unicode和非unicode字符集之间进行转换,然后将我的Excel目标重新映射到"复制字段x"为了使Excel文档正确创建。 这需要太长时间,我需要一种新的方法。
我在使用Excel = Microsoft.Office.Interop.Excel的脚本任务中使用以下方法:
private void ExportToExcel(DataTable dataTable, string excelFilePath = null)
{
Excel.Application excelApp = new Excel.Application();
Excel.Worksheet workSheet = null;
try
{
if (dataTable == null || dataTable.Columns.Count == 0)
throw new System.Exception("Null or empty input table!" + Environment.NewLine);
excelApp.Workbooks.Add();
workSheet = excelApp.ActiveSheet;
for (int i = 0; i < dataTable.Columns.Count; i++)
{
workSheet.Cells[1, (i + 1)] = dataTable.Columns[i].ColumnName;
}
foreach (DataTable dt in dataSet.Tables)
{
// Copy the DataTable to an object array
object[,] rawData = new object[dt.Rows.Count + 1, dt.Columns.Count];
// Copy the column names to the first row of the object array
for (int col = 0; col < dt.Columns.Count; col++)
{
rawData[0, col] = dt.Columns[col].ColumnName;
}
// Copy the values to the object array
for (int col = 0; col < dt.Columns.Count; col++)
{
for (int row = 0; row < dt.Rows.Count; row++)
{
rawData[row + 1, col] = dt.Rows[row].ItemArray[col];
}
}
// Calculate the final column letter
string finalColLetter = string.Empty;
string colCharset = "ABCDEFGHIJKLMNOPQRSTUVWXYZ";
int colCharsetLen = colCharset.Length;
if (dt.Columns.Count > colCharsetLen)
{
finalColLetter = colCharset.Substring((dt.Columns.Count - 1) / colCharsetLen - 1, 1);
}
finalColLetter += colCharset.Substring((dt.Columns.Count - 1) % colCharsetLen, 1);
workSheet.Name = dt.TableName;
// Fast data export to Excel
string excelRange = string.Format("A1:{0}{1}", finalColLetter, dt.Rows.Count + 1);
//The code crashes here (ONLY in SSIS):
workSheet.get_Range(excelRange, Type.Missing).Value2 = rawData;
// Mark the first row as BOLD
((Excel.Range)workSheet.Rows[1, Type.Missing]).Font.Bold = true;
}
List<int> lstColumnsToSum = new List<int>() { 9 };
Dictionary<int, string> dictColSumName = new Dictionary<int, string>() { { 9, "" } };
Dictionary<int, decimal> dictColumnSummation = new Dictionary<int, decimal>() { { 9, 0 } };
// rows
for (int i = 0; i < dataTable.Rows.Count; i++)
{
for (int j = 1; j <= dataTable.Columns.Count; j++)
{
workSheet.Cells[(i + 2), (j)] = dataTable.Rows[i][j - 1];
if (lstColumnsToSum.Exists(x => (x == j)))
{
decimal val = 0;
if (decimal.TryParse(dataTable.Rows[i][j - 1].ToString(), out val))
{
dictColumnSummation[j] += val;
}
}
}
}
//Footer
int footerRowIdx = 2 + dataTable.Rows.Count;
foreach (var summablecolumn in dictColSumName)
{
workSheet.Cells[footerRowIdx, summablecolumn.Key] = String.Format("{0}", dictColumnSummation[summablecolumn.Key]);
}
// check fielpath
if (excelFilePath != null && excelFilePath != "")
{
try
{
if (File.Exists(excelFilePath))
File.Delete(excelFilePath);
workSheet.Activate();
workSheet.Application.ActiveWindow.SplitRow = 1;
workSheet.Application.ActiveWindow.FreezePanes = true;
int row = 1;
int column = 1;
foreach (var item in dataTable.Columns)
{
Excel.Range range = workSheet.Cells[row, column] as Excel.Range;
range.NumberFormat = "@";
range.EntireColumn.AutoFit();
range.Interior.Color = System.Drawing.ColorTranslator.ToOle(System.Drawing.Color.LightGray);
column++;
}
Excel.Range InternalCalculatedAmount = workSheet.Cells[1, 9] as Excel.Range;
InternalCalculatedAmount.EntireColumn.NumberFormat = "#0.00";
InternalCalculatedAmount.Columns.AutoFit();
workSheet.SaveAs(excelFilePath);
}
catch (System.Exception ex)
{
throw new System.Exception("Excel file could not be saved! Check filepath." + Environment.NewLine + ex.Message);
}
}
else // no filepath is given
{
excelApp.Visible = true;
}
}
catch (System.Exception ex)
{
throw new System.Exception("ex.Message + Environment.NewLine, ex.InnerException);
}
}
在尝试执行以下代码时,抛出的异常是System.OutOfMemoryException:
workSheet.get_Range(excelRange, Type.Missing).Value2 = rawData;
我最大的挫折是这种方法在普通的C#应用程序中100%工作。
DataTable包含大约435000行。我知道它有相当多的数据,但我使用这种方法,当然是经过修改,在我的其他应用程序中的多个Excel工作表之间拆分数据,而DataSet包含大约1.1m的行。因此,我最大的DataSet中不到一半应该是一个步入式公园...
任何关于此事的光明都会令人惊叹!