【发布时间】：2012-08-16 12:31:51
【问题描述】：
我有一个 Excel 文档，它有大约 250000 行，需要永远导入。我对这个导入做了很多变体，但是有一些要求： - 需要验证每个单元格中的数据 - 必须检查数据库中是否存在重复项 - 如果存在重复，则更新条目 - 如果不存在条目，则插入一个新条目
我已经尽可能多地使用并行化，但是我确信必须有某种方法可以让这个导入运行得更快。任何帮助或想法将不胜感激。
请注意，数据库位于 LAN 上，是的，我知道我还没有使用参数化的 sql 命令。
public string BulkUserInsertAndUpdate()
{
DateTime startTime = DateTime.Now;
try
{
ProcessInParallel();
Debug.WriteLine("Time taken: " + (DateTime.Now - startTime));
}
catch (Exception ex)
{
return ex.Message;
}
return "";
}
private IEnumerable<Row> ReadDocument()
{
using (SpreadsheetDocument spreadSheetDocument = SpreadsheetDocument.Open(_fileName, false))
{
WorkbookPart workbookPart = spreadSheetDocument.WorkbookPart;
Sheet ss = workbookPart.Workbook.Descendants<Sheet>().SingleOrDefault(s => s.Name == "User");
if (ss == null)
throw new Exception("There was a problem trying to import the file. Please insure that the Sheet's name is: User");
WorksheetPart worksheetPart = (WorksheetPart)workbookPart.GetPartById(ss.Id);
OpenXmlReader reader = OpenXmlReader.Create(worksheetPart);
StringTablePart = workbookPart.SharedStringTablePart;
while (reader.Read())
{
if (reader.ElementType == typeof(Row))
{
do
{
if (reader.HasAttributes)
{
var rowNum = int.Parse(reader.Attributes.First(a => a.LocalName == "r").Value);
if (rowNum == 1)
continue;
var row = (Row)reader.LoadCurrentElement();
yield return row;
}
} while (reader.ReadNextSibling()); // Skip to the next row
break; // We just looped through all the rows so no need to continue reading the worksheet
}
}
}
}
private void ProcessInParallel()
{
// Use ConcurrentQueue to enable safe enqueueing from multiple threads.
var exceptions = new ConcurrentQueue<Exception>();
Parallel.ForEach(ReadDocument(), (row, loopState) =>
{
List<Cell> cells = row.Descendants<Cell>().ToList();
if (string.IsNullOrEmpty(GetCellValue(cells[0], StringTablePart)))
return;
// validation code goes here....
try
{
using (SqlConnection connection = new SqlConnection("user id=sa;password=D3vAdm!n@;server=196.30.181.143;database=TheUnlimitedUSSD;MultipleActiveResultSets=True"))
{
connection.Open();
SqlCommand command = new SqlCommand("SELECT count(*) FROM dbo.[User] WHERE MobileNumber = '" + mobileNumber + "'", connection);
var userCount = (int) command.ExecuteScalar();
if (userCount > 0)
{
// update
command = new SqlCommand("UPDATE [user] SET NewMenu = " + (newMenuIndicator ? "1" : "0") + ", PolicyNumber = '" + policyNumber + "', Status = '" + status + "' WHERE MobileNumber = '" + mobileNumber + "'", connection);
command.ExecuteScalar();
Debug.WriteLine("Update cmd");
}
else
{
// insert
command = new SqlCommand("INSERT INTO dbo.[User] ( MobileNumber , Status , PolicyNumber , NewMenu ) VALUES ( '" + mobileNumber + "' , '" + status + "' , '" + policyNumber + "' , " + (newMenuIndicator ? "1" : "0") + " )", connection);
command.ExecuteScalar();
Debug.WriteLine("Insert cmd");
}
}
}
catch (Exception ex)
{
exceptions.Enqueue(ex);
Debug.WriteLine(ex.Message);
loopState.Break();
}
});
// Throw the exceptions here after the loop completes.
if (exceptions.Count > 0)
throw new AggregateException(exceptions);
}
【问题讨论】：
-
是否需要从 .net 读取 excel 文件？我的意思是你为什么不在 SQL server 中使用 SSIS 或 Import 功能？
-
文件是通过asp.net网站读入的。此外，托管数据库的服务器没有安装 excel，因此很难导入该文件。
标签： c# excel import parallel-processing