该脚本已经运行了很长时间,但突然开始摔倒了
Error: 0x0 at (SCR) GetLineageIDs, ProcessDataFlowTask error:: An item with the same key has already been added.
at System.ThrowHelper.ThrowArgumentException(ExceptionResource resource)
at System.Collections.Generic.Dictionary`2.Insert(TKey key, TValue value, Boolean add)
at ST_b90e02c5aa5e4a7a992a1a75c6255cfa.ScriptMain.ProcessDataFlowTask(TaskHost currentDataFlowTask)
目标是将lineageID映射到我的SSIS包中的实际列名称(2012年,因此没有2016年的沿袭功能).
我知道我正在尝试添加一个已经添加到我的字典中的密钥,在下面的脚本中,我不确定它是如何以及为什么它突然开始出错,下面是完整的脚本.我想在我的ProcessDataFlowTask方法中需要某种if块,任何指针都会被感激地接收,并解释为什么重复键错误会突然出现？
namespace ST_b90e02c5aa5e4a7a992a1a75c6255cfa
{
/// <summary>
/// ScriptMain is the entry point class of the script. Do not change the name, attributes,
/// or parent of this class.
/// </summary>
[Microsoft.SqlServer.Dts.Tasks.ScriptTask.SSISScriptTaskEntryPointAttribute]
public partial class ScriptMain : Microsoft.SqlServer.Dts.Tasks.ScriptTask.VSTARTScriptObjectModelBase
{
Dictionary<int, string> lineageId = null;
public void Main()
{
try
{
// Grab the executables so we have to something to iterate over, and initialize our lineageIDs list
// Why the executables? Well, SSIS won't let us store a reference to the Package itself...
Dts.Variables["User::execsObj"].Value = ((Package)Dts.Variables["User::execsObj"].Parent).Executables;
Dts.Variables["User::lineageIds"].Value = new Dictionary<int, string>();
lineageId = (Dictionary<int, string>)Dts.Variables["User::lineageIds"].Value;
Executables execs = (Executables)Dts.Variables["User::execsObj"].Value;
ReadExecutables(execs);
Dts.TaskResult = (int)ScriptResults.Success;
}
catch (Exception ex)
{
//An error occurred.
Dts.Events.FireError(0, "SSIS variable read error:", ex.Message + "\r" + ex.StackTrace, String.Empty, 0);
Dts.TaskResult = (int)ScriptResults.Failure;
}
}
private void ReadExecutables(Executables executables)
{
try
{
foreach (Executable pkgExecutable in executables)
{
if (object.ReferenceEquals(pkgExecutable.GetType(), typeof(Microsoft.SqlServer.Dts.Runtime.TaskHost)))
{
TaskHost pkgExecTaskHost = (TaskHost)pkgExecutable;
if (pkgExecTaskHost.CreationName.StartsWith("SSIS.Pipeline"))
{
ProcessDataFlowTask(pkgExecTaskHost);
}
}
else if (object.ReferenceEquals(pkgExecutable.GetType(), typeof(Microsoft.SqlServer.Dts.Runtime.ForEachLoop)))
{
// Recurse into FELCs
ReadExecutables(((ForEachLoop)pkgExecutable).Executables);
}
}
}
catch (Exception ex)
{
//An error occurred.
Dts.Events.FireError(0, "ReadExecutables error:", ex.Message + "\r" + ex.StackTrace, String.Empty, 0);
Dts.TaskResult = (int)ScriptResults.Failure;
}
}
private void ProcessDataFlowTask(TaskHost currentDataFlowTask)
{
try
{
MainPipe currentDataFlow = (MainPipe)currentDataFlowTask.InnerObject;
foreach (IDTSComponentMetaData100 currentComponent in currentDataFlow.ComponentMetaDataCollection)
{
// Get the inputs in the component.
foreach (IDTSInput100 currentInput in currentComponent.InputCollection)
foreach (IDTSInputColumn100 currentInputColumn in currentInput.InputColumnCollection)
lineageId.Add(currentInputColumn.ID, currentInputColumn.Name);
// Get the outputs in the component.
foreach (IDTSOutput100 currentOutput in currentComponent.OutputCollection)
foreach (IDTSOutputColumn100 currentoutputColumn in currentOutput.OutputColumnCollection)
lineageId.Add(currentoutputColumn.ID, currentoutputColumn.Name);
}
}
catch (Exception ex)
{
//An error occurred.
Dts.Events.FireError(0, "ProcessDataFlowTask error:", ex.Message + "\r" + ex.StackTrace, String.Empty, 0);
Dts.TaskResult = (int)ScriptResults.Failure;
}
}
#region ScriptResults declaration
/// <summary>
/// This enum provides a convenient shorthand within the scope of this class for setting the
/// result of the script.
///
/// This code was generated automatically.
/// </summary>
enum ScriptResults
{
Success = Microsoft.SqlServer.Dts.Runtime.DTSExecResult.Success,
Failure = Microsoft.SqlServer.Dts.Runtime.DTSExecResult.Failure
};
#endregion
}
}
最佳答案 如果包中的任何数据流中有重复的列名,则会出现“重复键”错误.之前我遇到过这个问题,我通过添加以下两个步骤解决了这个问题.
步骤1
在lineageId.Add(…)的两个实例上对ProcessDataFlowTask方法进行以下更改
Remember to use currentOutputColumn.Name instead of currentInputColumn.Name at the second instance
改变
lineageId.Add(currentInputColumn.ID, currentInputColumn.Name);
至
strNewID = currentDataFlowTask.Name + "_" + currentInputColumn.ID.ToString();
lineageIDs.Add(strNewID, currentInputColumn.Name);
Basically giving a unique name for the Column Name by adding the Data Flow Name plus the ‘_’ (Underscore) as a prefix.
第2步
由于我们在添加到LineageIDs集合时修改了列名称,因此在比较另一个脚本任务中的Input0_ProcessInputRow方法中的列名时,我们需要使用修改后的列名称(即前缀数据流名称加上’_'(下划线)),这是必需的,你没有复制上面.
string newColNum = "DataFlowTaskName_" + Row.ErrorColumn.Value.ToString();
if (lineageIDs.ContainsKey(newColNum))
Row.ErrorColumnName = lineageIDs[newColNum];
注意：在上面的代码中,DataFlowTaskName_是硬编码值,需要替换为存在第二个脚本任务的数据流任务名称,因为它在Input0_ProcessInputRow方法中不可用,我们需要对其进行硬编码.
这只是一种方法,可能你可以找到另一种处理重复的方法,这就是我做的和它的工作方式.
希望这可以帮助.
