private void SaveExtractedData(DataOutputFormat dataOutputFormat, IEnumerable <IEnumerable <KeyValuePair <string, object> > > extractedDataCol)
{
ReturnMessage succesfullySaved;
DataTable extractedDataTable = null;
switch (dataOutputFormat)
{
case DataOutputFormat.XLSX:
extractedDataTable = ExtractedDataConverter.GenerateDataTable(extractedDataCol);
extractedDataTable.TableName = "ExtractedData";
var newWorkbook = new XLWorkbook();
newWorkbook.AddWorksheet(extractedDataTable);
succesfullySaved = _xlioService.SaveWorkbook(Path.Combine(ExtractionDirectory, $"{DateTime.Now.Ticks} Output.xlsx"), newWorkbook);
DisplaySuccessOrFailMessage(succesfullySaved);
break;
case DataOutputFormat.CSV:
extractedDataTable = ExtractedDataConverter.GenerateDataTable(extractedDataCol);
var generatedCSV = ExtractedDataConverter.ConvertToCSV(extractedDataTable);
succesfullySaved = _ioService.SaveText(generatedCSV, Path.Combine(ExtractionDirectory, $"{DateTime.Now.Ticks} Output.csv"));
DisplaySuccessOrFailMessage(succesfullySaved);
break;
default:
break;
}
if (extractedDataTable != null)
{
ExtractedDataTable = extractedDataTable;
}
}
private async Task <IEnumerable <ReturnMessage> > ExtractDataFromFiles(DirectoryInfo documentsDirectory, DataOutputFormat dataOutputFormat, IProgress <IEnumerable <ReturnMessage> > progress, CancellationToken cancellationToken)
{
if (documentsDirectory == null)
{
throw new ArgumentNullException("fileInfo", "Cannot be null");
}
if (cancellationToken == null)
{
throw new ArgumentNullException("cancellationToken", "Cannot be null");
}
var validExtensions = new string[] { ".xlsx", ".xlsm" };
var extractedDataCol = new BlockingCollection <IEnumerable <KeyValuePair <string, object> > >();
var returnMessages = new BlockingCollection <ReturnMessage>();
await Task.Run(() =>
{
//filter files to valid extensions, and ignore temporary Excel files if excel file is open.
var documents = documentsDirectory.GetFiles().Where(x => validExtensions.Contains(Path.GetExtension(x.FullName).ToLower()) && !x.Name.StartsWith(@"~$"));
TotalExtractionCount = documents.Count();
Parallel.ForEach(documents, (document) =>
{
try
{
if (!cancellationToken.IsCancellationRequested)
{
var extractionRequests = DataRetrievalRequestCollectionToExtractionRequestCollection(DataRetrievalRequests);
var dataExtractor = new DataExtractor(document.FullName);
foreach (var extraction in (dataExtractor.RetrieveDataCollectionFromAllWorksheets <object>(extractionRequests)))
{
extractedDataCol.Add(extraction);
}
returnMessages.Add(new ReturnMessage(true, $"{document.Name} successfully parsed and extracted from"));
}
}
catch (Exception e)
{
returnMessages.Add(new ReturnMessage(false, $"Failed to extract from {document.Name}.{Environment.NewLine}Error: {e.Message}"));
}
progress?.Report(returnMessages);
});
}, cancellationToken);
if (extractedDataCol != null)
{
SaveExtractedData(dataOutputFormat, extractedDataCol);
}
else
{
throw new NoDataOutputtedException($"No detected in files at {documentsDirectory.FullName}", "No Data");
}
return(returnMessages);
}
