public DocumentProcessingService(IDocumentContentExtractor documentContentExtractor,
IFormRecognizerService formRecognizerService,
IDataService <InvoiceData> dataService,
ILogger <DocumentProcessingService> log)
{
_documentContentExtractor = documentContentExtractor;
_formRecognizerService = formRecognizerService;
_dataService = dataService;
_log = log;
}
private async Task <Response> ParseFileImages(string fileName, string folderName)
{
string logMsg = "ControllerName: GroupDocsParserController FileName: " + fileName + " FolderName: " + folderName;
try
{
return(await ProcessTask(fileName, folderName, ".jpg", true, "", delegate(string inFilePath, string outPath, string zipOutFolder)
{
if (!Directory.Exists(zipOutFolder))
{
Directory.CreateDirectory(zipOutFolder);
}
string fileExt = Path.GetExtension(fileName).Substring(1).ToLower();
IDocumentContentExtractor extractor = GetContentExtractor(inFilePath, fileExt);
if (extractor == null)
{
throw new Exception("Unsupported file type for image extraction");
}
ImageAreaSearchOptions searchOptions = new ImageAreaSearchOptions();
searchOptions.Rectangle = new Rectangle(0, 0, 1920, 1080);
int pageCount = extractor.DocumentContent.PageCount;
for (int pageIndex = 0; pageIndex < pageCount; pageIndex++)
{
IList <ImageArea> imageAreas = extractor.DocumentContent.GetImageAreas(pageIndex, searchOptions);
if (pageIndex == 0 && imageAreas.Count == 0)
{
throw new Exception("No images found for extraction");
}
for (int i = 0; i < imageAreas.Count; i++)
{
using (Stream fs = System.IO.File.Create(String.Format(zipOutFolder + "/{0}-{1}.jpg", pageIndex + 1, i + 1)))
{
CopyStream(imageAreas[i].GetRawStream(), fs);
}
}
}
}));
}
catch (Exception exc)
{
return(new Response {
FileName = fileName, FolderName = folderName, OutputType = "zip", Status = exc.Message, StatusCode = 500, Text = exc.ToString()
});
}
}
private IDocumentContentExtractor GetContentExtractor(string inFilePath, string fileExt)
{
IDocumentContentExtractor extractor = null;
if (Array.Exists(WordTypesForImage, E => E == fileExt))
{
extractor = new WordsTextExtractor(inFilePath);
}
else if (Array.Exists(ExcelTypesForImage, E => E == fileExt))
{
extractor = new CellsTextExtractor(inFilePath);
}
else if (Array.Exists(SlidesTypesForImage, E => E == fileExt))
{
extractor = new SlidesTextExtractor(inFilePath);
}
else if (Array.Exists(PdfTypesForImage, E => E == fileExt))
{
extractor = new PdfTextExtractor(inFilePath);
}
return(extractor);
}
