←Select platform

OcrAutoRecognizeManagerJobOperation Enumeration

Summary
IOcrAutoRecognizeManager job operations.
Syntax
C#
Objective-C
C++/CLI
Java
Python
public enum OcrAutoRecognizeManagerJobOperation   
typedef NS_ENUM(NSInteger, LTOcrAutoRecognizeManagerJobOperation) { 
 LTOcrAutoRecognizeManagerJobOperationOther,  
 LTOcrAutoRecognizeManagerJobOperationCreateDocument,  
 LTOcrAutoRecognizeManagerJobOperationPrepareDocument,  
 LTOcrAutoRecognizeManagerJobOperationLoadPage,  
 LTOcrAutoRecognizeManagerJobOperationPreprocessPage,  
 LTOcrAutoRecognizeManagerJobOperationZonePage,  
 LTOcrAutoRecognizeManagerJobOperationRecognizePage,  
 LTOcrAutoRecognizeManagerJobOperationSavePage,  
 LTOcrAutoRecognizeManagerJobOperationAppendLtd,  
 LTOcrAutoRecognizeManagerJobOperationSaveDocument,  
 LTOcrAutoRecognizeManagerJobOperationConvertDocument 
}; 
public enum OcrAutoRecognizeManagerJobOperation 
public enum class OcrAutoRecognizeManagerJobOperation   
class OcrAutoRecognizeManagerJobOperation(Enum): 
   Other = 0 
   CreateDocument = 1 
   PrepareDocument = 2 
   LoadPage = 3 
   PreprocessPage = 4 
   ZonePage = 5 
   RecognizePage = 6 
   SavePage = 7 
   AppendLtd = 8 
   SaveDocument = 9 
   ConvertDocument = 10 
Members
ValueMemberDescription
0Other Other operation, such as unexpected and unrecoverable errors.
1CreateDocument The IOcrAutoRecognizeManager is creating a document with IOcrDocumentManager.CreateDocument.
2PrepareDocument Preparing the IOcrDocument, in certain situations, by clearing all the pages inside it.
3LoadPage Loading the image of a page using RasterCodecs.Load. The page is then created using IOcrEngine.CreatePage.
4PreprocessPage Preprocessing a page using IOcrPage.AutoPreprocess.
5ZonePage Zoning a page using IOcrPage.AutoZone or IOcrPage.LoadZone.Note that when using the IOcrAutoRecognizeManager.JobOperation event, you can use this operation to zone the page manually as shown in the OcrAutoRecognizeJobOperationEventArgs example.
6RecognizePage Recognizing a page using IOcrPage.Recognize.
7SavePage Saving a page using IOcrDocument.Save.
8AppendLtd Appending multiple LTD's using DocumentWriter.AppendLtd.
9SaveDocument Saving a document using IOcrDocument.Save.
10ConvertDocument Converting a document to its final format using DocumentWriter.Convert.
Remarks

Used as type for the following properties:

IOcrAutoRecognizeManager allows you to modify the raster image, OCR page or OCR document during some parts of the operation. Refer to OcrAutoRecognizeJobOperationEventArgs.PageImage for more information an example.

The OcrAutoRecognizeJobOperationEventArgs.Status property can be set to OcrAutoRecognizeJobStatus.Abort inside the event handler to abort the current operation. Aborting the operation will cause the whole job to be canceled. The only exception is with LoadPage. If Status is set to Abort, then the page will be skipped and not added to the final document. The following code performs custom processing (in this example, blank page detection) to skip specific pages from being added to the final document:

// Our IOcrAutoRecognizeManager.JobOperation event handler 
EventHandler<OcrAutoRecognizeJobOperationEventArgs> jobOperation = (object sender, OcrAutoRecognizeJobOperationEventArgs e) => 
{ 
   if (e.Operation == OcrAutoRecognizeManagerJobOperation.LoadPage && !e.PostOperation) 
   { 
      // IOcrPage has been created with an image loaded, check if it is empty 
      // Get the image 
      using (RasterImage image = e.Page.GetRasterImage(OcrPageType.Original)) 
      { 
         // Run the blank bage detector command 
         var blankPageDetector = new BlankPageDetectorCommand(BlankPageDetectorCommandFlags.None, 0, 0, 0, 0); 
         blankPageDetector.Run(image); 
         if (blankPageDetector.IsBlank) 
         { 
            // The image is blank, inform the OCR auto recognize manager to skip it 
            e.Status = OcrAutoRecognizeManagerJobStatus.Abort; 
         } 
      } 
   } 
}; 
             
IOcrAutoRecognizeManager ocrAutoRecognizeManager = ocrEngine.AutoRecognizeManager; 
             
// Create the job 
var jobData = new OcrAutoRecognizeJobData(inputFile, DocumentFormat.Pdf, outputFile); 
IOcrAutoRecognizeJob ocrJob = ocrAutoRecognizeManager.CreateJob(jobData); 
             
// Add our event 
ocrAutoRecognizeManager.JobOperation += jobOperation; 
// Run the job 
ocrAutoRecognizeManager.RunJob(ocrJob); 
ocrAutoRecognizeManager.JobOperation -= jobOperation; 
Example
C#
using Leadtools; 
using Leadtools.Codecs; 
using Leadtools.Ocr; 
using Leadtools.Document.Writer; 
using Leadtools.Forms.Common; 
using Leadtools.WinForms; 
 
public class RunJobExample 
{ 
   // Number of documents that are pending 
   private int _documentsPending; 
   // Event to trigger when all documents are finished 
   private AutoResetEvent _allDocumentsFinishedEvent; 
 
      public void Start() 
   { 
      string imagesDirectory = LEAD_VARS.ImagesDir; 
      string documentsDirectory = Path.Combine(LEAD_VARS.ImagesDir, "RunJobExample"); 
 
      // Create the output (documents) directory 
      if (!Directory.Exists(documentsDirectory)) 
      { 
         Directory.CreateDirectory(documentsDirectory); 
      } 
 
      // Get all TIF files in input (images) directory 
      string[] imageFileNames = Directory.GetFiles(imagesDirectory, "*.tif"); 
      if (imageFileNames.Length == 0) 
      { 
         Console.WriteLine("No images to OCR"); 
         return; 
      } 
 
      // Create a new OCR engine instance 
      OcrEngineType engineType = OcrEngineType.LEAD; 
      Console.WriteLine(string.Format("Starting up {0} engine", engineType)); 
      using (IOcrEngine ocrEngine = OcrEngineManager.CreateEngine(engineType)) 
      { 
         ocrEngine.Startup(null, null, null, LEAD_VARS.OcrLEADRuntimeDir); 
 
         // Setup document PDF save options: Image/Text with CCITT G4 encoding for B/W 
         DocumentWriter docWriter = ocrEngine.DocumentWriterInstance; 
         PdfDocumentOptions pdfOptions = docWriter.GetOptions(DocumentFormat.Pdf) as PdfDocumentOptions; 
         pdfOptions.ImageOverText = true; 
         pdfOptions.DocumentType = PdfDocumentType.Pdf; 
         pdfOptions.FontEmbedMode = DocumentFontEmbedMode.None; 
         pdfOptions.OneBitImageCompression = OneBitImageCompressionType.FaxG4; 
         docWriter.SetOptions(DocumentFormat.Pdf, pdfOptions); 
 
         // We are going to use multiple-threads, so disable threading in 
         // IOcrAutoRecognizeManager 
         IOcrAutoRecognizeManager autoRecognizeManager = ocrEngine.AutoRecognizeManager; 
         autoRecognizeManager.MaximumThreadsPerJob = 1; 
 
         // Tell the recognize manager to continue on errors 
         autoRecognizeManager.JobErrorMode = OcrAutoRecognizeManagerJobErrorMode.Continue; 
 
         // Instead of using events to trigger when documents are done, 
         // we will use the JobCompleted events of IOcrAutoRecognizeManager 
         // to decrement a counter and trigger one event when the counter reaches 0 
         autoRecognizeManager.JobStarted += new EventHandler<OcrAutoRecognizeRunJobEventArgs>(autoRecognizeManager_JobStarted); 
         autoRecognizeManager.JobCompleted += new EventHandler<OcrAutoRecognizeRunJobEventArgs>(autoRecognizeManager_JobCompleted); 
 
         int count = imageFileNames.Length; 
         _documentsPending = count; 
         _allDocumentsFinishedEvent = new AutoResetEvent(false); 
 
         for (int i = 0; i < count; i++) 
         { 
            // Create the job data 
            string imageFileName = imageFileNames[i]; 
            string name = "Document " + (i + 1).ToString(); 
            Console.WriteLine("Queuing {0} file {1}", name, imageFileName); 
 
            JobData data = new JobData(); 
            data.AutoRecognizeManager = autoRecognizeManager; 
            data.ImageFileName = imageFileName; 
            data.DocumentFileName = Path.Combine(documentsDirectory, Path.GetFileNameWithoutExtension(imageFileName) + ".pdf"); 
            data.JobName = name; 
 
            // Queue this job 
            ThreadPool.QueueUserWorkItem(new WaitCallback(RunJob), data); 
         } 
 
         // Wait for all documents to finish 
         _allDocumentsFinishedEvent.WaitOne(); 
         _allDocumentsFinishedEvent.Close(); 
 
         autoRecognizeManager.JobStarted -= new EventHandler<OcrAutoRecognizeRunJobEventArgs>(autoRecognizeManager_JobStarted); 
         autoRecognizeManager.JobCompleted -= new EventHandler<OcrAutoRecognizeRunJobEventArgs>(autoRecognizeManager_JobCompleted); 
 
         Console.WriteLine("All documents finished, check the result files in {0}", documentsDirectory); 
      } 
   } 
   private void autoRecognizeManager_JobStarted(object sender, OcrAutoRecognizeRunJobEventArgs e) 
   { 
      // This is not strictly needed in this example, we will 
      // use it to show information 
      Console.WriteLine("{0} started...", e.Job.JobData.JobName); 
 
      // Check if we need to abort 
      if (AbortJobs(e.Job)) 
      { 
         // Yes, abort all jobs 
         e.Job.AutoRecognizeManager.AbortAllJobs(); 
      } 
   } 
 
   private void autoRecognizeManager_JobCompleted(object sender, OcrAutoRecognizeRunJobEventArgs e) 
   { 
      string message = string.Format("{0} completed ", e.Job.JobData.JobName); 
 
      IOcrAutoRecognizeJob job = e.Job; 
 
      // Show any errors 
      if (job.Errors.Count == 0) 
      { 
         message += "successfully..."; 
      } 
      else 
      { 
         message += "with errors, first error is " + job.Errors[0].Exception.Message; 
 
         // And save the errors to a text file in the document directory 
         string documentFileName = job.JobData.DocumentFileName; 
         string textPathName = Path.Combine(Path.GetDirectoryName(documentFileName), Path.GetFileNameWithoutExtension(documentFileName) + "_errors.txt"); 
         using (StreamWriter writer = File.CreateText(textPathName)) 
         { 
            writer.WriteLine(job.JobData.JobName); 
            writer.WriteLine("Data:"); 
            writer.WriteLine(" Image file name: " + job.JobData.ImageFileName); 
            writer.WriteLine(" First page number: " + job.JobData.FirstPageNumber); 
            writer.WriteLine(" Last page number: " + job.JobData.LastPageNumber); 
            writer.WriteLine(" Format:" + job.JobData.Format); 
            writer.WriteLine(" Document file name: " + job.JobData.DocumentFileName); 
            writer.WriteLine("Errors:"); 
 
            foreach (OcrAutoRecognizeManagerJobError error in job.Errors) 
            { 
               writer.WriteLine(" Page: {0} during {1}. Error: {2}", error.ImagePageNumber, error.Operation, error.Exception.Message); 
            } 
         } 
      } 
 
      Console.WriteLine(message); 
 
      // Decrement the documents count, when we reach 0, we are done 
      // Since this will be called from multiple threads, we need 
      // to use a thread-safety procedure 
      int pending = Interlocked.Decrement(ref _documentsPending); 
 
      // If we are the last document, wait up main thread 
      if (pending == 0) 
      { 
         _allDocumentsFinishedEvent.Set(); 
      } 
   } 
 
   private class JobData 
   { 
      public IOcrAutoRecognizeManager AutoRecognizeManager; 
      public string ImageFileName; 
      public string DocumentFileName; 
      public string JobName; 
   } 
 
   private void RunJob(object state) 
   { 
      JobData data = state as JobData; 
 
      Console.WriteLine("Running {0}", data.JobName); 
 
      // Run it 
      OcrAutoRecognizeJobData jobData = new OcrAutoRecognizeJobData(data.ImageFileName, DocumentFormat.Pdf, data.DocumentFileName); 
      jobData.JobName = data.JobName; 
      IOcrAutoRecognizeJob job = data.AutoRecognizeManager.CreateJob(jobData); 
      data.AutoRecognizeManager.RunJob(job); 
   } 
 
   private bool AbortJobs(IOcrAutoRecognizeJob ocrJob) 
   { 
      // In your application, you can check if abortion is required, for example, if the user 
      // has pressed the Cancel button on a progress bar or if your service is shutting down. 
 
      // In this example, we will never abort, but you can change this code to return true 
      // upon any condition (or when a specific job is about to start) 
      // and the engine will abort all current and pending jobs 
      return false; 
   } 
} 
 
static class LEAD_VARS 
{ 
   public const string ImagesDir = @"C:\LEADTOOLS22\Resources\Images"; 
   public const string OcrLEADRuntimeDir = @"C:\LEADTOOLS22\Bin\Common\OcrLEADRuntime"; 
} 
Requirements

Target Platforms

Help Version 22.0.2023.3.31
Products | Support | Contact Us | Intellectual Property Notices
© 1991-2023 LEAD Technologies, Inc. All Rights Reserved.

Leadtools.Ocr Assembly
Products | Support | Contact Us | Intellectual Property Notices
© 1991-2023 LEAD Technologies, Inc. All Rights Reserved.