←Select platform

OcrAutoRecognizeManagerJobError Structure

Summary
Contains information on an IOcrAutoRecognizeManager job error.
Syntax
C#
Objective-C
C++/CLI
Java
Python
public struct OcrAutoRecognizeManagerJobError 
@interface LTOcrAutoRecognizeManagerJobError : NSObject 
public class OcrAutoRecognizeManagerJobError 
public value class OcrAutoRecognizeManagerJobError : public System.ValueType  
class OcrAutoRecognizeManagerJobError: 
Remarks

When the value of IOcrAutoRecognizeManager.JobErrorMode is OcrAutoRecognizeManagerJobErrorMode.Abort, any error that may occur while running a job will result in an exception being thrown.

If the value of this property is OcrAutoRecognizeManagerJobErrorMode.Continue, then none critical errors can be logged and running continues. For example, if a source document has a page that could not be recognized. The offending page will be added to the final document as a graphics images and recognition will continue to the next page. In this mode, the engine will not throw an exception if an error occur, instead, all errors will be logged into the job's IOcrAutoRecognizeJob.Errors collection. When recognition finishes, you can check if this collection is not empty and get the information of the errors and act upon them according to your application logic.

Each error in IOcrAutoRecognizeJob.Errors contains the following information:

Member Description
OcrAutoRecognizeManagerJobError.ImagePageNumber

The 1-based page number of the page in the source image file that caused the error. This value may be 0 if the error that occur is not specific for any page, for example, when creating an IOcrDocument or when DocumentWriter.Convert is called.

OperationOcrAutoRecognizeManagerJobError.Operation

The operation that caused the error.

ExceptionOcrAutoRecognizeManagerJobError.Exception

The exception that was thrown (if any). May be a null reference (Nothing in Visual Basic).

Example
C#
Java
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:\LEADTOOLS23\Resources\Images"; 
   public const string OcrLEADRuntimeDir = @"C:\LEADTOOLS23\Bin\Common\OcrLEADRuntime"; 
} 
 
import java.io.File; 
import java.io.FileNotFoundException; 
import java.io.FileWriter; 
import java.io.FilenameFilter; 
import java.io.IOException; 
import java.nio.file.Files; 
import java.nio.file.Path; 
import java.nio.file.Paths; 
import java.util.ArrayList; 
import java.util.concurrent.ExecutorService; 
import java.util.concurrent.Executors; 
import java.util.concurrent.atomic.AtomicInteger; 
 
import org.junit.*; 
import org.junit.runner.JUnitCore; 
import org.junit.runner.Result; 
import org.junit.runner.notification.Failure; 
 
import static org.junit.Assert.*; 
 
import leadtools.*; 
import leadtools.document.writer.*; 
import leadtools.internal.AutoResetEvent; 
import leadtools.ocr.*; 
 
 
// Number of documents that are pending 
private int _documentsPending; 
// Event to trigger when all documents are finished 
private AutoResetEvent _allDocumentsFinishedEvent; 
// Thread usage 
private final static AtomicInteger at = new AtomicInteger(); 
 
public void OcrAutoRecognizeManagerRunJobExample() throws IOException { 
   String LEAD_VARS_ImagesDir = "C:\\LEADTOOLS23\\Resources\\Images"; 
   String LEAD_VARS_OcrLEADRuntimeDir = "C:\\LEADTOOLS23\\Bin\\Common\\OcrLEADRuntime"; 
   String docsDir = combine(LEAD_VARS_ImagesDir, "RunJobExample"); 
   String imageDir = LEAD_VARS_ImagesDir; 
 
   // Create the output (documents) directory 
   Path docsPath = Paths.get(docsDir); 
   Files.createDirectories(docsPath); 
 
   // Get all TIF files in input (images) directory 
   Path imagePath = Paths.get(imageDir); 
   Files.createDirectories(imagePath); 
 
   FilenameFilter tifFileFilter = (d, s) -> { 
      return s.toLowerCase().endsWith(".tif"); 
   }; 
 
   File imageFolder = new File(imageDir); 
   String[] imageFileNames = imageFolder.list(tifFileFilter); 
   if (imageFileNames.length == 0) { 
      System.out.println("No images to OCR"); 
      return; 
   } 
 
   // Create a new OCR engine instance 
   OcrEngineType engineType = OcrEngineType.LEAD; 
   System.out.println("Starting up " + engineType + " engine"); 
   OcrEngine 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.getDocumentWriterInstance(); 
   PdfDocumentOptions pdfOptions = (PdfDocumentOptions) docWriter.getOptions(DocumentFormat.PDF); 
   pdfOptions.setImageOverText(true); 
   pdfOptions.setDocumentType(PdfDocumentType.PDF); 
   pdfOptions.setFontEmbedMode(DocumentFontEmbedMode.NONE); 
   pdfOptions.setOneBitImageCompression(OneBitImageCompressionType.FAX_G4); 
   docWriter.setOptions(DocumentFormat.PDF, pdfOptions); 
 
   // We are going to use multiple-threads, so disable threading in IOcrAutoRecognizeManager 
   OcrAutoRecognizeManager autoRecognizeManager = ocrEngine.getAutoRecognizeManager(); 
   autoRecognizeManager.setMaximumThreadsPerJob(1); 
 
   // Tell the recognize manager to continue on errors 
   autoRecognizeManager.setJobErrorMode(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.addJobStartedListener(autoRecognizeManager_JobStarted); 
   autoRecognizeManager.addJobCompletedListener(autoRecognizeManager_JobCompleted); 
   int count = imageFileNames.length; 
   _documentsPending = count; 
   at.set(_documentsPending); 
   _allDocumentsFinishedEvent = new AutoResetEvent(); 
 
   ExecutorService executorService = Executors.newFixedThreadPool(1); 
   System.out.println("Starting the threads and waiting..."); 
 
   for (int i = 0; i < count; i++) { 
      // Create the job data 
      String imageFileName = imageFileNames[i]; 
      String name = "Document " + (i + 1); 
      System.out.println("Queuing " + name + " file " + imageFileName); 
 
      JobData data = new JobData(); 
      data.AutoRecognizeManager = autoRecognizeManager; 
      data.ImageFileName = combine(LEAD_VARS_ImagesDir, imageFileName); 
      data.DocumentFileName = combine(docsDir,imageFileName.substring(0, imageFileName.indexOf(".")) + ".pdf"); 
      data.JobName = name; 
      File dataFile = new File(combine(docsDir,imageFileName.substring(0, imageFileName.indexOf(".")) + ".pdf")); 
      if (!dataFile.exists()) dataFile.createNewFile(); 
 
      Runnable runnableTask = new Runnable(){ 
 
         @Override 
         public void run(){ 
            RunJob(data); 
         } 
 
      }; 
  
      executorService.submit(runnableTask); 
   } 
 
   // Wait for all documents to finish 
   _allDocumentsFinishedEvent.waitOne(); 
   _allDocumentsFinishedEvent.close(); 
 
   System.out.println("All documents finished, check the result files in " + docsDir); 
   ocrEngine.dispose(); 
} 
 
OcrAutoRecognizeRunJobListener autoRecognizeManager_JobStarted = new OcrAutoRecognizeRunJobListener(){ 
 
   @Override public void onJob(OcrAutoRecognizeRunJobEvent e) { 
      // This is not strictly needed in this example, we will 
      // use it to show information 
      System.out.println(e.getJob().getJobData().getJobName()+" started..."); 
 
      // Check if we need to abort 
      if(AbortJobs(e.getJob())){ 
      // Yes, abort all jobs 
      e.getJob().getAutoRecognizeManager().abortAllJobs();} 
   } 
 
}; 
 
OcrAutoRecognizeRunJobListener autoRecognizeManager_JobCompleted = new OcrAutoRecognizeRunJobListener() { 
 
   @Override 
   public void onJob(OcrAutoRecognizeRunJobEvent e) { 
      OcrAutoRecognizeJob job = e.getJob(); 
      String message = job.getJobData().getJobName() + " completed "; 
 
      // Show any errors 
      if (job.getErrors().size()== 0) { 
         message += "successfully..."; 
      } 
      else { 
         message += " with errors, first error is " + job.getErrors().get(0).getException().getMessage(); 
 
         // And save the errors to a text file in the document directory 
         String documentFileName = job.getJobData().getDocumentFileName(); 
         File doc = new File(documentFileName); 
         String textPathName = combine(doc.getParent(), documentFileName.substring(0,documentFileName.indexOf(".")) + "_errors.txt"); 
 
         try (FileWriter writer = new FileWriter(textPathName)) { 
            writer.write(job.getJobData().getJobName()); 
            writer.write("Data:"+"\n"); 
            writer.write(" Image file name: " + job.getJobData().getImageFileName()+"\n"); 
            writer.write(" First page number: " + job.getJobData().getFirstPageNumber()+"\n"); 
            writer.write(" Last page number: " + job.getJobData().getLastPageNumber()+"\n"); 
            writer.write(" Format:" + job.getJobData().getFormat()+"\n"); 
            writer.write(" Document file name: " + job.getJobData().getDocumentFileName()+"\n"); 
            writer.write("Errors:"+"\n"); 
                
            for (OcrAutoRecognizeManagerJobError error : job.getErrors()) 
            { 
               writer.write(" Page: "+ error.getImagePageNumber() + " during " + error.getOperation() + ". Error: " + error.getException().getMessage() + "\n"); 
            } 
            writer.close(); 
         } catch (IOException e1) { 
            e1.printStackTrace(); 
         } 
      } 
 
      System.out.println(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 = at.decrementAndGet(); 
      System.out.println(pending); 
          
      // If we are the last document, wait up main thread 
      if (pending == 0) 
         _allDocumentsFinishedEvent.set(); 
   } 
 
}; 
 
class JobData { 
   public OcrAutoRecognizeManager AutoRecognizeManager; 
   public String ImageFileName; 
   public String DocumentFileName; 
   public String JobName; 
} 
 
private void RunJob(JobData state) { 
   JobData data = state; 
   System.out.println("Running " + data.JobName); 
 
   // Run it 
   OcrAutoRecognizeJobData jobData = new OcrAutoRecognizeJobData( 
      data.ImageFileName,  
      DocumentFormat.PDF, 
      data.DocumentFileName 
   ); 
   jobData.setJobName(data.JobName); 
   OcrAutoRecognizeJob job = data.AutoRecognizeManager.createJob(jobData); 
   data.AutoRecognizeManager.runJob(job); 
} 
 
private boolean AbortJobs(OcrAutoRecognizeJob 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; 
} 
 
public String combine(String path1, String path2) { 
   File file = new File(path1, path2); 
   return file.getPath(); 
} 
Requirements

Target Platforms

Help Version 23.0.2024.4.19
Products | Support | Contact Us | Intellectual Property Notices
© 1991-2024 LEAD Technologies, Inc. All Rights Reserved.

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