OcrAutoRecognizeJobData Structure

 
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(); 
}