DocumentCharacter Structure

 
import java.io.File; 
import java.io.FileOutputStream; 
import java.io.IOException; 
import java.net.MalformedURLException; 
import java.net.URI; 
import java.net.URISyntaxException; 
import java.net.URL; 
import java.nio.file.Files; 
import java.nio.file.Paths; 
import java.util.ArrayList; 
import java.util.Calendar; 
import java.util.List; 
import java.util.concurrent.Callable; 
import java.util.concurrent.ExecutorService; 
import java.util.concurrent.Executors; 
import java.util.concurrent.Future; 
import java.util.regex.Pattern; 
 
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.annotations.engine.*; 
import leadtools.barcode.*; 
import leadtools.caching.*; 
import leadtools.codecs.*; 
import leadtools.document.*; 
import leadtools.document.DocumentMimeTypes.UserGetDocumentStatusHandler; 
import leadtools.document.converter.*; 
import leadtools.document.writer.*; 
import leadtools.ocr.*; 
 
 
public void storeOcrPageCharactersExample() { 
   // Initialize an OCR engine 
   OcrEngine ocrEngine = OcrEngineManager.createEngine(OcrEngineType.LEAD); 
   // Start the engine using default parameters 
   ocrEngine.startup(null, null, null, "C:\\LEADTOOLS23\\Bin\\Common\\OcrLEADRuntime"); 
 
   // Load a document that we know will be OCRed 
   String documentFile = "C:\\LEADTOOLS23\\Resources\\Images\\ocr1.tif"; 
   LEADDocument document = DocumentFactory.loadFromFile(documentFile, new LoadDocumentOptions()); 
 
   // Set the OCR engine 
   document.getText().setOcrEngine(ocrEngine); 
   // First, do not store IOcrPageCharacters in DocumentPageText, this will 
   // cause our code to extract the character OCR confidences value to not work 
   document.getText().setStoreOcrPageCharacters(false); 
   System.out 
         .println("Obtaining OCR characters confidence with StoreOcrPageCharacters equals to false. Should fail"); 
 
   // Now get the text 
   DocumentPage documentPage = document.getPages().get(0); 
   DocumentPageText documentPageText = documentPage.getText(); 
   // Build the words 
   documentPageText.buildWords(); 
   showOcrConfidence(documentPageText); 
 
   System.out.println("Obtaining OCR characters confidence with StoreOcrPageCharacters equals to true. Should work"); 
   document.getText().setStoreOcrPageCharacters(true); 
   documentPageText = documentPage.getText(); 
   // Build the words 
   documentPageText.buildWords(); 
   showOcrConfidence(documentPageText); 
 
   ocrEngine.dispose(); 
} 
 
private void showOcrConfidence(DocumentPageText documentPageText) { 
 
   System.out.println("Showing OCR confidence value of the characters of the first word"); 
   if (documentPageText.getWords() == null) { 
      System.out.println("Nothing to show"); 
      return; 
   } 
 
   // Show the OCR character confidence for the first word 
   // Get the first word 
   DocumentWord word = documentPageText.getWords().get(0); 
   System.out.println("first word value:" + word.getValue()); 
   // Get its characters 
   for (int characterIndex = word.getFirstCharacterIndex(); characterIndex <= word 
         .getLastCharacterIndex(); characterIndex++) { 
      // DocumentCharacter reference 
      DocumentCharacter documentCharacter = documentPageText.getCharacters().get(characterIndex); 
      System.out.println(" character at index " + characterIndex + " is " + documentCharacter.getCode() 
            + " its isFromOcr value is " + documentCharacter.isFromOcr() + " and its bounds are " 
            + documentCharacter.getBounds()); 
      System.out.println("Is end of line: " + documentCharacter.isEndOfLine()); 
      System.out.println("Is end of word: " + documentCharacter.isEndOfWord()); 
      System.out.println("Is right to left: " + documentCharacter.isRightToLeft()); 
      // Ensure this is a character obtained from OCR 
      if (documentCharacter.isFromOcr()) { 
         // See if we stored the IOcrPageCharacters in 
         if (documentPageText.getOcrPageCharacters() != null) { 
            // We have it, get the corresponding OcrCharcater 
            // Get the zone characters 
            OcrZoneCharacters ocrZoneCharacters = documentPageText.getOcrPageCharacters() 
                  .get(documentCharacter.getOcrZoneIndex()); 
            // And the character in this zone 
            OcrCharacter ocrCharacter = ocrZoneCharacters.get(documentCharacter.getOcrCharacterIndex()); 
            int confidence = ocrCharacter.getConfidence(); 
            System.out.println( 
                  "   OCR character code is " + ocrCharacter.getCode() + " and confidence is " + confidence); 
            // Sanity check 
            assertTrue(ocrCharacter.getCode() == documentCharacter.getCode()); 
         } else { 
            System.out.println("   Failed to get OCR confidence"); 
         } 
      } 
   } 
}