Redact(Stream,string,IList<PDFRedact>) Method

 
import java.io.ByteArrayInputStream; 
import java.io.File; 
import java.io.FileInputStream; 
import java.io.FileNotFoundException; 
import java.io.FileOutputStream; 
import java.io.FileReader; 
import java.io.IOException; 
import java.io.InputStream; 
import java.nio.file.Files; 
import java.nio.file.Paths; 
import java.nio.file.StandardCopyOption; 
import java.util.ArrayList; 
import java.util.Date; 
import java.util.List; 
import java.util.Scanner; 
 
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.codecs.*; 
import leadtools.pdf.*; 
 
 
public void pdfFileRedactExample() throws IOException { 
 
   final String toRedact = "LEADTOOLS"; 
 
   // Make a copy of 'leadtools.pdf' installed with LEADTOOLS 
   final String LEAD_VARS_IMAGES_DIR = "C:\\LEADTOOLS23\\Resources\\Images"; 
   String pdfFileName = combine(LEAD_VARS_IMAGES_DIR, "leadtools-redacted.pdf"); 
   Files.copy(Paths.get(combine(LEAD_VARS_IMAGES_DIR, "leadtools.pdf")), Paths.get(pdfFileName), 
         StandardCopyOption.REPLACE_EXISTING); 
 
   // We will use PDFDocument to find the position of the words to redact 
 
   // Find any text containing the word "LEADTOOLS" in the document 
   ArrayList<MyPDFWord> allWords = new ArrayList<MyPDFWord>(); 
   PDFDocument pdfDocument = new PDFDocument(pdfFileName); 
   pdfDocument.parsePages(PDFParsePagesOptions.OBJECTS.getValue(), 1, -1); 
 
   // Build the words for each page from PDFDocumentPage.Objects 
   for (PDFDocumentPage pdfPage : pdfDocument.getPages()) { 
      ArrayList<MyPDFWord> words = GetPageWords(pdfPage); 
      allWords.addAll(words); 
   } 
   pdfDocument = null; 
 
   // Now create a PDFRedact object for each word that contains the value we want 
   // to redact 
   String toRedactLower = toRedact.toLowerCase(); 
   ArrayList<PDFRedact> pdfRedacts = new ArrayList<PDFRedact>(); 
   for (MyPDFWord word : allWords) { 
      if (word.Value.toLowerCase().contains(toRedactLower)) { 
         System.out.println("Found " + word.Value + " at " + word.Bounds + " in page " + word.PageNumber); 
         PDFRedact pdfRedact = new PDFRedact(); 
         pdfRedact.setPageNumber(word.PageNumber); 
         pdfRedact.setBounds(new PDFRect(word.Bounds.getLeft(), word.Bounds.getTop(), word.Bounds.getRight(), 
               word.Bounds.getBottom())); 
         pdfRedacts.add(pdfRedact); 
      } 
   } 
 
   // Redact the document 
   PDFFile.redact(pdfFileName, null, pdfRedacts); 
 
   // Finally, verify that the redact PDF does not have the redacted words anymore 
   pdfDocument = new PDFDocument(pdfFileName); 
   pdfDocument.parsePages(PDFParsePagesOptions.OBJECTS.getValue(), 1, -1); 
 
   // Build the words for each page from PDFDocumentPage.Objects 
   for (PDFDocumentPage pdfPage : pdfDocument.getPages()) { 
      ArrayList<MyPDFWord> words = GetPageWords(pdfPage); 
 
      for (MyPDFWord word : words) { 
         assertTrue(!word.Value.toLowerCase().contains(toRedactLower)); 
      } 
   } 
   pdfDocument = null; 
} 
 
// Class to define a word in a PDF page 
class MyPDFWord { 
 
   // Page number 
   public int PageNumber; 
 
   // The value as a string 
   public String Value; 
 
   // Its location in the PDF coordinate 
   public LeadRectD Bounds; 
 
} 
 
private static ArrayList<MyPDFWord> GetPageWords(PDFDocumentPage pdfPage) { 
   ArrayList<MyPDFWord> words = new ArrayList<MyPDFWord>(); 
 
   List<PDFObject> objects = pdfPage.getObjects(); 
   if (objects == null || objects.size() == 0) 
      return words; 
 
   int objectIndex = 0; 
   int objectCount = objects.size(); 
 
   double pageHeight = pdfPage.getHeight(); 
 
   // Loop through all the objects 
   while (objectIndex < objectCount) { 
      // Find the total bounding rectangle, begin and end index of the next word 
      LeadRectD wordBounds = LeadRectD.getEmpty(); 
      int firstObjectIndex = objectIndex; 
 
      // Loop till we reach EndOfWord or reach the end of the objects 
      boolean more = true; 
      while (more) { 
         PDFObject pdfObject = objects.get(objectIndex); 
         // Is it text? 
         if (pdfObject.getObjectType() == PDFObjectType.TEXT) { 
            PDFRect pdfBounds = pdfObject.getBounds(); 
 
            // objectBounds are in bottom-left coordinate, convert it to top-left 
            LeadRectD objectBounds = LeadRectD.fromLTRB(pdfObject.getBounds().getLeft(), 
                  pageHeight - pdfObject.getBounds().getTop(), pdfObject.getBounds().getRight(), 
                  pageHeight - pdfObject.getBounds().getBottom()); 
 
            // Add the bounding rectangle of this object 
            if (wordBounds.isEmpty()) 
               wordBounds = objectBounds; 
            else 
               wordBounds = LeadRectD.unionRects(wordBounds, objectBounds); 
         } else { 
            firstObjectIndex = objectIndex + 1; 
         } 
 
         objectIndex++; 
         more = (objectIndex < objectCount) && !pdfObject.getTextProperties().isEndOfWord() 
               && !pdfObject.getTextProperties().isEndOfLine(); 
      } 
 
      if (firstObjectIndex == objectIndex) { 
         continue; 
      } 
 
      // From the begin and end index, collect the characters into a string 
      StringBuilder sb = new StringBuilder(); 
      for (int i = firstObjectIndex; i < objectIndex; i++) { 
         if (objects.get(i).getObjectType() == PDFObjectType.TEXT) 
            sb.append(objects.get(i).getCode()); 
      } 
 
      PDFFilesExamples ex = new PDFFilesExamples(); 
      MyPDFWord word = ex.new MyPDFWord(); 
      word.PageNumber = pdfPage.getPageNumber(); 
      word.Value = sb.toString(); 
      word.Bounds = wordBounds; 
      words.add(word); 
   } 
   return words; 
}