Embedded Files in pdf using pdf box library

Date: 21-Dec-2017

JDK used for this demo: 1.7.079

Purpose:

Today we are going to see how to embed files in pdf using library called PDF BOX

pdfbox 1.8.9 library used in this article

The download link for the library is given belowl

Let us take an example.

I picked 3 files as shown below.

TEST-document.docx
TEST-Image.JPG
TEST-PDF.pdf

I am going to create new file and embed all 3 files in it.

Below code does the magic

Execute below code using any editor, i have used eclipse.

Step: 1

import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.nio.file.Files;
import java.util.GregorianCalendar;
import java.util.HashMap;

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDDocumentNameDictionary;
import org.apache.pdfbox.pdmodel.PDEmbeddedFilesNameTreeNode;
import org.apache.pdfbox.pdmodel.common.filespecification.PDComplexFileSpecification;
import org.apache.pdfbox.pdmodel.common.filespecification.PDEmbeddedFile;

public class pdfBox
{
  /**
   * Constructor.
   */
  public pdfBox()
  {
      super();
  }
  /**
   * create the second sample document from the PDF file format specification.
   *
   * @param file The file to write the PDF to.
   *
   * @throws IOException If there is an error writing the data.
   */

  public void doIt( String path, String fileName) throws IOException
  {
      // the document
      PDDocument doc = null;
      try
      {

          
       // get primary file name
          doc = PDDocument.load(new File(path+"TEST-PDF.pdf"));
          HashMap efMap = new HashMap();
          
    File file2 = new File(path);
  File[] listOfFiles = file2.listFiles();
  
  
  for (int i = 0; i < listOfFiles.length; i++) {
        if (listOfFiles[i].isFile()) {
          System.out.println("File " + listOfFiles[i].getName());
          
           //first create the file specification, which holds the embedded file
            PDComplexFileSpecification fs = new PDComplexFileSpecification();

                 File file1 = new File(path+listOfFiles[i].getName());
        FileInputStream fis = new FileInputStream(file1);
      
        fs.setFile( file1.getName() ); 
        
        
     byte fileContent[] = new byte[(int)file1.length()];
     fis.read(fileContent);
      fis.close();
     ByteArrayOutputStream bao = new ByteArrayOutputStream();
     bao.write(fileContent);
     
             byte[] data1 = bao.toByteArray();

             ByteArrayInputStream bin = new ByteArrayInputStream(data1);
             System.out.println(bin.available());

             System.out.println("Start custom - 2");

     
        
            PDEmbeddedFile ef = new PDEmbeddedFile(doc, bin );
            //now lets some of the optional parameters
//            ef.setSubtype( fileType );
            ef.setSize( data1.length );
            ef.setCreationDate( new GregorianCalendar() );
            ef.setModDate(new GregorianCalendar() );
            fs.setEmbeddedFile( ef );
            fs.setFileDescription("testing2");
            
            efMap.put("Attachments"+i, fs);
            
          
        } else if (listOfFiles[i].isDirectory()) {
          System.out.println("Directory " + listOfFiles[i].getName());
        }
      }              
          
          
  
          //embedded files are stored in a named tree
          PDEmbeddedFilesNameTreeNode efTree = new PDEmbeddedFilesNameTreeNode();
          efTree.setNames(efMap);

           
            // add the tree to the document catalog
          PDDocumentNameDictionary names = new PDDocumentNameDictionary( doc.getDocumentCatalog() );
          names.setEmbeddedFiles( efTree );
          doc.getDocumentCatalog().setNames( names );


          doc.save( path+fileName );
          doc.close();
         
      }
      
      catch (Exception  e){
   e.printStackTrace();
   System.out.println("Error");
   }
      
      finally
      {
          if( doc != null )
          {
              doc.close();
          }
      }


  }

  /**
       * This will create a hello world PDF document with an embedded file.
       * <br>
       * see usage() for commandline
       *
       * @param args Command line arguments.
       */
      public static void main(String[] args) throws IOException
      {
       pdfBox app = new pdfBox();
          
          if( args.length != 1 )
          {
//              app.usage();
 app.doIt( "c:\\temp\\article\\","Embedded-file.pdf" );
          }
          else
          {
              app.doIt( "c:\\temp\\article\\",args[0] );
          }
      }
  /**
   * This will print out a message telling how to use this example.
   */
//  private void usage()
//  {
//    System.out.println( ": " + this.getClass().getName() + " <output-file>" );
//      System.err.println( "usage: " + this.getClass().getName() + " <output-file>" );
//  }

}

If you have trouble in copying the code, i have given download link to download the code.

Step: 2

After you import the code, you will notice the error. This is because the library has not been imported. You are all set after library import.

Step: 3

After executing this is now the log looks like:

File TEST-document.docx
12394
Start custom - 2
File TEST-Image.JPG
12144
Start custom - 2
File TEST-PDF.pdf
1516
Start custom - 2

Step: 4

After i execute now i see new pdf file Embedded-file.pdf.

I have shared the download link below if you like to view how embedded-file.pdf file look like.

Step: 5

If i open the file i see other files are attached.