Musings of a West Texas Business Venture

PDF Graphic Conversion

As promised, here is some Java code which can pull a graphic out of a PDF, convert it to an array of bytes. You can then do whatever you like with it. Code is not final, but getting close.

 // Returns the contents of the file in a byte array.
 public static byte[] getBytesFromFile (File file) throws IOException {
  InputStream is = new FileInputStream (file);
  
  // Get the size of the file
  long length = file.length ();
  
  // Before converting to an int type, check
  // to ensure that file is not larger than Integer.MAX_VALUE.
  if (length > Integer.MAX_VALUE) {
   // File is too large
   return null;
  }
  
  // Create the byte array to hold the data
  byte[] bytes = new byte[(int)length];
  
  // Read in the bytes
  int offset = 0;
  int numRead = 0;
  while (offset < bytes.length && (numRead=is.read (bytes, offset, bytes.length-offset)) >= 0) {
   offset += numRead;
  }
  
  // Ensure all the bytes have been read in
  if (offset < bytes.length) {
   throw new IOException ("Could not completely read file "+file.getName ());
  }
  
  // Close the input stream and return bytes
  is.close ();
  return bytes;
 }
 
 /*
  * This method opens a byteArrayInputStream (and assumes it's a PDF)
  * Once open, the file is read in, and all of the images are located on the page (by the pageNumber).
  * The image specified (by the imageNumber) is returned.
  *
  * In this case, pageNumber and imageNumber are both "1" based
  *
  */ 
 private byte[] fetchImageFromPDF (ByteArrayInputStream inp, int pageNumber, int imageNumber) throws Exception {
  try {
   if (inp == null)
    return null;
   
   PDDocument document = PDDocument.load (inp);
   
   List pages = document.getDocumentCatalog ().getAllPages ();
   PDPage page = (PDPage) pages.get (pageNumber-1);
   PDResources resources = page.getResources ();
   Map images = resources.getImages ();
   ByteArrayOutputStream baOut = new ByteArrayOutputStream ();
   if (images != null) {
    Iterator imageIter = images.keySet ().iterator ();
    int i = 1;
    while (imageIter.hasNext ()) {
     if (i == imageNumber) {
      String key = (String) imageIter.next ();
      PDXObjectImage image = (PDXObjectImage)images.get ( key );
      image.write2OutputStream (baOut);
      // String name = "/tmp/out12";
      // System.out.println ( "Writing image:" + name + "." + image.getSuffix ());
      // image.write2file ( name );
      return baOut.toByteArray ();
     }
     i++;
    }
   }
  } catch (Exception e) {
   throw new Exception ("Exception fetching image from byteArray PDF: " + e.getMessage ());
  }
  
  return null;
 }
 
 /*
  *
  * This method is really a wrapper for the same method using a byteArray, using a File object.
  * This method calls the getBytesFromFile(); method
  *
  */ 
 private byte[] fetchImageFromPDF (File f, int pageNumber, int imageNumber) throws Exception {
  try {
   if (f == null)
    return null;
   
   byte[] bytes = getBytesFromFile (f);
   ByteArrayInputStream inp = new ByteArrayInputStream (bytes);
  
   return this.fetchImageFromPDF (inp, pageNumber, imageNumber);
  } catch (Exception e) {
   throw new Exception ("Exception fetching image from file PDF: " + e.getMessage ());
  }
 }

posted by Anthony Presley @ 11:37 AM