PDF to TIFF in Java

Recently I came across some code to convert PDF to Tiff.  I restructured it into a nice clean utility class and provided some overloads for the main covert method.
Requires:

• pdfbox-app-1.8.3.jar
• jai_imageio-1.1.jar
• log4j-1.2.16.jar

import java.awt.image.BufferedImage;

import java.io.File;

import java.io.IOException;

import java.util.List;

import javax.imageio.IIOImage;

import javax.imageio.ImageIO;

import javax.imageio.ImageTypeSpecifier;

import javax.imageio.ImageWriteParam;

import javax.imageio.ImageWriter;

import javax.imageio.metadata.IIOInvalidTreeException;

import javax.imageio.metadata.IIOMetadata;

import javax.imageio.stream.ImageOutputStream;

import org.apache.log4j.Logger;

import org.apache.pdfbox.pdmodel.PDDocument;

import org.apache.pdfbox.pdmodel.PDPage;

import com.sun.media.imageio.plugins.tiff.BaselineTIFFTagSet;

import com.sun.media.imageio.plugins.tiff.TIFFDirectory;

import com.sun.media.imageio.plugins.tiff.TIFFField;

import com.sun.media.imageio.plugins.tiff.TIFFTag;

import com.sun.media.imageioimpl.plugins.tiff.TIFFImageWriterSpi;

public class PDFToTiff

{

   private static final Logger log = Logger.getLogger(PDFToTiff.class);

   

   public static void main(String[] args) throws IOException

   {

   

      try

      {

         //usage

         new PDFToTiff().convert("data/sample.pdf", null  , null );

         new PDFToTiff().convert("data/sample.pdf", "out/"    );

         new PDFToTiff().convert("data/sample.pdf", "out/" , "TestPrefix"   );

    

       

      }

      catch(Exception e)

      {

         // TODO Auto-generated catch block

         e.printStackTrace();

      }

   }

  

   /***

    * Converts pdfFile to Tiff images and places them in the same folder.

    * Tiff files will use same name of the input pdffile and a suffix of the page number

    * @param pdfFilePath

    * @throws Exception

    */

   public void convert(String pdfFilePath) throws Exception

   {

      convert(pdfFilePath,null,null);

   }

  

   /**

    * Converts pdfFile to Tiff images and places them in the output folder or the same folder if outFolder is null.

    * Tiff files will use same name of the input pdffile name and a suffix of the page number

    * @param pdfFilePath

    * @param outFolder

    * @throws Exception

    */

   public void convert(String pdfFilePath, String outFolder) throws Exception

   {

      convert(pdfFilePath,outFolder,null);

   }

   /***

    * Converts pdfFile to Tiff images and places them in the output folder or the same folder if outFolder is null.

    * Tiff file names will use outFilePrefix + page number or input pdffile name + page number if outFilePrefix is null

    * @param pdfFile

    * @param outFolder if null uses same location as pdfFile

    * @param outFilePrefix if null uses the name of the pdfFile

    * @throws Exception

    */

   public void convert(String pdfFilePath, String outFolder, String outFilePrefix) throws Exception

   {

      File pdfFile = new File(pdfFilePath);

      File outputFolder = outFolder==null? pdfFile.getParentFile() : new File (outFolder);

      if (!pdfFile.exists())

         throw new Exception("File {"+pdfFilePath+"} not found!");

   

      if (!outputFolder.exists())

      {

         log.debug("Creating output Folder " + outputFolder.getAbsolutePath());

         if (!outputFolder.mkdirs())

            throw new Exception("Could not created folder : " + outFolder);

      }

     

      if (outFilePrefix==null)

      {

         outFilePrefix = pdfFile.getName();

         //exclude the extension;

         if (outFilePrefix.endsWith(".pdf"))

            outFilePrefix = outFilePrefix.substring(0,outFilePrefix.lastIndexOf("."));

      }

      log.debug("Converting " + pdfFile.getName() + " to Tiff in " + outputFolder.getAbsolutePath() + " using prefix: " + outFilePrefix  );

     

      PDDocument document = null;

      int resolution = 300;

      try {

         // Set main options

         int imageType = BufferedImage.TYPE_BYTE_BINARY;

    

         int maxPage = Integer.MAX_VALUE;

     

         // Create TIFF writer

         ImageWriter writer = null;

         ImageWriteParam writerParams = null;

         try {

             TIFFImageWriterSpi tiffspi = new TIFFImageWriterSpi();

             writer = tiffspi.createWriterInstance();

             writerParams = writer.getDefaultWriteParam();

             writerParams.setCompressionMode(ImageWriteParam.MODE_EXPLICIT);

             writerParams.setCompressionType("CCITT T.6");

             writerParams.setCompressionQuality(1.0f);

         } catch (Exception ex) {

             throw new Exception("Could not load the TIFF writer", ex);

         }

     

         // Create metadata for Java IO ImageWriter

         IIOMetadata metadata = createMetadata(writer, writerParams, resolution);

     

         // Load the pdf file

         document = PDDocument.load(pdfFile);

         @SuppressWarnings("unchecked")

         List pages = (List) document.getDocumentCatalog().getAllPages();

         // Loop over the pages

         for (int i = 0; i < pages.size() && i <= maxPage; i++) {

             // Write page to image file

             File outputFile = null;

             ImageOutputStream ios = null;

             try {

                 outputFile = new File(outputFolder.getAbsolutePath()  + File.separator  +  outFilePrefix  + "_" + (i+1) + ".tiff");

                 ios = ImageIO.createImageOutputStream(outputFile);

                 writer.setOutput(ios);

                 writer.write(null, new IIOImage(pages.get(i).convertToImage(imageType, resolution), null, metadata), writerParams);

             } catch (Exception ex) {

                 throw new Exception("Could not write the TIFF file", ex);

             } finally {

                 ios.close();

             }

     

             // do something with TIF file

         }

         log.debug("Successfully converted " + pages.size() + " to Tiff.");

     } catch (Exception ex) {

         throw new Exception("Error while converting PDF to TIFF", ex);

     } finally {

         try {

             if (document != null) {

                 document.close();

             }

         } catch (Exception ex) {

             log.error("Error while closing PDF document", ex);

         }

     }

   }

  

  

   private IIOMetadata createMetadata(ImageWriter writer, ImageWriteParam writerParams, int resolution) throws IIOInvalidTreeException {

      // Get default metadata from writer

      ImageTypeSpecifier type = writerParams.getDestinationType();

      IIOMetadata meta = writer.getDefaultImageMetadata(type, writerParams);

  

      // Convert default metadata to TIFF metadata

      TIFFDirectory dir = TIFFDirectory.createFromMetadata(meta);

  

      // Get {X,Y} resolution tags

      BaselineTIFFTagSet base = BaselineTIFFTagSet.getInstance();

      TIFFTag tagXRes = base.getTag(BaselineTIFFTagSet.TAG_X_RESOLUTION);

      TIFFTag tagYRes = base.getTag(BaselineTIFFTagSet.TAG_Y_RESOLUTION);

  

      // Create {X,Y} resolution fields

      TIFFField fieldXRes = new TIFFField(tagXRes, TIFFTag.TIFF_RATIONAL, 1, new long[][] { { resolution, 1 } });

      TIFFField fieldYRes = new TIFFField(tagYRes, TIFFTag.TIFF_RATIONAL, 1, new long[][] { { resolution, 1 } });

  

      // Add {X,Y} resolution fields to TIFFDirectory

      dir.addTIFFField(fieldXRes);

      dir.addTIFFField(fieldYRes);

  

      // Return TIFF metadata so it can be picked up by the IIOImage

      return dir.getAsMetadata();

  }

  

  

}