Develop Reference

How to merge or concat to byte [ ] arrays of PDF's type in java but am getting pdf1 as output [duplicate]

I want to merge many PDF files into one using PDFBox and this is what I've done:
PDDocument document = new PDDocument();
for (String pdfFile: pdfFiles) {
PDDocument part = PDDocument.load(pdfFile);
List<PDPage> list = part.getDocumentCatalog().getAllPages();
for (PDPage page: list) {
document.addPage(page);
}
part.close();
}
document.save("merged.pdf");
document.close();
Where pdfFiles is an ArrayList<String> containing all the PDF files.
When I'm running the above, I'm always getting:
org.apache.pdfbox.exceptions.COSVisitorException: Bad file descriptor
Am I doing something wrong? Is there any other way of doing it?

Why not use the PDFMergerUtility of pdfbox?
PDFMergerUtility ut = new PDFMergerUtility();
ut.addSource(...);
ut.addSource(...);
ut.addSource(...);
ut.setDestinationFileName(...);
ut.mergeDocuments();

A quick Google search returned this bug: "Bad file descriptor while saving a document w. imported PDFs".
It looks like you need to keep the PDFs to be merged open, until after you have saved and closed the combined PDF.

This is a ready to use code, merging four pdf files with itext.jar from http://central.maven.org/maven2/com/itextpdf/itextpdf/5.5.0/itextpdf-5.5.0.jar, more on http://tutorialspointexamples.com/
import com.itextpdf.text.Document;
import com.itextpdf.text.pdf.PdfContentByte;
import com.itextpdf.text.pdf.PdfImportedPage;
import com.itextpdf.text.pdf.PdfReader;
import com.itextpdf.text.pdf.PdfWriter;
/**
* This class is used to merge two or more
* existing pdf file using iText jar.
*/
public class PDFMerger {
static void mergePdfFiles(List<InputStream> inputPdfList,
OutputStream outputStream) throws Exception{
//Create document and pdfReader objects.
Document document = new Document();
List<PdfReader> readers =
new ArrayList<PdfReader>();
int totalPages = 0;
//Create pdf Iterator object using inputPdfList.
Iterator<InputStream> pdfIterator =
inputPdfList.iterator();
// Create reader list for the input pdf files.
while (pdfIterator.hasNext()) {
InputStream pdf = pdfIterator.next();
PdfReader pdfReader = new PdfReader(pdf);
readers.add(pdfReader);
totalPages = totalPages + pdfReader.getNumberOfPages();
}
// Create writer for the outputStream
PdfWriter writer = PdfWriter.getInstance(document, outputStream);
//Open document.
document.open();
//Contain the pdf data.
PdfContentByte pageContentByte = writer.getDirectContent();
PdfImportedPage pdfImportedPage;
int currentPdfReaderPage = 1;
Iterator<PdfReader> iteratorPDFReader = readers.iterator();
// Iterate and process the reader list.
while (iteratorPDFReader.hasNext()) {
PdfReader pdfReader = iteratorPDFReader.next();
//Create page and add content.
while (currentPdfReaderPage <= pdfReader.getNumberOfPages()) {
document.newPage();
pdfImportedPage = writer.getImportedPage(
pdfReader,currentPdfReaderPage);
pageContentByte.addTemplate(pdfImportedPage, 0, 0);
currentPdfReaderPage++;
}
currentPdfReaderPage = 1;
}
//Close document and outputStream.
outputStream.flush();
document.close();
outputStream.close();
System.out.println("Pdf files merged successfully.");
}
public static void main(String args[]){
try {
//Prepare input pdf file list as list of input stream.
List<InputStream> inputPdfList = new ArrayList<InputStream>();
inputPdfList.add(new FileInputStream("..\\pdf\\pdf_1.pdf"));
inputPdfList.add(new FileInputStream("..\\pdf\\pdf_2.pdf"));
inputPdfList.add(new FileInputStream("..\\pdf\\pdf_3.pdf"));
inputPdfList.add(new FileInputStream("..\\pdf\\pdf_4.pdf"));
//Prepare output stream for merged pdf file.
OutputStream outputStream =
new FileOutputStream("..\\pdf\\MergeFile_1234.pdf");
//call method to merge pdf files.
mergePdfFiles(inputPdfList, outputStream);
} catch (Exception e) {
e.printStackTrace();
}
}
}

Multiple pdf merged method using org.apache.pdfbox:
public void mergePDFFiles(List<File> files,
String mergedFileName) {
try {
PDFMergerUtility pdfmerger = new PDFMergerUtility();
for (File file : files) {
PDDocument document = PDDocument.load(file);
pdfmerger.setDestinationFileName(mergedFileName);
pdfmerger.addSource(file);
pdfmerger.mergeDocuments(MemoryUsageSetting.setupTempFileOnly());
document.close();
}
} catch (IOException e) {
logger.error("Error to merge files. Error: " + e.getMessage());
}
}
From main program, call mergePDFFiles method using list of files and target file name.
String mergedFileName = "Merged.pdf";
mergePDFFiles(files, mergedFileName);
After calling mergePDFFiles, load merged file
File mergedFile = new File(mergedFileName);

package article14;
import java.io.File;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.util.PDFMergerUtility;
public class Pdf
{
public static void main(String args[])
{
new Pdf().createNew();
new Pdf().combine();
}
public void combine()
{
try
{
PDFMergerUtility mergePdf = new PDFMergerUtility();
String folder ="pdf";
File _folder = new File(folder);
File[] filesInFolder;
filesInFolder = _folder.listFiles();
for (File string : filesInFolder)
{
mergePdf.addSource(string);
}
mergePdf.setDestinationFileName("Combined.pdf");
mergePdf.mergeDocuments();
}
catch(Exception e)
{
}
}
public void createNew()
{
PDDocument document = null;
try
{
String filename="test.pdf";
document=new PDDocument();
PDPage blankPage = new PDPage();
document.addPage( blankPage );
document.save( filename );
}
catch(Exception e)
{
}
}
}

If you want to combine two files where one overlays the other (example: document A is a template and document B has the text you want to put on the template), this works:
after creating "doc", you want to write your template (templateFile) on top of that -
PDDocument watermarkDoc = PDDocument.load(getServletContext()
.getRealPath(templateFile));
Overlay overlay = new Overlay();
overlay.overlay(watermarkDoc, doc);

Using iText (existing PDF in bytes)
public static byte[] mergePDF(List<byte[]> pdfFilesAsByteArray) throws DocumentException, IOException {
ByteArrayOutputStream outStream = new ByteArrayOutputStream();
Document document = null;
PdfCopy writer = null;
for (byte[] pdfByteArray : pdfFilesAsByteArray) {
try {
PdfReader reader = new PdfReader(pdfByteArray);
int numberOfPages = reader.getNumberOfPages();
if (document == null) {
document = new Document(reader.getPageSizeWithRotation(1));
writer = new PdfCopy(document, outStream); // new
document.open();
}
PdfImportedPage page;
for (int i = 0; i < numberOfPages;) {
++i;
page = writer.getImportedPage(reader, i);
writer.addPage(page);
}
}
catch (Exception e) {
e.printStackTrace();
}
}
document.close();
outStream.close();
return outStream.toByteArray();
}

How can I append an existing PDF to a generated PDF with flying saucer for Java [duplicate]

I want to merge many PDF files into one using PDFBox and this is what I've done:
PDDocument document = new PDDocument();
for (String pdfFile: pdfFiles) {
PDDocument part = PDDocument.load(pdfFile);
List<PDPage> list = part.getDocumentCatalog().getAllPages();
for (PDPage page: list) {
document.addPage(page);
}
part.close();
}
document.save("merged.pdf");
document.close();
Where pdfFiles is an ArrayList<String> containing all the PDF files.
When I'm running the above, I'm always getting:
org.apache.pdfbox.exceptions.COSVisitorException: Bad file descriptor
Am I doing something wrong? Is there any other way of doing it?

Why not use the PDFMergerUtility of pdfbox?
PDFMergerUtility ut = new PDFMergerUtility();
ut.addSource(...);
ut.addSource(...);
ut.addSource(...);
ut.setDestinationFileName(...);
ut.mergeDocuments();

A quick Google search returned this bug: "Bad file descriptor while saving a document w. imported PDFs".
It looks like you need to keep the PDFs to be merged open, until after you have saved and closed the combined PDF.

This is a ready to use code, merging four pdf files with itext.jar from http://central.maven.org/maven2/com/itextpdf/itextpdf/5.5.0/itextpdf-5.5.0.jar, more on http://tutorialspointexamples.com/
import com.itextpdf.text.Document;
import com.itextpdf.text.pdf.PdfContentByte;
import com.itextpdf.text.pdf.PdfImportedPage;
import com.itextpdf.text.pdf.PdfReader;
import com.itextpdf.text.pdf.PdfWriter;
/**
* This class is used to merge two or more
* existing pdf file using iText jar.
*/
public class PDFMerger {
static void mergePdfFiles(List<InputStream> inputPdfList,
OutputStream outputStream) throws Exception{
//Create document and pdfReader objects.
Document document = new Document();
List<PdfReader> readers =
new ArrayList<PdfReader>();
int totalPages = 0;
//Create pdf Iterator object using inputPdfList.
Iterator<InputStream> pdfIterator =
inputPdfList.iterator();
// Create reader list for the input pdf files.
while (pdfIterator.hasNext()) {
InputStream pdf = pdfIterator.next();
PdfReader pdfReader = new PdfReader(pdf);
readers.add(pdfReader);
totalPages = totalPages + pdfReader.getNumberOfPages();
}
// Create writer for the outputStream
PdfWriter writer = PdfWriter.getInstance(document, outputStream);
//Open document.
document.open();
//Contain the pdf data.
PdfContentByte pageContentByte = writer.getDirectContent();
PdfImportedPage pdfImportedPage;
int currentPdfReaderPage = 1;
Iterator<PdfReader> iteratorPDFReader = readers.iterator();
// Iterate and process the reader list.
while (iteratorPDFReader.hasNext()) {
PdfReader pdfReader = iteratorPDFReader.next();
//Create page and add content.
while (currentPdfReaderPage <= pdfReader.getNumberOfPages()) {
document.newPage();
pdfImportedPage = writer.getImportedPage(
pdfReader,currentPdfReaderPage);
pageContentByte.addTemplate(pdfImportedPage, 0, 0);
currentPdfReaderPage++;
}
currentPdfReaderPage = 1;
}
//Close document and outputStream.
outputStream.flush();
document.close();
outputStream.close();
System.out.println("Pdf files merged successfully.");
}
public static void main(String args[]){
try {
//Prepare input pdf file list as list of input stream.
List<InputStream> inputPdfList = new ArrayList<InputStream>();
inputPdfList.add(new FileInputStream("..\\pdf\\pdf_1.pdf"));
inputPdfList.add(new FileInputStream("..\\pdf\\pdf_2.pdf"));
inputPdfList.add(new FileInputStream("..\\pdf\\pdf_3.pdf"));
inputPdfList.add(new FileInputStream("..\\pdf\\pdf_4.pdf"));
//Prepare output stream for merged pdf file.
OutputStream outputStream =
new FileOutputStream("..\\pdf\\MergeFile_1234.pdf");
//call method to merge pdf files.
mergePdfFiles(inputPdfList, outputStream);
} catch (Exception e) {
e.printStackTrace();
}
}
}

Multiple pdf merged method using org.apache.pdfbox:
public void mergePDFFiles(List<File> files,
String mergedFileName) {
try {
PDFMergerUtility pdfmerger = new PDFMergerUtility();
for (File file : files) {
PDDocument document = PDDocument.load(file);
pdfmerger.setDestinationFileName(mergedFileName);
pdfmerger.addSource(file);
pdfmerger.mergeDocuments(MemoryUsageSetting.setupTempFileOnly());
document.close();
}
} catch (IOException e) {
logger.error("Error to merge files. Error: " + e.getMessage());
}
}
From main program, call mergePDFFiles method using list of files and target file name.
String mergedFileName = "Merged.pdf";
mergePDFFiles(files, mergedFileName);
After calling mergePDFFiles, load merged file
File mergedFile = new File(mergedFileName);

package article14;
import java.io.File;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.util.PDFMergerUtility;
public class Pdf
{
public static void main(String args[])
{
new Pdf().createNew();
new Pdf().combine();
}
public void combine()
{
try
{
PDFMergerUtility mergePdf = new PDFMergerUtility();
String folder ="pdf";
File _folder = new File(folder);
File[] filesInFolder;
filesInFolder = _folder.listFiles();
for (File string : filesInFolder)
{
mergePdf.addSource(string);
}
mergePdf.setDestinationFileName("Combined.pdf");
mergePdf.mergeDocuments();
}
catch(Exception e)
{
}
}
public void createNew()
{
PDDocument document = null;
try
{
String filename="test.pdf";
document=new PDDocument();
PDPage blankPage = new PDPage();
document.addPage( blankPage );
document.save( filename );
}
catch(Exception e)
{
}
}
}

If you want to combine two files where one overlays the other (example: document A is a template and document B has the text you want to put on the template), this works:
after creating "doc", you want to write your template (templateFile) on top of that -
PDDocument watermarkDoc = PDDocument.load(getServletContext()
.getRealPath(templateFile));
Overlay overlay = new Overlay();
overlay.overlay(watermarkDoc, doc);

Using iText (existing PDF in bytes)
public static byte[] mergePDF(List<byte[]> pdfFilesAsByteArray) throws DocumentException, IOException {
ByteArrayOutputStream outStream = new ByteArrayOutputStream();
Document document = null;
PdfCopy writer = null;
for (byte[] pdfByteArray : pdfFilesAsByteArray) {
try {
PdfReader reader = new PdfReader(pdfByteArray);
int numberOfPages = reader.getNumberOfPages();
if (document == null) {
document = new Document(reader.getPageSizeWithRotation(1));
writer = new PdfCopy(document, outStream); // new
document.open();
}
PdfImportedPage page;
for (int i = 0; i < numberOfPages;) {
++i;
page = writer.getImportedPage(reader, i);
writer.addPage(page);
}
}
catch (Exception e) {
e.printStackTrace();
}
}
document.close();
outStream.close();
return outStream.toByteArray();
}

How to make pdf file password protected?

I want to make pdf file password protected. I just goolge it for the same and find a good solution given below. It's working fine But it wipe out all the data which is already there in my pdf after i secure pdf using below given code.
Used jar files for this code are:
itextpdf-5.2.1.jar
bcmail-jdk16-1.46.jar
bcprov-jdk16-1.46.jar
bctsp-jdk16-1.46.jar
Code to secure PDF :
import com.itextpdf.text.Document;
import com.itextpdf.text.DocumentException;
import com.itextpdf.text.Paragraph;
import com.itextpdf.text.pdf.PdfWriter;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
public class Secure_file {
private static String USER_PASSWORD = "password";
private static String OWNER_PASSWORD = "secured";
public static void main(String[] args) throws IOException {
Document document = new Document();
try {
PdfWriter writer = PdfWriter.getInstance(document, new FileOutputStream("E:\\sample.pdf"));
writer.setEncryption(USER_PASSWORD.getBytes(),OWNER_PASSWORD.getBytes(), PdfWriter.ALLOW_PRINTING,PdfWriter.ENCRYPTION_AES_128);
document.open();
document.add(new Paragraph("This is Password Protected PDF document."));
document.close();
writer.close();
} catch (DocumentException e) {
e.printStackTrace();
} catch (FileNotFoundException e) {
e.printStackTrace();
}
}
}
what changes i need to made in this program ?

If you look up the iText in Action keywords you'll find encryption pointing to the sample part3.chapter12.EncryptionPdf. That sample's method createPdf essentially is equivalent to your code but the method encryptPdf is what you want:
/** User password. */
public static byte[] USER = "Hello".getBytes();
/** Owner password. */
public static byte[] OWNER = "World".getBytes();
...
public void encryptPdf(String src, String dest) throws IOException, DocumentException {
PdfReader reader = new PdfReader(src);
PdfStamper stamper = new PdfStamper(reader, new FileOutputStream(dest));
stamper.setEncryption(USER, OWNER,
PdfWriter.ALLOW_PRINTING, PdfWriter.ENCRYPTION_AES_128 | PdfWriter.DO_NOT_ENCRYPT_METADATA);
stamper.close();
reader.close();
}

example using iText5. If use iText7 is very similar but using another class instead of stampler.
PdfReader reader = new PdfReader(dp.getStream());
File tempFile = File.createTempFile("someFilename", FILE_EXTENSION_PDF);
tempFile.deleteOnExit();
FileOutputStream os = new FileOutputStream(tempFile);
PdfStamper stamper = new PdfStamper(reader, os);
String pdfPassword = "1234"
String pdfAdminPassword = "5678"
stamper.setEncryption(
pdfPassword.getBytes(),
pdfAdminPassword.getBytes(),
PdfWriter.ALLOW_PRINTING,
PdfWriter.ENCRYPTION_AES_128);
reader.close();
stamper.close();
InputStream encryptedFileIs = new FileInputStream(tempFile);
or apache lib pdfbox
PDDocument document = PDDocument.load(dp.getStream());
AccessPermission ap = new AccessPermission();
StandardProtectionPolicy spp = new StandardProtectionPolicy("1234", "1234", ap);
spp.setEncryptionKeyLength(128);
spp.setPermissions(ap);
document.protect(spp);
File tempFile = File.createTempFile("someFilename", FILE_EXTENSION_PDF);
tempFile.deleteOnExit();
FileOutputStream os = new FileOutputStream(tempFile);
document.save(os);
document.close();
InputStream encryptedFileIs = new FileInputStream(tempFile);
Good luck and happy coding :)

stamper.setEncryption(USER, OWNER,PdfWriter.ALLOW_PRINTING, PdfWriter.ENCRYPTION_AES_128);
I've used this code to add password for the pdf. it will ask for the password while opening the pdf

I have used FOP refer this document
FOUserAgent userAgent = fopFactory.newFOUserAgent();
useragent.getRendererOptions().put("encryption-params", new PDFEncryptionParams(
null, "password", false, false, true, true));
Fop fop = fopFactory.newFop(MimeConstants.MIME_PDF, userAgent);

iText – HTML to PDF - Image is not displayed in PDF

I have a html page with text, image and I am parsing the HTML content to iText to generate the PDF. In the generated PDF,Included images are not getting displayed and , only the text is getting displayed.
If I pass the absolute path like D:/Deiva/CRs/HTMLPage/article-101-horz.jpg then the image will get printed. But if I try to print the image from the server like
http://localhost:8085/content/dam/article-101-h1.jpg or http://www.google.co.in/intl/en_ALL/images/logos/images_logo_lg.gif
then it is not getting printed in the PDF.
NOTE: I am using itextpdf-5.2.1.jar to generate the PDF.
My HTML Code (Article.html):
<html>
<head>
</head>
<body>
<p>Generate PDF with image using iText.</p>
<img src="http://localhost:8085/content/dam/article-10-h1.jpg"></img>
<img src="http://www.google.co.in/intl/en_ALL/images/logos/imgs_logo_lg.gif"></img>
<img class="right horz" src="D:/Deiva/CRs/HTMLPage/article-101-horz.jpg"></img>
</body>
</html>
I am using the below java code for generating the PDF:
private void createPDF (){
String path = "D:/Deiva/Test.pdf";
PdfWriter pdfWriter = null;
//create a new document
Document document = new Document();
try {
//get Instance of the PDFWriter
pdfWriter = PdfWriter.getInstance(document, new FileOutputStream(path));
//document header attributes
document.addAuthor("betterThanZero");
document.addCreationDate();
document.addProducer();
document.addCreator("MySampleCode.com");
document.addTitle("Demo for iText XMLWorker");
document.setPageSize(PageSize.LETTER);
//open document
document.open();
InputStream is = new FileInputStream("D:/Deiva/CRs/Oncology/Phase5/CR1/HTMLPage/Article.html");
// create new input stream reader
InputStreamReader isr = new InputStreamReader(is);
//get the XMLWorkerHelper Instance
XMLWorkerHelper worker = XMLWorkerHelper.getInstance();
//convert to PDF
worker.parseXHtml(pdfWriter, document, isr);
//close the document
document.close();
//close the writer
pdfWriter.close();
} catch (Exception e) {
e.printStackTrace();
}
}
Please suggest a solution to display the image in PDF.
Thanks in advance.
Deiva

I think you can do it easily using a Servlet for viewing the image. How to write a servlet for this is here
Here a sample dispatcher for you. Just edit the required places as needed
#Controller
public class ImageController extends DispatcherServlet {
private static final int DEFAULT_BUFFER_SIZE = 10240; // 10KB.
// Properties ---------------------------------------------------------------------------------
private String imagePath;
#RequestMapping(value="images/{imageId:.+}", method = RequestMethod.GET)
public #ResponseBody void getImage(#PathVariable String imageId,HttpServletRequest request, HttpServletResponse response){
String requestedImage = request.getPathInfo();
this.imagePath ="image path in server here";
if (requestedImage == null) {
// Do your thing if the image is not supplied to the request URI.
// Throw an exception, or send 404, or show default/warning image, or just ignore it.
try {
response.sendError(HttpServletResponse.SC_NOT_FOUND);
}catch(IOException ioException){
logger.error("error image path incorrect:{}", ioException);
} // 404.
return;
}
File image=null;
try {
image = new File(imagePath, URLDecoder.decode(imageId, "UTF-8"));
} catch (UnsupportedEncodingException unsupportedEncodingException) {
logger.error("error image can not decode:{}", unsupportedEncodingException);
}
// Check if file actually exists in filesystem.
if (!image.exists()) {
// Do your thing if the file appears to be non-existing.
// Throw an exception, or send 404, or show default/warning image, or just ignore it.
try {
response.sendError(HttpServletResponse.SC_NOT_FOUND);
}catch(IOException ioException){
logger.error("error image does not exists:{}", ioException);
} // 404.
return;
}
// Get content type by filename.
String contentType = "jpeg";
contentType="image/"+contentType;
// Init servlet response.
response.reset();
response.setBufferSize(DEFAULT_BUFFER_SIZE);
response.setContentType(contentType);
response.setHeader("Content-Length", String.valueOf(image.length()));
response.setHeader("Content-Disposition", "inline; filename=\"" + image.getName() + "\"");
// Prepare streams.
BufferedInputStream input = null;
BufferedOutputStream output = null;
try {
// Open streams.
try {
input = new BufferedInputStream(new FileInputStream(image), DEFAULT_BUFFER_SIZE);
} catch (FileNotFoundException e) {
logger.error("error creating file input stream to the image file :{}", e);
}
try {
output = new BufferedOutputStream(response.getOutputStream(), DEFAULT_BUFFER_SIZE);
} catch (IOException e) {
logger.error("error creating output stream to the http response :{}", e);
}
// Write file contents to response.
byte[] buffer = new byte[DEFAULT_BUFFER_SIZE];
int length;
try {
while ((length = input.read(buffer)) > 0) {
output.write(buffer, 0, length);
}
} catch (IOException e) {
logger.error("error writing the image file to outputstream :{}", e);
}
} finally {
// Gently close streams.
close(output);
close(input);
}
}
// Helpers (can be refactored to public utility class) ----------------------------------------
private void close(Closeable resource) {
if (resource != null) {
try {
resource.close();
} catch (IOException e) {
// Do your thing with the exception. Print it, log it or mail it.
logger.error("error closing resources:{}", e);
}
}
}
}

Here are some examples: https://developers.itextpdf.com/examples/xml-worker-itext5/html-images
htmlContext.setImageProvider(new AbstractImageProvider() {
public String getImageRootPath() { return "src/main/resources/html/"; }
});
If the HTML file you're parsing is stored in a directory that is different from the working directory, iText won't be able to create Image objects. We have to supply an implementation of the ImageProvider interface that tells iText what to do if an img tag is encountered. This interface has the following methods:
Image retrieve(final String src);
String getImageRootPath();
void store(String src, Image img);
void reset();
You can write your own class implementing these four methods, or you can subclass AbstractImageProvider. It is preferred to do the latter. XML Worker will use the store() method of the AbstractImageProvider class to cache all the Image objects that are encountered in a Map. These objects will be reused when the retrieve() method is called for an image with the same src. If you don't cache images, your PDF will be bloated. The same image bits and bytes will be written to the PDF more than once. The reset() method clears the cache; it is used when an ImageProvider is cloned. Finally, the getImageRootPath() method isn't implemented.
If the HTML file you're parsing is stored in a directory that is different from the working directory, iText won't be able to create Image objects. We have to supply an implementation of the ImageProvider interface that tells iText what to do if an img tag is encountered. This interface has the following methods:
You can write your own class implementing these four methods, or you can subclass AbstractImageProvider. It is preferred to do the latter. XML Worker will use the store() method of the AbstractImageProvider class to cache all the Image objects that are encountered in a Map. These objects will be reused when the retrieve() method is called for an image with the same src. If you don't cache images, your PDF will be bloated. The same image bits and bytes will be written to the PDF more than once. The reset() method clears the cache; it is used when an ImageProvider is cloned. Finally, the getImageRootPath() method isn't implemented. You have to implement it yourself, as is done in the following snippet:

to show image with Itext, you have to Changing the default configuration about Image Provider Like it :
i do it from http://demo.itextsupport.com/xmlworker/itextdoc/flatsite.html
public class HtmlToPDF1 {
public static void main(String ... args ) throws DocumentException, IOException {
FontFactory.registerDirectories();
Document document = new Document();
PdfWriter writer = PdfWriter.getInstance(document,
new FileOutputStream("src/test/ressources/mypdf.pdf"));
document.open(); HtmlPipelineContext htmlContext = new HtmlPipelineContext(null);
htmlContext.setTagFactory(Tags.getHtmlTagProcessorFactory());
htmlContext.setImageProvider(new AbstractImageProvider() {
public String getImageRootPath() {
return "/home/fallphenix/workspace/JAVA/JEE/testHTMLtoPDF/src/test/ressources/";
}
}); CSSResolver cssResolver =
XMLWorkerHelper.getInstance().getDefaultCssResolver(true);
Pipeline<?> pipeline =
new CssResolverPipeline(cssResolver,
new HtmlPipeline(htmlContext,
new PdfWriterPipeline(document, writer)));
XMLWorker worker = new XMLWorker(pipeline, true);
XMLParser p = new XMLParser(worker);
p.parse(new FileInputStream("src/test/ressources/other.html"));
document.close();
System.out.println("Done.");
}}

Try getting the image into a memory or byte stream object and then cast that image object to an itextsharp image one.
explore the overloads of iTextSharp.text.Image
EDIT:
Although the code is in C#, it might help you.
Get image from your local drive as:
Bitmap image1;
image1 = new Bitmap(#"C:\Documents and Settings\All Users\"
+ #"Documents\My Music\music.jpeg", true);
Note:: If you have the image on your application folder then we have functions to get the local file path of them in C#. Don't know about Java. Images from external site can be downloaded as
System.Net.WebClient client = new WebClient();
client.DownloadFile(imageURL, localPathname); // look into java to get local path
Now convert this byte stream to an image object as
MemoryStream imgMemoryStream = new MemoryStream(imgByteArray);
Image myImage = Drawing.Image.FromStream(imgMemoryStream);
Now acreate an iTextSharp image object from it and add it to your doucment as
iTextSharp.text.Image pic = iTextSharp.text.Image.GetInstance(myImage, System.Drawing.Imaging.ImageFormat.Jpeg);
document.Add(pic);
Hope this helps you.

I also faced to same issue..
but it was working with the image absolute path. it seems not working with remote path.
What id did here is save the image in temp location of file system and generates pdf , finally delete the image file from temp location.
<img src="/home/jboss/temp/imgs/img.png"/>

I was looking for same requirement and this is what worked for me:
HtmlPipelineContext htmlContext = new HtmlPipelineContext(null);
htmlContext.setTagFactory(Tags.getHtmlTagProcessorFactory());
htmlContext.setImageProvider(new AbstractImageProvider() {
public String getImageRootPath() {
return null;
}
#Override
public Image retrieve(String src) {
try {
Image img = com.itextpdf.text.Image.getInstance(new URL(src));
return Image.getInstance(img);
} catch (Exception e) {
e.printStackTrace();
}
return null;
}
});

How to merge two PDF files into one in Java?

I want to merge many PDF files into one using PDFBox and this is what I've done:
PDDocument document = new PDDocument();
for (String pdfFile: pdfFiles) {
PDDocument part = PDDocument.load(pdfFile);
List<PDPage> list = part.getDocumentCatalog().getAllPages();
for (PDPage page: list) {
document.addPage(page);
}
part.close();
}
document.save("merged.pdf");
document.close();
Where pdfFiles is an ArrayList<String> containing all the PDF files.
When I'm running the above, I'm always getting:
org.apache.pdfbox.exceptions.COSVisitorException: Bad file descriptor
Am I doing something wrong? Is there any other way of doing it?

Why not use the PDFMergerUtility of pdfbox?
PDFMergerUtility ut = new PDFMergerUtility();
ut.addSource(...);
ut.addSource(...);
ut.addSource(...);
ut.setDestinationFileName(...);
ut.mergeDocuments();

A quick Google search returned this bug: "Bad file descriptor while saving a document w. imported PDFs".
It looks like you need to keep the PDFs to be merged open, until after you have saved and closed the combined PDF.

This is a ready to use code, merging four pdf files with itext.jar from http://central.maven.org/maven2/com/itextpdf/itextpdf/5.5.0/itextpdf-5.5.0.jar, more on http://tutorialspointexamples.com/
import com.itextpdf.text.Document;
import com.itextpdf.text.pdf.PdfContentByte;
import com.itextpdf.text.pdf.PdfImportedPage;
import com.itextpdf.text.pdf.PdfReader;
import com.itextpdf.text.pdf.PdfWriter;
/**
* This class is used to merge two or more
* existing pdf file using iText jar.
*/
public class PDFMerger {
static void mergePdfFiles(List<InputStream> inputPdfList,
OutputStream outputStream) throws Exception{
//Create document and pdfReader objects.
Document document = new Document();
List<PdfReader> readers =
new ArrayList<PdfReader>();
int totalPages = 0;
//Create pdf Iterator object using inputPdfList.
Iterator<InputStream> pdfIterator =
inputPdfList.iterator();
// Create reader list for the input pdf files.
while (pdfIterator.hasNext()) {
InputStream pdf = pdfIterator.next();
PdfReader pdfReader = new PdfReader(pdf);
readers.add(pdfReader);
totalPages = totalPages + pdfReader.getNumberOfPages();
}
// Create writer for the outputStream
PdfWriter writer = PdfWriter.getInstance(document, outputStream);
//Open document.
document.open();
//Contain the pdf data.
PdfContentByte pageContentByte = writer.getDirectContent();
PdfImportedPage pdfImportedPage;
int currentPdfReaderPage = 1;
Iterator<PdfReader> iteratorPDFReader = readers.iterator();
// Iterate and process the reader list.
while (iteratorPDFReader.hasNext()) {
PdfReader pdfReader = iteratorPDFReader.next();
//Create page and add content.
while (currentPdfReaderPage <= pdfReader.getNumberOfPages()) {
document.newPage();
pdfImportedPage = writer.getImportedPage(
pdfReader,currentPdfReaderPage);
pageContentByte.addTemplate(pdfImportedPage, 0, 0);
currentPdfReaderPage++;
}
currentPdfReaderPage = 1;
}
//Close document and outputStream.
outputStream.flush();
document.close();
outputStream.close();
System.out.println("Pdf files merged successfully.");
}
public static void main(String args[]){
try {
//Prepare input pdf file list as list of input stream.
List<InputStream> inputPdfList = new ArrayList<InputStream>();
inputPdfList.add(new FileInputStream("..\\pdf\\pdf_1.pdf"));
inputPdfList.add(new FileInputStream("..\\pdf\\pdf_2.pdf"));
inputPdfList.add(new FileInputStream("..\\pdf\\pdf_3.pdf"));
inputPdfList.add(new FileInputStream("..\\pdf\\pdf_4.pdf"));
//Prepare output stream for merged pdf file.
OutputStream outputStream =
new FileOutputStream("..\\pdf\\MergeFile_1234.pdf");
//call method to merge pdf files.
mergePdfFiles(inputPdfList, outputStream);
} catch (Exception e) {
e.printStackTrace();
}
}
}

Multiple pdf merged method using org.apache.pdfbox:
public void mergePDFFiles(List<File> files,
String mergedFileName) {
try {
PDFMergerUtility pdfmerger = new PDFMergerUtility();
for (File file : files) {
PDDocument document = PDDocument.load(file);
pdfmerger.setDestinationFileName(mergedFileName);
pdfmerger.addSource(file);
pdfmerger.mergeDocuments(MemoryUsageSetting.setupTempFileOnly());
document.close();
}
} catch (IOException e) {
logger.error("Error to merge files. Error: " + e.getMessage());
}
}
From main program, call mergePDFFiles method using list of files and target file name.
String mergedFileName = "Merged.pdf";
mergePDFFiles(files, mergedFileName);
After calling mergePDFFiles, load merged file
File mergedFile = new File(mergedFileName);

package article14;
import java.io.File;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.util.PDFMergerUtility;
public class Pdf
{
public static void main(String args[])
{
new Pdf().createNew();
new Pdf().combine();
}
public void combine()
{
try
{
PDFMergerUtility mergePdf = new PDFMergerUtility();
String folder ="pdf";
File _folder = new File(folder);
File[] filesInFolder;
filesInFolder = _folder.listFiles();
for (File string : filesInFolder)
{
mergePdf.addSource(string);
}
mergePdf.setDestinationFileName("Combined.pdf");
mergePdf.mergeDocuments();
}
catch(Exception e)
{
}
}
public void createNew()
{
PDDocument document = null;
try
{
String filename="test.pdf";
document=new PDDocument();
PDPage blankPage = new PDPage();
document.addPage( blankPage );
document.save( filename );
}
catch(Exception e)
{
}
}
}

If you want to combine two files where one overlays the other (example: document A is a template and document B has the text you want to put on the template), this works:
after creating "doc", you want to write your template (templateFile) on top of that -
PDDocument watermarkDoc = PDDocument.load(getServletContext()
.getRealPath(templateFile));
Overlay overlay = new Overlay();
overlay.overlay(watermarkDoc, doc);

Using iText (existing PDF in bytes)
public static byte[] mergePDF(List<byte[]> pdfFilesAsByteArray) throws DocumentException, IOException {
ByteArrayOutputStream outStream = new ByteArrayOutputStream();
Document document = null;
PdfCopy writer = null;
for (byte[] pdfByteArray : pdfFilesAsByteArray) {
try {
PdfReader reader = new PdfReader(pdfByteArray);
int numberOfPages = reader.getNumberOfPages();
if (document == null) {
document = new Document(reader.getPageSizeWithRotation(1));
writer = new PdfCopy(document, outStream); // new
document.open();
}
PdfImportedPage page;
for (int i = 0; i < numberOfPages;) {
++i;
page = writer.getImportedPage(reader, i);
writer.addPage(page);
}
}
catch (Exception e) {
e.printStackTrace();
}
}
document.close();
outStream.close();
return outStream.toByteArray();
}