Develop Reference

Annotations not copying when combining 2 Pdfs [duplicate]

I have the following problem when printing the pdf file after merge, the pdf documents get cut off.
Sometimes this happens because the documents aren't 8.5 x 11
they might be like 11 x 17.
Can we make it detect the page size and then use that same page size for those documents?
Or, if not, is it possible to have it fit to page?
Following is the code:
package com.sumit.program;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
import com.itextpdf.text.Document;
import com.itextpdf.text.PageSize;
import com.itextpdf.text.Rectangle;
import com.itextpdf.text.pdf.BaseFont;
import com.itextpdf.text.pdf.PdfContentByte;
import com.itextpdf.text.pdf.PdfImportedPage;
import com.itextpdf.text.pdf.PdfReader;
import com.itextpdf.text.pdf.PdfWriter;
public class MergePdf {
public static void main(String[] args) {
try {
List<InputStream> pdfs = new ArrayList<InputStream>();
pdfs.add(new FileInputStream("C:\\Documents and Settings\\Sumit\\Desktop\\NewEcnProject\\Document1.pdf"));
pdfs.add(new FileInputStream("C:\\Documents and Settings\\Sumit\\Desktop\\NewEcnProject\\Landscape.pdf"));
OutputStream output = new FileOutputStream("C:\\Documents and Settings\\Sumit\\Desktop\\NewEcnProject\\merge1.pdf");
MergePdf.concatPDFs(pdfs, output, true);
} catch (Exception e) {
e.printStackTrace();
}
}
public static void concatPDFs(List<InputStream> streamOfPDFFiles,
OutputStream outputStream, boolean paginate) {
Document document = new Document();
try {
List<InputStream> pdfs = streamOfPDFFiles;
List<PdfReader> readers = new ArrayList<PdfReader>();
int totalPages = 0;
Iterator<InputStream> iteratorPDFs = pdfs.iterator();
// Create Readers for the pdfs.
int i=1;
while (iteratorPDFs.hasNext()) {
InputStream pdf = iteratorPDFs.next();
PdfReader pdfReader = new PdfReader(pdf);
System.out.println("Page size is "+pdfReader.getPageSize(1));
readers.add(pdfReader);
totalPages += pdfReader.getNumberOfPages();
i++;
}
// Create a writer for the outputstream
PdfWriter writer = PdfWriter.getInstance(document, outputStream);
writer.setCompressionLevel(9);
document.open();
BaseFont bf = BaseFont.createFont(BaseFont.HELVETICA,
BaseFont.CP1252, BaseFont.NOT_EMBEDDED);
PdfContentByte cb = writer.getDirectContent(); // Holds the PDF data
PdfImportedPage page;
int currentPageNumber = 0;
int pageOfCurrentReaderPDF = 0;
Iterator<PdfReader> iteratorPDFReader = readers.iterator();
// Loop through the PDF files and add to the output.
while (iteratorPDFReader.hasNext()) {
PdfReader pdfReader = iteratorPDFReader.next();
// Create a new page in the target for each source page.
System.out.println("No. of pages "+pdfReader.getNumberOfPages());
i=0;
while (pageOfCurrentReaderPDF < pdfReader.getNumberOfPages()) {
Rectangle r=pdfReader.getPageSize(pdfReader.getPageN(pageOfCurrentReaderPDF+1));
if(r.getWidth()==792.0 && r.getHeight()==612.0)
document.setPageSize(PageSize.A4.rotate());
else
document.setPageSize(PageSize.A4);
document.newPage();
pageOfCurrentReaderPDF++;
currentPageNumber++;
i++;
page = writer.getImportedPage(pdfReader,
pageOfCurrentReaderPDF);
System.out.println("Width is "+page.getWidth());
System.out.println("Height is "+page.getHeight());
cb.newlineText();
cb.addTemplate(page, 0, 0);
// Code for pagination.
if (paginate) {
cb.beginText();
cb.setFontAndSize(bf, 9);
cb.showTextAligned(PdfContentByte.ALIGN_CENTER, ""
+ currentPageNumber + " of " + totalPages, 520,
5, 0);
cb.endText();
}
}
pageOfCurrentReaderPDF = 0;
}
outputStream.flush();
document.close();
outputStream.close();
System.out.println("Merging of Pdfs is done.......");
} catch (Exception e) {
e.printStackTrace();
} finally {
if (document.isOpen())
document.close();
try {
if (outputStream != null)
outputStream.close();
} catch (IOException ioe) {
ioe.printStackTrace();
}
}
}
}

Using the Document and PdfWriter class in combination with the addTemplate() method to merge documents is a bad idea. That's not what the addTemplate() method is meant for. You have explicitly or implicitly defined the page size for the Document you are working with. With the addTemplate() method, you add PdfImportedPage instances, and
when you add a new page with the same page size and rotation, you throw away all interactivity that exists in that page, but otherwise all is well,
when you add a new page with a different page size and rotation, you get the result you describe. Because of the difference in size, the imported page and the new page do not match. Parts get cut off, extra margins appear, rotations are different, etc.
This is all explained in chapter 6 of my book. You should use PdfCopy instead of PdfWriter. See for instance the FillFlattenMerge2 example:
Document document = new Document();
PdfCopy copy = new PdfSmartCopy(document, new FileOutputStream(dest));
document.open();
PdfReader reader;
String line = br.readLine();
// loop over readers
// add the PDF to PdfCopy
reader = new PdfReader(baos.toByteArray());
copy.addDocument(reader);
reader.close();
// end loop
document.close();
In your case, you also need to add page numbers, you can do this in a second go, as is done in the StampPageXofY example:
PdfReader reader = new PdfReader(src);
int n = reader.getNumberOfPages();
PdfStamper stamper = new PdfStamper(reader, new FileOutputStream(dest));
PdfContentByte pagecontent;
for (int i = 0; i < n; ) {
pagecontent = stamper.getOverContent(++i);
ColumnText.showTextAligned(pagecontent, Element.ALIGN_RIGHT,
new Phrase(String.format("page %s of %s", i, n)), 559, 806, 0);
}
stamper.close();
reader.close();
Or you can add them while merging, as is done in the MergeWithToc example.
Document document = new Document();
PdfCopy copy = new PdfCopy(document, new FileOutputStream(filename));
PageStamp stamp;
document.open();
int n;
int pageNo = 0;
PdfImportedPage page;
Chunk chunk;
for (Map.Entry<String, PdfReader> entry : filesToMerge.entrySet()) {
n = entry.getValue().getNumberOfPages();
for (int i = 0; i < n; ) {
pageNo++;
page = copy.getImportedPage(entry.getValue(), ++i);
stamp = copy.createPageStamp(page);
chunk = new Chunk(String.format("Page %d", pageNo));
if (i == 1)
chunk.setLocalDestination("p" + pageNo);
ColumnText.showTextAligned(stamp.getUnderContent(),
Element.ALIGN_RIGHT, new Phrase(chunk),
559, 810, 0);
stamp.alterContents();
copy.addPage(page);
}
}
document.close();
for (PdfReader r : filesToMerge.values()) {
r.close();
}
reader.close();
I strongly advise against using PdfWriter to merge documents! It's not impossible if you change the page size and the rotation of the page in the Document class, but you're making it harder on yourself. Moreover: using PdfWriter also throws away all interactivity (links, annotations,...) that exists in the pages you're merging. Your customer may experience that as a bug.

iTextSharp - Printing Merged PDF Templates

I am using iTextSharp in asp.net (C#) in order to merge more than one PDf template. There is a functionality of print which prints only data of the template. While merging the templates the fields/Controls which are available in the template is renamed using RenameField Method of iTextSharp.
This implementation has broken the Print functionality. As the Print functionality has been written according to the fields.
For merging Templates, I am using a PDFCopy.
Document document = new Document();
bool flag = true;
using (FileStream fileStream = File.Create(newFile))
{
PdfSmartCopy copy = new PdfSmartCopy(document, fileStream);
PdfReader reader;
MemoryStream baos;
for (int i = 0; i < loopCount; i++)
{
reader = new PdfReader(pdfTemplate);
baos = new MemoryStream();
stamper = new PdfStamper(reader, baos);
AcroFields pdfDoc = stamper.AcroFields;
BuildData(datarow,pdfDoc, obj)
renameFields(reader);
stamper.FormFlattening = false;
stamper.Close();
reader = new PdfReader(baos.ToArray());
copy.AddPage(copy.GetImportedPage(reader, 1));
}
document.Close();
strFileName = newFile;
}
private static void renameFields(PdfReader pdfReader)
{
string prepend = String.Format("_{0}", counter++);
foreach (KeyValuePair<string, AcroFields.Item> de in pdfReader.AcroFields.Fields)
{
pdfReader.AcroFields.RenameField(de.Key.ToString(), prepend + de.Key.ToString());
}
}
Edit1: This is the solution i found in itextsharp doc,BUT it's not working
"Using PdfCopy with documents
that have named destinations is one of these exceptions. All annotations, such
as link annotations, are kept with PdfCopy, but they no longer work for links to local
named destinations. There is a workaround for this problem."
PdfReader[] readers = {
new PdfReader(LinkActions.RESULT2),
new PdfReader(LinkActions.RESULT1) };
Document document = new Document();
PdfCopy copy =
new PdfCopy(document, new FileOutputStream(RESULT1));
document.open();
int n;
for (int i = 0; i < readers.length; i++) {
readers[i].consolidateNamedDestinations();
n = readers[i].getNumberOfPages();
for (int page = 0; page < n; ) {
copy.addPage(copy.getImportedPage(readers[i], ++page));
}
}

The forms no longer work because you have forgotten to add a single line: copy.setMergeFields();
See the MergeForms2 example:
public void manipulatePdf(String src, String dest) throws IOException, DocumentException {
Document document = new Document();
PdfCopy copy = new PdfSmartCopy(document, new FileOutputStream(dest));
copy.setMergeFields();
document.open();
List<PdfReader> readers = new ArrayList<PdfReader>();
for (int i = 0; i < 3; ) {
PdfReader reader = new PdfReader(renameFields(src, ++i));
readers.add(reader);
copy.addDocument(reader);
}
document.close();
for (PdfReader reader : readers) {
reader.close();
}
}
public byte[] renameFields(String src, int i) throws IOException, DocumentException {
ByteArrayOutputStream baos = new ByteArrayOutputStream();
PdfReader reader = new PdfReader(src);
PdfStamper stamper = new PdfStamper(reader, baos);
AcroFields form = stamper.getAcroFields();
Set<String> keys = new HashSet<String>(form.getFields().keySet());
for (String key : keys) {
form.renameField(key, String.format("%s_%d", key, i));
}
stamper.close();
reader.close();
return baos.toByteArray();
}
It seems that you're also making the assumption that your template consists of only one page:
copy.addPage(copy.getImportedPage(reader, 1));
It is safer to add the document all at once:
copy.addDocument(reader);
Important:
My examples are written in Java. You are working with iTextSharp in C#. You will have to adapt the methods by changing the Java-specific methods into C#-specific properties or methods.

Adding Page Navigation links to PDF document using itextsharp [duplicate]

I have written some code that merges together multiple PDF's into a single PDF that I then display from the MemoryStream. This works great. What I need to do is add a table of contents to the end of the file with links to the start of each of the individual PDF's. I planned on doing this using the GotoLocalPage action which has an option for page numbers but it doesn't seem to work. If I change the action to the code below to one of the presset ones like PDFAction.FIRSTPAGE it works fine. Does this not work because I am using the PDFCopy object for the writer parameter of GotoLocalPage?
Document mergedDoc = new Document();
MemoryStream ms = new MemoryStream();
PdfCopy copy = new PdfCopy(mergedDoc, ms);
mergedDoc.Open();
MemoryStream tocMS = new MemoryStream();
Document tocDoc = null;
PdfWriter tocWriter = null;
for (int i = 0; i < filesToMerge.Length; i++)
{
string filename = filesToMerge[i];
PdfReader reader = new PdfReader(filename);
copy.AddDocument(reader);
// Initialise TOC document based off first file
if (i == 0)
{
tocDoc = new Document(reader.GetPageSizeWithRotation(1));
tocWriter = PdfWriter.GetInstance(tocDoc, tocMS);
tocDoc.Open();
}
// Create link for TOC, added random number of 3 for now
Chunk link = new Chunk(filename);
PdfAction action = PdfAction.GotoLocalPage(3, new PdfDestination(PdfDestination.FIT), copy);
link.SetAction(action);
tocDoc.Add(new Paragraph(link));
}
// Add TOC to end of merged PDF
tocDoc.Close();
PdfReader tocReader = new PdfReader(tocMS.ToArray());
copy.AddDocument(tocReader);
copy.Close();
displayPDF(ms.ToArray());
I guess an alternative would be to link to a named element (instead of page number) but I can't see how to add an 'invisible' element to the start of each file before adding to the merged document?

I would just go with two passes. In your first pass, do the merge as you are but also record the filename and page number it should link to. In your second pass, use a PdfStamper which will give you access to a ColumnText that you can use general abstractions like Paragraph in. Below is a sample that shows this off:
Since I don't have your documents, the below code creates 10 documents with a random number of pages each just for testing purposes. (You obviously don't need to do this part.) It also creates a simple dictionary with a fake file name as the key and the raw bytes from the PDF as a value. You have a true file collection to work with but you should be able to adapt that part.
//Create a bunch of files, nothing special here
//files will be a dictionary of names and the raw PDF bytes
Dictionary<string, byte[]> Files = new Dictionary<string, byte[]>();
var r = new Random();
for (var i = 1; i <= 10; i++) {
using (var ms = new MemoryStream()) {
using (var doc = new Document()) {
using (var writer = PdfWriter.GetInstance(doc, ms)) {
doc.Open();
//Create a random number of pages
for (var j = 1; j <= r.Next(1, 5); j++) {
doc.NewPage();
doc.Add(new Paragraph(String.Format("Hello from document {0} page {1}", i, j)));
}
doc.Close();
}
}
Files.Add("File " + i.ToString(), ms.ToArray());
}
}
This next block merges the PDFs. This is mostly the same as your code except that instead of writing a TOC here I'm just keeping track of what I want to write in the future. Where I'm using file.value you'd use your full file path and where I'm using file.key you'd use your file's name instead.
//Dictionary of file names (for display purposes) and their page numbers
var pages = new Dictionary<string, int>();
//PDFs start at page 1
var lastPageNumber = 1;
//Will hold the final merged PDF bytes
byte[] mergedBytes;
//Most everything else below is standard
using (var ms = new MemoryStream()) {
using (var document = new Document()) {
using (var writer = new PdfCopy(document, ms)) {
document.Open();
foreach (var file in Files) {
//Add the current page at the previous page number
pages.Add(file.Key, lastPageNumber);
using (var reader = new PdfReader(file.Value)) {
writer.AddDocument(reader);
//Increment our current page index
lastPageNumber += reader.NumberOfPages;
}
}
}
}
mergedBytes = ms.ToArray();
}
This last block actually writes the TOC. If we use a PdfStamper we can create a ColumnText which allows us to use Paragraphs
//Will hold the final PDF
byte[] finalBytes;
using (var ms = new MemoryStream()) {
using (var reader = new PdfReader(mergedBytes)) {
using (var stamper = new PdfStamper(reader, ms)) {
//The page number to insert our TOC into
var tocPageNum = reader.NumberOfPages + 1;
//Arbitrarily pick one page to use as the size of the PDF
//Additional logic could be added or this could just be set to something like PageSize.LETTER
var tocPageSize = reader.GetPageSize(1);
//Arbitrary margin for the page
var tocMargin = 20;
//Create our new page
stamper.InsertPage(tocPageNum, tocPageSize);
//Create a ColumnText object so that we can use abstractions like Paragraph
var ct = new ColumnText(stamper.GetOverContent(tocPageNum));
//Set the working area
ct.SetSimpleColumn(tocPageSize.GetLeft(tocMargin), tocPageSize.GetBottom(tocMargin), tocPageSize.GetRight(tocMargin), tocPageSize.GetTop(tocMargin));
//Loop through each page
foreach (var page in pages) {
var link = new Chunk(page.Key);
var action = PdfAction.GotoLocalPage(page.Value, new PdfDestination(PdfDestination.FIT), stamper.Writer);
link.SetAction(action);
ct.AddElement(new Paragraph(link));
}
ct.Go();
}
}
finalBytes = ms.ToArray();
}

PDF Merging by ItextSharp

How would I merge several pdf pages into one with iTextSharp which also supports merging pages having form elements like textboxes, checkboxes, etc.
I have tried so many by googling, but nothing has worked well.

See my answer here Merging Memory Streams. I give an example of how to merge PDFs with itextsharp.
For updating form field names add this code that uses the stamper to change the form field names.
/// <summary>
/// Merges pdf files from a byte list
/// </summary>
/// <param name="files">list of files to merge</param>
/// <returns>memory stream containing combined pdf</returns>
public MemoryStream MergePdfForms(List<byte[]> files)
{
if (files.Count > 1)
{
string[] names;
PdfStamper stamper;
MemoryStream msTemp = null;
PdfReader pdfTemplate = null;
PdfReader pdfFile;
Document doc;
PdfWriter pCopy;
MemoryStream msOutput = new MemoryStream();
pdfFile = new PdfReader(files[0]);
doc = new Document();
pCopy = new PdfSmartCopy(doc, msOutput);
pCopy.PdfVersion = PdfWriter.VERSION_1_7;
doc.Open();
for (int k = 0; k < files.Count; k++)
{
for (int i = 1; i < pdfFile.NumberOfPages + 1; i++)
{
msTemp = new MemoryStream();
pdfTemplate = new PdfReader(files[k]);
stamper = new PdfStamper(pdfTemplate, msTemp);
names = new string[stamper.AcroFields.Fields.Keys.Count];
stamper.AcroFields.Fields.Keys.CopyTo(names, 0);
foreach (string name in names)
{
stamper.AcroFields.RenameField(name, name + "_file" + k.ToString());
}
stamper.Close();
pdfFile = new PdfReader(msTemp.ToArray());
((PdfSmartCopy)pCopy).AddPage(pCopy.GetImportedPage(pdfFile, i));
pCopy.FreeReader(pdfFile);
}
}
pdfFile.Close();
pCopy.Close();
doc.Close();
return msOutput;
}
else if (files.Count == 1)
{
return new MemoryStream(files[0]);
}
return null;
}

Here is my simplified version of Jonathan's Merge code with namespaces added, and stamping removed.
public IO.MemoryStream MergePdfForms(System.Collections.Generic.List<byte[]> files)
{
if (files.Count > 1) {
using (System.IO.MemoryStream msOutput = new System.IO.MemoryStream()) {
using (iTextSharp.text.Document doc = new iTextSharp.text.Document()) {
using (iTextSharp.text.pdf.PdfSmartCopy pCopy = new iTextSharp.text.pdf.PdfSmartCopy(doc, msOutput) { PdfVersion = iTextSharp.text.pdf.PdfWriter.VERSION_1_7 }) {
doc.Open();
foreach (byte[] oFile in files) {
using (iTextSharp.text.pdf.PdfReader pdfFile = new iTextSharp.text.pdf.PdfReader(oFile)) {
for (i = 1; i <= pdfFile.NumberOfPages; i++) {
pCopy.AddPage(pCopy.GetImportedPage(pdfFile, i));
pCopy.FreeReader(pdfFile);
}
}
}
}
}
return msOutput;
}
} else if (files.Count == 1) {
return new System.IO.MemoryStream(files[0]);
}
return null;
}

to merge PDF see "Merging two pdf pages into one using itextsharp"

Below is my code for pdf merging.Thanks Jonathan for giving suggestion abt renaming fields,which resolved the issues while merging pdf pages with form fields.
private static void CombineAndSavePdf(string savePath, List<string> lstPdfFiles)
{
using (Stream outputPdfStream = new FileStream(savePath, FileMode.Create, FileAccess.Write, FileShare.None))
{
Document document = new Document();
PdfSmartCopy copy = new PdfSmartCopy(document, outputPdfStream);
document.Open();
PdfReader reader;
int totalPageCnt;
PdfStamper stamper;
string[] fieldNames;
foreach (string file in lstPdfFiles)
{
reader = new PdfReader(file);
totalPageCnt = reader.NumberOfPages;
for (int pageCnt = 0; pageCnt < totalPageCnt; )
{
//have to create a new reader for each page or PdfStamper will throw error
reader = new PdfReader(file);
stamper = new PdfStamper(reader, outputPdfStream);
fieldNames = new string[stamper.AcroFields.Fields.Keys.Count];
stamper.AcroFields.Fields.Keys.CopyTo(fieldNames, 0);
foreach (string name in fieldNames)
{
stamper.AcroFields.RenameField(name, name + "_file" + pageCnt.ToString());
}
copy.AddPage(copy.GetImportedPage(reader, ++pageCnt));
}
copy.FreeReader(reader);
}
document.Close();
}
}

Changing font of PDF using iTextSharp

How can I change the font of a existing PDF file with iTextSharp in C#?
I want to change the whole documents font into one e.g. Arial

Finally I solved the problem.
The following code will open an existing Pdf file and will change all its font to 'Braille' as per my expectation.
private static void ChangeFont()
{
string strFile = #"E:\\xyz.pdf";
string OutputFile = #"E:\\xyz1.pdf";
PdfReader pdfReader = new PdfReader(strFile);
//Get first page,Generally we get font information on first page,however we can loop throw pages e.g for(int i=0;i<=pdfReader.NumberOfPages;i++)
PdfDictionary cpage = pdfReader.GetPageN(1);
if (cpage == null)
return;
PdfDictionary dictFonts = cpage.GetAsDict(PdfName.RESOURCES).GetAsDict(PdfName.FONT);
if (dictFonts != null)
{
foreach (var font in dictFonts)
{
var dictFontInfo = dictFonts.GetAsDict(font.Key);
if (dictFontInfo != null)
{
foreach (var f in dictFontInfo)
{
//Get the font name-optional code
var baseFont = dictFontInfo.Get(PdfName.BASEFONT);
string strFontName = System.Text.Encoding.ASCII.GetString(baseFont.GetBytes(), 0,
baseFont.Length);
//
//Remove the current font
dictFontInfo.Remove(PdfName.BASEFONT);
//Set new font eg. Braille, Areal etc
dictFontInfo.Put(PdfName.BASEFONT, new PdfString("Braille"));
break;
}
}
}
}
//Now create a new document with updated font
using (FileStream FS = new FileStream(OutputFile, FileMode.Create, FileAccess.Write, FileShare.None))
{
using (Document Doc = new Document())
{
using (PdfCopy writer = new PdfCopy(Doc, FS))
{
Doc.Open();
for (int j = 1; j <= pdfReader.NumberOfPages; j++)
{
writer.AddPage(writer.GetImportedPage(pdfReader, j));
}
Doc.Close();
}
}
}
pdfReader.Close();
}