how to append one pdf to other pdf file using itextsharp - pdf

How to append pages to one pdf file from another pdf file without creating a new pdf using itextsharp. I have metadata attached to one pdf so i just want to add only the other pdf pages,so that first pdf metadata should remain as it is.
Regards
Himvj

Assuming you have 2 pdf files: file1.pdf and file2.pdf that you want to concatenate and save the resulting pdf to file1.pdf (by replacing its contents) you could try the following:
using (var output = new MemoryStream())
{
var document = new Document();
var writer = new PdfCopy(document, output);
document.Open();
foreach (var file in new[] { "file1.pdf", "file2.pdf" })
{
var reader = new PdfReader(file);
int n = reader.NumberOfPages;
PdfImportedPage page;
for (int p = 1; p <= n; p++)
{
page = writer.GetImportedPage(reader, p);
writer.AddPage(page);
}
}
document.Close();
File.WriteAllBytes("file1.pdf", output.ToArray());
}

You can try this it add the whole document with metadata
public static void MergeFiles(string destinationFile, string[] sourceFiles)
{
try
{
//1: Create the MemoryStream for the destination document.
using (MemoryStream ms = new MemoryStream())
{
//2: Create the PdfCopyFields object.
PdfCopyFields copy = new PdfCopyFields(ms);
// - Set the security and other settings for the destination file.
//copy.Writer.SetEncryption(PdfWriter.STRENGTH128BITS, null, "1234", PdfWriter.AllowPrinting | PdfWriter.AllowCopy | PdfWriter.AllowFillIn);
copy.Writer.ViewerPreferences = PdfWriter.PageModeUseOutlines;
// - Create an arraylist to hold bookmarks for later use.
ArrayList outlines = new ArrayList();
int pageOffset = 0;
int f = 0;
//3: Import the documents specified in args[1], args[2], etc...
while (f < sourceFiles.Length)
{
// Grab the file from args[] and open it with PdfReader.
string file = sourceFiles[f];
PdfReader reader = new PdfReader(file);
// Import the pages from the current file.
copy.AddDocument(reader);
// Create an ArrayList of bookmarks in the file being imported.
// ArrayList bookmarkLst = SimpleBookmark.GetBookmark(reader);
// Shift the pages to accomidate any pages that were imported before the current document.
// SimpleBookmark.ShiftPageNumbers(bookmarkLst, pageOffset, null);
// Fill the outlines ArrayList with each bookmark as a HashTable.
// foreach (Hashtable ht in bookmarkLst)
// {
// outlines.Add(ht);
// }
// Set the page offset to the last page imported.
//copy.Writer.SetPageSize(rec);
pageOffset += reader.NumberOfPages;
f++;
}
//4: Put the outlines from all documents under a new "Root" outline and
// set them for destination document
// copy.Writer.Outlines = GetBookmarks("Root", ((Hashtable)outlines[0])["Page"], outlines);
//5: Close the PdfCopyFields object.
copy.Close();
//6: Save the MemoryStream to a file.
MemoryStreamToFile(ms, destinationFile);
}
}
catch (System.Exception e)
{
System.Console.Error.WriteLine(e.Message);
System.Console.Error.WriteLine(e.StackTrace);
System.Console.ReadLine();
}
}
public static void MemoryStreamToFile(MemoryStream MS, string FileName)
{
using (FileStream fs = new FileStream(#FileName, FileMode.Create))
{
byte[] data = MS.ToArray();
fs.Write(data, 0, data.Length);
fs.Close();
}
}

Related

Fill XFA without breaking usage rights

I have an XFA form that I can successfully fill in by extracting the XML modifying and writing back. Works great if you have the full Adobe Acrobat, but fails with Adobe Reader. I have seen various questions on the same thing with answers but they were some time ago so updating an XFA that is readable by Adobe Reader may no longer be doable?
I use this code below and I've utilised the StampingProperties of append as in the iText example but still failing. I'm using iText 7.1.15.
//open file and write to temp one
PdfDocument pdf = new(new PdfReader(FileToProcess), new PdfWriter(NewPDF), new StampingProperties().UseAppendMode());
PdfAcroForm form = PdfAcroForm.GetAcroForm(pdf, true);
XfaForm xfa = form.GetXfaForm();
XElement node = xfa.GetDatasetsNode();
IEnumerable<XNode> list = node.Nodes();
foreach (XNode item in list)
{
if (item is XElement element && "data".Equals(element.Name.LocalName))
{
node = element;
break;
}
}
XmlWriterSettings settings = new() { Indent = true };
using XmlWriter writer = XmlWriter.Create(XMLOutput, settings);
{
node.WriteTo(writer);
writer.Flush();
writer.Close();
}
//We now how to strip an extra xfa line if updating
if(update)
{
string TempXML= CSTrackerHelper.MakePath($"{AppContext.BaseDirectory}Temp", $"{Guid.NewGuid()}.XML");
StreamReader fsin = new(XMLOutput);
StreamWriter fsout = new(TempXML);
string linedata = string.Empty;
int cnt = 0;
while (!fsin.EndOfStream)
{
if (cnt != 3 && linedata != string.Empty)
{
fsout.WriteLine(linedata);
}
linedata = fsin.ReadLine();
cnt++;
}
fsout.Close();
fsin.Close();
XMLOutput = TempXML;
}
xlogger.Info("Populating pdf fields");
//Now loop through our field data and update the XML
XmlDocument xmldoc = new();
xmldoc.Load(XMLOutput);
XmlNamespaceManager xmlnsManager = new(xmldoc.NameTable);
xmlnsManager.AddNamespace("xfa", #"http://www.xfa.org/schema/xfa-data/1.0/");
string[] FieldValues;
string[] MultiNodes;
foreach (KeyValuePair<string, DocumentFieldData> v in DocumentData.FieldData)
{
if (!string.IsNullOrEmpty(v.Value.Field))
{
FieldValues = v.Value.Field.Contains(";") ? v.Value.Field.Split(';') : (new string[] { v.Value.Field });
foreach (string FValue in FieldValues)
{
XmlNodeList aNodes;
if (FValue.Contains("{"))
{
aNodes = xmldoc.SelectNodes(FValue.Substring(0, FValue.LastIndexOf("{")), xmlnsManager);
if (aNodes.Count > 1)
{
//We have a multinode
MultiNodes = FValue.Split('{');
int NodeIndex = int.Parse(MultiNodes[1].Replace("}", ""));
aNodes[NodeIndex].InnerText = v.Value.Data;
}
}
else
{
aNodes = xmldoc.SelectNodes(FValue, xmlnsManager);
if (aNodes.Count >= 1)
{
aNodes[0].InnerText = v.Value.Data;
}
}
}
}
}
xmldoc.Save(XMLOutput);
//Now we've updated the XML apply it to the pdf
xfa.FillXfaForm(new FileStream(XMLOutput, FileMode.Open, FileAccess.Read));
xfa.Write(pdf);
pdf.Close();
FYI I've also tried to set a field directly also with the same results.
PdfReader preader = new PdfReader(source);
PdfDocument pdfDoc=new PdfDocument(preader, new PdfWriter(dest), new StampingProperties().UseAppendMode());
PdfAcroForm pdfForm = PdfAcroForm.GetAcroForm(pdfDoc, true);
XfaForm xform = pdfForm.GetXfaForm();
xform.SetXfaFieldValue("VRM[0].CoverPage[0].Wrap2[0].Table[0].CSID[0]", "Test");
xform.Write(pdfForm);
pdfDoc.Close();
If anyone has any ideas it would be appreciated.
Cheers
I ran into a very similar issue. I was attempting to auto fill an XFA that was password protected while not breaking the certificate or usage rights (it allowed filling). iText7 seems to have made this not possible for legal/practical reasons, however it is still very much possible with iText5. I wrote the following working codeusing iTextSharp (C# version if iText5):
using iTextSharp.text;
using iTextSharp.text.pdf;
string pathToRead = "/Users/home/Desktop/c#pdfParser/encrypted_empty.pdf";
string pathToSave = "/Users/home/Desktop/c#pdfParser/xfa_encrypted_filled.pdf";
string data = "/Users/home/Desktop/c#pdfParser/sample_data.xml";
FillByItextSharp5(pathToRead, pathToSave, data);
static void FillByItextSharp5(string pathToRead, string pathToSave, string data)
{
using (FileStream pdf = new FileStream(pathToRead, FileMode.Open))
using (FileStream xml = new FileStream(data, FileMode.Open))
using (FileStream filledPdf = new FileStream(pathToSave, FileMode.Create))
{
PdfReader.unethicalreading = true;
PdfReader pdfReader = new PdfReader(pdf);
PdfStamper stamper = new PdfStamper(pdfReader, filledPdf, '\0', true);
stamper.AcroFields.Xfa.FillXfaForm(xml, true);
stamper.Close();
pdfReader.Close();
}
}
PdfStamper stamper = new PdfStamper(pdfReader, filledPdf, '\0', true)
you have to use this line.

CopyToAsync() dont' fill the memory stream

i'm using xamarin.forms app and need to save file(it this situation pdf file). This is my scenario: I'm using media plugin to save images with camera and from that images with PdfDocument object i generate PDF file:
PdfDocument document = new PdfDocument();
for (int i = 0; i < Images.Count(); i++)
{
PdfPage page = document.Pages.Add();
PdfGraphics graphics = page.Graphics;
Stream imageStream = Images.ElementAt(i);
PdfBitmap image = new PdfBitmap(imageStream);
page.Graphics.DrawImage(image, new PointF(40, 100));
}
MemoryStream stream = new MemoryStream();
document.Save(stream);
document.Close(true);
String localPath =
Task.Run(() => DependencyService.Get<ISave>().SaveFile(stream, "test.pdf")).Result;
And everything is working fine, its generates me pdf document with pages stream is filled with bytes, and the problem is in this SaveFile:
[assembly: Dependency(typeof(Save))]
namespace PdfSave.Droid.Shared
{
public class Save: ISave
{
private readonly string _rootDir = Path.Combine(System.Environment.GetFolderPath(System.Environment.SpecialFolder.Personal), "TestFolder");
public async Task<string> SaveFile(Stream pdfStream, string fileName)
{
if (!Directory.Exists(_rootDir))
Directory.CreateDirectory(_rootDir);
var filePath = Path.Combine(_rootDir, fileName);
using (var memoryStream = new MemoryStream())
{
await pdfStream.CopyToAsync(memoryStream);
File.WriteAllBytes(filePath, memoryStream.ToArray());
}
return filePath;
}
}
the problem is in this line
await pdfStream.CopyToAsync(memoryStream);
the memory stream is empty! . Anyone know what should might be the problem?

How to remove one indirectly referenced image from a PDF and keep all others?

I would like to parse a PDF and find the logo via known attributes and when I find a match, remove that image and then copy everything else.
I am using the code below to replace an image with a blank white image to remove a logo from PDFs that are to be printed on letterhead. It replaces the image with a white image of the same size. Is there a way to modify this to actually remove the image (and thus save some space, etc.?).
private static void Main(string[] args)
{
ManipulatePdf(#"C:\in.pdf", #"C:\out.pdf");
Console.WriteLine("Finished - press a key");
Console.ReadKey();
}
public static void ManipulatePdf(String src, String dest)
{
Console.WriteLine("Start");
PdfReader reader = new PdfReader(src);
// first read all references and find the one we wish to work on.
PdfDictionary page = reader.GetPageN(1); // all resources are available to every page (?)
PdfDictionary resources = page.GetAsDict(PdfName.RESOURCES);
PdfDictionary xobjects = resources.GetAsDict(PdfName.XOBJECT);
page = reader.GetPageN(1);
resources = page.GetAsDict(PdfName.RESOURCES);
xobjects = resources.GetAsDict(PdfName.XOBJECT);
foreach (PdfName pdfName in xobjects.Keys)
{
PRStream stream = (PRStream) xobjects.GetAsStream(pdfName);
if (stream.Length > 100000)
{
PdfImage image = new PdfImage(MakeBlankImg(), "", null);
Console.WriteLine("Calling replace stream");
ReplaceStream(stream, image);
}
}
PdfStamper stamper = new PdfStamper(reader, new FileStream(dest, FileMode.Create));
stamper.Close();
reader.Close();
}
public static iTextSharp.text.Image MakeBlankImg()
{
Console.WriteLine("Making small blank image");
byte[] array;
using (MemoryStream ms = new MemoryStream())
{
//var drawingImage = image.GetDrawingImage();
using (Bitmap newBi = new Bitmap(1, 1))
{
using (Graphics g = Graphics.FromImage(newBi))
{
g.Clear(Color.White);
g.Flush();
}
newBi.Save(ms, ImageFormat.Jpeg);
}
array = ms.ToArray();
}
Console.WriteLine("Image array is " + array.Length + " bytes.");
return iTextSharp.text.Image.GetInstance(array);
}
public static void ReplaceStream(PRStream orig, PdfStream stream)
{
orig.Clear();
MemoryStream ms = new MemoryStream();
stream.WriteContent(ms);
orig.SetData(ms.ToArray(), false);
Console.WriteLine("Iterating keys");
foreach (KeyValuePair<PdfName, PdfObject> keyValuePair in stream)
{
Console.WriteLine("Key: " + keyValuePair.Key.ToString());
orig.Put(keyValuePair.Key, stream.Get(keyValuePair.Key));
}
}
}

Pdfbox - adding pdf embedded File and save the PDDocument to OutputStream does not keep the embedded Files

I'm using Pdfbox (1.8.8) to adding attachments to a pdf. My problem is when one of the attachments is of type .pdf and i'm saving the PDDocument to OutputStream the final pdf document does not include the attachments. If a save the PDDocument to a file instead an OutputStream all works just fine, and if the attachments does not include any pdf, both save to file or OutputStream works fine.
I would like to know if there is any way to add pdf embedded Files and save the PDDocument to OutputStream keeping the attached files in the final pdf that is generated.
The code i'm using is:
private void insertAttachments(OutputStream out, ArrayList<Attachment> attachmentsResources) {
final PDDocument doc;
Boolean hasPdfAttach = false;
try {
doc = PDDocument.load(new ByteArrayInputStream(((ByteArrayOutputStream) out).toByteArray()));
// final PDFTextStripper pdfStripper = new PDFTextStripper();
// final String text = pdfStripper.getText(doc);
final PDEmbeddedFilesNameTreeNode efTree = new PDEmbeddedFilesNameTreeNode();
final Map embeddedFileMap = new HashMap();
PDEmbeddedFile embeddedFile;
File file = null;
for (Attachment attach : attachmentsResources) {
// first create the file specification, which holds the embedded file
final PDComplexFileSpecification fileSpecification = new PDComplexFileSpecification();
fileSpecification.setFile(attach.getFilename());
file = AttachmentUtils.getAttachmentFile(attach);
final InputStream is = new FileInputStream(file.getAbsolutePath());
embeddedFile = new PDEmbeddedFile(doc, is);
// set some of the attributes of the embedded file
if ("application/pdf".equals(attach.getMimetype())) {
hasPdfAttach = true;
}
embeddedFile.setSubtype(attach.getMimetype());
embeddedFile.setSize((int) (long) attach.getFilesize());
fileSpecification.setEmbeddedFile(embeddedFile);
// now add the entry to the embedded file tree and set in the document.
embeddedFileMap.put(attach.getFilename(), fileSpecification);
// final String text2 = pdfStripper.getText(doc);
}
// final String text3 = pdfStripper.getText(doc);
efTree.setNames(embeddedFileMap);
// ((COSDictionary) efTree.getCOSObject()).removeItem(COSName.LIMITS); (this not work for me)
// attachments are stored as part of the "names" dictionary in the document catalog
final PDDocumentNameDictionary names = new PDDocumentNameDictionary(doc.getDocumentCatalog());
names.setEmbeddedFiles(efTree);
doc.getDocumentCatalog().setNames(names);
// final ByteArrayOutputStream pdfboxToDocumentStream = new ByteArrayOutputStream();
final String tmpfile = "temporary.pdf";
if (hasPdfAttach) {
final File f = new File(tmpfile);
doc.save(f);
doc.close();
//i have try with parser but without success too
// PDFParser parser = new PDFParser(new FileInputStream(tmpfile));
// parser.parse();
// PDDocument doc2 = parser.getPDDocument();
final PDDocument doc2 = PDDocument.loadNonSeq(f, new RandomAccessFile(new File(getHomeTMP()
+ "tempppp.pdf"), "r"));
doc2.save(out);
doc2.close();
} else {
doc.save(out);
doc.close();
}
//that does not work too
// final InputStream in = new FileInputStream(tmpfile);
// IOUtils.copy(in, out);
// out = new FileOutputStream(tmpFile);
// doc.save (out);
} catch (IOException e1) {
e1.printStackTrace();
} catch (Exception e2) {
e2.printStackTrace();
}
}
Best regards
Solution:
private void insertAttachments(OutputStream out, ArrayList<Attachment> attachmentsResources) {
final PDDocument doc;
try {
doc = PDDocument.load(new ByteArrayInputStream(((ByteArrayOutputStream) out).toByteArray()));
((ByteArrayOutputStream) out).reset();
final PDEmbeddedFilesNameTreeNode efTree = new PDEmbeddedFilesNameTreeNode();
final Map embeddedFileMap = new HashMap();
PDEmbeddedFile embeddedFile;
File file = null;
for (Attachment attach : attachmentsResources) {
// first create the file specification, which holds the embedded file
final PDComplexFileSpecification fileSpecification = new PDComplexFileSpecification();
fileSpecification.setFile(attach.getFilename());
file = AttachmentUtils.getAttachmentFile(attach);
final InputStream is = new FileInputStream(file.getAbsolutePath());
embeddedFile = new PDEmbeddedFile(doc, is);
// set some of the attributes of the embedded file
embeddedFile.setSubtype(attach.getMimetype());
embeddedFile.setSize((int) (long) attach.getFilesize());
fileSpecification.setEmbeddedFile(embeddedFile);
// now add the entry to the embedded file tree and set in the document.
embeddedFileMap.put(attach.getFilename(), fileSpecification);
}
efTree.setNames(embeddedFileMap);
((COSDictionary) efTree.getCOSObject()).removeItem(COSName.LIMITS);
// attachments are stored as part of the "names" dictionary in the document catalog
final PDDocumentNameDictionary names = new PDDocumentNameDictionary(doc.getDocumentCatalog());
names.setEmbeddedFiles(efTree);
doc.getDocumentCatalog().setNames(names);
((COSDictionary) efTree.getCOSObject()).removeItem(COSName.LIMITS);
doc.save(out);
doc.close();
} catch (IOException e1) {
e1.printStackTrace();
} catch (Exception e2) {
e2.printStackTrace();
}
}
You store the new PDF after the original PDF in out:
Look at all the uses of out in your method:
private void insertAttachments(OutputStream out, ArrayList<Attachment> attachmentsResources) {
...
doc = PDDocument.load(new ByteArrayInputStream(((ByteArrayOutputStream) out).toByteArray()));
...
doc2.save(out);
...
doc.save(out);
So you get as input a ByteArrayOutputStream and take its current content as input (i.e. the ByteArrayOutputStream is not empty but already contains a PDF) and after some processing you append the modified PDF to the ByteArrayOutputStream. Depending on the PDF viewer you present this to, you will be shown either the original or the manipulated PDF or a (very correct) error message that the file is garbage.
If you want the ByteArrayOutputStream to contain only the manipulated PDF, simply add
((ByteArrayOutputStream) out).reset();
or (if you are not sure about the state of the stream)
out = new ByteArrayOutputStream();
right after
doc = PDDocument.load(new ByteArrayInputStream(((ByteArrayOutputStream) out).toByteArray()));
PS: According to the comments the OP tried the above proposed changes to his code without success.
I cannot run the code as presented in the question because it is not self-contained. Thus, I reduced it to the essentials to get a self-contained test:
#Test
public void test() throws IOException, COSVisitorException
{
ByteArrayOutputStream baos = new ByteArrayOutputStream();
try (
InputStream sourceStream = getClass().getResourceAsStream("test.pdf");
InputStream attachStream = getClass().getResourceAsStream("artificial text.pdf"))
{
final PDDocument document = PDDocument.load(sourceStream);
final PDEmbeddedFile embeddedFile = new PDEmbeddedFile(document, attachStream);
embeddedFile.setSubtype("application/pdf");
embeddedFile.setSize(10993);
final PDComplexFileSpecification fileSpecification = new PDComplexFileSpecification();
fileSpecification.setFile("artificial text.pdf");
fileSpecification.setEmbeddedFile(embeddedFile);
final Map<String, PDComplexFileSpecification> embeddedFileMap = new HashMap<String, PDComplexFileSpecification>();
embeddedFileMap.put("artificial text.pdf", fileSpecification);
final PDEmbeddedFilesNameTreeNode efTree = new PDEmbeddedFilesNameTreeNode();
efTree.setNames(embeddedFileMap);
final PDDocumentNameDictionary names = new PDDocumentNameDictionary(document.getDocumentCatalog());
names.setEmbeddedFiles(efTree);
document.getDocumentCatalog().setNames(names);
document.save(baos);
document.close();
}
Files.write(Paths.get("attachment.pdf"), baos.toByteArray());
}
As you see PDFBox here uses only streams. The result:
Thus, PDFBox without problem stores a PDF into which it has embedded a PDF file attachment.
The problem, therefore, most likely have nothing to do with this work flow as such

iTextSharp - Using PDFAction.GotoLocalPage in Merged PDF

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();
}