I have one PDF form which is filled by supervisor(or a user).
I want to merge generated PDFs.
I have done simple merging but in it i have to first generate multiple files and then merge them.
Is there any way that when user fills multiple forms and then at the time of final submission or printing i get only a single merged of all filled PDFs.
Try out this Merge function to merge PDF files:
public static void Merge(string[] sourceFiles, string destinationFile)
{
try
{
int f = 0;
// we create a reader for a certain document
PdfReader reader = new PdfReader(sourceFiles[f]);
// we retrieve the total number of pages
int n = reader.NumberOfPages;
//Debug.WriteLine("There are " + n + " pages in the original file.");
// step 1: creation of a document-object
Document document = new Document(reader.GetPageSizeWithRotation(1));
// step 2: we create a writer that listens to the document
PdfWriter writer = PdfWriter.GetInstance(document, new FileStream(destinationFile, FileMode.Create));
// step 3: we open the document
document.Open();
PdfContentByte cb = writer.DirectContent;
PdfImportedPage page;
int rotation;
// step 4: we add content
while (f < sourceFiles.Length)
{
int i = 0;
while (i < n)
{
i++;
document.SetPageSize(reader.GetPageSizeWithRotation(i));
document.NewPage();
page = writer.GetImportedPage(reader, i);
rotation = reader.GetPageRotation(i);
if (rotation == 90 || rotation == 270)
{
cb.AddTemplate(page, 0, -1f, 1f, 0, 0, reader.GetPageSizeWithRotation(i).Height);
}
else
{
cb.AddTemplate(page, 1f, 0, 0, 1f, 0, 0);
}
//Debug.WriteLine("Processed page " + i);
}
f++;
if (f < sourceFiles.Length)
{
reader = new PdfReader(sourceFiles[f]);
// we retrieve the total number of pages
n = reader.NumberOfPages;
//Debug.WriteLine("There are " + n + " pages in the original file.");
}
}
// step 5: we close the document
document.Close();
}
catch (Exception ex)
{
throw ex;
}
}
Reference: Merge PDF Files using iTextSharp
based off the merge code I sourced in my comments above..
I use this to write to the output stream of an http response. It returns a byte[], but you can use the original code and this to get the job done.
public static byte[] MergeFiles(List<byte[]> sourceFiles)
{
Document document = new Document();
MemoryStream output = new MemoryStream();
try
{
// Initialize pdf writer
PdfWriter writer = PdfWriter.GetInstance(document, output);
// Open document to write
document.Open();
PdfContentByte content = writer.DirectContent;
// Iterate through all pdf documents
for (int fileCounter = 0; fileCounter < sourceFiles.Count; fileCounter++)
{
// Create pdf reader
PdfReader reader = new PdfReader(sourceFiles[fileCounter]);
int numberOfPages = reader.NumberOfPages;
// Iterate through all pages
for (int currentPageIndex = 1; currentPageIndex <=
numberOfPages; currentPageIndex++)
{
// Determine page size for the current page
document.SetPageSize(
reader.GetPageSizeWithRotation(currentPageIndex));
// Create page
document.NewPage();
PdfImportedPage importedPage =
writer.GetImportedPage(reader, currentPageIndex);
// Determine page orientation
int pageOrientation = reader.GetPageRotation(currentPageIndex);
if ((pageOrientation == 90) || (pageOrientation == 270))
{
content.AddTemplate(importedPage, 0, -1f, 1f, 0, 0,
reader.GetPageSizeWithRotation(currentPageIndex).Height);
}
else
{
content.AddTemplate(importedPage, 1f, 0, 0, 1f, 0, 0);
}
}
}
}
catch (Exception exception)
{
throw new Exception("There has an unexpected exception" +
" occured during the pdf merging process.", exception);
}
finally
{
document.Close();
}
return output.GetBuffer();
}
Related
I am using this code to merge a pdf file to the start of pdf but want to set it to the 2nd page of existing pdf.
How do I do that ? How to go with this?
I have spent days on it but no luck.
public static string MergeFiles(string destinationFile, string[] sourceFiles)
{
try
{
string NewFileName = "InspectionReport" + DateTime.Now.ToString("ddMMMyyyy HHmmss").Replace(" ", "");
destinationFile = HostingEnvironment.MapPath(#"/Downloads/Files/" + NewFileName + ".pdf");
int f = 0;
PdfReader reader = new PdfReader(sourceFiles[f]);
int n = reader.NumberOfPages;
Document document = new Document(reader.GetPageSizeWithRotation(1));
PdfWriter writer = PdfWriter.GetInstance(document, new FileStream(destinationFile, FileMode.Create));
document.Open();
PdfContentByte cb = writer.DirectContent;
PdfImportedPage page;
int rotation;
while (f < sourceFiles.Length)
{
int i = 0;
while (i < n)
{
i++;
document.SetPageSize(reader.GetPageSizeWithRotation(i));
document.NewPage();
page = writer.GetImportedPage(reader, i);
rotation = reader.GetPageRotation(i);
if (rotation == 90 || rotation == 270)
{
cb.AddTemplate(page, 0, -1f, 1f, 0, 0, reader.GetPageSizeWithRotation(i).Height);
}
else
{
cb.AddTemplate(page, 1f, 0, 0, 1f, 0, 0);
}
}
f++;
if (f < sourceFiles.Length)
{
reader = new PdfReader(sourceFiles[f]);
n = reader.NumberOfPages;
}
}
document.Close();
}
catch (Exception e)
{
string strOb = e.Message;
}
return destinationFile;
}
Now, it only appends at the top and I can think of no way of adding to the 2nd page of the existing pdf.
I am trying to merge two PDF in this method but after successfully adding, I am unable to convert iTextSharp.text.Document into byte array . Please help me.
protected byte[] MergePDFs(byte[] First, byte[] Second, string RptTitle)
{
iTextSharp.text.Document doc = new iTextSharp.text.Document();
iTextSharp.text.pdf.PdfReader reader = null;
int numberOfPages = 0;
int currentPageNumber = 0;
iTextSharp.text.pdf.PdfWriter writer = iTextSharp.text.pdf.PdfWriter.GetInstance(doc, MemStream);
doc.Open();
iTextSharp.text.pdf.PdfContentByte cb = writer.DirectContent;
iTextSharp.text.pdf.PdfImportedPage page = null;
//Third, append all the PDFs--THIS IS THE MAGIC PART
if (First != null)
{
reader = new iTextSharp.text.pdf.PdfReader(First);
numberOfPages = reader.NumberOfPages;
currentPageNumber = 0;
while ((currentPageNumber < numberOfPages))
{
currentPageNumber += 1;
doc.SetPageSize(iTextSharp.text.PageSize.A4);
doc.NewPage();
page = writer.GetImportedPage(reader, currentPageNumber);
//we know that the page would always be in Potrait Format
cb.AddTemplate(page, 1f, 0, 0, 1f, 0, 1);
}
}
if (Second != null)
{
reader = new iTextSharp.text.pdf.PdfReader(Second);
numberOfPages = reader.NumberOfPages;
currentPageNumber = 0;
while ((currentPageNumber < numberOfPages))
{
currentPageNumber += 1;
doc.SetPageSize(iTextSharp.text.PageSize.A4.Rotate());
//.Rotate());
doc.NewPage();
page = writer.GetImportedPage(reader, currentPageNumber);
//we know that the page would always be in LandScape Format
// cb.AddTemplate(page,0, -1f, 1f, 0,0, reader.GetPageSizeWithRotation(currentPageNumber).Height+300);
cb.AddTemplate(page, 1, 0, 0, 1, 0, 0);
}
}
doc.Close();
byte[] cc = StringToByteArray(doc.ToString());
return cc;
I don't know where you people get this examples, they are completely wrong.
First, use PdfCopy, not PdfWriter. That way the correct page size and orientation will be correctly imported.
Second, if your MemStream is a MemoryStream you would use MemStream.ToArray() to get the PDF bytes.
PS: Where did that invention of doc.ToString() come from? It's completely rubbish.
I am using acrobat 8.0 professional for cropping text from a PDF.
One page of Original pdf is
After cropping pdf above page is
In mine project i am using cropped pdf and extract individual pages from it by following code
private void ExtractPages(string inputFile, string outputFile, int start, int end)
{
// get input document
PdfReader inputPdf = new PdfReader(inputFile);
// retrieve the total number of pages
int pageCount = inputPdf.NumberOfPages;
if (end < start || end > pageCount)
{
end = pageCount;
}
//var pgSize = new iTextSharp.text.Rectangle(myWidth, myHeight);
//var doc = new iTextSharp.text.Document(pgSize, leftMargin, rightMargin, topMargin, bottomMargin);
// load the input document
Document inputDoc = new Document(inputPdf.GetPageSizeWithRotation(1));
// create the filestream
using (FileStream fs = new FileStream(outputFile, FileMode.Create))
{
// create the output writer
PdfWriter outputWriter = PdfWriter.GetInstance(inputDoc, fs);
inputDoc.Open();
PdfContentByte cb1 = outputWriter.DirectContent;
// copy pages from input to output document
for (int i = start; i <= end; i++)
{
inputDoc.SetPageSize(inputPdf.GetPageSizeWithRotation(i));
inputDoc.NewPage();
PdfImportedPage page = outputWriter.GetImportedPage(inputPdf, i);
int rotation = inputPdf.GetPageRotation(i);
if (rotation == 90 || rotation == 270)
{
cb1.AddTemplate(page, 0, -1f, 1f, 0, 0, inputPdf.GetPageSizeWithRotation(i).Height);
}
else
{
cb1.AddTemplate(page, 1f, 0, 0, 1f, 0, 0);
}
}
inputDoc.Close();
}
}
Problem is that after page extraction cropping information is not retained in extracted pdf. Extracted pdf is same as original pdf with extra text in it.
How to retained cropped information in extracted pdf ?
I want to add page numbers to the footer of the itextsharp pdf file.Im generating pdf from html (asp.net repeater).And Im using XMLWorkerHelper to parse the html content.I searched a lot but cant find anything useful to achive this.
You'll have to open the PDF with iTextSharp and add the page numbers yourself. I did something like this a while back, here's my function that might give you a start.
The function adds the current page to the lower left, so you might have to place it somewhere else that fits your needs.
public static byte[] AddPageNumbers(byte[] pdf)
{
MemoryStream ms = new MemoryStream();
// we create a reader for a certain document
PdfReader reader = new PdfReader(pdf);
// we retrieve the total number of pages
int n = reader.NumberOfPages;
// we retrieve the size of the first page
Rectangle psize = reader.GetPageSize(1);
// step 1: creation of a document-object
Document document = new Document(psize, 50, 50, 50, 50);
// step 2: we create a writer that listens to the document
PdfWriter writer = PdfWriter.GetInstance(document, ms);
// step 3: we open the document
document.Open();
// step 4: we add content
PdfContentByte cb = writer.DirectContent;
int p = 0;
Console.WriteLine("There are " + n + " pages in the document.");
for (int page = 1; page <= reader.NumberOfPages; page++)
{
document.NewPage();
p++;
PdfImportedPage importedPage = writer.GetImportedPage(reader, page);
cb.AddTemplate(importedPage, 0, 0);
BaseFont bf = BaseFont.CreateFont(BaseFont.HELVETICA, BaseFont.CP1252, BaseFont.NOT_EMBEDDED);
cb.BeginText();
cb.SetFontAndSize(bf, 10);
cb.ShowTextAligned(PdfContentByte.ALIGN_LEFT, +p + "/" + n, 7, 44, 0);
cb.EndText();
}
// step 5: we close the document
document.Close();
return ms.ToArray();
}
Something like this should work:
var sourceFileList = new List<string>();
//add files to merge
int sourceIndex = 0;
PdfReader reader = new PdfReader(sourceFileList[sourceIndex]);
int sourceFilePageCount = reader.NumberOfPages;
Document doc = new Document(reader.GetPageSizeWithRotation(1));
PdfWriter writer = PdfWriter.GetInstance(doc, new FileStream(destinationFileName, FileMode.Create));
doc.Open();
PdfImportedPage page;
PdfContentByte contentByte = writer.DirectContent;
int rotation;
while (sourceIndex < sourceFileList.Count)
{
int pageIndex = 0;
while (pageIndex < sourceFilePageCount)
{
pageIndex++;
doc.SetPageSize(reader.GetPageSizeWithRotation(pageIndex));
doc.NewPage();
page = writer.GetImportedPage(reader, pageIndex);
rotation = reader.GetPageRotation(pageIndex);
if (rotation.Equals(90 | 270))
contentByte.AddTemplate(page, 0, -1f, 1f, 0, 0, reader.GetPageSizeWithRotation(pageIndex).Height);
else
contentByte.AddTemplate(page, 1f, 0, 0, 1f, 0, 0);
}
sourceIndex++;
if (sourceIndex < sourceFileList.Count)
{
reader = new PdfReader(sourceFileList[sourceIndex]);
sourceFilePageCount = reader.NumberOfPages;
}
}
doc.Close();
//the func merges the src pdf with the memory stream, wherein the stream may contain
//few othr src pdf streams in previous calls to this func
//in first cal, ms would be null
public static void MergePdf(MemoryStream ms, string srcFile)
{
PdfReader reader = new PdfReader(srcFile);
Document document = null;
PdfWriter writer = null;
int n = reader.NumberOfPages;
if (document == null)
{
document = new Document(reader.GetPageSizeWithRotation(1));
writer = PdfWriter.GetInstance(document, ms);
document.Open();
}
PdfContentByte cb = writer.DirectContent;
PdfImportedPage page;
int rotation;
int i = 0;
while (i < n)
{
i++;
document.SetPageSize(reader.GetPageSizeWithRotation(i));
document.NewPage();
page = writer.GetImportedPage(reader, i);
rotation = reader.GetPageRotation(i);
if (rotation == 90 || rotation == 270)
{
cb.AddTemplate(page, 0, -1f, 1f, 0, 0,
reader.GetPageSizeWithRotation(i).Height);
}
else
{
cb.AddTemplate(page, 1f, 0, 0, 1f, 0, 0);
}
}
}
I write the Memory stream, back to context.response.Outputstream; but the pdf doesnt load, the page 'Failed to load Pdf' results; Is there any problem in converting btwn memorystream and Pdf contents, or what may be the issue?
I had the same problem, and it turned out that the cause was not closing the document, and adding the following line of code:
document.Close();
should fix the problem.