Develop Reference

Create borderless table in iText 7

I am porting an application from iTextSharp 5 to iText 7. In the original application I added page numbers using a stamper that added a table to the top of the page. I have almost succeeded but I am unable to create a table with only a bottom border (internal, left, right and top is borderless. I tried the example from the iText building blocks book and have looked at itext 7 table borderless
But I still get top, internal and side borders. Here is my code:
private Table makepagetable(string doctitle, int curpage, int totalpage)
{
PdfFont font = PdfFontFactory.CreateFont(iText.IO.Font.Constants.StandardFonts.TIMES_ROMAN);
Text title = new Text(doctitle).SetFontSize(11f).SetFont(font);
Text pages = new Text("page " + curpage.ToString() + " of " + totalpage.ToString()).SetFont(font);
Paragraph p1 = new Paragraph(title).SetTextAlignment(TextAlignment.LEFT);
Paragraph p2 = new Paragraph(pages).SetTextAlignment(TextAlignment.RIGHT);
Table mytable = new Table(new float[] { 3, 1 })
.SetBorderTop(Border.NO_BORDER)
.SetBorderRight(Border.NO_BORDER)
.SetBorderLeft(Border.NO_BORDER)
.SetBorderBottom(new SolidBorder(2));
float pval = 500;
mytable.SetWidth(pval);
mytable.AddCell(new Cell().Add(p1)).SetBorder(Border.NO_BORDER);
mytable.AddCell(new Cell().Add(p2)).SetBorder(Border.NO_BORDER);
// SetBorderTop(Border.NO_BORDER).SetBorderLeft(Border.NO_BORDER).SetBorderRight(Border.NO_BORDER);
return mytable;
}
I have also tried mytable.AddCell(new Cell().Add(p2)).SetBorderTop(Border.NO_BORDER).SetBorderLeft(Border.NO_BORDER).SetBorderRight(Border.NO_BORDER); and various similar combinations on the table object, but I still get the borders.
For completion here is the routine that calls this function
public Byte[] AddPageNumbers(Byte[] firstpass, string doctitle) {
//firstpass = array of the original pdfdocument
// doctitle = text on left of table
int i;
float x = 30;
float y = 810;
MemoryStream ms2 = new MemoryStream(firstpass);
PdfReader reader = new PdfReader(ms2);
MemoryStream ms3 = new MemoryStream();
PdfDocument pdfDoc = new PdfDocument(reader, new PdfWriter(ms3));
Document document = new Document(pdfDoc, PageSize.A4, false);
int n = pdfDoc.GetNumberOfPages();
for (i = 3; i <= n; i++)
{
Paragraph header;
//PdfPage page = pdfDoc.GetPage(i);
//header = new Paragraph(String.Format(doctitle + " Page {0} of {1}", i, n));
Table table;
PdfPage page = pdfDoc.GetPage(i);
table = makepagetable(doctitle, i, n);
header = new Paragraph().Add(table);
document.ShowTextAligned(header,x,y, i, TextAlignment.JUSTIFIED, VerticalAlignment.MIDDLE, 0);
}
document.Close();
pdfDoc.Close();
return ms3.ToArray();
}

Borderless Table or Cell, for c# and iText7, you can use:
//Table with no border
table.SetBorder(Border.NO_BORDER);
//Cell with no border
cell.SetBorder(Border.NO_BORDER);
I review your code:
//your source code
mytable.AddCell(new Cell().Add(p1)).SetBorder(Border.NO_BORDER);
//changed code
mytable.AddCell(new Cell().Add(p1).SetBorder(Border.NO_BORDER));
Hope this is helpful.

Compression of Splited PDF Files

How to compress a sliced pdf documents in c#..??
i have a pdf document. i am slicing that document. if the orginal pdf document size 10 mb after slicing size is increasing to 15 mb. thats why i have to compress the sliced document. is any way to compress..?? please help me..
public int ExtractPages(string sourcePdfPath, string DestinationFolder)
{
int p = 0, initialcount = 0;
try
{
iTextSharp.text.Document document;
iTextSharp.text.pdf.PdfReader reader = new iTextSharp.text.pdf.PdfReader(new iTextSharp.text.pdf.RandomAccessFileOrArray(sourcePdfPath), new ASCIIEncoding().GetBytes(""));
if (!Directory.Exists(DestinationFolder))
{
Directory.CreateDirectory(DestinationFolder);
}
else
{
DirectoryInfo di = new DirectoryInfo(DestinationFolder);
initialcount = di.GetFiles("*.pdf", SearchOption.AllDirectories).Length;
}
for (p = 1; p <= reader.NumberOfPages; p++)
{
using (MemoryStream memoryStream = new MemoryStream())
{
document = new iTextSharp.text.Document();
iTextSharp.text.pdf.PdfWriter writer = iTextSharp.text.pdf.PdfWriter.GetInstance(document, memoryStream);
writer.SetPdfVersion(iTextSharp.text.pdf.PdfWriter.PDF_VERSION_1_2);
writer.CompressionLevel = iTextSharp.text.pdf.PdfStream.BEST_COMPRESSION;
writer.SetFullCompression();
document.SetPageSize(reader.GetPageSize(p));
document.NewPage();
document.Open();
document.AddDocListener(writer);
iTextSharp.text.pdf.PdfContentByte cb = writer.DirectContent;
iTextSharp.text.pdf.PdfImportedPage pageImport = writer.GetImportedPage(reader, p);
int rot = reader.GetPageRotation(p);
if (rot == 90 || rot == 270)
{
cb.AddTemplate(pageImport, 0, -1.0F, 1.0F, 0, 0, reader.GetPageSizeWithRotation(p).Height);
}
else
{
cb.AddTemplate(pageImport, 1.0F, 0, 0, 1.0F, 0, 0);
}
document.Close();
document.Dispose();
File.WriteAllBytes(DestinationFolder + "/" + p + ".pdf", memoryStream.ToArray());
}
}
reader.Close();
reader.Dispose();
}
catch
{
}
finally
{
GC.Collect();
}
if (initialcount > (p - 1))
{
for (int k = (p - 1) + 1; k <= initialcount; k++)
{
try
{
File.Delete(DestinationFolder + "/" + k + ".pdf");
}
catch
{
}
}
}
return p - 1;
}

First of all you should not use PdfWriter with GetImportedPage and its direct content with AddTemplate for a task like that at hand. Instead have a look at the Webified iTextSharp Examples of iText in Action — 2nd Edition.
There you'll find the sample Burst.cs with the central code
PdfReader reader = new PdfReader(pdf);
// loop over all the pages in the original PDF
int n = reader.NumberOfPages;
for (int i = 0; i < n; i++)
{
using (MemoryStream ms = new MemoryStream())
{
// We'll create as many new PDFs as there are pages
using (Document document = new Document())
{
using (PdfCopy copy = new PdfCopy(document, ms))
{
document.Open();
copy.AddPage(copy.GetImportedPage(reader, i + 1));
}
}
// store ms.ToArray() somewhere
}
}
(I removed some ZIP file packing those webified samples use.)
As you see, no need anymore to deal with page rotations or anything.
Now this all being said, the sum of the sizes of the individual files will very likely be larger than the size of the original file. After all, in the original file resources could be shared. E,g, a font used on all pages only needed to be embedded once while in the split documents the font has to be embedded in each individual document with a page on which that font is used.
PS: If keeping meta information is important, you might want to use PdfReader.selectPages and PdfStamper instead. For this I only have Java code:
for (int i = 1; i <= TEST_FILE_PAGES; i++)
{
FileOutputStream fos = new FileOutputStream(String.format("%03d.pdf", i));
PdfReader reader = new PdfReader(TEST_FILE);
reader.selectPages(Collections.singletonList(i));
PdfStamper stamper = new PdfStamper(reader, fos);
stamper.close();
fos.close();
}
This keeps the PDF meta information and, therefore, might be more apropos depending on your requirements. It is much slower, though, as for each page export the PdfReader contents are manipulated and, therefore, have to be re-read for exporting the next page.

Convert Pdf file pages to Images with itextsharp

I want to convert Pdf pages in Images using ItextSharp lib.
Have any idea how to convert each page in image file

iText/iTextSharp can generate and/or modify existing PDFs but they do not perform any rendering which is what you are looking for. I would recommend checking out Ghostscript or some other library that knows how to actually render a PDF.

you can use ImageMagick convert pdf to image
convert -density 300 "d:\1.pdf" -scale #1500000 "d:\a.jpg"
and split pdf can use itextsharp
here is the code from others.
void SplitePDF(string filepath)
{
iTextSharp.text.pdf.PdfReader reader = null;
int currentPage = 1;
int pageCount = 0;
//string filepath_New = filepath + "\\PDFDestination\\";
System.Text.UTF8Encoding encoding = new System.Text.UTF8Encoding();
//byte[] arrayofPassword = encoding.GetBytes(ExistingFilePassword);
reader = new iTextSharp.text.pdf.PdfReader(filepath);
reader.RemoveUnusedObjects();
pageCount = reader.NumberOfPages;
string ext = System.IO.Path.GetExtension(filepath);
for (int i = 1; i <= pageCount; i++)
{
iTextSharp.text.pdf.PdfReader reader1 = new iTextSharp.text.pdf.PdfReader(filepath);
string outfile = filepath.Replace((System.IO.Path.GetFileName(filepath)), (System.IO.Path.GetFileName(filepath).Replace(".pdf", "") + "_" + i.ToString()) + ext);
reader1.RemoveUnusedObjects();
iTextSharp.text.Document doc = new iTextSharp.text.Document(reader.GetPageSizeWithRotation(currentPage));
iTextSharp.text.pdf.PdfCopy pdfCpy = new iTextSharp.text.pdf.PdfCopy(doc, new System.IO.FileStream(outfile, System.IO.FileMode.Create));
doc.Open();
for (int j = 1; j <= 1; j++)
{
iTextSharp.text.pdf.PdfImportedPage page = pdfCpy.GetImportedPage(reader1, currentPage);
pdfCpy.SetFullCompression();
pdfCpy.AddPage(page);
currentPage += 1;
}
doc.Close();
pdfCpy.Close();
reader1.Close();
reader.Close();
}
}

You can use Ghostscript
to convert the PDF files into Images, I used the following parameters to convert the needed PDF into tiff image with multiple frames :
gswin32c.exe -sDEVICE=tiff12nc -dBATCH -r200 -dNOPAUSE -sOutputFile=[Output].tiff [PDF FileName]
Also you can use the -q parameter for silent mode
You can get more information about its output devices from here
After that I can easily load the tiff frames like the following
using (FileStream stream = new FileStream(#"C:\tEMP\image_$i.tiff", FileMode.Open, FileAccess.Read, FileShare.Read))
{
BitmapDecoder dec = BitmapDecoder.Create(stream, BitmapCreateOptions.IgnoreImageCache, BitmapCacheOption.None);
BitmapEncoder enc = BitmapEncoder.Create(dec.CodecInfo.ContainerFormat);
enc.Frames.Add(dec.Frames[frameIndex]);
}

I did it with MuPDFCore NuGet. Here is the link to guide I used : https://giorgiobianchini.com/MuPDFCore/MuPDFCore.pdf
using System;
using System.Threading.Tasks;
using MuPDFCore;
using VectSharp.Raster;
MuPDFContext context = new MuPDFContext();
MuPDFDocument document = new MuPDFDocument(context, #"C:\install\test.pdf");
//Renderers: one per page
MuPDFMultiThreadedPageRenderer[] renderers = new MuPDFMultiThreadedPageRenderer[document.Pages.Count];
//Page size: one per page
RoundedSize[] renderedPageSizes = new RoundedSize[document.Pages.Count];
//Boundaries of the tiles that make up each page: one array per page, with one element per thread
RoundedRectangle[][] tileBounds = new RoundedRectangle[document.Pages.Count][];
//Addresses of the memory areas where the image data of the tiles will be stored: one array per page, with one element per thread
IntPtr[][] destinations = new IntPtr[document.Pages.Count][];
//Cycle through the pages in the document to initialise everything
for (int i = 0; i < document.Pages.Count; i++)
{
//Initialise the renderer for the current page, using two threads (total number of threads: number of pages x 2
renderers[i] = document.GetMultiThreadedRenderer(i, 2);
//Determine the boundaries of the page when it is rendered with a 1.5x zoom factor
RoundedRectangle roundedBounds = document.Pages[i].Bounds.Round(2);//quality ..can use 0.5 ,1 etc.
renderedPageSizes[i] = new RoundedSize(roundedBounds.Width, roundedBounds.Height);
//Determine the boundaries of each tile by splitting the total size of the page by the number of threads.
tileBounds[i] = renderedPageSizes[i].Split(renderers[i].ThreadCount);
destinations[i] = new IntPtr[renderers[i].ThreadCount];
for (int j = 0; j < renderers[i].ThreadCount; j++)
{
//Allocate the required memory for the j-th tile of the i-th page.
//Since we will be rendering with a 24-bit-per-pixel format, the required memory in bytes is height x width x 3.
destinations[i][j] = System.Runtime.InteropServices.Marshal.AllocHGlobal(tileBounds[i][j].Height * tileBounds[i][j].Width * 3);
}
}
//Start the actual rendering operations in parallel.
Parallel.For(0, document.Pages.Count, i =>
{
renderers[i].Render(renderedPageSizes[i], document.Pages[i].Bounds, destinations[i], PixelFormats.RGB);
});
//The code in this for-loop is not really part of MuPDFCore - it just shows an example of using VectSharp to "stitch" the tiles up and produce the full image.
for (int i = 0; i < document.Pages.Count; i++)
{
//Create a new (empty) image to hold the whole page.
VectSharp.Page renderedPage = new VectSharp.Page(renderedPageSizes[i].Width,
renderedPageSizes[i].Height);
//Draw each tile onto the image.
for (int j = 0; j < renderers[i].ThreadCount; j++)
{
//Create a raster image object containing the pixel data. Yay, we do not need to copy/marshal anything!
VectSharp.RasterImage tile = new VectSharp.RasterImage(destinations[i][j], tileBounds[i][j].Width,
tileBounds[i][j].Height, false, false);
//Draw the tile on the main image page.
renderedPage.Graphics.DrawRasterImage(tileBounds[i][j].X0, tileBounds[i][j].Y0, tile);
}
//Save the full page as a PNG image.
renderedPage.SaveAsPNG(#"C:\install\page"+ i.ToString() + ".png");
}
//Clean-up code.
for (int i = 0; i < document.Pages.Count; i++)
{
//Release the allocated memory.
for (int j = 0; j < renderers[i].ThreadCount; j++)
{
System.Runtime.InteropServices.Marshal.FreeHGlobal(destinations[i][j]);
}
//Release the renderer (if you skip this, the quiescent renderer’s threads will not be stopped, and your application will never exit!
renderers[i].Dispose();
}
document.Dispose();
context.Dispose();
}

you can extract Image from PDF
and save as JPG
here is the sample code
you need Itext Sharp
public IEnumerable<System.Drawing.Image> ExtractImagesFromPDF(string sourcePdf)
{
// NOTE: This will only get the first image it finds per page.
var pdf = new PdfReader(sourcePdf);
var raf = new RandomAccessFileOrArray(sourcePdf);
try
{
for (int pageNum = 1; pageNum <= pdf.NumberOfPages; pageNum++)
{
PdfDictionary pg = pdf.GetPageN(pageNum);
// recursively search pages, forms and groups for images.
PdfObject obj = ExtractImagesFromPDF_FindImageInPDFDictionary(pg);
if (obj != null)
{
int XrefIndex = Convert.ToInt32(((PRIndirectReference)obj).Number.ToString(CultureInfo.InvariantCulture));
PdfObject pdfObj = pdf.GetPdfObject(XrefIndex);
PdfStream pdfStrem = (PdfStream)pdfObj;
PdfImageObject pdfImage = new PdfImageObject((PRStream)pdfStrem);
System.Drawing.Image img = pdfImage.GetDrawingImage();
yield return img;
}
}
}
finally
{
pdf.Close();
raf.Close();
}
}

Using itextsharp to split a pdf into smaller pdf's based on size

So we have some really inefficient code that splits a pdf into smaller chunks based on a maximum size allowed. Aka. if the max size is 10megs, an 8 meg file would be skipped, while a 16 meg file would be split based on the number of pages.
This is code that I inherited and feel like there has got to be a more efficient way to do this that requiring only one method and less instantiation of objects.
We use the following code to call the methods:
List<int> splitPoints = null;
List<byte[]> documents = null;
splitPoints = this.GetPDFSplitPoints(currentDocument, maxSize);
documents = this.SplitPDF(currentDocument, maxSize, splitPoints);
Methods:
private List<int> GetPDFSplitPoints(IClaimDocument currentDocument, int maxSize)
{
List<int> splitPoints = new List<int>();
PdfReader reader = null;
Document document = null;
int pagesRemaining = currentDocument.Pages;
while (pagesRemaining > 0)
{
reader = new PdfReader(currentDocument.Data);
document = new Document(reader.GetPageSizeWithRotation(1));
using (MemoryStream ms = new MemoryStream())
{
PdfCopy copy = new PdfCopy(document, ms);
PdfImportedPage page = null;
document.Open();
//Add pages until we run out from the original
for (int i = 0; i < currentDocument.Pages; i++)
{
int currentPage = currentDocument.Pages - (pagesRemaining - 1);
if (pagesRemaining == 0)
{
//The whole document has bee traversed
break;
}
page = copy.GetImportedPage(reader, currentPage);
copy.AddPage(page);
//If the current collection of pages exceeds the maximum size, we save off the index and start again
if (copy.CurrentDocumentSize > maxSize)
{
if (i == 0)
{
//One page is greater than the maximum size
throw new Exception("one page is greater than the maximum size and cannot be processed");
}
//We have gone one page too far, save this split index
splitPoints.Add(currentDocument.Pages - (pagesRemaining - 1));
break;
}
else
{
pagesRemaining--;
}
}
page = null;
document.Close();
document.Dispose();
copy.Close();
copy.Dispose();
copy = null;
}
}
if (reader != null)
{
reader.Close();
reader = null;
}
document = null;
return splitPoints;
}
private List<byte[]> SplitPDF(IClaimDocument currentDocument, int maxSize, List<int> splitPoints)
{
var documents = new List<byte[]>();
PdfReader reader = null;
Document document = null;
MemoryStream fs = null;
int pagesRemaining = currentDocument.Pages;
while (pagesRemaining > 0)
{
reader = new PdfReader(currentDocument.Data);
document = new Document(reader.GetPageSizeWithRotation(1));
fs = new MemoryStream();
PdfCopy copy = new PdfCopy(document, fs);
PdfImportedPage page = null;
document.Open();
//Add pages until we run out from the original
for (int i = 0; i <= currentDocument.Pages; i++)
{
int currentPage = currentDocument.Pages - (pagesRemaining - 1);
if (pagesRemaining == 0)
{
//We have traversed all pages
//The call to copy.Close() MUST come before using fs.ToArray() because copy.Close() finalizes the document
fs.Flush();
copy.Close();
documents.Add(fs.ToArray());
document.Close();
fs.Dispose();
break;
}
page = copy.GetImportedPage(reader, currentPage);
copy.AddPage(page);
pagesRemaining--;
if (splitPoints.Contains(currentPage + 1) == true)
{
//Need to start a new document
//The call to copy.Close() MUST come before using fs.ToArray() because copy.Close() finalizes the document
fs.Flush();
copy.Close();
documents.Add(fs.ToArray());
document.Close();
fs.Dispose();
break;
}
}
copy = null;
page = null;
fs.Dispose();
}
if (reader != null)
{
reader.Close();
reader = null;
}
if (document != null)
{
document.Close();
document.Dispose();
document = null;
}
if (fs != null)
{
fs.Close();
fs.Dispose();
fs = null;
}
return documents;
}
As far as I can tell, the only code online that I can see is VB and doesn't necessarily address the size issue.
UPDATE:
We're experiencing OutofMemory exceptions and I believe it's an issue with the Large Object Heap. So one thought was to reduce the code footprint and that would possibly reduce the number of large objects on the heap.
Basically this is part of a loop that goes through any number of PDF's, and then splits them and stores them in the database. Right now, we had to change the method from doing all of them at once (last run was 97 pdf's of various sizes), to running 5 pdf's through the system every 5 minutes. This is not ideal and won't scale well when we ramp up the tool to more clients.
(we're dealing with 50 -100 meg pdf's, but they could be larger).

I also inherited this exact code, and there appears to be a major flaw in it. In the GetPDFSplitPoints method, it's checking the total size of the copied pages against maxsize to determine at which page to split the file.
In the SplitPDF method, when it reaches the page where the split occurs, sure enough the MemoryStream at that point is below the maximum size allowed, and one more page would put it over the limit. But after document.Close(); is executed, much more is added to the MemoryStream (in one example PDF I worked with, the Length of the MemoryStream went from 9 MB to 19 MB before and after the document.Close). My understanding is that all the necessary resources for the copied pages are added upon Close.
I'm guessing I'll have to rewrite this code completely to ensure I don't exceed the max size while retaining the integrity of the original pages.

Using iTextSharp to add repeating data to an existing PDF?

I am going to be using iTextSharp to insert data to a PDF that the Graphics department has created. Most of this data is simple data-to-field mapping, but some data is a list of items that needs to be added (e.g. product data; users can have any number of products and the data needs to be displayed for all of them).
Is it possible to do this with iTextSharp? The PDF template cannot, obviously, be created with a certain number of fields as there is no way of knowing how many fields there will be - it could be 1, or 10, or even 100; what I need to be able to do is "re-use" a section of the PDF and repeat that section for each item within a loop.
Is that doable?

In the past I needed to do something similar. I needed to create a PDF with an unknown number of images + content. In my case an 'Entry' was defined by an image and a set of fields.
What I did is I had a doc. that served as a 'Entry' template. I then generated a temp. pdf file for each 'Entry', and stored the generated file names in a List.
After all 'Entries' were processed I then merged all temporary pdf docs, into one final document.
Here is some code to give you a better idea (it's not compilable, just serves as a ref, as I took certain parts from my older project).
List<string> files = new List<string>(); // list of files to merge
foreach (string pageId in pages)
{
// create an intermediate page
string intermediatePdf = Path.Combine(_tempPath, System.Guid.NewGuid() + ".pdf");
files.Add(intermediatePdf);
string pdfTemplate = Path.Combine(_templatePath, _template);
CreatePage(pdfTemplate, intermediatePdf, pc, pageValues, imageMap, tmd);
}
// merge into resulting pdf file
string outputFolder = "~/Output/";
if (preview)
{
outputFolder = "~/temp/";
}
string pdfResult = Path.Combine(HttpContext.Current.Server.MapPath(outputFolder), Guid.NewGuid().ToString() + ".pdf");
PdfMerge.MergeFiles(pdfResult, files);
//////////////////////////////////////////////////////////////////////////
// delete temporary files...
foreach (string fd in files)
{
File.Delete(fd);
}
return pdfResult;
Here is the code to merge the templates:
public class PdfMerge
{
public static void MergeFiles(string destinationFile, List<string> sourceFiles)
{
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;
// 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.Count)
{
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.Count)
{
reader = new PdfReader(sourceFiles[f]);
// we retrieve the total number of pages
n = reader.NumberOfPages;
}
}
// step 5: we close the document
document.Close();
}
}
Hope it helps!