Java Code Examples for com.itextpdf.text.pdf.PdfReader#getNumberOfPages()

/**
 * <a href="http://stackoverflow.com/questions/43870545/filling-a-pdf-with-itextsharp-and-then-hiding-the-base-layer">
 * Filling a PDF with iTextsharp and then hiding the base layer
 * </a>
 * <p>
 * This test shows how to cover all content using a white rectangle.
 * </p>
 */
@Test
public void testHideContenUnderRectangle() throws IOException, DocumentException
{
    try (   InputStream resource = getClass().getResourceAsStream("document.pdf");
            OutputStream result = new FileOutputStream(new File(RESULT_FOLDER, "document-hiddenContent.pdf")))
    {
        PdfReader pdfReader = new PdfReader(resource);
        PdfStamper pdfStamper = new PdfStamper(pdfReader, result);
        for (int page = 1; page <= pdfReader.getNumberOfPages(); page++)
        {
            Rectangle pageSize = pdfReader.getPageSize(page);
            PdfContentByte canvas = pdfStamper.getOverContent(page);
            canvas.setColorFill(BaseColor.WHITE);
            canvas.rectangle(pageSize.getLeft(), pageSize.getBottom(), pageSize.getWidth(), pageSize.getHeight());
            canvas.fill();
        }
        pdfStamper.close();
    }
}
 

@Test
public void testIdentity20150211600() throws IOException, DocumentException
{
    try (   InputStream resource = getClass().getResourceAsStream("/mkl/testarea/itext5/extract/20150211600.PDF");
            OutputStream result = new FileOutputStream(new File(RESULT_FOLDER, "20150211600-identity.pdf")))
    {
        PdfReader pdfReader = new PdfReader(resource);
        PdfStamper pdfStamper = new PdfStamper(pdfReader, result);
        PdfContentStreamEditor identityEditor = new PdfContentStreamEditor();

        for (int i = 1; i <= pdfReader.getNumberOfPages(); i++)
        {
            identityEditor.editPage(pdfStamper, i);
        }
        
        pdfStamper.close();
    }
}
 

@Test
public void testIdentityTest3() throws IOException, DocumentException
{
    try (   InputStream resource = getClass().getResourceAsStream("test3.pdf");
            OutputStream result = new FileOutputStream(new File(RESULT_FOLDER, "test3-identity.pdf")))
    {
        PdfReader pdfReader = new PdfReader(resource);
        PdfStamper pdfStamper = new PdfStamper(pdfReader, result);
        PdfContentStreamEditor identityEditor = new PdfContentStreamEditor();

        for (int i = 1; i <= pdfReader.getNumberOfPages(); i++)
        {
            identityEditor.editPage(pdfStamper, i);
        }
        
        pdfStamper.close();
    }
}
 

/**
 * <a href="http://stackoverflow.com/questions/40549977/reading-legacy-word-forms-checkboxes-converted-to-pdf">
 * Reading legacy Word forms checkboxes converted to PDF
 * </a>
 * <br>
 * <a href="https://www.dropbox.com/s/4z7ky3yy2yaj53i/Doc1.pdf?dl=0">
 * Doc1.pdf
 * </a>
 * <p>
 * This test shows how one can extract the sample drawn "checkboxes" from the
 * sample PDF provided by the OP.
 * </p>
 */
@Test
public void testExtractDoc1() throws IOException
{
    try (   InputStream resource = getClass().getResourceAsStream("Doc1.pdf"))
    {
        PdfReader pdfReader = new PdfReader(resource);

        for (int page = 1; page <= pdfReader.getNumberOfPages(); page++)
        {
            System.out.printf("\nPage %s\n====\n", page);

            CheckBoxExtractionStrategy strategy = new CheckBoxExtractionStrategy();
            PdfReaderContentParser parser = new PdfReaderContentParser(pdfReader);
            parser.processContent(page, strategy);

            for (Box box : strategy.getBoxes())
            {
                Vector basePoint = box.getDiagonal().getStartPoint();
                System.out.printf("at %s, %s - %s\n", basePoint.get(Vector.I1), basePoint.get(Vector.I2),
                        box.isChecked() ? "checked" : "unchecked");
            }
        }
    }
}
 

void merge(PdfReader reader) throws IOException
{
    PdfReaderContentParser parser = new PdfReaderContentParser(reader);
    for (int page = 1; page <= reader.getNumberOfPages(); page++)
    {
        merge(reader, parser, page);
    }
}
 

void merge(PdfReader reader) throws IOException
{
    PdfReaderContentParser parser = new PdfReaderContentParser(reader);
    for (int page = 1; page <= reader.getNumberOfPages(); page++)
    {
        merge(reader, parser, page);
    }
}
 

/**
 * <a href="http://stackoverflow.com/questions/37275267/how-to-make-pdf-annotation-as-read-only-using-itext">
 * how to make pdf annotation as read only using itext?
 * </a>
 * <br/>
 * test-annotated.pdf <i>simple PDF with sticky note</i>
 * 
 * <p>
 * This test shows how to set the read-only flags of all annotations of a document.
 * </p>
 */
@Test
public void testMarkAnnotationsReadOnly() throws IOException, DocumentException
{
    try (   InputStream resourceStream = getClass().getResourceAsStream("test-annotated.pdf");
            OutputStream outputStream = new FileOutputStream(new File(RESULT_FOLDER, "test-annotated-ro.pdf"))    )
    {
        PdfReader reader = new PdfReader(resourceStream);
        PdfStamper stamper = new PdfStamper(reader, outputStream);

        for (int page = 1; page <= reader.getNumberOfPages(); page++)
        {
            PdfDictionary pageDictionary = reader.getPageN(page);
            PdfArray annotationArray = pageDictionary.getAsArray(PdfName.ANNOTS);
            if (annotationArray == null)
                continue;
            for (PdfObject object : annotationArray)
            {
                PdfObject directObject = PdfReader.getPdfObject(object);
                if (directObject instanceof PdfDictionary)
                {
                    PdfDictionary annotationDictionary = (PdfDictionary) directObject;
                    PdfNumber flagsNumber = annotationDictionary.getAsNumber(PdfName.F);
                    int flags = flagsNumber != null ? flagsNumber.intValue() : 0;
                    flags |= PdfAnnotation.FLAGS_READONLY;
                    annotationDictionary.put(PdfName.F, new PdfNumber(flags));
                }
            }
        }

        stamper.close();
    }
}
 

public static CropJob createCropJob(ClusterJob curClusterJob) throws IOException {
    File source = curClusterJob.getSource();
    if (source != null && source.exists()) {
        PdfReader reader = new PdfReader(source.getAbsolutePath());
        CropJob result = new CropJob(source, reader.getNumberOfPages(), reader.getInfo(),
            SimpleBookmark.getBookmark(reader));
        reader.close();
        result.setClusterCollection(curClusterJob.getClusterCollection());
        return result;
    }
    return null;
}
 

/**
 * <a href="http://stackoverflow.com/questions/37748346/extract-text-with-itext-not-works-encoding-or-crypted-text">
 * Extract text with iText not works: encoding or crypted text?
 * </a>
 * <br/>
 * <a href="https://dl.dropboxusercontent.com/u/6413030/pb.pdf">
 * pb.pdf
 * </a>
 * <p>
 * The document has not been provided by the OP but by
 * <a href="http://stackoverflow.com/users/1127485/sschuberth">sschuberth</a>
 * in a comment.
 * </p>
 * <p>
 * In contrast to {@link #testPb()}, we here first remove the <b>ToUnicode</b>
 * tables of the fonts. And indeed, now extraction succeeds.
 * </p>
 */
@Test
public void testPbNoToUnicode() throws Exception
{
    InputStream resourceStream = getClass().getResourceAsStream("pb.pdf");
    try
    {
        PdfReader reader = new PdfReader(resourceStream);
        for (int i = 1; i <= reader.getNumberOfPages(); i++)
        {
            PdfDictionary pageResources = reader.getPageResources(i);
            if (pageResources == null)
                continue;
            PdfDictionary pageFonts = pageResources.getAsDict(PdfName.FONT); 
            if (pageFonts == null)
                continue;
            for (PdfName key : pageFonts.getKeys())
            {
                PdfDictionary fontDictionary = pageFonts.getAsDict(key);
                fontDictionary.put(PdfName.TOUNICODE, null);
            }
        }

        String content = extractAndStore(reader, new File(RESULT_FOLDER, "pb-noToUnicode.%s.txt").toString());

        System.out.println("\nText pb.pdf without ToUnicode\n************************");
        System.out.println(content);
        System.out.println("************************");
    }
    finally
    {
        if (resourceStream != null)
            resourceStream.close();
    }
}
 

/**
 * pdf 用文字加水印，存在问题，如何支持中文
 * @author eko.zhan at 2018年9月2日 下午1:44:40
 * @throws FileNotFoundException
 * @throws IOException
 * @throws DocumentException
 */
@Test
public void testVisioAsPdfWithText() throws FileNotFoundException, IOException, DocumentException{
	File inputFile = new File("E:/ConvertTester/TestFiles/I_am_a_vsdx.vsdx");
	File outputFile = new File("E:/ConvertTester/TestFiles/I_am_a_vsdx_libreoffice.pdf");
	if (!outputFile.exists()) {
		convert(inputFile, outputFile);
	}
	File destFile = new File("E:/ConvertTester/TestFiles/I_am_a_vsdx_libreoffice_watermark.pdf");
	//转换成 pdf 后利用 itext 加水印 
	PdfReader reader = new PdfReader(new FileInputStream(outputFile));
	PdfStamper stamper = new PdfStamper(reader, new FileOutputStream(destFile));
	int pageNo = reader.getNumberOfPages();
	Font f = new Font(FontFamily.HELVETICA, 28);
	Phrase p = new Phrase("Xiaoi Robot", f);
	for (int i=1;i<=pageNo;i++) {
		PdfContentByte over = stamper.getOverContent(i);
		over.saveState();
		PdfGState gs1 = new PdfGState();
		gs1.setFillOpacity(0.5f);
		over.setGState(gs1);
		ColumnText.showTextAligned(over, Element.ALIGN_CENTER, p, 297, 450, 0);
		over.restoreState();
	}
	stamper.close();
	reader.close();
}
 

@Test
public void testWithStamperExtFinder() throws DocumentException, IOException
{
    InputStream resourceStream = getClass().getResourceAsStream("test.pdf");
    try
    {
        PdfReader reader = new PdfReader(resourceStream);
        PdfStamper stamper = new PdfStamper(reader, new FileOutputStream(new File(RESULT_FOLDER, "test-trimmed-stamper-ext.pdf")));
        
        // Go through all pages
        int n = reader.getNumberOfPages();
        for (int i = 1; i <= n; i++)
        {
            Rectangle pageSize = reader.getPageSize(i);
            Rectangle rect = getOutputPageSize4(pageSize, reader, i);

            PdfDictionary page = reader.getPageN(i);
            page.put(PdfName.CROPBOX, new PdfArray(new float[]{rect.getLeft(), rect.getBottom(), rect.getRight(), rect.getTop()}));
            stamper.markUsed(page);
        }
        stamper.close();
    }
    finally
    {
        if (resourceStream != null)
            resourceStream.close();
    }
}
 

public PdfMetaInformation(final File source) throws IOException {
    PdfReader reader = new PdfReader(source.getAbsolutePath());
    this.sourcePageCount = reader.getNumberOfPages();
    this.sourceMetaInfo = reader.getInfo();
    this.sourceBookmarks = SimpleBookmark.getBookmark(reader);
    reader.close();

}
 

public static byte[] Merge(File[] documentPaths) throws IOException, DocumentException
{
    byte[] mergedDocument;

    try (ByteArrayOutputStream memoryStream = new ByteArrayOutputStream())
    {
        Document document = new Document();
        PdfSmartCopy pdfSmartCopy = new PdfSmartCopy(document, memoryStream);
        document.open();

        for (File docPath : documentPaths)
        {
            PdfReader reader = new PdfReader(docPath.toString());
            try
            {
                reader.consolidateNamedDestinations();
                int numberOfPages = reader.getNumberOfPages();
                for (int page = 0; page < numberOfPages;)
                {
                    PdfImportedPage pdfImportedPage = pdfSmartCopy.getImportedPage(reader, ++page);
                    pdfSmartCopy.addPage(pdfImportedPage);
                }
            }
            finally
            {
                reader.close();
            }
        }

        document.close();
        mergedDocument = memoryStream.toByteArray();
    }

    return mergedDocument;
}
 

void split(PdfReader reader) throws IOException {
    for (int page = 1; page <= reader.getNumberOfPages(); page++) {
        split(reader, page);
    }
}
 

/**
 * <a href="http://stackoverflow.com/questions/40401800/traverse-whole-pdf-and-change-some-attribute-with-some-object-in-it-using-itext">
 * Traverse whole PDF and change some attribute with some object in it using iText
 * </a>
 * <p>
 * This test shows how to change the color of text of a given color. In this case,
 * black text is changed to green.
 * </p>
 * <p>
 * Beware, this is a proof-of-concept, not a final and complete solution. In particular
 * </p>
 * <ul>
 * <li>Text is considered to be black if for its <code>color</code> the expression
 * <code>BaseColor.BLACK.equals(color)</code> is <code>true</code>; as equality among
 * <code>BaseColor</code> and its descendant classes is not completely well-defined,
 * this might lead to some false positives.
 * <li><code>PdfContentStreamEditor</code> only inspects and edits the content
 * stream of the page itself, not the content streams of displayed form xobjects
 * or patterns; thus, some text may not be found.
 * </ul>
 * <p>
 * Improving the class to properly detect black color and to recursively traverse and
 * edit the content streams of used patterns and xobjects remains as an exercise for
 * the reader.
 * </p> 
 */
@Test
public void testChangeBlackTextToGreenDocument() throws IOException, DocumentException
{
    try (   InputStream resource = getClass().getResourceAsStream("document.pdf");
            OutputStream result = new FileOutputStream(new File(RESULT_FOLDER, "document-blackTextToGreen.pdf")))
    {
        PdfReader pdfReader = new PdfReader(resource);
        PdfStamper pdfStamper = new PdfStamper(pdfReader, result);
        PdfContentStreamEditor editor = new PdfContentStreamEditor()
        {
            @Override
            protected void write(PdfContentStreamProcessor processor, PdfLiteral operator, List<PdfObject> operands) throws IOException
            {
                String operatorString = operator.toString();

                if (TEXT_SHOWING_OPERATORS.contains(operatorString))
                {
                    if (currentlyReplacedBlack == null)
                    {
                        BaseColor currentFillColor = gs().getFillColor();
                        if (BaseColor.BLACK.equals(currentFillColor))
                        {
                            currentlyReplacedBlack = currentFillColor;
                            super.write(processor, new PdfLiteral("rg"), Arrays.asList(new PdfNumber(0), new PdfNumber(1), new PdfNumber(0), new PdfLiteral("rg")));
                        }
                    }
                }
                else if (currentlyReplacedBlack != null)
                {
                    if (currentlyReplacedBlack instanceof CMYKColor)
                    {
                        super.write(processor, new PdfLiteral("k"), Arrays.asList(new PdfNumber(0), new PdfNumber(0), new PdfNumber(0), new PdfNumber(1), new PdfLiteral("k")));
                    }
                    else if (currentlyReplacedBlack instanceof GrayColor)
                    {
                        super.write(processor, new PdfLiteral("g"), Arrays.asList(new PdfNumber(0), new PdfLiteral("g")));
                    }
                    else
                    {
                        super.write(processor, new PdfLiteral("rg"), Arrays.asList(new PdfNumber(0), new PdfNumber(0), new PdfNumber(0), new PdfLiteral("rg")));
                    }
                    currentlyReplacedBlack = null;
                }
                
                super.write(processor, operator, operands);
            }

            BaseColor currentlyReplacedBlack = null;

            final List<String> TEXT_SHOWING_OPERATORS = Arrays.asList("Tj", "'", "\"", "TJ");
        };

        for (int i = 1; i <= pdfReader.getNumberOfPages(); i++)
        {
            editor.editPage(pdfStamper, i);
        }
        
        pdfStamper.close();
    }
}
 

/**
     * <a href="http://stackoverflow.com/questions/43211367/getting-exception-while-redacting-pdf-using-itext">
     * getting exception while redacting pdf using itext
     * </a>
     * <br/>
     * <a href="https://drive.google.com/file/d/0B-zalNTEeIOwM1JJVWctcW8ydU0/view?usp=drivesdk">
     * edited_120192824_5 (1).pdf
     * </a>
     * <p>
     * Indeed, the PdfClean classes throw a {@link NullPointerException} on page
     * 1 of this PDF. As it turns out, the cause is that the PDF makes use of a
     * construct which according to the PDF specification is obsolete and iText,
     * therefore, chose not to support. 
     * </p>
     */
    @Test
    public void testRedactLikeDevAvitesh() throws DocumentException, IOException
    {
//      InputStream resource = new FileInputStream("D:/itext/edited_120192824_5 (1).pdf");
//      OutputStream result = new FileOutputStream(new File(OUTPUTDIR,
//              "aviteshs.pdf"));

        try (   InputStream resource = getClass().getResourceAsStream("edited_120192824_5 (1).pdf");
                OutputStream result = new FileOutputStream(new File(OUTPUTDIR, "edited_120192824_5 (1)-redacted.pdf")) )
        {
            PdfReader reader = new PdfReader(resource);
            PdfStamper stamper = new PdfStamper(reader, result);
            int pageCount = reader.getNumberOfPages();
            Rectangle linkLocation1 = new Rectangle(440f, 700f, 470f, 710f);
            Rectangle linkLocation2 = new Rectangle(308f, 205f, 338f, 215f);
            Rectangle linkLocation3 = new Rectangle(90f, 155f, 130f, 165f);
            List<PdfCleanUpLocation> cleanUpLocations = new ArrayList<PdfCleanUpLocation>();
            for (int currentPage = 1; currentPage <= pageCount; currentPage++) {
                if (currentPage == 1) {
                    cleanUpLocations.add(new PdfCleanUpLocation(currentPage,
                            linkLocation1, BaseColor.BLACK));
                    cleanUpLocations.add(new PdfCleanUpLocation(currentPage,
                            linkLocation2, BaseColor.BLACK));
                    cleanUpLocations.add(new PdfCleanUpLocation(currentPage,
                            linkLocation3, BaseColor.BLACK));
                } else {
                    cleanUpLocations.add(new PdfCleanUpLocation(currentPage,
                            linkLocation1, BaseColor.BLACK));
                }
            }
            PdfCleanUpProcessor cleaner = new PdfCleanUpProcessor(cleanUpLocations,
                    stamper);
            try {
                cleaner.cleanUp();
            } catch (Exception e) {
                e.printStackTrace();
            }
            stamper.close();
            reader.close();
        }
    }
 

/**
   * <a href="https://stackoverflow.com/questions/46120706/when-i-open-a-pdf-in-adobe-acrobat-pro-dc-the-text-is-getting-messed-up-for-pdf">
   * when i open a pdf in adobe acrobat pro Dc the text is getting messed up for pdf creation i used itext5.5.12
   * </a>
   * <p>
   * Test files "1 Loyds.pdf", "2 CRPWLI.pdf", "3 SLC Dec.pdf", "4 Schedule.pdf",
   * and "5 Sched of INS.pdf" were received via e-mail from Kishore Rachakonda
   * ([email protected]) on 2017-09-11 17:31.
   * </p>
   * <p>
   * This test is a port of the Ruby-on-Rails merge routine provided by the OP.
   * The result does not have the problem described by the OP.
   * </p>
   * <p>
   * Later it became clear that the OP's merge result was post-processed by at
   * least two other programs, and one of those post processors appears to have
   * optimized the use of embedded fonts. Unfortunately "5 Sched of INS.pdf" is
   * not a completely valid PDF: It uses an embedded subset of a font but does
   * not mark the font name accordingly. Thus, the optimizing post processor
   * added this mere font subset (assuming it to be the whole font program) to
   * font resources which require glyphs missing in the subset.
   * </p> 
   */
  @Test
  public void testMergeLikeKishoreSagar() throws IOException, DocumentException {
      try (   InputStream resource1 = getClass().getResourceAsStream("1 Loyds.pdf");
              InputStream resource2 = getClass().getResourceAsStream("2 CRPWLI.pdf");
              InputStream resource3 = getClass().getResourceAsStream("3 SLC Dec.pdf");
              InputStream resource4 = getClass().getResourceAsStream("4 Schedule.pdf");
              InputStream resource5 = getClass().getResourceAsStream("5 Sched of INS.pdf");
              OutputStream result = new FileOutputStream(new File(RESULT_FOLDER, "mergeLikeKishoreSagar.pdf"))) {
          InputStream[] pdf_files = {resource1, resource2, resource3, resource4, resource5};

          Document doc = new Document();
          PdfCopy pdf_copy = new PdfCopy(doc, result);
          doc.open();
          
          for (InputStream pdf : pdf_files) {
              PdfReader reader = new PdfReader(pdf);
              int pages = reader.getNumberOfPages();
              for (int p = 1; p <= pages; p++)
                  pdf_copy.addPage(pdf_copy.getImportedPage(reader, p));
              reader.close();
          }

          doc.close();
      }

      /* ported from the original:
doc =Document.new
pdf_copy = PdfCopy.new(doc, FileStream.new(@output_filename))
doc.open
@pdf_files.each do |pdf|
  reader = PdfReader.new(pdf)
  pages = reader.getNumberOfPages()
  (1..pages).each do |p|
    pdf_copy.addPage(pdf_copy.getImportedPage(reader, p))
  end
  reader.close
end
doc.close
       */
  }
 

/**
 * pdf 用图片加水印
 * @author eko.zhan at 2018年9月2日 下午1:44:58
 * @throws FileNotFoundException
 * @throws IOException
 * @throws DocumentException
 */
@Test
public void testVisioAsPdfWithImg() throws FileNotFoundException, IOException, DocumentException{
	File inputFile = new File("E:/ConvertTester/TestFiles/I_am_a_vsdx.vsdx");
	File outputFile = new File("E:/ConvertTester/TestFiles/I_am_a_vsdx_libreoffice.pdf");
	if (!outputFile.exists()) {
		convert(inputFile, outputFile);
	}
	File destFile = new File("E:/ConvertTester/TestFiles/I_am_a_vsdx_libreoffice_watermark.pdf");
	final String IMG = "D:\\Xiaoi\\logo\\logo.png";
	//转换成 pdf 后利用 itext 加水印 
	PdfReader reader = new PdfReader(new FileInputStream(outputFile));
	PdfStamper stamper = new PdfStamper(reader, new FileOutputStream(destFile));
	int pageNo = reader.getNumberOfPages();
	// text watermark
	Font f = new Font(FontFamily.HELVETICA, 30);
	Phrase p = new Phrase("Xiaoi Robot Image", f);
	// image watermark
	Image img = Image.getInstance(IMG);
	float w = img.getScaledWidth();
	float h = img.getScaledHeight();
	// transparency
	PdfGState gs1 = new PdfGState();
	gs1.setFillOpacity(0.5f);
	// properties
	PdfContentByte over;
	Rectangle pagesize;
	float x, y;
	// loop over every page
	for (int i = 1; i <= pageNo; i++) {
		pagesize = reader.getPageSizeWithRotation(i);
		x = (pagesize.getLeft() + pagesize.getRight()) / 2;
		y = (pagesize.getTop() + pagesize.getBottom()) / 2;
		over = stamper.getOverContent(i);
		over.saveState();
		over.setGState(gs1);
		if (i % 2 == 1)
			ColumnText.showTextAligned(over, Element.ALIGN_CENTER, p, x, y, 0);
		else
			over.addImage(img, w, 0, 0, h, x - (w / 2), y - (h / 2));
		over.restoreState();
	}
	stamper.close();
	reader.close();
}
 

/**
 * <a href="https://stackoverflow.com/questions/47101222/how-to-decode-image-with-asciihexdecode">
 * How to decode image with /ASCIIHexDecode
 * </a>
 * <br/>
 * <a href="https://1drv.ms/b/s!AjcEvFO-aWLMkbtXNVl_rmUXv6nnBQ">
 * test.pdf
 * </a>
 * <p>
 * The issue can be reproduced. Without studying the format
 * of the integrated image in detail, though, it is hard to
 * tell whether this is a bug in iText or a bug in the PDF.
 * </p>
 */
@Test
public void testExtractImageLikeSteveB() throws IOException
{
    try (InputStream resource = getClass().getResourceAsStream("testSteveB.pdf")) {
        PdfReader reader = new PdfReader(resource);
        for (int pageNumber = 1; pageNumber <= reader.getNumberOfPages(); pageNumber++)
        {
            PdfDictionary dictionary = reader.getPageN(pageNumber);
            FindImages(reader, dictionary);
        }
    }
}
 

/**
 * <p>
 * This method restricts the media boxes of the pages in the given {@link PdfReader}
 * to the actual content found by the {@link MarginFinder} extended render listener.
 * </p>
 * <p>
 * It essentially is copied from the {@link TestTrimPdfPage} methods
 * {@link TestTrimPdfPage#testWithStamperExtFinder()} and
 * {@link TestTrimPdfPage#getOutputPageSize4(Rectangle, PdfReader, int)}.
 * In contrast to the code there this method manipulates
 * the media box because this is the only box respected by
 * {@link PdfWriter#getImportedPage(PdfReader, int)}.
 * </p>
 */
static void cropPdf(PdfReader reader) throws IOException
{
    int n = reader.getNumberOfPages();
    for (int i = 1; i <= n; i++)
    {
        PdfReaderContentParser parser = new PdfReaderContentParser(reader);
        MarginFinder finder = parser.processContent(i, new MarginFinder());
        Rectangle rect = new Rectangle(finder.getLlx(), finder.getLly(), finder.getUrx(), finder.getUry());

        PdfDictionary page = reader.getPageN(i);
        page.put(PdfName.MEDIABOX, new PdfArray(new float[]{rect.getLeft(), rect.getBottom(), rect.getRight(), rect.getTop()}));
    }
}