Java Code Examples for com.itextpdf.text.pdf.PdfDictionary#getAsDict()

/**
 * These two methods ({@link #extractAttachments(PdfReader, String)} and
 * {@link #extractAttachment(PdfReader, File, PdfString, PdfDictionary)})
 * essentially are the OP's original code posted in his question. They
 * extract files without the folder structure.
 */
public static void extractAttachments(PdfReader reader, String dir) throws IOException
{
    File folder = new File(dir);
    folder.mkdirs();

    PdfDictionary root = reader.getCatalog();

    PdfDictionary names = root.getAsDict(PdfName.NAMES);
    System.out.println("" + names.getKeys().toString());
    PdfDictionary embedded = names.getAsDict(PdfName.EMBEDDEDFILES);
    System.out.println("" + embedded.toString());

    PdfArray filespecs = embedded.getAsArray(PdfName.NAMES);

    //System.out.println(filespecs.getAsString(root1));
    for (int i = 0; i < filespecs.size();)
    {
        extractAttachment(reader, folder, filespecs.getAsString(i++), filespecs.getAsDict(i++));
    }
}
 

/**
 * <p>
 * These two methods ({@link #extractAttachmentsWithFolders(PdfReader, String)} and
 * {@link #extractAttachment(PdfReader, Map, PdfString, PdfDictionary)}) extend the
 * functionality of the OP's original code posted in his question. They extract files
 * with the folder structure.
 * </p>
 * <p>
 * The information concerning the portfolio folder structure is retrieved using
 * the method {@link #retrieveFolders(PdfReader, File)} and its helper method
 * {@link #collectFolders(Map, PdfDictionary, File)}.
 * </p>
 */
public static void extractAttachmentsWithFolders(PdfReader reader, String dir) throws IOException, DocumentException
{
    File folder = new File(dir);
    folder.mkdirs();

    Map<Integer, File> folders = retrieveFolders(reader, folder);

    PdfDictionary root = reader.getCatalog();

    PdfDictionary names = root.getAsDict(PdfName.NAMES);
    System.out.println("" + names.getKeys().toString());
    PdfDictionary embedded = names.getAsDict(PdfName.EMBEDDEDFILES);
    System.out.println("" + embedded.toString());

    PdfArray filespecs = embedded.getAsArray(PdfName.NAMES);

    for (int i = 0; i < filespecs.size();)
    {
        extractAttachment(reader, folders, folder, filespecs.getAsString(i++), filespecs.getAsDict(i++));
    }
}
 

static Map<Integer, File> retrieveFolders(PdfReader reader, File baseDir) throws DocumentException
{
    Map<Integer, File> result = new HashMap<Integer, File>();

    PdfDictionary root = reader.getCatalog();
    PdfDictionary collection = root.getAsDict(PdfName.COLLECTION);
    if (collection == null)
        throw new DocumentException("Document has no Collection dictionary");
    PdfDictionary folders = collection.getAsDict(FOLDERS);
    if (folders == null)
        throw new DocumentException("Document collection has no folders dictionary");
    
    collectFolders(result, folders, baseDir);

    return result;
}
 

@Override
public void renderText(TextRenderInfo renderInfo)
{
    DocumentFont font =renderInfo.getFont();
    PdfDictionary dict = font.getFontDictionary();
    PdfDictionary encoding = dict.getAsDict(PdfName.ENCODING);
    PdfArray diffs = encoding.getAsArray(PdfName.DIFFERENCES);

    ;
    StringBuilder builder = new StringBuilder();
    for (byte b : renderInfo.getPdfString().getBytes())
    {
        PdfName name = diffs.getAsName((char)b);
        String s = name.toString().substring(2);
        int i = Integer.parseUnsignedInt(s, 16);
        builder.append((char)i);
    }

    try
    {
        stringField.set(renderInfo, builder.toString());
    }
    catch (IllegalArgumentException | IllegalAccessException e)
    {
        e.printStackTrace();
    }
    strategy.renderText(renderInfo);
}
 

/**
 * <p>
 * A primitive attempt at copying links from page <code>sourcePage</code>
 * of <code>PdfReader reader</code> to page <code>targetPage</code> of
 * <code>PdfStamper stamper</code>.
 * </p>
 * <p>
 * This method is meant only for the use case at hand, i.e. copying a link
 * to an external URI without expecting any advanced features.
 * </p>
 */
void copyLinks(PdfStamper stamper, int targetPage, PdfReader reader, int sourcePage)
{
    PdfDictionary sourcePageDict = reader.getPageNRelease(sourcePage);
    PdfArray annotations = sourcePageDict.getAsArray(PdfName.ANNOTS);
    if (annotations != null && annotations.size() > 0)
    {
        for (PdfObject annotationObject : annotations)
        {
            annotationObject = PdfReader.getPdfObject(annotationObject);
            if (!annotationObject.isDictionary())
                continue;
            PdfDictionary annotation = (PdfDictionary) annotationObject;
            if (!PdfName.LINK.equals(annotation.getAsName(PdfName.SUBTYPE)))
                continue;

            PdfArray rectArray = annotation.getAsArray(PdfName.RECT);
            if (rectArray == null || rectArray.size() < 4)
                continue;
            Rectangle rectangle = PdfReader.getNormalizedRectangle(rectArray);

            PdfName hightLight = annotation.getAsName(PdfName.H);
            if (hightLight == null)
                hightLight = PdfAnnotation.HIGHLIGHT_INVERT;

            PdfDictionary actionDict = annotation.getAsDict(PdfName.A);
            if (actionDict == null || !PdfName.URI.equals(actionDict.getAsName(PdfName.S)))
                continue;
            PdfString urlPdfString = actionDict.getAsString(PdfName.URI);
            if (urlPdfString == null)
                continue;
            PdfAction action = new PdfAction(urlPdfString.toString());

            PdfAnnotation link = PdfAnnotation.createLink(stamper.getWriter(), rectangle, hightLight, action);
            stamper.addAnnotation(link, targetPage);
        }
    }
}
 

void show(FdfReader fdfReader)
{
    PdfDictionary catalog = fdfReader.getCatalog();
    catalog = catalog.getAsDict(PdfName.FDF);
    Assert.assertNotNull("FDF catalogue is null", catalog);
    PdfArray annots = catalog.getAsArray(PdfName.ANNOTS);
    Assert.assertNotNull("FDF annotations are null", annots);
    System.out.println(annots);
}
 

/**
 * <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();
    }
}
 

static void collectFolders(Map<Integer, File> collection, PdfDictionary folder, File baseDir)
{
    PdfString name = folder.getAsString(PdfName.NAME);
    File folderDir = new File(baseDir, name.toString());
    folderDir.mkdirs();
    PdfNumber id = folder.getAsNumber(PdfName.ID);
    collection.put(id.intValue(), folderDir);

    PdfDictionary next = folder.getAsDict(PdfName.NEXT);
    if (next != null)
        collectFolders(collection, next, baseDir);
    PdfDictionary child = folder.getAsDict(CHILD);
    if (child != null)
        collectFolders(collection, child, folderDir);
}
 

PdfDictionary getGraphicsStateDictionary(PdfName gsName) {
    PdfDictionary extGStates = resources.getAsDict(PdfName.EXTGSTATE);
    return extGStates.getAsDict(gsName);
}
 

/**
 * <a href="http://stackoverflow.com/questions/28911509/how-to-retain-page-labels-when-concatenating-an-existing-pdf-with-a-pdf-created">
 * How to retain page labels when concatenating an existing pdf with a pdf created from scratch?
 * </a>
 * <p>
 * A proposal how to implement the task using a {@link PdfStamper}.
 */
@Test
public void testInsertTitlePage() throws IOException, DocumentException
{
    try (   InputStream documentStream = getClass().getResourceAsStream("Labels.pdf");
            InputStream titleStream = getClass().getResourceAsStream("Cover.pdf");
            OutputStream outputStream = new FileOutputStream(new File(RESULT_FOLDER, "labels-with-cover-page.pdf"))    )
    {
        PdfReader titleReader = new PdfReader(titleStream);
        PdfReader reader = new PdfReader(documentStream);
        PdfStamper stamper = new PdfStamper(reader, outputStream);

        PdfImportedPage page = stamper.getImportedPage(titleReader, 1);
        stamper.insertPage(1, titleReader.getPageSize(1));
        PdfContentByte content = stamper.getUnderContent(1);
        content.addTemplate(page, 0, 0);
        copyLinks(stamper, 1, titleReader, 1);

        PdfDictionary root = reader.getCatalog();
        PdfDictionary labels = root.getAsDict(PdfName.PAGELABELS);
        if (labels != null)
        {
            PdfArray newNums = new PdfArray();
            
            newNums.add(new PdfNumber(0));
            PdfDictionary coverDict = new PdfDictionary();
            coverDict.put(PdfName.P, new PdfString("Cover Page"));
            newNums.add(coverDict);

            PdfArray nums = labels.getAsArray(PdfName.NUMS);
            if (nums != null)
            {
                for (int i = 0; i < nums.size() - 1; )
                {
                    int n = nums.getAsNumber(i++).intValue();
                    newNums.add(new PdfNumber(n+1));
                    newNums.add(nums.getPdfObject(i++));
                }
            }

            labels.put(PdfName.NUMS, newNums);
            stamper.markUsed(labels);
        }

        stamper.close();
    }
}
 

/**
 * <a href="http://stackoverflow.com/questions/41090131/searching-pdf-for-a-specific-string-in-javascript-action-in-itext">
 * Searching PDF for a specific string in JavaScript action in iText
 * </a>
 * <br/>
 * <a href="http://www21.zippyshare.com/v/RDdOJI97/file.html">
 * file.pdf
 * </a>
 * <p>
 * This test shows how to process the immediate JavaScript code in annotation actions.
 * </p> 
 */
@Test
public void testSearchJsActionInFile() throws IOException
{
    try (   InputStream resource = getClass().getResourceAsStream("file.pdf")   )
    {
        System.out.println("file.pdf - Looking for special JavaScript actions.");
        // Reads and parses a PDF document
        PdfReader reader = new PdfReader(resource);

        // For each PDF page
        for (int i = 1; i <= reader.getNumberOfPages(); i++)
        {
            System.out.printf("\nPage %d\n", i);
            // Get a page a PDF page
            PdfDictionary page = reader.getPageN(i);
            // Get all the annotations of page i
            PdfArray annotsArray = page.getAsArray(PdfName.ANNOTS);

            // If page does not have annotations
            if (annotsArray == null)
            {
                System.out.printf("No annotations.\n", i);
                continue;
            }

            // For each annotation
            for (int j = 0; j < annotsArray.size(); ++j)
            {
                System.out.printf("Annotation %d - ", j);

                // For current annotation
                PdfDictionary curAnnot = annotsArray.getAsDict(j);

                // check if has JS as described below
                PdfDictionary annotationAction = curAnnot.getAsDict(PdfName.A);
                if (annotationAction == null)
                {
                    System.out.print("no action");
                }
                // test if it is a JavaScript action
                else if (PdfName.JAVASCRIPT.equals(annotationAction.get(PdfName.S)))
                {
                    PdfObject scriptObject = annotationAction.getDirectObject(PdfName.JS);
                    if (scriptObject == null)
                    {
                        System.out.print("missing JS entry");
                        continue;
                    }
                    final String script;
                    if (scriptObject.isString())
                        script = ((PdfString)scriptObject).toUnicodeString();
                    else if (scriptObject.isStream())
                    {
                        try (   ByteArrayOutputStream baos = new ByteArrayOutputStream()    )
                        {
                            ((PdfStream)scriptObject).writeContent(baos);
                            script = baos.toString("ISO-8859-1");
                        }
                    }
                    else
                    {
                        System.out.println("malformed JS entry");
                        continue;
                    }

                    if (script.contains("if (this.hostContainer) { try {"))
                        System.out.print("contains test string - ");

                    System.out.printf("\n---\n%s\n---", script);
                    // what here?
                }
                else
                {
                    System.out.print("no JavaScript action");
                }
                System.out.println();
            }
        }
    }
}
 

/**
 * <a href="https://stackoverflow.com/questions/49370352/how-do-i-get-a-get-destination-page-of-a-link-in-pdf-file">
 * How do I get a get destination page of a link in PDF file?
 * </a>
 * <br/>
 * local-link.pdf - output of the test {@link CreateLink}.
 * <p>
 * This test shows how to access data of the target page, once by
 * directly reading from the page dictionary referenced from the
 * link destination, once by first determining the page number and
 * then using {@link PdfReader} helper methods.
 * </p>
 */
@Test
public void testDetermineTargetPage() throws IOException {
    try (   InputStream src = getClass().getResourceAsStream("local-link.pdf")  ) {
        PdfReader reader = new PdfReader(src);
        PdfDictionary page = reader.getPageN(1);
        PdfArray annots = page.getAsArray(PdfName.ANNOTS); 
        for (int i = 0; i < annots.size(); i++) {
            PdfDictionary annotation = annots.getAsDict(i);
            if (PdfName.LINK.equals(annotation.getAsName(PdfName.SUBTYPE))) {
                PdfArray d = annotation.getAsArray(PdfName.DEST);
                if (d == null) {
                    PdfDictionary action = annotation.getAsDict(PdfName.A);
                    if (action != null)
                        d = action.getAsArray(PdfName.D);
                }
                    
                if (d != null && d.size() > 0) {
                    System.out.println("Next destination -");
                    PdfIndirectReference pageReference = d.getAsIndirectObject(0);

                    // Work with target dictionary directly
                    PdfDictionary pageDict = d.getAsDict(0);
                    PdfArray boxArray = pageDict.getAsArray(PdfName.CROPBOX);
                    if (boxArray == null) {
                        boxArray = pageDict.getAsArray(PdfName.MEDIABOX);
                    }
                    Rectangle box = PdfReader.getNormalizedRectangle(boxArray);
                    System.out.printf("* Target page object %s has cropbox %s\n", pageReference, box);

                    // Work via page number
                    for (int pageNr = 1; pageNr <= reader.getNumberOfPages(); pageNr++) {
                        PRIndirectReference pp = reader.getPageOrigRef(pageNr);
                        if (pp.getGeneration() == pageReference.getGeneration() && pp.getNumber() == pageReference.getNumber()) {
                            System.out.printf("* Target page %s has cropbox %s\n", pageNr, reader.getCropBox(pageNr));
                            break;
                        }
                    }
                }
            }
        }
    }
}