Java Code Examples for org.apache.pdfbox.cos.COSName#getPDFName()

/**
 * Returns a unique key for a new resource.
 */
private COSName createKey(COSName kind, String prefix)
{
    COSDictionary dict = (COSDictionary)resources.getDictionaryObject(kind);
    if (dict == null)
    {
        return COSName.getPDFName(prefix + 1);
    }

    // find a unique key
    String key;
    int n = dict.keySet().size();
    do
    {
        ++n;
        key = prefix + n;
    }
    while (dict.containsKey(key));
    return COSName.getPDFName(key);
}
 

/**
 * Removes a class name.
 * 
 * @param className the class name
 */
public void removeClassName(String className)
{
    if (className == null)
    {
        return;
    }
    COSName key = COSName.C;
    COSBase c = this.getCOSObject().getDictionaryObject(key);
    COSName name = COSName.getPDFName(className);
    if (c instanceof COSArray)
    {
        COSArray array = (COSArray) c;
        array.remove(name);
        if ((array.size() == 2) && (array.getInt(1) == 0))
        {
            this.getCOSObject().setItem(key, array.getObject(0));
        }
    }
    else
    {
        COSBase directC = c;
        if (c instanceof COSObject)
        {
            directC = ((COSObject) c).getObject();
        }
        if (name.equals(directC))
        {
            this.getCOSObject().setItem(key, null);
        }
    }
}
 

@Override
public void createImageForm(PDResources imageFormResources, PDResources innerFormResource,
                            PDStream imageFormStream, PDRectangle bbox, AffineTransform at,
                            PDImageXObject img) throws IOException
{
    PDFormXObject imageForm = new PDFormXObject(imageFormStream);
    imageForm.setBBox(bbox);
    imageForm.setMatrix(at);
    imageForm.setResources(imageFormResources);
    imageForm.setFormType(1);

    imageFormResources.getCOSObject().setDirect(true);

    COSName imageFormName = COSName.getPDFName("n2");
    innerFormResource.put(imageFormName, imageForm);
    COSName imageName = imageFormResources.add(img, "img");
    pdfStructure.setImageForm(imageForm);
    pdfStructure.setImageFormName(imageFormName);
    pdfStructure.setImageName(imageName);
    LOG.info("Created image form");
}
 

protected COSName getName(PDColorSpace colorSpace)
{
    if (colorSpace instanceof PDDeviceGray ||
        colorSpace instanceof PDDeviceRGB ||
        colorSpace instanceof PDDeviceCMYK)
    {
        return COSName.getPDFName(colorSpace.getName());
    }
    else
    {
        return resources.add(colorSpace);
    }
}
 

private COSName getName(PDColorSpace colorSpace) throws IOException
{
    if (colorSpace instanceof PDDeviceGray ||
        colorSpace instanceof PDDeviceRGB ||
        colorSpace instanceof PDDeviceCMYK)
    {
        return COSName.getPDFName(colorSpace.getName());
    }
    else
    {
        return resources.add(colorSpace);
    }
}
 

/**
 * This will set the font name.
 *
 * @param fontName The new name for the font.
 */
public void setFontName( String fontName )
{
    COSName name = null;
    if( fontName != null )
    {
        name = COSName.getPDFName( fontName );
    }
    dic.setItem( COSName.FONT_NAME, name );
}
 

/**
 * This will set the font stretch.
 *
 * @param fontStretch The new stretch for the font.
 */
public void setFontStretch( String fontStretch )
{
    COSName name = null;
    if( fontStretch != null )
    {
        name = COSName.getPDFName( fontStretch );
    }
    dic.setItem( COSName.FONT_STRETCH, name );
}
 

/**
 * <a href="https://stackoverflow.com/questions/45812696/pdfbox-delete-comment-maintain-strikethrough">
 * PDFBox delete comment maintain strikethrough
 * </a>
 * <br/>
 * <a href="https://expirebox.com/files/3d955e6df4ca5874c38dbf92fc43b5af.pdf">
 * only_fields.pdf
 * </a>
 * <a href="https://file.io/DTvqhC">
 * (alternative download)
 * </a>
 * <p>
 * The OP only wanted the comment removed, not the strike-through. Thus, we must
 * not remove the annotation but merely the comment building attributes.
 * </p>
 */
@Test
public void testRemoveLikeStephanImproved() throws IOException {
    final COSName POPUP = COSName.getPDFName("Popup");
    try (InputStream resource = getClass().getResourceAsStream("only_fields.pdf")) {
        PDDocument document = Loader.loadPDF(resource);
        List<PDAnnotation> annotations = new ArrayList<>();
        PDPageTree allPages = document.getDocumentCatalog().getPages();

        List<COSObjectable> objectsToRemove = new ArrayList<>();

        for (int i = 0; i < allPages.getCount(); i++) {
            PDPage page = allPages.get(i);
            annotations = page.getAnnotations();

            for (PDAnnotation annotation : annotations) {
                if ("StrikeOut".equals(annotation.getSubtype()))
                {
                    COSDictionary annotationDict = annotation.getCOSObject();
                    COSBase popup = annotationDict.getItem(POPUP);
                    annotationDict.removeItem(POPUP);
                    annotationDict.removeItem(COSName.CONTENTS); // plain text comment
                    annotationDict.removeItem(COSName.RC);       // rich text comment
                    annotationDict.removeItem(COSName.T);        // author

                    if (popup != null)
                        objectsToRemove.add(popup);
                }
            }

            annotations.removeAll(objectsToRemove);
        }

        document.save(new File(RESULT_FOLDER, "only_fields-removeImproved.pdf"));
    }
}
 

/**
 * This will parse a PDF name from the stream.
 *
 * @return The parsed PDF name.
 * @throws IOException If there is an error reading from the stream.
 */
protected COSName parseCOSName() throws IOException
{
    readExpectedChar('/');
    ByteArrayOutputStream buffer = new ByteArrayOutputStream();
    int c = seqSource.read();
    while (c != -1)
    {
        int ch = c;
        if (ch == '#')
        {
            int ch1 = seqSource.read();
            int ch2 = seqSource.read();
            // Prior to PDF v1.2, the # was not a special character.  Also,
            // it has been observed that various PDF tools do not follow the
            // spec with respect to the # escape, even though they report
            // PDF versions of 1.2 or later.  The solution here is that we
            // interpret the # as an escape only when it is followed by two
            // valid hex digits.
            if (isHexDigit((char)ch1) && isHexDigit((char)ch2))
            {
                String hex = Character.toString((char) ch1) + (char) ch2;
                try
                {
                    buffer.write(Integer.parseInt(hex, 16));
                }
                catch (NumberFormatException e)
                {
                    throw new IOException("Error: expected hex digit, actual='" + hex + "'", e);
                }
                c = seqSource.read();
            }
            else
            {
                // check for premature EOF
                if (ch2 == -1 || ch1 == -1)
                {
                    LOG.error("Premature EOF in BaseParser#parseCOSName");
                    c = -1;
                    break;
                }
                seqSource.unread(ch2);
                c = ch1;
                buffer.write(ch);
            }
        }
        else if (isEndOfName(ch))
        {
            break;
        }
        else
        {
            buffer.write(ch);
            c = seqSource.read();
        }
    }
    if (c != -1)
    {
        seqSource.unread(c);
    }
    
    byte[] bytes = buffer.toByteArray();
    String string;
    if (isValidUTF8(bytes))
    {
        string = new String(buffer.toByteArray(), Charsets.UTF_8);
    }
    else
    {
        // some malformed PDFs don't use UTF-8 see PDFBOX-3347
        string = new String(buffer.toByteArray(), Charsets.WINDOWS_1252);
    }
    return COSName.getPDFName(string);
}
 

@Override
public COSBase getCOSObject()
{
    return COSName.getPDFName(getName());
}
 

@Override
public COSBase getCOSObject()
{
    return COSName.getPDFName("ZapfDingbatsEncoding");
}
 

@Override
public COSBase getCOSObject()
{
    return COSName.getPDFName("SymbolEncoding");
}
 

/**
     * <a href="http://stackoverflow.com/questions/42032729/render-type3-font-character-as-image-using-pdfbox">
     * Render Type3 font character as image using PDFBox
     * </a>
     * <br/>
     * <a href="https://drive.google.com/file/d/0B0f6X4SAMh2KRDJTbm4tb3E1a1U/view">
     * 4700198773.pdf
     * </a>
     * from
     * <a href="http://stackoverflow.com/questions/37754112/extract-text-with-custom-font-result-non-readble">
     * extract text with custom font result non readble
     * </a>
     * <p>
     * This test shows how one can render individual Type 3 font glyphs as bitmaps.
     * Unfortunately PDFBox out-of-the-box does not provide a class to render contents
     * of arbitrary XObjects, merely for rendering pages; thus, we simply create a page
     * with the glyph in question and render that page.   
     * </p>
     * <p>
     * As the OP did not provide a sample PDF, we simply use one from another
     * stackoverflow question. There obviously might remain issues with the
     * OP's files.
     * </p>
     */
    @Test
    public void testRender4700198773() throws IOException, NoSuchMethodException, SecurityException, IllegalAccessException, IllegalArgumentException, InvocationTargetException
    {
        Method PDPageContentStreamWrite = PDPageContentStream.class.getSuperclass().getDeclaredMethod("write", String.class);
        PDPageContentStreamWrite.setAccessible(true);

        try (   InputStream resource = getClass().getResourceAsStream("4700198773.pdf"))
        {
            PDDocument document = Loader.loadPDF(resource);

            PDPage page = document.getPage(0);
            PDResources pageResources = page.getResources();
            COSName f1Name = COSName.getPDFName("F1");
            PDType3Font fontF1 = (PDType3Font) pageResources.getFont(f1Name);
            Map<String, Integer> f1NameToCode = fontF1.getEncoding().getNameToCodeMap();

            COSDictionary charProcsDictionary = fontF1.getCharProcs();
            for (COSName key : charProcsDictionary.keySet())
            {
                COSStream stream = (COSStream) charProcsDictionary.getDictionaryObject(key);
                PDType3CharProc charProc = new PDType3CharProc(fontF1, stream);
                PDRectangle bbox = charProc.getGlyphBBox();
                if (bbox == null)
                    bbox = charProc.getBBox();
                Integer code = f1NameToCode.get(key.getName());

                if (code != null)
                {
                    PDDocument charDocument = new PDDocument();
                    PDPage charPage = new PDPage(bbox);
                    charDocument.addPage(charPage);
                    charPage.setResources(pageResources);
                    PDPageContentStream charContentStream = new PDPageContentStream(charDocument, charPage);
                    charContentStream.beginText();
                    charContentStream.setFont(fontF1, bbox.getHeight());
//                    charContentStream.write(String.format("<%2X> Tj\n", code).getBytes());
                    PDPageContentStreamWrite.invoke(charContentStream, String.format("<%2X> Tj\n", code));
                    charContentStream.endText();
                    charContentStream.close();

                    File result = new File(RESULT_FOLDER, String.format("4700198773-%s-%s.png", key.getName(), code));
                    PDFRenderer renderer = new PDFRenderer(charDocument);
                    BufferedImage image = renderer.renderImageWithDPI(0, 96);
                    ImageIO.write(image, "PNG", result);
                    charDocument.save(new File(RESULT_FOLDER, String.format("4700198773-%s-%s.pdf", key.getName(), code)));
                    charDocument.close();
                }
            }
        }
    }
 

/**
 * <a href="http://stackoverflow.com/questions/42032729/render-type3-font-character-as-image-using-pdfbox">
 * Render Type3 font character as image using PDFBox
 * </a>
 * <br/>
 * <a href="https://drive.google.com/file/d/0B0f6X4SAMh2KRDJTbm4tb3E1a1U/view">
 * 4700198773.pdf
 * </a>
 * from
 * <a href="http://stackoverflow.com/questions/37754112/extract-text-with-custom-font-result-non-readble">
 * extract text with custom font result non readble
 * </a>
 * <p>
 * This test shows how one can render individual Type 3 font glyphs as bitmaps.
 * Unfortunately PDFBox out-of-the-box does not provide a class to render contents
 * of arbitrary XObjects, merely for rendering pages; thus, we simply create a page
 * with the glyph in question and render that page.   
 * </p>
 * <p>
 * As the OP did not provide a sample PDF, we simply use one from another
 * stackoverflow question. There obviously might remain issues with the
 * OP's files.
 * </p>
 */
@Test
public void testRenderSdnList() throws IOException, IllegalAccessException, IllegalArgumentException, InvocationTargetException, NoSuchMethodException, SecurityException
{
    Method PDPageContentStreamWrite = PDPageContentStream.class.getSuperclass().getDeclaredMethod("write", String.class);
    PDPageContentStreamWrite.setAccessible(true);

    try (   InputStream resource = getClass().getResourceAsStream("sdnlist.pdf"))
    {
        PDDocument document = Loader.loadPDF(resource);

        PDPage page = document.getPage(1);
        PDResources pageResources = page.getResources();
        COSName f1Name = COSName.getPDFName("R144");
        PDType3Font fontF1 = (PDType3Font) pageResources.getFont(f1Name);
        Map<String, Integer> f1NameToCode = fontF1.getEncoding().getNameToCodeMap();

        COSDictionary charProcsDictionary = fontF1.getCharProcs();
        for (COSName key : charProcsDictionary.keySet())
        {
            COSStream stream = (COSStream) charProcsDictionary.getDictionaryObject(key);
            PDType3CharProc charProc = new PDType3CharProc(fontF1, stream);
            PDRectangle bbox = charProc.getGlyphBBox();
            if (bbox == null)
                bbox = charProc.getBBox();
            Integer code = f1NameToCode.get(key.getName());

            if (code != null)
            {
                PDDocument charDocument = new PDDocument();
                PDPage charPage = new PDPage(bbox);
                charDocument.addPage(charPage);
                charPage.setResources(pageResources);
                PDPageContentStream charContentStream = new PDPageContentStream(charDocument, charPage);
                charContentStream.beginText();
                charContentStream.setFont(fontF1, bbox.getHeight());
                //charContentStream.getOutputStream().write(String.format("<%2X> Tj\n", code).getBytes());
                PDPageContentStreamWrite.invoke(charContentStream, String.format("<%2X> Tj\n", code));
                charContentStream.endText();
                charContentStream.close();

                File result = new File(RESULT_FOLDER, String.format("sdnlist-%s-%s.png", key.getName(), code));
                PDFRenderer renderer = new PDFRenderer(charDocument);
                BufferedImage image = renderer.renderImageWithDPI(0, 96);
                ImageIO.write(image, "PNG", result);
                charDocument.save(new File(RESULT_FOLDER, String.format("sdnlist-%s-%s.pdf", key.getName(), code)));
                charDocument.close();
            }
        }
    }
}