org.apache.pdfbox.pdmodel.font.PDType3Font Java Examples

private Shape calculateFontBounds(TextPosition text) throws IOException
{
    // glyph space -> user space
    // note: text.getTextMatrix() is *not* the Text Matrix, it's the Text Rendering Matrix
    AffineTransform at = text.getTextMatrix().createAffineTransform();

    // show rectangle with the real vertical bounds, based on the font bounding box y values
    // usually, the height is identical to what you see when marking text in Adobe Reader
    PDFont font = text.getFont();
    BoundingBox bbox = font.getBoundingBox();

    // advance width, bbox height (glyph space)
    float xadvance = font
        .getWidth(text.getCharacterCodes()[0]); // todo: should iterate all chars
    Rectangle2D.Float rect = new Rectangle2D.Float(0, bbox.getLowerLeftY(), xadvance,
        bbox.getHeight());

    if (font instanceof PDType3Font) {
        // bbox and font matrix are unscaled
        at.concatenate(font.getFontMatrix().createAffineTransform());
    }
    else {
        // bbox and font matrix are already scaled to 1000
        at.scale(1 / 1000f, 1 / 1000f);
    }
    Shape s = at.createTransformedShape(rect);
    s = flipAT.createTransformedShape(s);
    s = rotateAT.createTransformedShape(s);
    return s;
}
 

private static boolean recognizeWithFont(
        @NotNull String[] keywords,
        @NotNull byte[] inputText,
        @NotNull Set<PDFont> pdFonts,
        @NotNull boolean useStrict) {
    final String encodedInput = generateByteString(inputText);
    for (PDFont f : pdFonts) {
        if (Objects.isNull(f)) {
            continue;
        }

        /* do not encode unsupported font */
        if ((f instanceof PDType0Font && ((PDType0Font) f).getDescendantFont() instanceof PDCIDFontType0)
                || f instanceof PDType3Font) {
            continue;
        }

        for (String k : keywords) {
            try {
                final byte[] encodedKeywordBytes = f.encode(k);
                final String encodedKeyword = generateByteString(encodedKeywordBytes);

                if (checkDuplicate(encodedInput, encodedKeyword, useStrict)) {
                    return true;
                }
            } catch (Exception ignored) {
            }
        }
    }
    return false;
}
 

@Override
protected void showType3Glyph(Matrix textRenderingMatrix, PDType3Font font, int code,
        String unicode, Vector displacement) throws IOException
{
    PDGraphicsState state = getGraphicsState();
    RenderingMode renderingMode = state.getTextState().getRenderingMode();
    if (!RenderingMode.NEITHER.equals(renderingMode))
    {
        super.showType3Glyph(textRenderingMatrix, font, code, unicode, displacement);
    }
}
 

/**
 * Called when a glyph is to be processed.This method is intended for overriding in subclasses,
 * the default implementation does nothing.
 *
 * @param textRenderingMatrix the current text rendering matrix, T<sub>rm</sub>
 * @param font the current font
 * @param code internal PDF character code for the glyph
 * @param unicode the Unicode text for this glyph, or null if the PDF does provide it
 * @param displacement the displacement (i.e. advance) of the glyph in text space
 * @throws IOException if the glyph cannot be processed
 */
protected void showGlyph(Matrix textRenderingMatrix, PDFont font, int code, String unicode,
                         Vector displacement) throws IOException
{
    if (font instanceof PDType3Font)
    {
        showType3Glyph(textRenderingMatrix, (PDType3Font)font, code, unicode, displacement);
    }
    else
    {
        showFontGlyph(textRenderingMatrix, font, code, unicode, displacement);
    }
}
 

@Override
protected void writeString(String text, List<TextPosition> textPositions) throws IOException {
    text = text.toLowerCase();
    int index = text.indexOf(mTextToHighlight);
    if (index != -1) {
        PDPage          currentPage     = getCurrentPage();
        PDRectangle     pageBoundingBox = currentPage.getBBox();
        AffineTransform flip            = new AffineTransform();
        flip.translate(0, pageBoundingBox.getHeight());
        flip.scale(1, -1);
        PDRectangle mediaBox    = currentPage.getMediaBox();
        float       mediaHeight = mediaBox.getHeight();
        float       mediaWidth  = mediaBox.getWidth();
        int         size        = textPositions.size();
        while (index != -1) {
            int last = index + mTextToHighlight.length() - 1;
            for (int i = index; i <= last; i++) {
                TextPosition      pos  = textPositions.get(i);
                PDFont            font = pos.getFont();
                BoundingBox       bbox = font.getBoundingBox();
                Rectangle2D.Float rect = new Rectangle2D.Float(0, bbox.getLowerLeftY(), font.getWidth(pos.getCharacterCodes()[0]), bbox.getHeight());
                AffineTransform   at   = pos.getTextMatrix().createAffineTransform();
                if (font instanceof PDType3Font) {
                    at.concatenate(font.getFontMatrix().createAffineTransform());
                } else {
                    at.scale(1 / 1000.0f, 1 / 1000.0f);
                }
                Shape           shape     = flip.createTransformedShape(at.createTransformedShape(rect));
                AffineTransform transform = mGC.getTransform();
                int             rotation  = currentPage.getRotation();
                if (rotation != 0) {
                    switch (rotation) {
                    case 90:
                        mGC.translate(mediaHeight, 0);
                        break;
                    case 270:
                        mGC.translate(0, mediaWidth);
                        break;
                    case 180:
                        mGC.translate(mediaWidth, mediaHeight);
                        break;
                    default:
                        break;
                    }
                    mGC.rotate(Math.toRadians(rotation));
                }
                mGC.fill(shape);
                if (rotation != 0) {
                    mGC.setTransform(transform);
                }
            }
            index = last < size - 1 ? text.indexOf(mTextToHighlight, last + 1) : -1;
        }
    }
}
 

/**
     * <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();
            }
        }
    }
}
 

/**
 * Called when a glyph is to be processed.This method is intended for overriding in subclasses,
 * the default implementation does nothing.
 *
 * @param textRenderingMatrix the current text rendering matrix, T<sub>rm</sub>
 * @param font the current font
 * @param code internal PDF character code for the glyph
 * @param unicode the Unicode text for this glyph, or null if the PDF does provide it
 * @param displacement the displacement (i.e. advance) of the glyph in text space
 * @throws IOException if the glyph cannot be processed
 */
protected void showType3Glyph(Matrix textRenderingMatrix, PDType3Font font, int code,
                              String unicode, Vector displacement) throws IOException
{
    PDType3CharProc charProc = font.getCharProc(code);
    if (charProc != null)
    {
        processType3Stream(charProc, textRenderingMatrix);
    }
}