Example usage for org.apache.pdfbox.rendering PDFRenderer renderImage

Introduction

In this page you can find the example usage for org.apache.pdfbox.rendering PDFRenderer renderImage.

Prototype

public BufferedImage renderImage(int pageIndex, float scale) throws IOException 

Source Link

Document

Returns the given page as an RGB image at the given scale.

Usage

From source file:com.apache.pdfbox.ocr.tesseract.BadScan.java

License:Apache License

@Test
public void textBadScan() {
    try {//from  w w w .ja  va2  s .  com
        PDDocument document = PDDocument.load(new File("src/test/resources/samples/scansmpl.pdf"));
        PDFRenderer renderer = new PDFRenderer(document);
        BufferedImage image = renderer.renderImage(0, 3);

        TessBaseAPI api = new TessBaseAPI();
        boolean init = api.init("eng");
        api.setBufferedImage(image);
        String text = api.getUTF8Text();
        System.out.println(text);
        api.end();
        assertEquals(init, true);
        document.close();
    } catch (IOException e) {
        e.printStackTrace();
    }
}

---

From source file:com.apache.pdfbox.ocr.tesseract.TessBaseAPITest.java

License:Apache License

@Test
public void textBadScan() {
    try {/*from  ww w.j a  va2s  . co m*/
        PDDocument document = PDDocument.load(new File("src/test/resources/samples/scansmpl.pdf"));
        PDFRenderer renderer = new PDFRenderer(document);
        BufferedImage image = renderer.renderImage(0, 3);

        TessBaseAPI api = new TessBaseAPI();
        boolean init = api.init("eng");
        api.setBufferedImage(image);
        String text = api.getUTF8Text();
        System.out.println(text);
        api.end();
        assertEquals(true, true);
        document.close();
    } catch (IOException e) {
        e.printStackTrace();
    }
}

---

From source file:com.apache.pdfbox.ocr.tesseract.TessBaseAPITest.java

License:Apache License

@Test
public void testBufferedImage() {
    try {//from w w  w  .  java 2  s  .  co  m
        PDDocument document = PDDocument.load(new File("src/test/resources/samples/pdf1.pdf"));
        PDFRenderer renderer = new PDFRenderer(document);
        BufferedImage image = renderer.renderImage(0, 3);

        TessBaseAPI api = new TessBaseAPI();
        boolean init = api.init("eng");
        api.setBufferedImage(image);
        String text = api.getUTF8Text();
        System.out.println(text);
        api.end();
        assertEquals(init, true);
        document.close();
    } catch (IOException e) {
        e.printStackTrace();
    }
}

---

From source file:com.apache.pdfbox.ocr.tesseract.TessBaseAPITest.java

License:Apache License

@Test
public void testByteStream() {
    try {/*from   www . jav  a2 s.co m*/
        PDDocument document = PDDocument.load(new File("src/test/resources/samples/pdf2.pdf"));
        PDFRenderer renderer = new PDFRenderer(document);
        BufferedImage image = renderer.renderImage(0, 3);
        int width = image.getWidth();
        int height = image.getHeight();
        int bpp = 3;
        int bpl = width * 3;

        TessBaseAPI api = new TessBaseAPI();
        byte data[] = api.getByteStream(image);
        boolean init = api.init("eng");
        api.setImage(data, width, height, bpp, bpl);
        String text = api.getUTF8Text();
        System.out.println(text);
        api.end();
        assertEquals(init, true);
        document.close();
    } catch (IOException e) {
        e.printStackTrace();
    }
}

---

From source file:com.apache.pdfbox.ocr.tesseract.TessBaseAPITest.java

License:Apache License

@Test
public void testIterator() {
    try {/*from  w  w  w .  jav  a 2 s.c  om*/
        PDDocument document = PDDocument.load(new File("src/test/resources/samples/pdf3.pdf"));
        PDFRenderer renderer = new PDFRenderer(document);
        BufferedImage image = renderer.renderImage(0, 3);
        TessBaseAPI api = new TessBaseAPI();
        boolean init = api.init("eng");
        api.setBufferedImage(image);
        api.getResultIterator();
        if (api.isResultIteratorAvailable()) {
            do {
                System.out.println(api.getWord().trim());
                String result = api.getBoundingBox();
                System.out.println(result);
            } while (api.resultIteratorNext());
        }
        api.end();
        assertEquals(init, true);
        document.close();
    } catch (IOException e) {
        e.printStackTrace();
    }
}

---

From source file:com.formkiq.core.service.conversion.PdfToPngFormatConverter.java

License:Apache License

@Override
public ConversionResult convert(final Object data, final WorkflowOutputDocumentType inputType,
        final WorkflowOutputDocumentType outputType) throws IOException {

    PDDocument doc = (PDDocument) data;/*from w  ww . j  av  a 2s . co m*/

    PDFRenderer pdfRenderer = new PDFRenderer(doc);

    BufferedImage[] images = new BufferedImage[doc.getNumberOfPages()];

    for (int page = 0; page < doc.getNumberOfPages(); ++page) {
        BufferedImage bim = pdfRenderer.renderImage(page, SCALE);
        images[page] = bim;
    }

    ConversionResult result = merge(images);

    List<ConversionField> fields = findSigningButtons(doc, result);
    result.setFields(fields);

    return result;
}

---

From source file:com.yiyihealth.tools.test.DrawPrintTextLocations.java

License:Apache License

private void stripPage(int page) throws IOException {
    PDFRenderer pdfRenderer = new PDFRenderer(document);
    image = pdfRenderer.renderImage(page, SCALE);

    PDPage pdPage = document.getPage(page);
    PDRectangle cropBox = pdPage.getCropBox();

    // flip y-axis
    flipAT = new AffineTransform();
    flipAT.translate(0, pdPage.getBBox().getHeight());
    flipAT.scale(1, -1);//from  www  .j  a va  2 s .  co m

    // page may be rotated
    rotateAT = new AffineTransform();
    int rotation = pdPage.getRotation();
    if (rotation != 0) {
        PDRectangle mediaBox = pdPage.getMediaBox();
        switch (rotation) {
        case 90:
            rotateAT.translate(mediaBox.getHeight(), 0);
            break;
        case 270:
            rotateAT.translate(0, mediaBox.getWidth());
            break;
        case 180:
            rotateAT.translate(mediaBox.getWidth(), mediaBox.getHeight());
            break;
        default:
            break;
        }
        rotateAT.rotate(Math.toRadians(rotation));
    }

    g2d = image.createGraphics();
    g2d.setStroke(new BasicStroke(0.1f));
    g2d.scale(SCALE, SCALE);

    setStartPage(page + 1);
    setEndPage(page + 1);

    Writer dummy = new OutputStreamWriter(new ByteArrayOutputStream());
    writeText(document, dummy);

    // beads in green
    g2d.setStroke(new BasicStroke(0.4f));
    List<PDThreadBead> pageArticles = pdPage.getThreadBeads();
    for (PDThreadBead bead : pageArticles) {
        PDRectangle r = bead.getRectangle();
        GeneralPath p = r
                .transform(Matrix.getTranslateInstance(-cropBox.getLowerLeftX(), cropBox.getLowerLeftY()));

        Shape s = flipAT.createTransformedShape(p);
        s = rotateAT.createTransformedShape(s);
        g2d.setColor(Color.green);
        g2d.draw(s);
    }

    g2d.dispose();

    String imageFilename = filename;
    int pt = imageFilename.lastIndexOf('.');
    imageFilename = imageFilename.substring(0, pt) + "-marked-" + (page + 1) + ".png";
    ImageIO.write(image, "png", new File(imageFilename));
}

---