List of usage examples for com.itextpdf.text.pdf PdfContentByte setTextRenderingMode
public void setTextRenderingMode(final int rendering)
From source file:com.automaster.autoview.server.servlet.TextStateOperators.java
/** * Creates a PDF document.//w w w . j av a 2 s.c o m * @param filename the path to the new PDF document * @throws DocumentException * @throws IOException */ public void createPdf(String filename) throws IOException, DocumentException { // step 1 Rectangle rect = new Rectangle(595, 842); Document document = new Document(rect, 30, 30, 30, 30); // step 2 PdfWriter writer = PdfWriter.getInstance(document, new FileOutputStream(filename)); // step 3 document.open(); // step 4 //PdfAcroForm canva = writer.getAcroForm(); BaseFont bf = BaseFont.createFont(); //canva.addMultiLineTextField("txtTeste", "texto de teste vamos ver se le quebra a linha", bf, 15, 300, 800, 100, 100); PdfContentByte canvas = writer.getDirectContent(); String text = "AWAY again"; String text1 = "TESTE Rua alameda luis de sousa santos, N 52, castanhal, CEP: 68742-783, ao lado do posto adriano"; canvas.beginText(); // line 1 canvas.setFontAndSize(bf, 16); canvas.moveText(36, 800); canvas.moveTextWithLeading(0, -24); canvas.setTextRise(10); canvas.showText(text); // line 2 canvas.setWordSpacing(20); canvas.newlineShowText(text); // line 3 canvas.setCharacterSpacing(10); canvas.newlineShowText(text); canvas.setWordSpacing(0); canvas.setCharacterSpacing(0); // line 4 canvas.setHorizontalScaling(50); canvas.newlineShowText(text); canvas.setHorizontalScaling(100); // line 5 canvas.newlineShowText(text); canvas.setTextRise(15); canvas.setFontAndSize(bf, 12); canvas.setColorFill(BaseColor.RED); canvas.showText("2"); canvas.setColorFill(GrayColor.GRAYBLACK); // line 6 canvas.setLeading(56); canvas.setMiterLimit(5); canvas.newlineShowText( "Rua alameda luis de sousa santos, N 52, castanhal, CEP: 68742-783, ao lado do posto" + text); canvas.setLeading(24); canvas.newlineText(); Paragraph paragraph = new Paragraph("teste"); PdfWriter pdfWriter = canvas.getPdfWriter(); PdfAcroForm pdfAcroForm = pdfWriter.getAcroForm(); //pdfAcroForm.addMultiLineTextField("txtTeste", "Changing the adriano leading: Rua alameda luis de sousa santos, N 52, castanhal, CEP: 68742-783, ao lado do posto", bf, 12, 30, 650, 550, 750); //pdfAcroForm.addHiddenField("txtTeste", text); PdfFormField pdfFormField = new PdfFormField(pdfWriter, 30, 650, 550, 750, null); pdfFormField.setFieldName("txtTeste"); pdfFormField.setValueAsString(text1); //TextField textField = new TextField(canvas.getPdfWriter(), new Rectangle(30, 650, 550, 750), "txtTest"); //textField.setText(text); pdfAcroForm.addFormField(pdfFormField); // line 7 PdfTextArray array = new PdfTextArray("A"); array.add(120); array.add("W"); array.add(120); array.add("A"); array.add(95); array.add("Y again"); canvas.showText(array); canvas.endText(); canvas.setColorFill(BaseColor.BLUE); canvas.beginText(); canvas.setTextMatrix(360, 770); canvas.setTextRenderingMode(PdfContentByte.TEXT_RENDER_MODE_FILL); canvas.setFontAndSize(bf, 24); canvas.showText(text); canvas.endText(); canvas.beginText(); canvas.setTextMatrix(360, 730); canvas.setTextRenderingMode(PdfContentByte.TEXT_RENDER_MODE_STROKE); canvas.setFontAndSize(bf, 24); canvas.showText(text); canvas.endText(); canvas.beginText(); canvas.setTextMatrix(360, 690); canvas.setTextRenderingMode(PdfContentByte.TEXT_RENDER_MODE_FILL_STROKE); canvas.setFontAndSize(bf, 24); canvas.showText(text); canvas.endText(); canvas.beginText(); canvas.setTextMatrix(360, 650); canvas.setTextRenderingMode(PdfContentByte.TEXT_RENDER_MODE_INVISIBLE); canvas.setFontAndSize(bf, 24); canvas.showText(text); canvas.endText(); PdfTemplate template = canvas.createTemplate(200, 36); template.setLineWidth(2); for (int i = 0; i < 6; i++) { template.moveTo(0, i * 6); template.lineTo(200, i * 6); } template.stroke(); canvas.saveState(); canvas.beginText(); canvas.setTextMatrix(360, 610); canvas.setTextRenderingMode(PdfContentByte.TEXT_RENDER_MODE_FILL_CLIP); canvas.setFontAndSize(bf, 24); canvas.showText(text); canvas.endText(); canvas.addTemplate(template, 360, 610); canvas.restoreState(); canvas.saveState(); canvas.beginText(); canvas.setTextMatrix(360, 570); canvas.setTextRenderingMode(PdfContentByte.TEXT_RENDER_MODE_STROKE_CLIP); canvas.setFontAndSize(bf, 24); canvas.showText(text); canvas.endText(); canvas.addTemplate(template, 360, 570); canvas.restoreState(); canvas.saveState(); canvas.beginText(); canvas.setTextMatrix(360, 530); canvas.setTextRenderingMode(PdfContentByte.TEXT_RENDER_MODE_FILL_STROKE_CLIP); canvas.setFontAndSize(bf, 24); canvas.showText(text); canvas.endText(); canvas.addTemplate(template, 360, 530); canvas.restoreState(); canvas.saveState(); canvas.beginText(); canvas.setTextMatrix(360, 490); canvas.setTextRenderingMode(PdfContentByte.TEXT_RENDER_MODE_CLIP); canvas.setFontAndSize(bf, 24); canvas.showText(text); canvas.endText(); canvas.addTemplate(template, 360, 490); canvas.restoreState(); // step 5 //document.add((Element) pdfAcroForm); document.close(); }
From source file:com.ephesoft.dcma.imagemagick.MultiPageExecutor.java
License:Open Source License
/** * The <code>addImageToPdf</code> method is used to add image to pdf and make it searchable by adding image text in invisible mode * w.r.t parameter 'isPdfSearchable' passed. * //w ww . j av a 2 s . co m * @param pdfWriter {@link PdfWriter} writer of pdf in which image has to be added * @param htmlUrl {@link HocrPage} corresponding html file for fetching text and coordinates * @param imageUrl {@link String} url of image to be added in pdf * @param isPdfSearchable true for searchable pdf else otherwise * @param widthOfLine */ private void addImageToPdf(PdfWriter pdfWriter, HocrPage hocrPage, String imageUrl, boolean isPdfSearchable, final int widthOfLine) { if (null != pdfWriter && null != imageUrl && imageUrl.length() > 0) { try { LOGGER.info("Adding image" + imageUrl + " to pdf using iText"); Image pageImage = Image.getInstance(imageUrl); float dotsPerPointX = pageImage.getDpiX() / PDF_RESOLUTION; float dotsPerPointY = pageImage.getDpiY() / PDF_RESOLUTION; PdfContentByte pdfContentByte = pdfWriter.getDirectContent(); pageImage.scaleToFit(pageImage.getWidth() / dotsPerPointX, pageImage.getHeight() / dotsPerPointY); pageImage.setAbsolutePosition(0, 0); // Add image to pdf pdfWriter.getDirectContentUnder().addImage(pageImage); pdfWriter.getDirectContentUnder().add(pdfContentByte); // If pdf is to be made searchable if (isPdfSearchable) { LOGGER.info("Adding invisible text for image: " + imageUrl); float pageImagePixelHeight = pageImage.getHeight(); Font defaultFont = FontFactory.getFont(FontFactory.HELVETICA, 8, Font.BOLD, CMYKColor.BLACK); // Fetch text and coordinates for image to be added Map<String, int[]> textCoordinatesMap = getTextWithCoordinatesMap(hocrPage, widthOfLine); Set<String> ketSet = textCoordinatesMap.keySet(); // Add text at specific location for (String key : ketSet) { int[] coordinates = textCoordinatesMap.get(key); float bboxWidthPt = (coordinates[2] - coordinates[0]) / dotsPerPointX; float bboxHeightPt = (coordinates[3] - coordinates[1]) / dotsPerPointY; pdfContentByte.beginText(); // To make text added as invisible pdfContentByte.setTextRenderingMode(PdfContentByte.TEXT_RENDER_MODE_INVISIBLE); pdfContentByte.setLineWidth(Math.round(bboxWidthPt)); // Ceil is used so that minimum font of any text is 1 // For exception of unbalanced beginText() and endText() if (bboxHeightPt > 0.0) { pdfContentByte.setFontAndSize(defaultFont.getBaseFont(), (float) Math.ceil(bboxHeightPt)); } else { pdfContentByte.setFontAndSize(defaultFont.getBaseFont(), 1); } float xCoordinate = (float) (coordinates[0] / dotsPerPointX); float yCoordinate = (float) ((pageImagePixelHeight - coordinates[3]) / dotsPerPointY); pdfContentByte.moveText(xCoordinate, yCoordinate); pdfContentByte.showText(key); pdfContentByte.endText(); } } pdfContentByte.closePath(); } catch (BadElementException badElementException) { LOGGER.error("Error occurred while adding image" + imageUrl + " to pdf using Itext: " + badElementException.toString()); } catch (DocumentException documentException) { LOGGER.error("Error occurred while adding image" + imageUrl + " to pdf using Itext: " + documentException.toString()); } catch (MalformedURLException malformedURLException) { LOGGER.error("Error occurred while adding image" + imageUrl + " to pdf using Itext: " + malformedURLException.toString()); } catch (IOException ioException) { LOGGER.error("Error occurred while adding image" + imageUrl + " to pdf using Itext: " + ioException.toString()); } } }
From source file:com.github.ossdevs.jhocr.converter.HocrPageProcessor.java
License:Open Source License
/** * TODO add documentation describing what this method does actually do. * * @param cb TODO describe this parameter &/ it's purpose. * @param hocrLine is used to process the {@link com.itextpdf.text.pdf.PdfContentByte} * @throws IOException//from w w w.j a va 2 s. c om * @throws DocumentException * @see https://code.google.com/p/jhocr/issues/detail?id=4 */ private void processHocrLine(PdfContentByte cb, HocrLine hocrLine) { try { String lineText = hocrLine.getText(); /** * TODO add documentation */ if (!lineText.isEmpty()) { float lineHeightPt = hocrLine.getBbox().getHeight() / getDotsPerPointY(); float fontSize = Math.round(lineHeightPt) - 0.8f; // Coloquei para o limite de erro if (fontSize == 0) { fontSize = 0.5f; } cb.setFontAndSize(baseFont, fontSize); cb.setTextRenderingMode(PdfContentByte.TEXT_RENDER_MODE_INVISIBLE); cb.beginText(); int t = hocrLine.getWords().size(); /** * TODO add documentation * * @see <a>https://code.google.com/p/jhocr/issues/detail?id=4</a> */ for (int i = 0; i < t; i++) { HocrWord hocrWord = hocrLine.getWords().get(i); float wordWidthPt = hocrWord.getBbox().getWidth() / getDotsPerPointX(); processHocrWordCharacterSpacing(cb, hocrWord, wordWidthPt); float y = (getHocrPage().getBbox().getHeight() + lineHeightPt / 2 - hocrLine.getBbox().getBottom()) / dotsPerPointY; float x = hocrWord.getBbox().getLeft() / getDotsPerPointX(); cb.showTextAligned(PdfContentByte.ALIGN_LEFT, hocrWord.getText(), x, y, 0); } cb.endText(); } } catch (Exception e) { // TODO log error e.printStackTrace(); } }
From source file:com.googlecode.jhocr.converter.HocrPageProcessor.java
License:Open Source License
/** * TODO add documentation describing what this method does actually do. * /* ww w. j av a2 s . c o m*/ * @see https://code.google.com/p/jhocr/issues/detail?id=4 * @param cb * TODO describe this parameter &/ it's purpose. * @param hocrLine * is used to process the {@link com.itextpdf.text.pdf.PdfContentByte} * @throws IOException * @throws DocumentException */ private void processHocrLine(PdfContentByte cb, HocrLine hocrLine) { try { String lineText = hocrLine.getText(); /** * TODO add documentation */ if (!lineText.isEmpty()) { float lineHeightPt = hocrLine.getBbox().getHeight() / getDotsPerPointY(); float fontSize = Math.round(lineHeightPt) - 0.8f; // Coloquei para o limite de erro if (fontSize == 0) { fontSize = 0.5f; } cb.setFontAndSize(baseFont, fontSize); cb.setTextRenderingMode(PdfContentByte.TEXT_RENDER_MODE_INVISIBLE); cb.beginText(); int t = hocrLine.getWords().size(); /** * TODO add documentation * * @see <a>https://code.google.com/p/jhocr/issues/detail?id=4</a> */ for (int i = 0; i < t; i++) { HocrWord hocrWord = hocrLine.getWords().get(i); float wordWidthPt = hocrWord.getBbox().getWidth() / getDotsPerPointX(); processHocrWordCharacterSpacing(cb, hocrWord, wordWidthPt); float y = (getHocrPage().getBbox().getHeight() + lineHeightPt / 2 - hocrLine.getBbox().getBottom()) / dotsPerPointY; float x = hocrWord.getBbox().getLeft() / getDotsPerPointX(); cb.showTextAligned(PdfContentByte.ALIGN_LEFT, hocrWord.getText(), x, y, 0); } cb.endText(); } } catch (Exception e) { // TODO log error e.printStackTrace(); } }
From source file:org.gephi.preview.plugin.renderers.EdgeLabelRenderer.java
License:Open Source License
public void renderPDF(PDFTarget target, String label, float x, float y, Color color, float outlineSize, Color outlineColor) {/* ww w . j a v a 2 s . com*/ PdfContentByte cb = target.getContentByte(); cb.setRGBColorFill(color.getRed(), color.getGreen(), color.getBlue()); BaseFont bf = target.getBaseFont(font); float textHeight = getTextHeight(bf, font.getSize(), label); if (outlineSize > 0) { cb.setTextRenderingMode(PdfContentByte.TEXT_RENDER_MODE_STROKE); cb.setRGBColorStroke(outlineColor.getRed(), outlineColor.getGreen(), outlineColor.getBlue()); cb.setLineWidth(outlineSize); cb.setLineJoin(PdfContentByte.LINE_JOIN_ROUND); cb.setLineCap(PdfContentByte.LINE_CAP_ROUND); if (outlineColor.getAlpha() < 255) { cb.saveState(); float alpha = outlineColor.getAlpha() / 255f; PdfGState gState = new PdfGState(); gState.setStrokeOpacity(alpha); cb.setGState(gState); } cb.beginText(); cb.setFontAndSize(bf, font.getSize()); cb.showTextAligned(PdfContentByte.ALIGN_CENTER, label, x, -y - (textHeight / 2f), 0f); cb.endText(); if (outlineColor.getAlpha() < 255) { cb.restoreState(); } } cb.setTextRenderingMode(PdfContentByte.TEXT_RENDER_MODE_FILL); cb.beginText(); cb.setFontAndSize(bf, font.getSize()); cb.showTextAligned(PdfContentByte.ALIGN_CENTER, label, x, -y - (textHeight / 2f), 0f); cb.endText(); }
From source file:org.gephi.preview.plugin.renderers.NodeLabelRenderer.java
License:Open Source License
public void renderPDF(PDFTarget target, Node node, String label, float x, float y, int fontSize, Color color, float outlineSize, Color outlineColor, boolean showBox, Color boxColor) { Font font = fontCache.get(fontSize); PdfContentByte cb = target.getContentByte(); BaseFont bf = target.getBaseFont(font); //Box/*from w w w . ja v a2 s. co m*/ if (showBox) { cb.setRGBColorFill(boxColor.getRed(), boxColor.getGreen(), boxColor.getBlue()); if (boxColor.getAlpha() < 255) { cb.saveState(); float alpha = boxColor.getAlpha() / 255f; PdfGState gState = new PdfGState(); gState.setFillOpacity(alpha); cb.setGState(gState); } float textWidth = getTextWidth(bf, fontSize, label); float textHeight = getTextHeight(bf, fontSize, label); //A height of just textHeight seems to be half the text height sometimes //BaseFont getAscentPoint and getDescentPoint may be not very precise cb.rectangle(x - textWidth / 2f - outlineSize / 2f, -y - outlineSize / 2f - textHeight, textWidth + outlineSize, textHeight * 2f + outlineSize); cb.fill(); if (boxColor.getAlpha() < 255) { cb.restoreState(); } } cb.setRGBColorFill(color.getRed(), color.getGreen(), color.getBlue()); float textHeight = getTextHeight(bf, fontSize, label); if (outlineSize > 0) { cb.setTextRenderingMode(PdfContentByte.TEXT_RENDER_MODE_STROKE); cb.setRGBColorStroke(outlineColor.getRed(), outlineColor.getGreen(), outlineColor.getBlue()); cb.setLineWidth(outlineSize); cb.setLineJoin(PdfContentByte.LINE_JOIN_ROUND); cb.setLineCap(PdfContentByte.LINE_CAP_ROUND); if (outlineColor.getAlpha() < 255) { cb.saveState(); float alpha = outlineColor.getAlpha() / 255f; PdfGState gState = new PdfGState(); gState.setStrokeOpacity(alpha); cb.setGState(gState); } cb.beginText(); cb.setFontAndSize(bf, font.getSize()); cb.showTextAligned(PdfContentByte.ALIGN_CENTER, label, x, -y - (textHeight / 2f), 0f); cb.endText(); if (outlineColor.getAlpha() < 255) { cb.restoreState(); } } cb.setTextRenderingMode(PdfContentByte.TEXT_RENDER_MODE_FILL); cb.beginText(); cb.setFontAndSize(bf, font.getSize()); cb.showTextAligned(PdfContentByte.ALIGN_CENTER, label, x, -y - (textHeight / 2f), 0f); cb.endText(); }
From source file:pl.marcinmilkowski.hocrtopdf.Main.java
License:Open Source License
/** * @param args/*from w w w. j a va2 s . c o m*/ */ public static void main(String[] args) { try { if (args.length < 1 || args[0] == "--help" || args[0] == "-h") { System.out.print("Usage: java pl.marcinmilkowski.hocrtopdf.Main INPUTURL.html OUTPUTURL.pdf\n" + "\n" + "Converts hOCR files into PDF\n" + "\n" + "Example: java pl.marcinmilkowski.hocrtopdf.Main hocr.html output.pdf\n"); if (args.length < 1) System.exit(-1); else System.exit(0); } URL inputHOCRFile = null; FileOutputStream outputPDFStream = null; try { File file = new File(args[0]); inputHOCRFile = file.toURI().toURL(); } catch (MalformedURLException e) { System.out.println("The first parameter has to be a valid file."); System.out.println("We got an error: " + e.getMessage()); System.exit(-1); } try { outputPDFStream = new FileOutputStream(args[1]); } catch (FileNotFoundException e) { System.out.println("The second parameter has to be a valid URL"); System.exit(-1); } // The resolution of a PDF file (using iText) is 72pt per inch float pointsPerInch = 72.0f; // Using the jericho library to parse the HTML file Source source = new Source(inputHOCRFile); int pageCounter = 1; Document pdfDocument = null; PdfWriter pdfWriter = null; PdfContentByte cb = null; RandomAccessFileOrArray ra = null; // Find the tag of class ocr_page in order to load the scanned image StartTag pageTag = source.getNextStartTag(0, "class", OCRPAGE); while (pageTag != null) { int prevPos = pageTag.getEnd(); Pattern imagePattern = Pattern.compile("image\\s+([^;]+)"); Matcher imageMatcher = imagePattern.matcher(pageTag.getElement().getAttributeValue("title")); if (!imageMatcher.find()) { System.out.println("Could not find a tag of class \"ocr_page\", aborting."); System.exit(-1); } // Load the image Image pageImage = null; try { File file = new File(imageMatcher.group(1)); pageImage = Image.getInstance(file.toURI().toURL()); } catch (MalformedURLException e) { System.out.println("Could not load the scanned image from: " + "file://" + imageMatcher.group(1) + ", aborting."); System.exit(-1); } if (pageImage.getOriginalType() == Image.ORIGINAL_TIFF) { // this might // be // multipage // tiff! File file = new File(imageMatcher.group(1)); if (pageCounter == 1 || ra == null) { ra = new RandomAccessFileOrArray(file.toURI().toURL()); } int nPages = TiffImage.getNumberOfPages(ra); if (nPages > 0 && pageCounter <= nPages) { pageImage = TiffImage.getTiffImage(ra, pageCounter); } } int dpiX = pageImage.getDpiX(); if (dpiX == 0) { // for images that don't set the resolution we assume // 300 dpi dpiX = 300; } int dpiY = pageImage.getDpiY(); if (dpiY == 0) { // as above for dpiX dpiY = 300; } float dotsPerPointX = dpiX / pointsPerInch; float dotsPerPointY = dpiY / pointsPerInch; float pageImagePixelHeight = pageImage.getHeight(); if (pdfDocument == null) { pdfDocument = new Document(new Rectangle(pageImage.getWidth() / dotsPerPointX, pageImage.getHeight() / dotsPerPointY)); pdfWriter = PdfWriter.getInstance(pdfDocument, outputPDFStream); pdfDocument.open(); // Put the text behind the picture (reverse for debugging) // cb = pdfWriter.getDirectContentUnder(); cb = pdfWriter.getDirectContent(); } else { pdfDocument.setPageSize(new Rectangle(pageImage.getWidth() / dotsPerPointX, pageImage.getHeight() / dotsPerPointY)); pdfDocument.newPage(); } // first define a standard font for our text BaseFont base = BaseFont.createFont(BaseFont.HELVETICA, BaseFont.CP1250, BaseFont.EMBEDDED); Font defaultFont = new Font(base, 8); // FontFactory.getFont(FontFactory.HELVETICA, 8, Font.BOLD, // CMYKColor.BLACK); cb.setHorizontalScaling(1.0f); pageImage.scaleToFit(pageImage.getWidth() / dotsPerPointX, pageImage.getHeight() / dotsPerPointY); pageImage.setAbsolutePosition(0, 0); // Put the image in front of the text (reverse for debugging) // pdfWriter.getDirectContent().addImage(pageImage); pdfWriter.getDirectContentUnder().addImage(pageImage); // In order to place text behind the recognised text snippets we are // interested in the bbox property Pattern bboxPattern = Pattern.compile("bbox(\\s+\\d+){4}"); // This pattern separates the coordinates of the bbox property Pattern bboxCoordinatePattern = Pattern.compile("(\\d+)\\s+(\\d+)\\s+(\\d+)\\s+(\\d+)"); // Only tags of the ocr_line class are interesting StartTag ocrTag = source.getNextStartTag(prevPos, "class", OCRPAGEORLINE); while (ocrTag != null) { prevPos = ocrTag.getEnd(); if ("ocrx_word".equalsIgnoreCase(ocrTag.getAttributeValue("class"))) { net.htmlparser.jericho.Element lineElement = ocrTag.getElement(); Matcher bboxMatcher = bboxPattern.matcher(lineElement.getAttributeValue("title")); if (bboxMatcher.find()) { // We found a tag of the ocr_line class containing a bbox property Matcher bboxCoordinateMatcher = bboxCoordinatePattern.matcher(bboxMatcher.group()); bboxCoordinateMatcher.find(); int[] coordinates = { Integer.parseInt((bboxCoordinateMatcher.group(1))), Integer.parseInt((bboxCoordinateMatcher.group(2))), Integer.parseInt((bboxCoordinateMatcher.group(3))), Integer.parseInt((bboxCoordinateMatcher.group(4))) }; String line = lineElement.getContent().getTextExtractor().toString(); float bboxWidthPt = (coordinates[2] - coordinates[0]) / dotsPerPointX; float bboxHeightPt = (coordinates[3] - coordinates[1]) / dotsPerPointY; // Put the text into the PDF cb.beginText(); // Comment the next line to debug the PDF output (visible Text) cb.setTextRenderingMode(PdfContentByte.TEXT_RENDER_MODE_INVISIBLE); // height cb.setFontAndSize(defaultFont.getBaseFont(), Math.max(Math.round(bboxHeightPt), 1)); // width cb.setHorizontalScaling(bboxWidthPt / cb.getEffectiveStringWidth(line, false)); cb.moveText((coordinates[0] / dotsPerPointX), ((pageImagePixelHeight - coordinates[3]) / dotsPerPointY)); cb.showText(line); cb.endText(); cb.setHorizontalScaling(1.0f); } } else { if ("ocr_page".equalsIgnoreCase(ocrTag.getAttributeValue("class"))) { pageCounter++; pageTag = ocrTag; break; } } ocrTag = source.getNextStartTag(prevPos, "class", OCRPAGEORLINE); } if (ocrTag == null) { pdfDocument.close(); break; } } } catch (DocumentException e) { // TODO Auto-generated catch block e.printStackTrace(); } catch (IOException e) { // TODO Auto-generated catch block e.printStackTrace(); } }