List of usage examples for com.itextpdf.text.pdf RandomAccessFileOrArray RandomAccessFileOrArray
@Deprecated public RandomAccessFileOrArray(byte arrayIn[])
From source file:pl.marcinmilkowski.hocrtopdf.Main.java
License:Open Source License
/** * @param args/*from w w w. j a v a 2 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(); } }
From source file:sc.emea.tools.image.Tiff2PDF.java
License:Apache License
public static void main(String args[]) { int page_counter = 0; try {/*from w w w .j av a2 s. c o m*/ // Read the Tiff File FileList myFileList = new FileList("C:\\DEV\\Eclipse-Workspace\\Luna-J\\Tiff2PdfConverter\\TIFF\\"); myFileList.setFilterPreMiddleSuffix("", "", ".tiff"); myFileList.sort(ComparableAttribute.dateLastModified, SortingDirection.asc); File[] myTiffFileFiles = myFileList.getFilesArray(); if (myTiffFileFiles.length < 1) return; else for (File file : myTiffFileFiles) System.out.println(file.getName()); Document myDocument = new Document(); myDocument.setMargins(0, 0, 0, 0); PdfWriter.getInstance(myDocument, new FileOutputStream("C:\\DEV\\Eclipse-Workspace\\Luna-J\\Tiff2PdfConverter\\PDF\\test.pdf")); myDocument.open(); RandomAccessSourceFactory rasFactory = new RandomAccessSourceFactory(); for (File file : myTiffFileFiles) { FileInputStream _fis = new FileInputStream(file.getAbsolutePath()); RandomAccessSource _ra_source = rasFactory.createSource(_fis); RandomAccessFileOrArray _ra_file = new RandomAccessFileOrArray(_ra_source); int numberOfPages = TiffImage.getNumberOfPages(_ra_file); for (int i = 1; i <= numberOfPages; i++) { Image _image = TiffImage.getTiffImage(_ra_file, i); _image.scaleAbsolute(myDocument.getPageSize()); myDocument.add(_image); page_counter++; } } myDocument.close(); System.out.println("Tiff to PDF conversion completed for " + page_counter); } catch (Exception i1) { i1.printStackTrace(); } }
From source file:spntoolsdata.pdf.util.RemoveBlankPageFromPDF.java
public static void removeBlankPdfPages(String source, String destination) throws IOException, DocumentException { PdfReader r = null;// w w w . j a v a 2 s .com RandomAccessSourceFactory rasf = null; RandomAccessFileOrArray raf = null; Document document = null; PdfCopy writer = null; try { r = new PdfReader(source); // deprecated // RandomAccessFileOrArray raf // = new RandomAccessFileOrArray(pdfSourceFile); // itext 5.4.1 rasf = new RandomAccessSourceFactory(); raf = new RandomAccessFileOrArray(rasf.createBestSource(source)); document = new Document(r.getPageSizeWithRotation(1)); writer = new PdfCopy(document, new FileOutputStream(destination)); document.open(); PdfImportedPage page = null; for (int i = 1; i <= r.getNumberOfPages(); i++) { // first check, examine the resource dictionary for /Font or // /XObject keys. If either are present -> not blank. PdfDictionary pageDict = r.getPageN(i); PdfDictionary resDict = (PdfDictionary) pageDict.get(PdfName.RESOURCES); boolean noFontsOrImages = true; if (resDict != null) { noFontsOrImages = resDict.get(PdfName.FONT) == null && resDict.get(PdfName.XOBJECT) == null; } if (!noFontsOrImages) { byte bContent[] = r.getPageContent(i, raf); ByteArrayOutputStream bs = new ByteArrayOutputStream(); bs.write(bContent); if (bs.size() > BLANK_THRESHOLD) { page = writer.getImportedPage(r, i); writer.addPage(page); } } } } finally { if (document != null) document.close(); if (writer != null) writer.close(); if (raf != null) raf.close(); if (r != null) r.close(); } }