List of usage examples for org.apache.pdfbox.pdmodel PDDocument save
public void save(OutputStream output) throws IOException
From source file:mil.tatrc.physiology.utilities.Excel2PDF.java
License:Apache License
public static void convert(String from, String to) throws IOException { FileInputStream xlFile = new FileInputStream(new File(from)); // Read workbook into HSSFWorkbook XSSFWorkbook xlWBook = new XSSFWorkbook(xlFile); //We will create output PDF document objects at this point PDDocument pdf = new PDDocument(); //pdf.addTitle(); for (int s = 0; s < xlWBook.getNumberOfSheets(); s++) { XSSFSheet xlSheet = xlWBook.getSheetAt(s); Log.info("Processing Sheet : " + xlSheet.getSheetName()); PDPage page = new PDPage(PDRectangle.A4); page.setRotation(90);//from w w w . j a va 2 s .c o m pdf.addPage(page); PDRectangle pageSize = page.getMediaBox(); PDPageContentStream contents = new PDPageContentStream(pdf, page); contents.transform(new Matrix(0, 1, -1, 0, pageSize.getWidth(), 0));// including a translation of pageWidth to use the lower left corner as 0,0 reference contents.setFont(PDType1Font.HELVETICA_BOLD, 16); contents.beginText(); contents.newLineAtOffset(50, pageSize.getWidth() - 50); contents.showText(xlSheet.getSheetName()); contents.endText(); contents.close(); int rows = xlSheet.getPhysicalNumberOfRows(); for (int r = 0; r < rows; r++) { XSSFRow row = xlSheet.getRow(r); if (row == null) continue; int cells = row.getPhysicalNumberOfCells(); if (cells == 0) continue;// Add an empty Roe } } /* //We will use the object below to dynamically add new data to the table PdfPCell table_cell; //Loop through rows. while(rowIterator.hasNext()) { Row row = rowIterator.next(); Iterator<Cell> cellIterator = row.cellIterator(); while(cellIterator.hasNext()) { Cell cell = cellIterator.next(); //Fetch CELL switch(cell.getCellType()) { //Identify CELL type //you need to add more code here based on //your requirement / transformations case Cell.CELL_TYPE_STRING: //Push the data from Excel to PDF Cell table_cell=new PdfPCell(new Phrase(cell.getStringCellValue())); //feel free to move the code below to suit to your needs my_table.addCell(table_cell); break; } //next line } } */ pdf.save(new File(to)); pdf.close(); xlWBook.close(); xlFile.close(); //close xls }
From source file:model.objects.Project.java
License:Apache License
public void savePDF(final String firstPath) throws IOException { PDDocument doc = document.getPDDocument(); System.out.println(doc);/*from www .j a va2 s. co m*/ try { final boolean newlyCreated = (doc == null); if (newlyCreated) { // create new document and insert empty page to the document. doc = new PDDocument(); } else { // reset wrong settings. State.setBorderBottomPercentExport(0); State.setBorderRightPercentExport(0); State.setBorderLeftPercentExport(0); State.setBorderTopPercentExport(0); State.setExportAlpha(true); } for (int i = 0; i < pictures.length; i++) { int index = i + 0; if (newlyCreated) { index = -1; } attatchToPDF(doc, pictures[i].getBufferedImage(0, 0, false), index); } //save and close doc.save(firstPath); } finally { if (doc != null) { // doc.close(); } } }
From source file:model.util.pdf.PDFUtils.java
License:Apache License
/** * Test: Create pdf from image and pdf file. * * @param _inputFile pdf input/*from ww w . j av a 2s . c o m*/ * @param _imagePath image input * @param _outputFile pdf output * * @throws IOException occurs if reading the data fails. */ public void saveAsPdf(String _imagePath, String _outputFile) throws IOException { PDDocument doc = null; try { // create new document and insert empty page to the document. doc = new PDDocument(); PDPage page = new PDPage(); doc.addPage(page); // createFromFile is the easiest way with an image file // if you already have the image in a BufferedImage, // call LosslessFactory.createFromImage() instead PDImageXObject pdImage = PDImageXObject.createFromFile(_imagePath, doc); PDPageContentStream contentStream = new PDPageContentStream(doc, page, true, true); // contentStream.drawImage(ximage, 20, 20 ); // better method inspired by http://stackoverflow.com/a/22318681/535646 // reduce this value if the image is too large float scale = 1f; contentStream.drawImage(pdImage, 20, 20, pdImage.getWidth() * scale, pdImage.getHeight() * scale); contentStream.close(); doc.save(_outputFile); } finally { if (doc != null) { doc.close(); } } }
From source file:name.marcelomorales.siqisiqi.pdfbox.CoordinatesGenerator.java
License:Apache License
public void generarPdf(OutputStream os, String template, Map<String, Object> m, String path, String coordenates, float fontSize, float ancho) throws IOException { long t = System.currentTimeMillis(); PDDocument doc = null; try {//from ww w . j a v a 2 s. c o m doc = PDDocument.load(new File(path)); List pages = doc.getDocumentCatalog().getAllPages(); PDPage sourcePage = (PDPage) pages.get(0); boolean append = sourcePage.getContents() != null; PDPageContentStream contentStream = new PDPageContentStream(doc, sourcePage, append, true); StringReader fileReader = null; try { fileReader = new StringReader(template); List<String> list = CharStreams.readLines(fileReader); boolean textHasBegun = false; float currentOffset = 0f; for (String line : list) { if (line == null) { continue; } if (line.startsWith("#")) { continue; } final Iterable<String> str = Splitter.on(',').omitEmptyStrings().trimResults().split(line); final String[] split = Iterables.toArray(str, String.class); if (split == null || split.length < 4) { continue; } if (Character.isDigit(split[0].charAt(0))) { if (textHasBegun) { contentStream.endText(); } contentStream.beginText(); textHasBegun = true; contentStream.moveTextPositionByAmount(parseFloat(split[0]), parseFloat(split[1])); } else { contentStream.moveTextPositionByAmount(currentOffset, 0); } if (!textHasBegun) { LOGGER.warn("Hay un posible mal uso de un .ree", new Throwable()); contentStream.beginText(); textHasBegun = true; } PDType1Font font; if ("b".equals(split[2])) { font = HELVETICA_BOLD; } else { font = HELVETICA; } contentStream.setFont(font, fontSize); Object text = null; if (split[3].startsWith("\"")) { // TODO: text = substring(split[3], 1, -1); } else { // TODO: text = new PropertyModel(m, split[3]).getObject(); } if (text == null) { LOGGER.warn("Propiedad {} no se encuentra", split[3]); //contentStream.drawString("ERROR: propiedad no encontrada"); contentStream.drawString(" "); } else { String string = text.toString(); currentOffset = font.getStringWidth(string) * ancho; contentStream.drawString(string); } } if (textHasBegun) { contentStream.endText(); } } finally { Closeables.closeQuietly(fileReader); } contentStream.close(); try { doc.save(os); } catch (COSVisitorException e) { throw new IOException("Ha ocurrido un error al escribir en el Os", e); } } finally { if (doc != null) { doc.close(); } LOGGER.info("Me ha tomado {} milisegundos hacer el pdf", System.currentTimeMillis() - t); } }
From source file:net.bookinaction.ExtractAnnotations.java
License:Apache License
public void doJob(String job, Float[] pA) throws IOException { PDDocument document = null; Stamper s = new Stamper(); // utility class final String job_file = job + ".pdf"; final String dic_file = job + "-dict.txt"; final String new_job = job + "-new.pdf"; PrintWriter writer = new PrintWriter(dic_file); ImageLocationListener imageLocationsListener = new ImageLocationListener(); AnnotationMaker annotMaker = new AnnotationMaker(); try {/*from ww w . j av a2s.c o m*/ document = PDDocument.load(new File(job_file)); int pageNum = 0; for (PDPage page : document.getPages()) { pageNum++; PDRectangle cropBox = page.getCropBox(); List<PDAnnotation> annotations = page.getAnnotations(); // extract image locations List<Rectangle2D> imageRects = new ArrayList<Rectangle2D>(); imageLocationsListener.setImageRects(imageRects); imageLocationsListener.processPage(page); int im = 0; for (Rectangle2D pdImageRect : imageRects) { s.recordImage(writer, pageNum, "[im" + im + "]", (Rectangle2D.Float) pdImageRect); annotations.add(annotMaker.squareAnnotation(Color.YELLOW, (Rectangle2D.Float) pdImageRect, "[im" + im + "]")); im++; } PDFTextStripperByArea stripper = new PDFTextStripperByArea(); int j = 0; List<PDAnnotation> viableAnnots = new ArrayList(); for (PDAnnotation annot : annotations) { if (annot instanceof PDAnnotationTextMarkup || annot instanceof PDAnnotationLink) { stripper.addRegion(Integer.toString(j++), s.getAwtRect( s.adjustedRect(annot.getRectangle(), pA[0], pA[1], pA[2], pA[3]), cropBox)); viableAnnots.add(annot); } else if (annot instanceof PDAnnotationPopup || annot instanceof PDAnnotationText) { viableAnnots.add(annot); } } stripper.extractRegions(page); List<PDRectangle> rects = new ArrayList<PDRectangle>(); List<String> comments = new ArrayList<String>(); List<String> highlightTexts = new ArrayList<String>(); j = 0; for (PDAnnotation viableAnnot : viableAnnots) { if (viableAnnot instanceof PDAnnotationTextMarkup) { String highlightText = stripper.getTextForRegion(Integer.toString(j++)); String withoutCR = highlightText.replace((char) 0x0A, '^'); String comment = viableAnnot.getContents(); String colorString = String.format("%06x", viableAnnot.getColor().toRGB()); PDRectangle aRect = s.adjustedRect(viableAnnot.getRectangle(), pA[4], pA[5], pA[6], pA[7]); rects.add(aRect); comments.add(comment); highlightTexts.add(highlightText); s.recordTextMarkup(writer, pageNum, comment, withoutCR, aRect, colorString); } else if (viableAnnot instanceof PDAnnotationText) { String comment = viableAnnot.getContents(); String colorString = String.format("%06x", viableAnnot.getColor().toRGB()); for (Rectangle2D pdImageRect : imageRects) { if (pdImageRect.contains(viableAnnot.getRectangle().getLowerLeftX(), viableAnnot.getRectangle().getLowerLeftY())) { s.recordTextMarkup(writer, pageNum, comment, "", (Rectangle2D.Float) pdImageRect, colorString); annotations.add(annotMaker.squareAnnotation(Color.GREEN, (Rectangle2D.Float) pdImageRect, comment)); } ; } } } PDPageContentStream canvas = new PDPageContentStream(document, page, true, true, true); int i = 0; for (PDRectangle pdRect : rects) { String comment = comments.get(i); String highlightText = highlightTexts.get(i); //annotations.add(linkAnnotation(pdRect, comment, highlightText)); //annotations.add(annotationSquareCircle(pdRect, BLUE)); s.showBox(canvas, new Rectangle2D.Float(pdRect.getLowerLeftX(), pdRect.getUpperRightY(), pdRect.getWidth(), pdRect.getHeight()), cropBox, Color.BLUE); i++; } canvas.close(); } writer.close(); document.save(new_job); } finally { if (document != null) { document.close(); } } }
From source file:net.bookinaction.TextInfoExtractor.java
License:Apache License
public void doTextPosition(String source, String coord_text, StripperParam stripperParam) throws IOException { String source_pdf = source;//from w ww .j a v a2 s. c o m String new_file = source.split("\\.")[0] + "-new.pdf"; PDDocument document = PDDocument.load(new File(source_pdf)); PrintWriter writer = new PrintWriter(new File(coord_text)); //s.recordHeader(writer, source_pdf, document.getNumberOfPages(), sParam); for (int i = 0; i < document.getNumberOfPages(); i++) { getTextPositionFromPage(document, stripperParam, i + 1, writer, true); } if (document != null) { document.save(new_file); document.close(); } if (writer != null) writer.close(); }
From source file:net.sf.jabref.plugins.pdftasks.PDFTaskSidePane.java
License:Open Source License
private void doTasks() { // PDF file type representation final ExternalFileType pdf_type = Globals.prefs.getExternalFileTypeByExt("pdf"); // get Bibtex database associated with the current tab final BasePanel db_panel = frame.basePanel(); final BibtexDatabase db = db_panel.database(); final MetaData db_meta = db_panel.metaData(); // get selected Bibtex entries from the current tab final BibtexEntry[] db_entries = db_panel.getSelectedEntries(); // get Bibtex database file for current tab final File db_file = db_panel.getFile(); if (db_file == null || db_file.getParentFile() == null) { JOptionPane.showMessageDialog(frame, "Bibtex database must be saved before performing PDF tasks.", title, JOptionPane.INFORMATION_MESSAGE); return;//w w w.j a v a2 s . c o m } // get array of directories that PDF files could possibly be in final List<File> db_dirs = new LinkedList<File>(); for (String dir : db_meta.getFileDirectory(GUIGlobals.FILE_FIELD)) { db_dirs.add(new File(dir)); } if (db_dirs.size() == 0 || !db_dirs.contains(db_file.getParentFile())) { db_dirs.add(db_file.getParentFile()); } // return if no entries are selected if (db_entries.length == 0) { JOptionPane.showMessageDialog(frame, "No entries selected for PDF tasks.", title, JOptionPane.INFORMATION_MESSAGE); return; } // get PDF file directory final File pdf_dir = absoluteFile(pdf_dir_txt.getText(), db_file.getParentFile()); // do tasks encapsulated in a worker-thread class AbstractWorker tasks = new AbstractWorker() { boolean cancelled = false; boolean confirmed = false; boolean erred = false; // get user confirmation for PDF file modifications private boolean getUserConfirmation() { if (!confirmed) { confirmed = JOptionPane.showConfirmDialog(frame, "Are you sure you want to rename, move, and/or modify PDF files?\n" + "This operations cannot be undone.", title, JOptionPane.YES_NO_OPTION) == JOptionPane.YES_OPTION; } return confirmed; } public void init() { // block main window frame.block(); } public void run() { // for debugging purposes final boolean modifyDatabase = true; // iterate over selected Bibtex entries int entry_count = 0; for (BibtexEntry entry : db_entries) { ++entry_count; // get Bibtex key, check is not null String key = entry.getCiteKey(); if (key == null || key.length() == 0) { JOptionPane.showMessageDialog(frame, "BibTeX entry '" + entry.getId() + "' does not have a key!", title, JOptionPane.ERROR_MESSAGE); erred = true; return; } // update status bar frame.output(String.format("Processing BibTeX entry: %s (%d of %d)...", key, entry_count, db_entries.length)); // get table of file links for this Bibtex entry FileListTableModel files = new FileListTableModel(); files.setContent(entry.getField(GUIGlobals.FILE_FIELD)); for (int fileindex = 0; fileindex < files.getRowCount(); ++fileindex) { FileListEntry file_entry = files.getEntry(fileindex); // skip if this is not a PDF file link if (!file_entry.getType().equals(pdf_type)) continue; // get PDF file File pdf_file = null; for (File db_dir : db_dirs) { pdf_file = absoluteFile(file_entry.getLink(), db_dir); if (pdf_file.isFile()) { break; } pdf_file = null; } if (pdf_file == null) { String errmsg = "Could not find PDF file '" + file_entry.getLink() + "' in '" + db_dirs.get(0); for (int i = 1; i < db_dirs.size(); ++i) { errmsg += "', '" + db_dirs.get(i); } errmsg += "'!"; JOptionPane.showMessageDialog(frame, errmsg, title, JOptionPane.ERROR_MESSAGE); erred = true; return; } // get PDF file description String pdf_desc = file_entry.getDescription(); // new PDF file File new_pdf_file = pdf_file; // rename PDF file if (rename_pdfs_chk.isSelected()) { // build new PDF name String new_name = key; if (!pdf_desc.isEmpty()) { new_name += "_" + pdf_desc.replace(" ", "_"); } new_name += "." + pdf_type.getExtension(); // set new PDF file new_pdf_file = absoluteFile(new_name, new_pdf_file.getParentFile()); } // move PDF file if (move_to_pdf_dir_chk.isSelected()) { new_pdf_file = absoluteFile(new_pdf_file.getName(), pdf_dir); } // if PDF file needs to be moved if (!new_pdf_file.equals(pdf_file)) { // get user confirmation if (!getUserConfirmation()) { cancelled = true; return; } // perform move/rename operations if (modifyDatabase) { String errmsg = ""; try { // create parent directories File new_pdf_dir = new_pdf_file.getParentFile(); if (new_pdf_dir != null && !new_pdf_dir.isDirectory()) { errmsg = "Could not create directory '" + new_pdf_file.getParentFile().getPath() + "'"; erred = !new_pdf_file.getParentFile().mkdirs(); } if (!erred) { // check if PDF file already exists, and ask for confirmation to replace it if (new_pdf_file.isFile()) { switch (JOptionPane.showConfirmDialog(frame, "PDF file '" + new_pdf_file.getPath() + "' already exists.\n" + "Are you sure you want to replace it with " + "PDF file '" + pdf_file.getPath() + "'?\n" + "This operation cannot be undone.", title, JOptionPane.YES_NO_CANCEL_OPTION)) { case JOptionPane.NO_OPTION: continue; case JOptionPane.CANCEL_OPTION: cancelled = true; return; case JOptionPane.YES_OPTION: errmsg = "Could not delete PDF file '" + new_pdf_file.getPath() + "'"; erred = !new_pdf_file.delete(); } } // otherwise test that we can create the new PDF file else { errmsg = "Could not access PDF file '" + new_pdf_file.getPath() + "'"; erred = !new_pdf_file.createNewFile() || !new_pdf_file.delete(); } if (!erred) { // try to move/rename PDF file errmsg = "Could not rename PDF file '" + pdf_file.getPath() + "' to '" + new_pdf_file.getPath() + "'"; erred = !pdf_file.renameTo(new_pdf_file); } } } // possible exceptions catch (SecurityException e) { erred = true; errmsg += ": insufficient permissions"; } catch (IOException e) { e.printStackTrace(); erred = true; errmsg += ": an I/O exception occurred"; } if (erred) { JOptionPane.showMessageDialog(frame, errmsg + ".", title, JOptionPane.ERROR_MESSAGE); return; } // everything was successful pdf_file = new_pdf_file; } } // update file entry table and Bibtex entry file_entry.setLink(relativePath(pdf_file, db_dirs.get(0))); if (modifyDatabase) { String new_files = files.getStringRepresentation(); if (!new_files.equals(entry.getField(GUIGlobals.FILE_FIELD))) { entry.setField(GUIGlobals.FILE_FIELD, new_files); db_panel.markNonUndoableBaseChanged(); } } // perform operations on PDF file contents if (write_pdf_docinfo_chk.isSelected()) { if (erase_pdf_docinfo_chk.isSelected()) { // get user confirmation if (!getUserConfirmation()) { cancelled = true; return; } // open PDF file PDDocument document = null; try { document = PDDocument.load(pdf_file); } catch (IOException e) { e.printStackTrace(); erred = true; JOptionPane.showMessageDialog(frame, "Could not open PDF file '" + pdf_file.getPath() + "': an I/O exception occurred.", title, JOptionPane.ERROR_MESSAGE); return; } // erase document information document.setDocumentInformation(new PDDocumentInformation()); // erase XML metadata document.getDocumentCatalog().setMetadata(null); // save and close PDF file try { document.save(pdf_file.getPath()); document.close(); } catch (COSVisitorException e) { e.printStackTrace(); erred = true; JOptionPane.showMessageDialog(frame, "Could not save PDF file '" + pdf_file.getPath() + "': an exception occurred.", title, JOptionPane.ERROR_MESSAGE); return; } catch (IOException e) { e.printStackTrace(); erred = true; JOptionPane.showMessageDialog(frame, "Could not save/close PDF file '" + pdf_file.getPath() + "': an I/O exception occurred.", title, JOptionPane.ERROR_MESSAGE); return; } } // write XMP / PDF document catalog metadata try { XMPUtil.writeXMP(pdf_file, entry, db); } catch (IOException e) { e.printStackTrace(); erred = true; JOptionPane.showMessageDialog(frame, "Could not write XMP to PDF file '" + pdf_file.getPath() + "': an I/O exception occurred.", title, JOptionPane.ERROR_MESSAGE); return; } catch (TransformerException e) { e.printStackTrace(); erred = true; JOptionPane .showMessageDialog(frame, "Could not write XMP to PDF file '" + pdf_file.getPath() + "': an exception occurred.", title, JOptionPane.ERROR_MESSAGE); return; } } } } } public void update() { // unblock main window frame.unblock(); // print to status bar if (erred) { frame.output("An error occurred during PDF Tasks"); } else if (cancelled) { frame.output("Cancelled PDF Tasks"); } else { frame.output("Completed PDF Tasks"); } } }; // run task thread (based on code in BasePanel.runCommand()) try { tasks.init(); tasks.getWorker().run(); tasks.getCallBack().update(); } catch (Throwable e) { frame.unblock(); e.printStackTrace(); } }
From source file:net.sf.jabref.util.XMPUtil.java
License:Open Source License
/** * Try to write the given BibTexEntry in the XMP-stream of the given * PDF-file./*w ww. j ava 2 s . co m*/ * * Throws an IOException if the file cannot be read or written, so the user * can remove a lock or cancel the operation. * * The method will overwrite existing BibTeX-XMP-data, but keep other * existing metadata. * * @param file * The file to write the entries to. * @param bibtexEntries * The entries to write to the file. * * @param database * maybenull An optional database which the given bibtex entries * belong to, which will be used to resolve strings. If the * database is null the strings will not be resolved. * @param writePDFInfo * Write information also in PDF document properties * @throws TransformerException * If the entry was malformed or unsupported. * @throws IOException * If the file could not be written to or could not be found. */ @SuppressWarnings("unchecked") public static void writeXMP(File file, Collection<BibtexEntry> bibtexEntries, BibtexDatabase database, boolean writePDFInfo) throws IOException, TransformerException { if (database != null) { bibtexEntries = database.resolveForStrings(bibtexEntries, false); } PDDocument document = null; try { document = PDDocument.load(file.getAbsoluteFile()); if (document.isEncrypted()) { throw new EncryptionNotSupportedException("Error: Cannot add metadata to encrypted document."); } if (writePDFInfo && (bibtexEntries.size() == 1)) { XMPUtil.writeDocumentInformation(document, bibtexEntries.iterator().next(), null); XMPUtil.writeDublinCore(document, bibtexEntries, null); } PDDocumentCatalog catalog = document.getDocumentCatalog(); PDMetadata metaRaw = catalog.getMetadata(); XMPMetadata meta; if (metaRaw != null) { meta = new XMPMetadata(XMLUtil.parse(metaRaw.createInputStream())); } else { meta = new XMPMetadata(); } meta.addXMLNSMapping(XMPSchemaBibtex.NAMESPACE, XMPSchemaBibtex.class); // Remove all current Bibtex-schemas List<XMPSchema> schemas = meta.getSchemasByNamespaceURI(XMPSchemaBibtex.NAMESPACE); for (XMPSchema schema : schemas) { XMPSchemaBibtex bib = (XMPSchemaBibtex) schema; bib.getElement().getParentNode().removeChild(bib.getElement()); } for (BibtexEntry e : bibtexEntries) { XMPSchemaBibtex bibtex = new XMPSchemaBibtex(meta); meta.addSchema(bibtex); bibtex.setBibtexEntry(e, null); } // Save to stream and then input that stream to the PDF ByteArrayOutputStream os = new ByteArrayOutputStream(); meta.save(os); ByteArrayInputStream is = new ByteArrayInputStream(os.toByteArray()); PDMetadata metadataStream = new PDMetadata(document, is, false); catalog.setMetadata(metadataStream); // Save try { document.save(file.getAbsolutePath()); } catch (COSVisitorException e) { throw new TransformerException("Could not write XMP-metadata: " + e.getLocalizedMessage()); } } finally { if (document != null) { document.close(); } } }
From source file:nominas.sei.form.Principal.java
private void ordenaNominas(String rutaEntrada, String rutaSalida) { ArrayList<PaginaNomina> paginasNomina = new ArrayList<PaginaNomina>(); for (int x = 0; x < 1; x++) {//RECORREMOS EL ARREGLO CON LOS NOMBRES DE ARCHIVO try {//w w w.ja v a 2 s . c o m PDDocument pd = PDDocument.load(rutaEntrada); //CARGAR EL PDF List l = pd.getDocumentCatalog().getAllPages();//NUMERO LAS PAGINAS DEL ARCHIVO Object[] obj = l.toArray();//METO EN UN OBJETO LA LISTA DE PAGINAS PARA MANIPULARLA for (int i = 0; i < l.size(); i++) { PDPage page = (PDPage) obj[i];//PAGE ES LA PAGINA 1 DE LA QUE CONSTA EL ARCHIVO PageFormat pageFormat = pd.getPageFormat(0);//PROPIEDADES DE LA PAGINA (FORMATO) Double d1 = new Double(pageFormat.getHeight());//ALTO Double d2 = new Double(pageFormat.getWidth());//ANCHO int width = d1.intValue();//ANCHO int eigth = 1024;//ALTO PDFTextStripperByArea stripper = new PDFTextStripperByArea();//COMPONENTE PARA ACCESO AL TEXTO Rectangle rect = new Rectangle(0, 0, width, eigth);//DEFNIR AREA DONDE SE BUSCARA EL TEXTO stripper.addRegion("area1", rect);//REGISTRAMOS LA REGION CON UN NOMBRE stripper.extractRegions(page);//EXTRAE TEXTO DEL AREA String contenido = new String();//CONTENIDO = A LO QUE CONTENGA EL AREA O REGION contenido = (stripper.getTextForRegion("area1")); String[] lines = contenido.split("[\\r\\n]+"); String nombre = lines[1].substring(28, lines[1].length() - 10);//Separamos el nombre PaginaNomina nomina = new PaginaNomina(page, nombre); paginasNomina.add(nomina); } Collections.sort(paginasNomina); // Create a new empty document PDDocument document = new PDDocument(); for (int i = 0; i < paginasNomina.size(); i++) { System.out.println(paginasNomina.get(i).getNombre()); document.addPage(paginasNomina.get(i).getPagina()); } // Save the newly created document document.save(rutaSalida); // finally make sure that the document is properly // closed. document.close(); pd.close();//CERRAMOS OBJETO ACROBAT } catch (Exception e) { System.out.println(e.getMessage()); } //CATCH } //FOR }
From source file:nominas.sei.NominasSEI.java
/** * @param args the command line arguments *///from w w w. java 2s. c om public static void main(String[] args) { ArrayList<PaginaNomina> paginasNomina = new ArrayList<PaginaNomina>(); for (int x = 0; x < 1; x++) {//RECORREMOS EL ARREGLO CON LOS NOMBRES DE ARCHIVO String ruta = new String();//VARIABLE QUE DETERMINARA LA RUTA DEL ARCHIVO A LEER. ruta = (".\\NOMINAS.pdf"); //SE ALMACENA LA RUTA DEL ARCHIVO A LEER. try { PDDocument pd = PDDocument.load(ruta); //CARGAR EL PDF List l = pd.getDocumentCatalog().getAllPages();//NUMERO LAS PAGINAS DEL ARCHIVO Object[] obj = l.toArray();//METO EN UN OBJETO LA LISTA DE PAGINAS PARA MANIPULARLA for (int i = 0; i < l.size(); i++) { PDPage page = (PDPage) obj[i];//PAGE ES LA PAGINA 1 DE LA QUE CONSTA EL ARCHIVO PageFormat pageFormat = pd.getPageFormat(0);//PROPIEDADES DE LA PAGINA (FORMATO) Double d1 = new Double(pageFormat.getHeight());//ALTO Double d2 = new Double(pageFormat.getWidth());//ANCHO int width = d1.intValue();//ANCHO int eigth = 1024;//ALTO PDFTextStripperByArea stripper = new PDFTextStripperByArea();//COMPONENTE PARA ACCESO AL TEXTO Rectangle rect = new Rectangle(0, 0, width, eigth);//DEFNIR AREA DONDE SE BUSCARA EL TEXTO stripper.addRegion("area1", rect);//REGISTRAMOS LA REGION CON UN NOMBRE stripper.extractRegions(page);//EXTRAE TEXTO DEL AREA String contenido = new String();//CONTENIDO = A LO QUE CONTENGA EL AREA O REGION contenido = (stripper.getTextForRegion("area1")); String[] lines = contenido.split("[\\r\\n]+"); String nombre = lines[1].substring(28, lines[1].length() - 10); PaginaNomina nomina = new PaginaNomina(page, nombre); paginasNomina.add(nomina); } Collections.sort(paginasNomina); // Create a new empty document PDDocument document = new PDDocument(); for (int i = 0; i < paginasNomina.size(); i++) { System.out.println(paginasNomina.get(i).getNombre()); document.addPage(paginasNomina.get(i).getPagina()); } // Save the newly created document document.save("NominasOrdenadas.pdf"); // finally make sure that the document is properly // closed. document.close(); pd.close();//CERRAMOS OBJETO ACROBAT } catch (Exception e) { System.out.println(e.getMessage()); } //CATCH } //FOR }