List of usage examples for org.apache.poi.ss.usermodel Workbook getAllPictures
List<? extends PictureData> getAllPictures();
From source file:com.actelion.research.spiritapp.ui.util.PDFUtils.java
License:Open Source License
public static void convertHSSF2Pdf(Workbook wb, String header, File reportFile) throws Exception { assert wb != null; assert reportFile != null; //Precompute formula FormulaEvaluator evaluator = wb.getCreationHelper().createFormulaEvaluator(); for (int i = 0; i < wb.getNumberOfSheets(); i++) { Sheet sheet = wb.getSheetAt(i);// w ww .j a v a 2 s. co m for (Row r : sheet) { for (Cell c : r) { if (c.getCellType() == HSSFCell.CELL_TYPE_FORMULA) { try { evaluator.evaluateFormulaCell(c); } catch (Exception e) { System.err.println(e); } } } } } File tmp = File.createTempFile("tmp_", ".xlsx"); try (OutputStream out = new BufferedOutputStream(new FileOutputStream(tmp))) { wb.write(out); } //Find page orientation int maxColumnsGlobal = 0; for (int sheetNo = 0; sheetNo < wb.getNumberOfSheets(); sheetNo++) { Sheet sheet = wb.getSheetAt(sheetNo); for (Iterator<Row> rowIterator = sheet.iterator(); rowIterator.hasNext();) { Row row = rowIterator.next(); maxColumnsGlobal = Math.max(maxColumnsGlobal, row.getLastCellNum()); } } Rectangle pageSize = maxColumnsGlobal < 10 ? PageSize.A4 : PageSize.A4.rotate(); Document pdfDocument = new Document(pageSize, 10f, 10f, 20f, 20f); PdfWriter writer = PdfWriter.getInstance(pdfDocument, new FileOutputStream(reportFile)); addHeader(writer, header); pdfDocument.open(); //we have two columns in the Excel sheet, so we create a PDF table with two columns //Note: There are ways to make this dynamic in nature, if you want to. //Loop through sheets for (int sheetNo = 0; sheetNo < wb.getNumberOfSheets(); sheetNo++) { Sheet sheet = wb.getSheetAt(sheetNo); //Loop through rows, to find number of columns int minColumns = 1000; int maxColumns = 0; for (Iterator<Row> rowIterator = sheet.iterator(); rowIterator.hasNext();) { Row row = rowIterator.next(); if (row.getFirstCellNum() >= 0) minColumns = Math.min(minColumns, row.getFirstCellNum()); if (row.getLastCellNum() >= 0) maxColumns = Math.max(maxColumns, row.getLastCellNum()); } if (maxColumns == 0) continue; //Loop through first rows, to find relative width float[] widths = new float[maxColumns]; int totalWidth = 0; for (int c = 0; c < maxColumns; c++) { int w = sheet.getColumnWidth(c); widths[c] = w; totalWidth += w; } for (int c = 0; c < maxColumns; c++) { widths[c] /= totalWidth; } //Create new page and a new chapter with the sheet's name if (sheetNo > 0) pdfDocument.newPage(); Chapter pdfSheet = new Chapter(sheet.getSheetName(), sheetNo + 1); PdfPTable pdfTable = null; PdfPCell pdfCell = null; boolean inTable = false; //Loop through cells, to create the content // boolean leftBorder = true; // boolean[] topBorder = new boolean[maxColumns+1]; for (int r = 0; r <= sheet.getLastRowNum(); r++) { Row row = sheet.getRow(r); //Check if we exited a table (empty line) if (row == null) { if (pdfTable != null) { addTable(pdfDocument, pdfSheet, totalWidth, widths, pdfTable); pdfTable = null; } inTable = false; continue; } //Check if we start a table (>MIN_COL_IN_TABLE columns) if (row.getLastCellNum() >= MIN_COL_IN_TABLE) { inTable = true; } if (!inTable) { //Process the data outside table, just add the text boolean hasData = false; Iterator<Cell> cellIterator = row.cellIterator(); while (cellIterator.hasNext()) { Cell cell = cellIterator.next(); if (cell.getCellType() == Cell.CELL_TYPE_BLANK) continue; Chunk chunk = getChunk(wb, cell); pdfSheet.add(chunk); pdfSheet.add(new Chunk(" ")); hasData = true; } if (hasData) pdfSheet.add(Chunk.NEWLINE); } else { //Process the data in table if (pdfTable == null) { //Create table pdfTable = new PdfPTable(maxColumns); pdfTable.setWidths(widths); // topBorder = new boolean[maxColumns+1]; } int cellNumber = minColumns; // leftBorder = false; Iterator<Cell> cellIterator = row.cellIterator(); while (cellIterator.hasNext()) { Cell cell = cellIterator.next(); for (; cellNumber < cell.getColumnIndex(); cellNumber++) { pdfCell = new PdfPCell(); pdfCell.setBorder(0); pdfTable.addCell(pdfCell); } Chunk phrase = getChunk(wb, cell); pdfCell = new PdfPCell(new Phrase(phrase)); pdfCell.setFixedHeight(row.getHeightInPoints() - 3); pdfCell.setNoWrap(!cell.getCellStyle().getWrapText()); pdfCell.setPaddingLeft(1); pdfCell.setHorizontalAlignment( cell.getCellStyle().getAlignment() == CellStyle.ALIGN_CENTER ? PdfPCell.ALIGN_CENTER : cell.getCellStyle().getAlignment() == CellStyle.ALIGN_RIGHT ? PdfPCell.ALIGN_RIGHT : PdfPCell.ALIGN_LEFT); pdfCell.setUseBorderPadding(false); pdfCell.setUseVariableBorders(false); pdfCell.setBorderWidthRight(cell.getCellStyle().getBorderRight() == 0 ? 0 : .5f); pdfCell.setBorderWidthBottom(cell.getCellStyle().getBorderBottom() == 0 ? 0 : cell.getCellStyle().getBorderBottom() > 1 ? 1 : .5f); pdfCell.setBorderWidthLeft(cell.getCellStyle().getBorderLeft() == 0 ? 0 : cell.getCellStyle().getBorderLeft() > 1 ? 1 : .5f); pdfCell.setBorderWidthTop(cell.getCellStyle().getBorderTop() == 0 ? 0 : cell.getCellStyle().getBorderTop() > 1 ? 1 : .5f); String color = cell.getCellStyle().getFillForegroundColorColor() == null ? null : ((XSSFColor) cell.getCellStyle().getFillForegroundColorColor()).getARGBHex(); if (color != null) pdfCell.setBackgroundColor(new Color(Integer.decode("0x" + color.substring(2)))); pdfTable.addCell(pdfCell); cellNumber++; } for (; cellNumber < maxColumns; cellNumber++) { pdfCell = new PdfPCell(); pdfCell.setBorder(0); pdfTable.addCell(pdfCell); } } //Custom code to add all images on the first sheet (works for reporting) if (sheetNo == 0 && row.getRowNum() == 0) { for (PictureData pd : wb.getAllPictures()) { try { Image pdfImg = Image.getInstance(pd.getData()); pdfImg.scaleToFit( pageSize.getWidth() * .8f - pageSize.getBorderWidthLeft() - pageSize.getBorderWidthRight(), pageSize.getHeight() * .8f - pageSize.getBorderWidthTop() - pageSize.getBorderWidthBottom()); pdfSheet.add(pdfImg); } catch (Exception e) { e.printStackTrace(); } } } } if (pdfTable != null) { addTable(pdfDocument, pdfSheet, totalWidth, widths, pdfTable); } pdfDocument.add(pdfSheet); } pdfDocument.close(); }
From source file:org.sleuthkit.autopsy.imageExtractor.ImageExtractor.java
private List<ExtractedImage> extractImagesFromXls(AbstractFile af) { List<ExtractedImage> listOfExtractedImages = new ArrayList<ExtractedImage>(); String parentFileName = getUniqueName(af); Workbook workbook; try {// w w w . j av a 2 s. c om workbook = new HSSFWorkbook(new ReadContentInputStream(af)); } catch (IOException ex) { logger.log(Level.WARNING, "HSSFWorkbook container could not be instantiated while reading " + af.getName(), ex); return null; } List<? extends org.apache.poi.ss.usermodel.PictureData> listOfAllPictures = workbook.getAllPictures(); // if no images are extracted from the ppt, return null, else initialize // the output folder for image extraction. String outputFolderPath; if (listOfAllPictures.isEmpty()) { return null; } else { outputFolderPath = getOutputFolderPath(parentFileName); } if (outputFolderPath == null) { logger.log(Level.WARNING, "Could not get path for image extraction from AbstractFile: {0}", af.getName()); return null; } int i = 0; for (org.apache.poi.ss.usermodel.PictureData pictureData : listOfAllPictures) { String imageName = UNKNOWN_NAME_PREFIX + i + "." + pictureData.suggestFileExtension(); FileOutputStream fos = null; try { fos = new FileOutputStream(outputFolderPath + File.separator + imageName); } catch (FileNotFoundException ex) { logger.log(Level.WARNING, "Invalid path provided for image extraction", ex); continue; } try { fos.write(pictureData.getData()); fos.close(); i++; } catch (IOException ex) { logger.log(Level.WARNING, "Could not write to the provided location", ex); continue; } String fileRelativePath = File.separator + moduleDirRelative + File.separator + parentFileName + File.separator + imageName; long size = pictureData.getData().length; ExtractedImage extractedimage = new ExtractedImage(imageName, fileRelativePath, size, af); listOfExtractedImages.add(extractedimage); } return listOfExtractedImages; }
From source file:org.sleuthkit.autopsy.imageExtractor.ImageExtractor.java
private List<ExtractedImage> extractImagesFromXlsx(AbstractFile af) { List<ExtractedImage> listOfExtractedImages = new ArrayList<ExtractedImage>(); String parentFileName = getUniqueName(af); Workbook workbook; try {/*from ww w . j a v a 2s. com*/ workbook = new XSSFWorkbook(new ReadContentInputStream(af)); } catch (IOException ex) { logger.log(Level.WARNING, "HSSFWorkbook container could not be instantiated while reading " + af.getName(), ex); return null; } List<? extends org.apache.poi.ss.usermodel.PictureData> listOfAllPictures = workbook.getAllPictures(); // if no images are extracted from the ppt, return null, else initialize // the output folder for image extraction. String outputFolderPath; if (listOfAllPictures.isEmpty()) { return null; } else { outputFolderPath = getOutputFolderPath(parentFileName); } if (outputFolderPath == null) { logger.log(Level.WARNING, "Could not get path for image extraction from AbstractFile: {0}", af.getName()); return null; } int i = 0; for (org.apache.poi.ss.usermodel.PictureData pictureData : listOfAllPictures) { String imageName = UNKNOWN_NAME_PREFIX + i + "." + pictureData.suggestFileExtension(); FileOutputStream fos = null; try { fos = new FileOutputStream(outputFolderPath + File.separator + imageName); } catch (FileNotFoundException ex) { logger.log(Level.WARNING, "Invalid path provided for image extraction", ex); continue; } try { fos.write(pictureData.getData()); fos.close(); i++; } catch (IOException ex) { logger.log(Level.WARNING, "Could not write to the provided location", ex); continue; } String fileRelativePath = File.separator + moduleDirRelative + File.separator + parentFileName + File.separator + imageName; long size = pictureData.getData().length; ExtractedImage extractedimage = new ExtractedImage(imageName, fileRelativePath, size, af); listOfExtractedImages.add(extractedimage); } return listOfExtractedImages; }
From source file:org.sleuthkit.autopsy.modules.embeddedfileextractor.ImageExtractor.java
License:Open Source License
/** * Extract images from xls format files. * * @param af the file from which images are to be extracted. * * @return list of extracted images. Returns null in case no images were * extracted./*from www . ja va 2s .c o m*/ */ private List<ExtractedImage> extractImagesFromXls(AbstractFile af) { List<ExtractedImage> listOfExtractedImages; Workbook xls; try { xls = new HSSFWorkbook(new ReadContentInputStream(af)); } catch (Throwable ex) { // instantiating POI containers throw RuntimeExceptions logger.log(Level.WARNING, String.format("%s%s", NbBundle.getMessage(this.getClass(), "EmbeddedFileExtractorIngestModule.ImageExtractor.xlsContainer.init.err", af.getName()), af.getName()), ex); //NON-NLS return null; } List<? extends org.apache.poi.ss.usermodel.PictureData> listOfAllPictures = null; try { listOfAllPictures = xls.getAllPictures(); } catch (Exception ex) { // log internal Java and Apache errors as WARNING logger.log(Level.WARNING, NbBundle.getMessage(this.getClass(), "EmbeddedFileExtractorIngestModule.ImageExtractor.processing.err", af.getName()), ex); //NON-NLS return null; } // if no images are extracted from the PPT, return null, else initialize // the output folder for image extraction. String outputFolderPath; if (listOfAllPictures.isEmpty()) { return null; } else { outputFolderPath = getOutputFolderPath(this.parentFileName); } if (outputFolderPath == null) { logger.log(Level.WARNING, NbBundle.getMessage(this.getClass(), "EmbeddedFileExtractorIngestModule.ImageExtractor.extractImageFrom.outputPath.exception.msg", af.getName())); //NON-NLS return null; } int i = 0; listOfExtractedImages = new ArrayList<>(); byte[] data = null; for (org.apache.poi.ss.usermodel.PictureData pictureData : listOfAllPictures) { String imageName = UNKNOWN_NAME_PREFIX + i + "." + pictureData.suggestFileExtension(); //NON-NLS try { data = pictureData.getData(); } catch (Exception ex) { // log internal Java and Apache errors as WARNING logger.log(Level.WARNING, NbBundle.getMessage(this.getClass(), "EmbeddedFileExtractorIngestModule.ImageExtractor.processing.err", af.getName()), ex); //NON-NLS return null; } writeExtractedImage(Paths.get(outputFolderPath, imageName).toString(), data); listOfExtractedImages.add(new ExtractedImage(imageName, getFileRelativePath(imageName), pictureData.getData().length, af)); i++; } return listOfExtractedImages; }
From source file:org.sleuthkit.autopsy.modules.embeddedfileextractor.ImageExtractor.java
License:Open Source License
/** * Extract images from xlsx format files. * * @param af the file from which images are to be extracted. * * @return list of extracted images. Returns null in case no images were * extracted./*from ww w. ja va2 s.c o m*/ */ private List<ExtractedImage> extractImagesFromXlsx(AbstractFile af) { List<ExtractedImage> listOfExtractedImages; Workbook xlsx; try { xlsx = new XSSFWorkbook(new ReadContentInputStream(af)); } catch (Throwable ex) { // instantiating POI containers throw RuntimeExceptions logger.log(Level.WARNING, NbBundle.getMessage(this.getClass(), "EmbeddedFileExtractorIngestModule.ImageExtractor.xlsxContainer.init.err", af.getName()), ex); //NON-NLS return null; } List<? extends org.apache.poi.ss.usermodel.PictureData> listOfAllPictures = null; try { listOfAllPictures = xlsx.getAllPictures(); } catch (Exception ex) { // log internal Java and Apache errors as WARNING logger.log(Level.WARNING, NbBundle.getMessage(this.getClass(), "EmbeddedFileExtractorIngestModule.ImageExtractor.processing.err", af.getName()), ex); //NON-NLS return null; } // if no images are extracted from the PPT, return null, else initialize // the output folder for image extraction. String outputFolderPath; if (listOfAllPictures.isEmpty()) { return null; } else { outputFolderPath = getOutputFolderPath(this.parentFileName); } if (outputFolderPath == null) { logger.log(Level.WARNING, NbBundle.getMessage(this.getClass(), "EmbeddedFileExtractorIngestModule.ImageExtractor.extractImageFrom.outputPath.exception.msg", af.getName())); //NON-NLS return null; } int i = 0; listOfExtractedImages = new ArrayList<>(); byte[] data = null; for (org.apache.poi.ss.usermodel.PictureData pictureData : listOfAllPictures) { String imageName = UNKNOWN_NAME_PREFIX + i + "." + pictureData.suggestFileExtension(); try { data = pictureData.getData(); } catch (Exception ex) { // log internal Java and Apache errors as WARNING logger.log(Level.WARNING, NbBundle.getMessage(this.getClass(), "EmbeddedFileExtractorIngestModule.ImageExtractor.processing.err", af.getName()), ex); //NON-NLS return null; } writeExtractedImage(Paths.get(outputFolderPath, imageName).toString(), data); listOfExtractedImages.add(new ExtractedImage(imageName, getFileRelativePath(imageName), pictureData.getData().length, af)); i++; } return listOfExtractedImages; }