Example usage for org.apache.poi.xslf.usermodel XSLFPictureData getData

Introduction

In this page you can find the example usage for org.apache.poi.xslf.usermodel XSLFPictureData getData.

Prototype

public byte[] getData() 

Source Link

Document

Gets the picture data as a byte array.

Usage

From source file:mj.ocraptor.extraction.tika.parser.microsoft.ooxml.XSLFPowerPointExtractorDecorator.java

License:Apache License

/**
 * @see org.apache.poi.xslf.extractor.XSLFPowerPointExtractor#getText()
 *//* w w  w. ja v  a2  s. c o m*/
protected void buildXHTML(XHTMLContentHandler xhtml) throws SAXException, IOException {
    XMLSlideShow slideShow = (XMLSlideShow) extractor.getDocument();

    XSLFSlide[] slides = slideShow.getSlides();
    for (XSLFSlide slide : slides) {
        String slideDesc;

        if (slide.getPackagePart() != null && slide.getPackagePart().getPartName() != null) {
            slideDesc = getJustFileName(slide.getPackagePart().getPartName().toString());
            slideDesc += "_";
        } else {
            slideDesc = null;
        }

        // slide
        extractContent(slide.getShapes(), false, xhtml, slideDesc);

        // slide layout which is the master sheet for this slide
        XSLFSheet slideLayout = slide.getMasterSheet();
        extractContent(slideLayout.getShapes(), true, xhtml, null);

        // slide master which is the master sheet for all text layouts
        XSLFSheet slideMaster = slideLayout.getMasterSheet();
        extractContent(slideMaster.getShapes(), true, xhtml, null);

        // notes (if present)
        XSLFSheet slideNotes = slide.getNotes();
        if (slideNotes != null) {
            extractContent(slideNotes.getShapes(), false, xhtml, slideDesc);
            // master sheet for this notes
            XSLFSheet notesMaster = slideNotes.getMasterSheet();
            extractContent(notesMaster.getShapes(), true, xhtml, null);
        }

        // comments (if present)
        XSLFComments comments = slide.getComments();
        if (comments != null) {
            for (CTComment comment : comments.getCTCommentsList().getCmList()) {
                xhtml.element("p", comment.getText());
            }
        }
    }

    if (Config.inst().getProp(ConfigBool.ENABLE_IMAGE_OCR)) {
        TikaImageHelper helper = new TikaImageHelper(metadata);
        try {
            List<XSLFPictureData> pictures = slideShow.getAllPictures();
            for (XSLFPictureData picture : pictures) {
                ByteArrayInputStream imageData = new ByteArrayInputStream(picture.getData());
                BufferedImage image = ImageIO.read(imageData);
                helper.addImage(image);
                helper.addTextToHandler(xhtml);
            }
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            if (extractor != null) {
                extractor.close();
            }
            if (helper != null) {
                helper.close();
            }
        }
    }
}

---

From source file:org.sleuthkit.autopsy.imageExtractor.ImageExtractor.java

private List<ExtractedImage> extractImagesFromPptx(AbstractFile af) {
    List<ExtractedImage> listOfExtractedImages = new ArrayList<ExtractedImage>();
    String parentFileName = getUniqueName(af);
    XMLSlideShow pptx;/*  w  w  w  .  j  a  v a 2 s . c  om*/
    try {
        pptx = new XMLSlideShow(new ReadContentInputStream(af));
    } catch (IOException ex) {
        logger.log(Level.WARNING, "SlideShow container could not be instantiated while reading " + af.getName(),
                ex);
        return null;
    }
    List<XSLFPictureData> listOfAllPictures = pptx.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;
    }

    for (XSLFPictureData xslsPicture : listOfAllPictures) {

        // get image file name, write it to the module outputFolder, and add
        // it to the listOfExtractedImages.
        String fileName = xslsPicture.getFileName();
        FileOutputStream fos = null;
        try {
            fos = new FileOutputStream(outputFolderPath + File.separator + fileName);
        } catch (FileNotFoundException ex) {
            logger.log(Level.WARNING, "Invalid path provided for image extraction", ex);
            continue;
        }
        try {
            fos.write(xslsPicture.getData());
            fos.close();
        } 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 + fileName;
        long size = xslsPicture.getData().length;
        ExtractedImage extractedimage = new ExtractedImage(fileName, 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 pptx 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  w  w  w .ja  v  a 2 s.c om
 */
private List<ExtractedImage> extractImagesFromPptx(AbstractFile af) {
    List<ExtractedImage> listOfExtractedImages;
    XMLSlideShow pptx;
    try {
        pptx = new XMLSlideShow(new ReadContentInputStream(af));
    } catch (Throwable ex) {
        // instantiating POI containers throw RuntimeExceptions
        logger.log(Level.WARNING, NbBundle.getMessage(this.getClass(),
                "EmbeddedFileExtractorIngestModule.ImageExtractor.pptxContainer.init.err", af.getName()), ex); //NON-NLS
        return null;
    }
    List<XSLFPictureData> listOfAllPictures = null;
    try {
        listOfAllPictures = pptx.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;
    }

    listOfExtractedImages = new ArrayList<>();
    byte[] data = null;
    for (XSLFPictureData xslsPicture : listOfAllPictures) {

        // get image file name, write it to the module outputFolder, and add
        // it to the listOfExtractedImageAbstractFiles.
        String fileName = xslsPicture.getFileName();
        try {
            data = xslsPicture.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, fileName).toString(), data);
        listOfExtractedImages.add(
                new ExtractedImage(fileName, getFileRelativePath(fileName), xslsPicture.getData().length, af));

    }

    return listOfExtractedImages;

}

---