Example usage for org.apache.poi.hwpf.model PicturesTable getAllPictures

Introduction

In this page you can find the example usage for org.apache.poi.hwpf.model PicturesTable getAllPictures.

Prototype

public List<Picture> getAllPictures() 

Source Link

Document

Not all documents have all the images concatenated in the data stream although MS claims so.

Usage

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

private List<ExtractedImage> extractImagesFromDoc(AbstractFile af) {
    // TODO check for BBArtifact ENCRYPTION_DETECTED? Might be detected elsewhere...?
    List<ExtractedImage> listOfExtractedImages = new ArrayList<ExtractedImage>();
    String parentFileName = getUniqueName(af);
    HWPFDocument docA = null;/*from   w ww  . j ava2s .  co  m*/
    try {
        docA = new HWPFDocument(new ReadContentInputStream(af));
    } catch (IOException ex) {
        logger.log(Level.WARNING,
                "HWPFDocument container could not be instantiated while reading " + af.getName(), ex);
        return null;
    }
    PicturesTable pictureTable = docA.getPicturesTable();
    List<org.apache.poi.hwpf.usermodel.Picture> listOfAllPictures = pictureTable.getAllPictures();
    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 (org.apache.poi.hwpf.usermodel.Picture picture : listOfAllPictures) {
        FileOutputStream fos = null;
        String fileName = picture.suggestFullFileName();
        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(picture.getContent());
            fos.close();
        } catch (IOException ex) {
            logger.log(Level.WARNING, "Could not write to the provided location", ex);
            continue;
        }
        // TODO Extract more info from the Picture viz ctime, crtime, atime, mtime
        String fileRelativePath = File.separator + moduleDirRelative + File.separator + parentFileName
                + File.separator + fileName;
        long size = picture.getSize();
        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 doc 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 . j  a va 2  s  .  c  o  m
 */
private List<ExtractedImage> extractImagesFromDoc(AbstractFile af) {
    List<ExtractedImage> listOfExtractedImages;
    HWPFDocument doc = null;
    try {
        doc = new HWPFDocument(new ReadContentInputStream(af));
    } catch (Throwable ex) {
        // instantiating POI containers throw RuntimeExceptions
        logger.log(Level.WARNING,
                NbBundle.getMessage(this.getClass(),
                        "EmbeddedFileExtractorIngestModule.ImageExtractor.docContainer.init.err", af.getName()),
                ex); //NON-NLS
        return null;
    }

    PicturesTable pictureTable = null;
    List<org.apache.poi.hwpf.usermodel.Picture> listOfAllPictures = null;
    try {
        pictureTable = doc.getPicturesTable();
        listOfAllPictures = pictureTable.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;
    }

    String outputFolderPath;
    if (listOfAllPictures.isEmpty()) {
        return null;
    } else {
        outputFolderPath = getOutputFolderPath(this.parentFileName);
    }
    if (outputFolderPath == null) {
        return null;
    }
    listOfExtractedImages = new ArrayList<>();
    byte[] data = null;
    for (org.apache.poi.hwpf.usermodel.Picture picture : listOfAllPictures) {
        String fileName = picture.suggestFullFileName();
        try {
            data = picture.getContent();
        } 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);
        // TODO Extract more info from the Picture viz ctime, crtime, atime, mtime
        listOfExtractedImages
                .add(new ExtractedImage(fileName, getFileRelativePath(fileName), picture.getSize(), af));
    }

    return listOfExtractedImages;
}

---