Example usage for org.apache.poi.xwpf.usermodel XWPFDocument getAllPictures

Introduction

In this page you can find the example usage for org.apache.poi.xwpf.usermodel XWPFDocument getAllPictures.

Prototype

public List<XWPFPictureData> getAllPictures() 

Source Link

Document

Returns all Pictures, which are referenced from the document itself.

Usage

From source file:com.swg.parse.docx.NewExtract.java

private void extractImages(String src, int cnt) {

    try {//from w  w  w.  jav  a 2s .c o m

        FileInputStream fs = new FileInputStream(src);
        XWPFDocument docx = new XWPFDocument(fs);
        List<XWPFPictureData> piclist = docx.getAllPictures();
        Iterator<XWPFPictureData> iterator = piclist.iterator();
        int i = 0;
        new File(
                "C:\\Users\\KXK3\\Documents\\NetBeansProjects\\ParseSuite2\\ParseDocx\\build\\test\\unit\\results\\NewPicFolder"
                        + cnt).mkdir();
        while (iterator.hasNext()) {
            XWPFPictureData pic = iterator.next();
            byte[] bytepic = pic.getData();
            BufferedImage imag = ImageIO.read(new ByteArrayInputStream(bytepic));
            File CreatedImageFile = new File(
                    "C:\\Users\\KXK3\\Documents\\NetBeansProjects\\ParseSuite2\\ParseDocx\\build\\test\\unit\\results\\NewPicFolder"
                            + cnt + "\\imagefromword" + i + ".jpg");
            ImageIO.write(imag, "jpg", new File(
                    "C:\\Users\\KXK3\\Documents\\NetBeansProjects\\ParseSuite2\\ParseDocx\\build\\test\\unit\\results\\NewPicFolder"
                            + cnt + "\\imagefromword" + i + ".jpg"));
            i++;
            System.out.println("path to image " + i + " = " + CreatedImageFile.getAbsolutePath());
            labelBeforePOJO.add("path to image " + i);
            ValueBeforePOJO.add(CreatedImageFile.getAbsolutePath());
            sectionBeforePOJO.add(section);
        }
    } catch (Exception e) {//I can handle the image advance conversion here?
        System.exit(-1);
    }

}

---

From source file:demo.poi.image.SimpleImages.java

License:Apache License

public static List<byte[]> extractImagesFromWord(InputStream file) {
    try {/* w w  w  . j a  v  a 2 s.  co  m*/
        List<byte[]> result = new ArrayList<byte[]>();
        XWPFDocument doc = new XWPFDocument(file);
        log.debug("{}", doc);

        for (XWPFPictureData picture : doc.getAllPictures()) {
            result.add(picture.getData());
            log.debug("{}", picture.getFileName());
        }

        return result;
    } catch (Exception e) {
        throw new RuntimeException(e);
    }
}

---

From source file:kz.service.DocumentReader.java

public static String readDocxFile(String fileName) {

    try {//from  w  w w . ja v a2s .c  o m
        File file = new File(fileName);
        FileInputStream fis = new FileInputStream(file.getAbsolutePath());
        StringBuffer content = new StringBuffer();

        XWPFDocument document = new XWPFDocument(fis);
        XWPFStyles styles = document.getStyles();

        List<XWPFParagraph> paragraphs = document.getParagraphs();
        List<XWPFTable> tables = document.getTables();
        List<XWPFPictureData> pictures = document.getAllPictures();

        //int Picture_ID = 0;
        for (XWPFPictureData picture : pictures) {
            //XWPFPictureData picture = pictures.get(Picture_ID);
            System.out.println("Picture: " + picture.getFileName());
            byte[] pictureData = picture.getData();
            BufferedImage image = ImageIO.read(new ByteArrayInputStream(pictureData));
            ImageIO.write(image, picture.getFileName(), file);
            content.append("<p>");
            content.append("Here must be image");
            content.append("</p>");
            //Picture_ID++;
        }

        Iterator<IBodyElement> bodyElementIterator = document.getBodyElementsIterator();
        int Table_ID = 0;
        int Paragraph_ID = 0;
        while (bodyElementIterator.hasNext()) {

            IBodyElement element = bodyElementIterator.next();
            System.out.println(element.getElementType().name());//prints Element type name

            if ("TABLE".equalsIgnoreCase(element.getElementType().name())) {

                content.append("<table>");
                XWPFTable table = tables.get(Table_ID);
                CTTbl cttbl = table.getCTTbl();
                CTTblPr cttblPr = cttbl.getTblPr();

                List<XWPFTableRow> tblRows = table.getRows();
                for (XWPFTableRow tblRow : tblRows) {
                    content.append("<tr>");
                    List<XWPFTableCell> tblCells = tblRow.getTableCells();
                    for (XWPFTableCell tblCell : tblCells) {
                        content.append("<td>");
                        content.append(tblCell.getText());
                        content.append("</td>");
                    }
                    content.append("</tr>");
                }
                content.append("</table>");
                Table_ID++;

            } else if ("PARAGRAPH".equalsIgnoreCase(element.getElementType().name())) {

                XWPFParagraph paragraph = paragraphs.get(Paragraph_ID);

                String styleClass = null;
                if (paragraph.getStyleID() != null) {
                    content.append("<p class=''>");
                    XWPFStyle style = styles.getStyle(paragraph.getStyleID());
                    if (style != null && style.getName() != null) {
                        //here will be code creation of tag with class style
                    }
                } else {
                    content.append("<p>");
                }
                content.append(paragraph.getText());
                content.append("</p>");
                Paragraph_ID++;

            }
        }

        fis.close();
        return content.toString();
    } catch (Exception e) {
        return e.toString();
    }

}

---

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

private List<ExtractedImage> extractImagesFromDocx(AbstractFile af) {
    // check for BBArtifact ENCRYPTION_DETECTED? Might be detected elsewhere...?
    // TODO check for BBArtifact ENCRYPTION_DETECTED? Might be detected elsewhere...?
    List<ExtractedImage> listOfExtractedImages = new ArrayList<ExtractedImage>();
    String parentFileName = getUniqueName(af);
    XWPFDocument docxA = null;
    try {// w ww.  j  a  va2  s  .  c o  m
        docxA = new XWPFDocument(new ReadContentInputStream(af));
    } catch (IOException ex) {
        logger.log(Level.WARNING,
                "XWPFDocument container could not be instantiated while reading " + af.getName(), ex);
        return null;
    }
    List<XWPFPictureData> listOfAllPictures = docxA.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 (XWPFPictureData xwpfPicture : listOfAllPictures) {
        String fileName = xwpfPicture.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(xwpfPicture.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 = xwpfPicture.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 docx 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  .  jav  a  2 s .c  om*/
 */
private List<ExtractedImage> extractImagesFromDocx(AbstractFile af) {
    List<ExtractedImage> listOfExtractedImages;
    XWPFDocument docx = null;
    try {
        docx = new XWPFDocument(new ReadContentInputStream(af));
    } catch (Throwable ex) {
        // instantiating POI containers throw RuntimeExceptions
        logger.log(Level.WARNING, NbBundle.getMessage(this.getClass(),
                "EmbeddedFileExtractorIngestModule.ImageExtractor.docxContainer.init.err", af.getName()), ex); //NON-NLS
        return null;
    }
    List<XWPFPictureData> listOfAllPictures = null;
    try {
        listOfAllPictures = docx.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 (XWPFPictureData xwpfPicture : listOfAllPictures) {
        String fileName = xwpfPicture.getFileName();
        try {
            data = xwpfPicture.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), xwpfPicture.getData().length, af));
    }
    return listOfExtractedImages;
}

---