Example usage for org.apache.poi.xwpf.usermodel XWPFPictureData getData

List of usage examples for org.apache.poi.xwpf.usermodel XWPFPictureData getData

  1. HOME
  2. Java
  3. org.apache.poi
  4. org.apache.poi.xwpf.usermodel.*
  5. XWPFPictureData
  6. getData

Introduction

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

Prototype

public byte[] getData()

Source Link

Document

Gets the picture data as a byte array.

Usage

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

private void extractImages(String src, int cnt) {

    try {/*  w w w .jav  a2s  . 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 va2  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:fr.opensagres.poi.xwpf.converter.core.XWPFDocumentVisitor.java

License:Open Source License

private void visitGraphicalObject(T parentContainer, CTGraphicalObject graphic, Float offsetX,
        STRelFromH.Enum relativeFromH, Float offsetY, STRelFromV.Enum relativeFromV, STWrapText.Enum wrapText)
        throws Exception {
    if (graphic != null) {
        CTGraphicalObjectData graphicData = graphic.getGraphicData();
        if (graphicData != null) {
            XmlCursor c = graphicData.newCursor();
            c.selectPath("./*");
            while (c.toNextSelection()) {
                XmlObject o = c.getObject();
                if (o instanceof CTPicture) {
                    CTPicture picture = (CTPicture) o;
                    // extract the picture if needed
                    IImageExtractor extractor = getImageExtractor();
                    if (extractor != null) {
                        XWPFPictureData pictureData = getPictureData(picture);
                        if (pictureData != null) {
                            try {
                                extractor.extract(WORD_MEDIA + pictureData.getFileName(),
                                        pictureData.getData());
                            } catch (Throwable e) {
                                LOGGER.log(Level.SEVERE,
                                        "Error while extracting the image " + pictureData.getFileName(), e);
                            }//w w w.j av  a 2 s .  c  om
                        }
                    }
                    // visit the picture.
                    visitPicture(picture, offsetX, relativeFromH, offsetY, relativeFromV, wrapText,
                            parentContainer);
                }
            }
            c.dispose();
        }
    }
}

From source file:fr.opensagres.poi.xwpf.converter.pdf.internal.PdfMapper.java

License:Open Source License

@Override
protected void visitPicture(CTPicture picture, Float offsetX,
        org.openxmlformats.schemas.drawingml.x2006.wordprocessingDrawing.STRelFromH.Enum relativeFromH,
        Float offsetY,/*from w w w  . j  av  a 2s .c  om*/
        org.openxmlformats.schemas.drawingml.x2006.wordprocessingDrawing.STRelFromV.Enum relativeFromV,
        STWrapText.Enum wrapText, IITextContainer pdfParentContainer) throws Exception {

    CTPositiveSize2D ext = picture.getSpPr().getXfrm().getExt();
    long x = ext.getCx();
    long y = ext.getCy();

    XWPFPictureData pictureData = super.getPictureData(picture);
    if (pictureData != null) {
        try {
            Image img = Image.getInstance(pictureData.getData());
            img.scaleAbsolute(emu2points(x), emu2points(y));

            IITextContainer parentOfParentContainer = pdfParentContainer.getITextContainer();
            if (parentOfParentContainer != null && parentOfParentContainer instanceof PdfPCell) {
                parentOfParentContainer.addElement(img);
            } else {
                float chunkOffsetX = 0;
                if (offsetX != null) {
                    if (STRelFromH.CHARACTER.equals(relativeFromH)) {
                        chunkOffsetX = offsetX;
                    } else if (STRelFromH.COLUMN.equals(relativeFromH)) {
                        chunkOffsetX = offsetX;
                    } else if (STRelFromH.INSIDE_MARGIN.equals(relativeFromH)) {
                        chunkOffsetX = offsetX;
                    } else if (STRelFromH.LEFT_MARGIN.equals(relativeFromH)) {
                        chunkOffsetX = offsetX;
                    } else if (STRelFromH.MARGIN.equals(relativeFromH)) {
                        chunkOffsetX = pdfDocument.left() + offsetX;
                    } else if (STRelFromH.OUTSIDE_MARGIN.equals(relativeFromH)) {
                        chunkOffsetX = offsetX;
                    } else if (STRelFromH.PAGE.equals(relativeFromH)) {
                        chunkOffsetX = offsetX - pdfDocument.left();
                    }
                }

                float chunkOffsetY = 0;
                boolean useExtendedImage = false;
                if (STRelFromV.PARAGRAPH.equals(relativeFromV)) {
                    useExtendedImage = true;
                }

                if (useExtendedImage) {
                    ExtendedImage extImg = new ExtendedImage(img, -offsetY);

                    if (STRelFromV.PARAGRAPH.equals(relativeFromV)) {
                        chunkOffsetY = -extImg.getScaledHeight();
                    }

                    Chunk chunk = new Chunk(extImg, chunkOffsetX, chunkOffsetY, false);
                    pdfParentContainer.addElement(chunk);
                }
                /*
                 * float chunkOffsetY = 0; if ( wrapText != null ) {
                 * chunkOffsetY = -img.getScaledHeight(); } boolean
                 * useExtendedImage = offsetY != null; // if (
                 * STRelFromV.PARAGRAPH.equals( relativeFromV ) ) // { //
                 * useExtendedImage = true; // } // if ( useExtendedImage )
                 * { float imgY = -offsetY; if ( pdfHeader != null ) { float
                 * headerY = pdfHeader.getY() != null ? pdfHeader.getY() :
                 * 0; imgY += - img.getScaledHeight() + headerY; }
                 * ExtendedImage extImg = new ExtendedImage( img, imgY ); //
                 * if ( STRelFromV.PARAGRAPH.equals( relativeFromV ) ) // {
                 * // chunkOffsetY = -extImg.getScaledHeight(); // } Chunk
                 * chunk = new Chunk( extImg, chunkOffsetX, chunkOffsetY,
                 * false ); pdfParentContainer.addElement( chunk ); }
                 */
                else {
                    if (pdfParentContainer instanceof Paragraph) {
                        // I don't know why but we need add some spacing
                        // before in the paragraph
                        // otherwise the image cut the text of the below
                        // paragraph (see FormattingTests JUnit)?
                        Paragraph paragraph = (Paragraph) pdfParentContainer;
                        paragraph.setSpacingBefore(paragraph.getSpacingBefore() + 5f);
                    }
                    pdfParentContainer.addElement(new Chunk(img, chunkOffsetX, chunkOffsetY, false));
                }
            }

        } catch (Exception e) {
            LOGGER.severe(e.getMessage());
        }

    }
}

From source file:kz.service.DocumentReader.java

public static String readDocxFile(String fileName) {

    try {//  w  w  w .  ja v  a  2 s .  c  om
        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:offishell.word.WordHeleper.java

License:MIT License

/**
 * <p>//from w w  w  .j a  v  a2 s.  co  m
 * Helper method to clone {@link XWPFRun}.
 * </p>
 * 
 * @param in
 * @param out
 * @param model
 */
public static void copy(XWPFRun in, XWPFRun out, UnaryOperator<String> converter) {
    // copy
    out.setBold(in.isBold());
    out.setCapitalized(in.isCapitalized());
    out.setCharacterSpacing(in.getCharacterSpacing());
    out.setColor(in.getColor());
    out.setDoubleStrikethrough(in.isDoubleStrikeThrough());
    out.setEmbossed(in.isEmbossed());
    out.setFontFamily(in.getFontFamily());
    out.setFontSize(in.getFontSize());
    out.setImprinted(in.isImprinted());
    out.setItalic(in.isItalic());
    out.setKerning(in.getKerning());
    out.setShadow(in.isShadowed());
    out.setSmallCaps(in.isSmallCaps());
    out.setStrikeThrough(in.isStrikeThrough());
    out.setVerticalAlignment(out.getVerticalAlignment().toString());
    out.setTextPosition(in.getTextPosition());
    out.setUnderline(in.getUnderline());

    // copy context
    CTR inCTR = in.getCTR();
    CTRPr inPR = inCTR.getRPr();
    CTR outCTR = out.getCTR();
    CTRPr outPR = outCTR.isSetRPr() ? outCTR.getRPr() : outCTR.addNewRPr();
    outPR.set(inCTR.getRPr());
    out.setVerticalAlignment(
            inPR == null || inPR.getVertAlign() == null ? "baseline" : inPR.getVertAlign().toString());

    // // copy tab
    // CTEmpty[] tabs = inCTR.getTabArray();
    //
    // if (tabs.length != 0) {
    // out.addTab();
    // }
    outCTR.setAnnotationRefArray(inCTR.getAnnotationRefList().toArray(CTEmpty[]::new));
    outCTR.setBrArray(inCTR.getBrList().toArray(CTBr[]::new));
    outCTR.setCommentReferenceArray(inCTR.getCommentReferenceList().toArray(CTMarkup[]::new));
    outCTR.setContinuationSeparatorArray(inCTR.getContinuationSeparatorList().toArray(CTEmpty[]::new));
    outCTR.setCrArray(inCTR.getCrList().toArray(CTEmpty[]::new));
    outCTR.setDelInstrTextArray(inCTR.getDelInstrTextList().toArray(CTText[]::new));
    outCTR.setDrawingArray(inCTR.getDrawingList().toArray(CTDrawing[]::new));
    outCTR.setEndnoteRefArray(inCTR.getEndnoteRefList().toArray(CTEmpty[]::new));
    outCTR.setFldCharArray(inCTR.getFldCharList().toArray(CTFldChar[]::new));
    outCTR.setFootnoteRefArray(inCTR.getFootnoteRefList().toArray(CTEmpty[]::new));
    outCTR.setInstrTextArray(inCTR.getInstrTextList().toArray(CTText[]::new));
    outCTR.setLastRenderedPageBreakArray(inCTR.getLastRenderedPageBreakList().toArray(CTEmpty[]::new));
    outCTR.setObjectArray(inCTR.getObjectList().toArray(CTObject[]::new));
    outCTR.setPictArray(inCTR.getPictList().toArray(CTPicture[]::new));
    outCTR.setPtabArray(inCTR.getPtabList().toArray(CTPTab[]::new));
    outCTR.setSymArray(inCTR.getSymList().toArray(CTSym[]::new));
    outCTR.setTabArray(inCTR.getTabList().toArray(CTEmpty[]::new));

    // copy image
    for (XWPFPicture inPicture : in.getEmbeddedPictures()) {
        try {
            XWPFPictureData inData = inPicture.getPictureData();
            String outId = out.getDocument().addPictureData(new ByteArrayInputStream(inData.getData()),
                    inData.getPictureType());

            select(CTBlip.class, outCTR).to(blip -> blip.setEmbed(outId));
        } catch (Exception e) {
            throw I.quiet(e);
        }
    }

    // copy text
    write(out, converter.apply(in.text()));
}

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;/*from w  w w . j a  va  2s . c om*/
    try {
        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 ww  w .java2s .  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;
}