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

List of usage examples for org.apache.poi.xwpf.usermodel XWPFDocument XWPFDocument

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

Introduction

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

Prototype

public XWPFDocument(InputStream is) throws IOException

Source Link

Usage

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.// w  w  w . ja va 2s. c  o  m
 */
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;
}

From source file:org.terrier.indexing.POIDocument.java

License:Mozilla Public License

protected POITextExtractor getExtractor(String filename, InputStream docStream) throws IOException {
    //Word .doc: 
    if (filename.endsWith(".doc")) {
        return new WordExtractor(docStream);
    }//from  w w w.j a v  a 2s.c  om
    //Word .docx:
    if (filename.endsWith(".docx")) {
        return new XWPFWordExtractor(new XWPFDocument(docStream));
    }
    //Powertpoint .ppt: 
    if (filename.endsWith(".ppt")) {
        return new PowerPointExtractor(docStream);
    }
    //Powertpoint .pptx: 
    if (filename.endsWith(".pptx")) {
        return new XSLFPowerPointExtractor(new XMLSlideShow(docStream));
    }
    //Publisher .pub: 
    if (filename.endsWith(".pub")) {
        return new PublisherTextExtractor(docStream);
    }
    //Excel: .xls:
    if (filename.endsWith(".xls")) {
        return new ExcelExtractor(new POIFSFileSystem(docStream));
    }
    //Excel: .xlsx:
    if (filename.endsWith(".xlsx")) {
        return new org.apache.poi.xssf.extractor.XSSFExcelExtractor(new XSSFWorkbook(docStream));
    }
    //Visio: .vsd:
    if (filename.endsWith(".vsd")) {
        return new VisioTextExtractor(docStream);
    }
    return null;
}

From source file:org.wandora.utils.MSOfficeBox.java

License:Open Source License

public static String getDocxText(File file) {
    try {/*from ww w .ja va  2s. co  m*/
        XWPFDocument docx = new XWPFDocument(new FileInputStream(file));
        XWPFWordExtractor extractor = new XWPFWordExtractor(docx);
        String text = extractor.getText();
        return text;
    } catch (Exception e) {
        e.printStackTrace();
    }
    return null;
}

From source file:org.wso2.carbon.apimgt.impl.indexing.indexer.DocumentIndexer.java

License:Open Source License

/**
 * Write document content to document artifact as its raw content
 *
 * @param registry//from ww w. j  a  v  a 2 s  . c  o m
 * @param documentResource
 * @return
 * @throws RegistryException
 * @throws IOException
 * @throws APIManagementException
 */
private String fetchDocumentContent(Registry registry, Resource documentResource)
        throws RegistryException, IOException, APIManagementException {
    GenericArtifactManager docArtifactManager = APIUtil.getArtifactManager(registry,
            APIConstants.DOCUMENTATION_KEY);
    GenericArtifact documentArtifact = docArtifactManager.getGenericArtifact(documentResource.getUUID());
    String sourceType = documentArtifact.getAttribute(APIConstants.DOC_SOURCE_TYPE);

    String contentString = null;
    if (Documentation.DocumentSourceType.FILE.name().equals(sourceType)) {
        Association fileAssociations[] = registry.getAssociations(documentResource.getPath(),
                APIConstants.DOCUMENTATION_FILE_ASSOCIATION);
        Association fileAssociation;

        if (fileAssociations.length < 1) {
            String error = "No document associated to API";
            log.error(error);
            throw new APIManagementException(error);
        }

        //a file document can have one file association
        fileAssociation = fileAssociations[0];
        String contentPath = fileAssociation.getDestinationPath();

        if (!registry.resourceExists(contentPath)) {
            String error = "API not found at " + contentPath;
            log.error(error);
            throw new APIManagementException(error);
        }

        Resource contentResource = registry.get(contentPath);

        String fileName = ((ResourceImpl) contentResource).getName();
        String extension = FilenameUtils.getExtension(fileName);
        InputStream inputStream = null;
        try {
            inputStream = contentResource.getContentStream();
            switch (extension) {
            case APIConstants.PDF_EXTENSION:
                PDFParser pdfParser = new PDFParser(inputStream);
                pdfParser.parse();
                COSDocument cosDocument = pdfParser.getDocument();
                PDFTextStripper stripper = new PDFTextStripper();
                contentString = stripper.getText(new PDDocument(cosDocument));
                break;
            case APIConstants.DOC_EXTENSION: {
                POIFSFileSystem pfs = new POIFSFileSystem(inputStream);
                WordExtractor msWord2003Extractor = new WordExtractor(pfs);
                contentString = msWord2003Extractor.getText();
                break;
            }
            case APIConstants.DOCX_EXTENSION:
                XWPFDocument doc = new XWPFDocument(inputStream);
                XWPFWordExtractor msWord2007Extractor = new XWPFWordExtractor(doc);
                contentString = msWord2007Extractor.getText();
                break;
            case APIConstants.XLS_EXTENSION: {
                POIFSFileSystem pfs = new POIFSFileSystem(inputStream);
                ExcelExtractor extractor = new ExcelExtractor(pfs);
                contentString = extractor.getText();
                break;
            }
            case APIConstants.XLSX_EXTENSION:
                XSSFWorkbook xssfSheets = new XSSFWorkbook(inputStream);
                XSSFExcelExtractor xssfExcelExtractor = new XSSFExcelExtractor(xssfSheets);
                contentString = xssfExcelExtractor.getText();
                break;
            case APIConstants.PPT_EXTENSION: {
                POIFSFileSystem fs = new POIFSFileSystem(inputStream);
                PowerPointExtractor extractor = new PowerPointExtractor(fs);
                contentString = extractor.getText();
                break;
            }
            case APIConstants.PPTX_EXTENSION:
                XMLSlideShow xmlSlideShow = new XMLSlideShow(inputStream);
                XSLFPowerPointExtractor xslfPowerPointExtractor = new XSLFPowerPointExtractor(xmlSlideShow);
                contentString = xslfPowerPointExtractor.getText();
                break;
            case APIConstants.TXT_EXTENSION:
            case APIConstants.WSDL_EXTENSION:
            case APIConstants.XML_DOC_EXTENSION:
                BufferedReader reader = new BufferedReader(new InputStreamReader(inputStream));
                String line;
                StringBuilder contentBuilder = new StringBuilder();
                while ((line = reader.readLine()) != null) {
                    contentBuilder.append(line);
                }
                contentString = contentBuilder.toString();
                break;
            }
        } finally {
            IOUtils.closeQuietly(inputStream);
        }

    } else if (Documentation.DocumentSourceType.INLINE.name().equals(sourceType)) {
        Association contentAssociations[] = registry.getAssociations(documentResource.getPath(),
                APIConstants.DOCUMENTATION_CONTENT_ASSOCIATION);
        Association contentAssociation;

        //an inline document can have one or no content associations
        if (contentAssociations.length == 1) {
            contentAssociation = contentAssociations[0];
            String contentPath = contentAssociation.getDestinationPath();

            if (registry.resourceExists(contentPath)) {
                Resource contentResource = registry.get(contentPath);

                InputStream instream = null;
                BufferedReader reader = null;
                String line;
                try {
                    instream = contentResource.getContentStream();
                    reader = new BufferedReader(new InputStreamReader(instream));
                    StringBuilder contentBuilder = new StringBuilder();
                    while ((line = reader.readLine()) != null) {
                        contentBuilder.append(line);
                    }
                    contentString = contentBuilder.toString();
                } finally {
                    if (reader != null) {
                        IOUtils.closeQuietly(reader);
                    }
                }
            }
        }
    }
    return contentString;
}

From source file:org.wso2.carbon.pc.core.DocumentIndexer.java

License:Open Source License

@Override
public IndexDocument getIndexedDocument(AsyncIndexer.File2Index fileData)
        throws SolrException, RegistryException {
    try {//from  www .jav a2  s  .  c  om
        String wordText = null;
        try {
            //Extract MSWord 2003 document files
            POIFSFileSystem fs = new POIFSFileSystem(new ByteArrayInputStream(fileData.data));

            WordExtractor msWord2003Extractor = new WordExtractor(fs);
            wordText = msWord2003Extractor.getText();

        } catch (OfficeXmlFileException e) {
            //if 2003 extraction failed, try with MSWord 2007 document files extractor
            XWPFDocument doc = new XWPFDocument(new ByteArrayInputStream(fileData.data));

            XWPFWordExtractor msWord2007Extractor = new XWPFWordExtractor(doc);
            wordText = msWord2007Extractor.getText();

        } catch (Exception e) {
            //The reason for not throwing an exception is that since this is an indexer that runs in the background
            //throwing an exception might lead to adverse behaviors in the client side and might lead to
            //other files not being indexed
            String msg = "Failed to extract the document while indexing";
            log.error(msg, e);
        }
        IndexDocument indexDoc = new IndexDocument(fileData.path, wordText, null);

        Map<String, List<String>> fields = new HashMap<String, List<String>>();
        fields.put("path", Arrays.asList(fileData.path));
        if (fileData.mediaType != null) {
            fields.put(IndexingConstants.FIELD_MEDIA_TYPE, Arrays.asList(fileData.mediaType));
        } else {
            fields.put(IndexingConstants.FIELD_MEDIA_TYPE, Arrays.asList("application/pdf"));
        }

        indexDoc.setFields(fields);

        return indexDoc;

    } catch (IOException e) {
        String msg = "Failed to write to the index";
        log.error(msg, e);
        throw new SolrException(SolrException.ErrorCode.SERVER_ERROR, msg);
    }
}

From source file:org.wurtele.ifttt.watchers.TrainingScheduleWatcher.java

License:Open Source License

private void processWordFile(Path path) {
    try {/*from  w  w w  .  j  a va  2  s  .  c om*/
        XWPFDocument doc = new XWPFDocument(Files.newInputStream(path));
        XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
        List<List<String>> data = new ArrayList<>();
        DateFormat df1 = new SimpleDateFormat("MMM dd, yyyy");
        DateFormat df2 = new SimpleDateFormat("MMM dd, yyyy HH:mm");
        Arrays.asList(extractor.getText().split("\n")).stream().forEach((line) -> {
            try {
                df1.parse(line.split("\t")[0]);
                List<String> list = new ArrayList<>();
                list.addAll(Arrays.asList(line.split("\t")));
                data.add(list);
            } catch (ParseException pe) {
            }
            if (line.startsWith("\t"))
                data.get(data.size() - 1).addAll(Arrays.asList(line.substring(1).split("\t")));
        });
        List<TrainingScheduleEntry> entries = new ArrayList<>();
        for (List<String> event : data) {
            TrainingScheduleEntry entry = new TrainingScheduleEntry();
            entry.setStart(df2.parse(event.get(0) + " " + event.get(1)));
            entry.setEnd(df2.parse(event.get(0) + " " + event.get(2)));
            entry.setGroup(event.get(4));
            entry.setTitle(event.get(5));
            entry.setNotes(event.get(6).length() > 6 ? event.get(6).substring(6) : event.get(6));
            if (event.size() > 13) {
                for (int i = 7; i < 7 + event.size() - 13; i++) {
                    entry.setNotes(entry.getNotes() + " " + event.get(i));
                }
            }
            entry.setInstructor(event.get(event.size() - 6).trim());
            entry.setUniform(event.get(event.size() - 5));
            entry.setLocation(event.get(event.size() - 2));
            entries.add(entry);
        }

        if (!entries.isEmpty()) {
            Collections.sort(entries);

            try (OutputStream os = Files.newOutputStream(processedPath(path));
                    ObjectOutputStream oos = new ObjectOutputStream(os)) {
                oos.writeObject(entries);
            }
            logger.info("Processed " + path);
            Date start = DateUtils.truncate(entries.get(0).getStart(), Calendar.DATE);
            Date end = DateUtils.truncate(entries.get(entries.size() - 1).getEnd(), Calendar.DATE);
            DateFormat df = new SimpleDateFormat("MMM d, yyyy");
            String payload = APNS.newPayload().category("scheduleCategory")
                    .alertTitle("Training Schedule Received")
                    .alertBody(entries.size() + " events found for "
                            + (start.before(end) ? df.format(start) + " - " + df.format(end)
                                    : df.format(start)))
                    .sound("default").customField("schedule", path.getParent().getFileName().toString() + "/"
                            + FilenameUtils.getBaseName(path.getFileName().toString()))
                    .build();
            PushDevices.getDevices().stream().forEach((device) -> {
                PushUtils.getService().push(device, payload);
            });
        }
    } catch (Exception e) {
        logger.error("Failed to process training schedule file: " + path, e);
        FAILED.add(path);
    }
}

From source file:pe.gob.onpe.rae.controller.registro.registroController.java

@RequestMapping(value = "generateFVDoc/{codExpediente}", method = RequestMethod.GET)
public void generateFVDoc(HttpServletRequest request, @PathVariable("codExpediente") int codExpediente,
        HttpServletResponse response) {/*from   w  w w  .ja  va 2  s  .  c  o  m*/
    try {
        ServletContext sc = request.getSession().getServletContext();

        Expediente expediente = new Expediente(codExpediente);
        expediente = expedienteDAO.find(expediente);

        Ambito amb = new Ambito(expediente.getAmbito().getId());
        amb = ambitoDAO.find(amb);

        int totalElectoresRemitidos = expedientePadronDAO.getCountByExpediente(expediente);
        int totalElectoresIncorporados = expedientePadronDAO.getCountByExpedienteAndEstado(expediente,
                Parametros.ESTADO_ELECTOR_ACTIVO);

        JsonParser jsonParser = new JsonParser();
        JsonObject jsonObject = (JsonObject) jsonParser.parse(amb.getInformacion());
        String nombre = jsonObject.get("nombres").toString() + " "
                + jsonObject.get("apellidoPaterno").toString() + " "
                + jsonObject.get("apellidoMaterno").toString();

        InputStream is = registroController.class.getResourceAsStream("/ejemplo.docx");
        XWPFDocument document = new XWPFDocument(is);

        XWPFHeaderFooterPolicy policy = document.getHeaderFooterPolicy();
        if (policy == null) {
            CTSectPr sectPr = document.getDocument().getBody().addNewSectPr();
            policy = new XWPFHeaderFooterPolicy(document, sectPr);
        }

        if (policy.getDefaultHeader() == null && policy.getFirstPageHeader() == null
                && policy.getDefaultFooter() == null) {
            XWPFFooter footerD = policy.getFooter(1);// createFooter(policy.DEFAULT);
            XWPFRun run = footerD.getParagraphs().get(0).createRun();
            run.setText("usuario");
            XWPFParagraph paragraph = footerD.createParagraph();
            paragraph.setAlignment(ParagraphAlignment.DISTRIBUTE);
            run = paragraph.createRun();
            run.setFontFamily("Arial");
            run.setFontSize(8);
            run.setText(
                    "Jr.Washington N 1894, Cercado de Lima. Central Telefonica: 417-0630 www.onpe.gob.pe informes@onpe.gob.pe");

        }

        XWPFParagraph paragraph = document.createParagraph();

        XWPFRun run = paragraph.createRun();
        run.setFontSize(11);
        run.setFontFamily("Arial");
        run.setText("Lima,");
        run.addBreak();

        paragraph = document.createParagraph();
        run = paragraph.createRun();
        run.setFontSize(11);
        run.setFontFamily("Arial");
        run.setBold(true);
        run.setText("OFICIO N       -2016-GPP/ONPE");
        run.setUnderline(UnderlinePatterns.SINGLE);
        run.addBreak();

        paragraph = document.createParagraph();
        run = paragraph.createRun();
        run.setFontSize(11);
        run.setFontFamily("Arial");
        run.setText("Seor");

        XWPFRun run1 = paragraph.createRun();
        run1.setFontSize(11);
        run1.setFontFamily("Arial");
        run1.setText(nombre.replace("\"", ""));
        run1.setBold(true);
        run1.addBreak();

        XWPFRun run2 = paragraph.createRun();
        run2.setFontSize(11);
        run2.setFontFamily("Arial");
        run2.setText(jsonObject.get("cargo").toString().replace("\"", ""));
        run2.addBreak();
        run2.setText("Centro Poblado " + amb.getNombreAmbito());
        run2.addBreak();
        run2.setText("Av. 28 de Julio S/N Centro Cvico Huacrachuco - Municipalidad Provincial de "
                + amb.getProvincia());
        run2.addBreak();
        run2.setText(amb.getDepartamento() + " - " + amb.getProvincia() + " - " + amb.getDistrito());
        run2.addBreak();

        run2 = paragraph.createRun();
        run2.setFontSize(11);
        run2.setFontFamily("Arial");
        run2.setUnderline(UnderlinePatterns.WORDS);
        run2.setText("Presente");

        run2 = paragraph.createRun();
        run2.setFontSize(11);
        run2.setFontFamily("Arial");
        run2.setText(".-");

        paragraph = document.createParagraph();
        run.addBreak();
        run = paragraph.createRun();
        run.setFontSize(11);
        run.setFontFamily("Arial");
        run.addBreak();
        run.setText("Asunto");
        run.addTab();
        run.addTab();
        run.setText(": SOLICITUD DE CREACIN DE MESA DE SUFRAGIO.");
        run.addBreak();

        paragraph = document.createParagraph();
        run = paragraph.createRun();
        run.setFontSize(11);
        run.setFontFamily("Arial");
        run.setText("Referencia");
        run.addTab();
        run.setText(": OFICIO N 087-2016/M-CP.CHOCOBAMBA (16AGO2016) - Exp. " + expediente.getExpediente());
        run.addBreak();

        paragraph = document.createParagraph();
        paragraph.setAlignment(ParagraphAlignment.THAI_DISTRIBUTE);
        run = paragraph.createRun();
        run.setFontSize(11);
        run.setFontFamily("Arial");
        run.setText(
                "Me dirijo a usted con relacin al documento de la referencia con la finalidad de hacer de su "
                        + "conocimiento que se ha cumplido con todos los requisitos que dan inicio al trmite de "
                        + "instalacin de mesas de sufragio en el Centro Poblado " + amb.getNombreAmbito()
                        + ", distrito " + amb.getDistrito() + ", " + "provincia " + amb.getProvincia()
                        + ", departamento " + amb.getDepartamento() + ".");
        paragraph = document.createParagraph();
        paragraph.setAlignment(ParagraphAlignment.THAI_DISTRIBUTE);
        run = paragraph.createRun();
        run.setFontSize(11);
        run.setFontFamily("Arial");
        run.addBreak();
        run.setText("Al respecto, el mencionado expediente contiene un listado de electores que solicitan ser "
                + "parte de la mesa de sufragio de la localidad " + amb.getNombreAmbito()
                + ", el cual, luego de la validacin " + "realizada, se informa que podrn ser incorporados "
                + totalElectoresIncorporados + " electores del total de " + totalElectoresRemitidos
                + " registros "
                + "de electores remitidos. Se adjunta un cuadro resumen con las observaciones mencionadas.");
        paragraph = document.createParagraph();
        paragraph.setAlignment(ParagraphAlignment.THAI_DISTRIBUTE);
        run = paragraph.createRun();
        run.setFontSize(11);
        run.setFontFamily("Arial");
        run.addBreak();
        run.setText(
                "Asimismo, se programar un viaje para la verificacin de rutas, tiempos y servicios de la "
                        + "localidad, la cual se coordinar previamente con las autoridades del centro poblado a fin de "
                        + "programarla adecuadamente; luego de lo cual se emitir un informe de respuesta al "
                        + "resultado de la solicitud, que de ser positivo, conllevara a la instalacin de mesas de sufragio "
                        + "en el centro poblado en mencin, con miras a las ");
        run = paragraph.createRun();
        run.setFontSize(11);
        run.setFontFamily("Arial");
        run.setBold(true);
        run.setText("Elecciones Regionales y Municipales de 2018.");
        paragraph = document.createParagraph();
        paragraph.setAlignment(ParagraphAlignment.THAI_DISTRIBUTE);
        run = paragraph.createRun();
        run.setFontSize(11);
        run.setFontFamily("Arial");
        run.addBreak();
        run.setText("Finalmente, de requerir mayor informacin, agradeceremos se comunique con nosotros al "
                + "telefono 417-0630 anexo 8484 o al 8481.");
        paragraph = document.createParagraph();
        paragraph.setAlignment(ParagraphAlignment.THAI_DISTRIBUTE);
        run = paragraph.createRun();
        run.setFontSize(11);
        run.setFontFamily("Arial");
        run.addBreak();
        run.setText("Sin otro particular.");

        paragraph = document.createParagraph();
        paragraph.setAlignment(ParagraphAlignment.THAI_DISTRIBUTE);
        run = paragraph.createRun();
        run.setFontSize(11);
        run.setFontFamily("Arial");
        run.addBreak();
        run.addBreak();
        run.setText("Atentamente,");
        response.setContentType("application/vnd.openxmlformats-officedocument.wordprocessingml.document");
        document.write(response.getOutputStream());
    } catch (Exception ex) {
        Logger.getLogger(registroController.class.getName()).log(Level.SEVERE, null, ex);
    }
}

From source file:persistentie.PixelMapper.java

public List<String> leesDocFile(String bestandsNaam) {
    List<String> zin = new ArrayList<>();
    letterLijst = new ArrayList<>();
    File file = null;/*w  ww .  j a  v  a2s  .c om*/
    XWPFWordExtractor extractor = null;
    try {
        XWPFDocument document = new XWPFDocument(Files.newInputStream(Paths.get(bestandsNaam)));
        List<XWPFParagraph> paragraphs = document.getParagraphs();
        for (XWPFParagraph par : paragraphs) {
            /**
             * Elke paragraph op spaties splitten en elk woord in de letterlijst plaatsen.
             */
            zin = Arrays.asList(par.getParagraphText().split(" "));
            for (String woord : zin) {
                letterLijst.add(woord);
                letterLijst.add(" ");
            }
            letterLijst.add("\n");
        }
    } catch (Exception exep) {
        exep.printStackTrace();
    }

    return letterLijst;
}

From source file:poi.xssf.usermodel.examples.EmbeddedObjects.java

License:Apache License

public static void main(String[] args) throws Exception {
    OPCPackage pkg = OPCPackage.open(args[0]);
    XSSFWorkbook workbook = new XSSFWorkbook(pkg);
    for (PackagePart pPart : workbook.getAllEmbedds()) {
        String contentType = pPart.getContentType();
        // Excel Workbook - either binary or OpenXML
        if (contentType.equals("application/vnd.ms-excel")) {
            HSSFWorkbook embeddedWorkbook = new HSSFWorkbook(pPart.getInputStream());
        }/*w w w  . j a  v  a  2s.  c  om*/
        // Excel Workbook - OpenXML file format
        else if (contentType.equals("application/vnd.openxmlformats-officedocument.spreadsheetml.sheet")) {
            XSSFWorkbook embeddedWorkbook = new XSSFWorkbook(pPart.getInputStream());
        }
        // Word Document - binary (OLE2CDF) file format
        else if (contentType.equals("application/msword")) {
            HWPFDocument document = new HWPFDocument(pPart.getInputStream());
        }
        // Word Document - OpenXML file format
        else if (contentType
                .equals("application/vnd.openxmlformats-officedocument.wordprocessingml.document")) {
            XWPFDocument document = new XWPFDocument(pPart.getInputStream());
        }
        // PowerPoint Document - binary file format
        else if (contentType.equals("application/vnd.ms-powerpoint")) {
            HSLFSlideShow slideShow = new HSLFSlideShow(pPart.getInputStream());
        }
        // PowerPoint Document - OpenXML file format
        else if (contentType
                .equals("application/vnd.openxmlformats-officedocument.presentationml.presentation")) {
            OPCPackage docPackage = OPCPackage.open(pPart.getInputStream());
            XSLFSlideShow slideShow = new XSLFSlideShow(docPackage);
        }
        // Any other type of embedded object.
        else {
            System.out.println("Unknown Embedded Document: " + contentType);
            InputStream inputStream = pPart.getInputStream();
        }
    }
    pkg.close();
}

From source file:ro.dabuno.office.integration.MailMerge.java

private void merge(File wordTemplate, File dataFile, String outputFile) throws Exception {
    log.info("Merging data from " + wordTemplate + " and " + dataFile + " into " + outputFile);

    // read the data-rows from the CSV or XLS(X) file
    Data data = new Data();
    data.read(dataFile);//ww  w .  j a  v  a 2s . c o  m

    // now open the word file and apply the changes
    try (InputStream is = new FileInputStream(wordTemplate)) {
        try (XWPFDocument doc = new XWPFDocument(is)) {
            // apply the lines and concatenate the results into the document
            applyLines(data, doc);

            log.info("Writing overall result to " + outputFile);
            try (OutputStream out = new FileOutputStream(outputFile)) {
                doc.write(out);
            }
        }
    }
}