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.exoplatform.services.document.impl.MSXWordDocumentReader.java

License:Open Source License

/**
 * @see org.exoplatform.services.document.DocumentReader#getProperties(java.io.InputStream)
 */// w ww .j  av a 2 s .c o m
public Properties getProperties(final InputStream is) throws IOException, DocumentReadException {
    POIPropertiesReader reader = new POIPropertiesReader();
    reader.readDCProperties(
            SecurityHelper.doPrivilegedIOExceptionAction(new PrivilegedExceptionAction<XWPFDocument>() {
                public XWPFDocument run() throws Exception {
                    return new XWPFDocument(is);
                }
            }));

    return reader.getProperties();
}

From source file:org.isisaddons.module.xdocreport.dom.example.Generate2Pdf.java

License:Apache License

public static void main(String[] args) throws IOException, XDocReportException {

    // 1) Load DOCX into XWPFDocument
    InputStream in = new FileInputStream(new File("target/Project.docx"));
    XWPFDocument document = new XWPFDocument(in);

    // 2) Prepare Pdf options
    PdfOptions options = PdfOptions.create();

    // 3) Convert XWPFDocument to Pdf
    OutputStream out = new FileOutputStream(new File("target/Project.pdf"));
    PdfConverter.getInstance().convert(document, out, options);
}

From source file:org.isisaddons.module.xdocreport.dom.service.XDocReportService.java

License:Apache License

private byte[] toPdf(final byte[] docxBytes) throws IOException {

    XWPFDocument document = new XWPFDocument(new ByteArrayInputStream(docxBytes));

    final ByteArrayOutputStream baos = new ByteArrayOutputStream();
    PdfConverter.getInstance().convert(document, baos, pdfOptions);

    return baos.toByteArray();
}

From source file:org.joeffice.wordprocessor.reader.POIDocxReader.java

License:Apache License

/**
 * Reads content of specified stream to the document.
 *
 * @param in stream.// ww w . j  a  v  a2 s  . c  o m
 */
public void read(InputStream in, int offset) throws IOException, BadLocationException {
    poiDocument = new XWPFDocument(in);

    iteratePart(poiDocument.getBodyElements());

    this.currentOffset = offset;
    document.putProperty("XWPFDocument", poiDocument);
}

From source file:org.kimios.kernel.index.filters.ExcelXFilter.java

License:Open Source License

public String getBody(InputStream in) throws IOException {
    XWPFDocument doc = new XWPFDocument(in);
    XWPFWordExtractor ex = new XWPFWordExtractor(doc);
    String text = ex.getText();/*from   ww  w . java 2s .co  m*/
    return text;
}

From source file:org.kino.server.api.contractgenerator.java

static void writeDocxTemplate(InputStream src, OutputStream dststrem, Map<String, String> replacementMap)
        throws InvalidFormatException, IOException {
    XWPFDocument doc = new XWPFDocument(src);
    replaceInParagraphs(replacementMap, doc.getParagraphs());
    for (XWPFTable tbl : doc.getTables()) {
        for (XWPFTableRow row : tbl.getRows()) {
            for (XWPFTableCell cell : row.getTableCells()) {
                replaceInParagraphs(replacementMap, cell.getParagraphs());

            }/* w w w.  j  av  a  2s  .com*/
        }
    }

    doc.write(dststrem);

}

From source file:org.knime.ext.textprocessing.nodes.source.parser.word.WordDocumentParser.java

License:Open Source License

private Document parseInternal(final InputStream is) throws Exception {
    m_currentDoc = new DocumentBuilder(m_tokenizerName);
    m_currentDoc.setDocumentFile(new File(m_docPath));
    m_currentDoc.setDocumentType(m_type);
    m_currentDoc.addDocumentCategory(m_category);
    m_currentDoc.addDocumentSource(m_source);

    POIFSFileSystem poifs = null;//from   ww  w .  ja  va 2s  .c  o m
    HWPFDocument hdoc = null;
    XWPFDocument hdoc2 = null;
    WordExtractor extractor = null;

    try {
        // doc files
        if (m_docPath.endsWith(".doc")) {
            // copy content of input stream into byte array since content have to be red twice unfortunately.
            final ByteArrayOutputStream baos = new ByteArrayOutputStream();
            final byte[] buf = new byte[1024];
            int i = 0;
            while ((i = is.read(buf)) >= 0) {
                baos.write(buf, 0, i);
            }
            final byte[] content = baos.toByteArray();

            // open stream with copied content to read text
            InputStream copiedInput = new ByteArrayInputStream(content);
            hdoc = new HWPFDocument(copiedInput);
            extractor = new WordExtractor(hdoc);
            for (String p : extractor.getParagraphText()) {
                p = p.trim();
                if (!onlyWhitepscaes(p)) {
                    m_currentDoc.addParagraph(p);
                }
            }

            // open stream again with copied content to read meta info
            copiedInput = new ByteArrayInputStream(content);
            poifs = new POIFSFileSystem(copiedInput);
            final DirectoryEntry dir = poifs.getRoot();
            final DocumentEntry siEntry = (DocumentEntry) dir.getEntry(SummaryInformation.DEFAULT_STREAM_NAME);
            final PropertySet ps = new PropertySet(new DocumentInputStream(siEntry));

            final SummaryInformation si = new SummaryInformation(ps);

            setAuthor(si.getAuthor());
            setPublicationDate(si.getCreateDateTime());

            // docx files
        } else if (m_docPath.endsWith(".docx") || m_docPath.endsWith(".docm")) {
            hdoc2 = new XWPFDocument(is);
            final List<XWPFParagraph> paragraphs = hdoc2.getParagraphs();
            for (final XWPFParagraph paragraph : paragraphs) {
                final String text = paragraph.getText();
                if (!onlyWhitepscaes(text)) {
                    m_currentDoc.addParagraph(text);
                }
            }

            setAuthor(hdoc2.getProperties().getCoreProperties().getCreator());
            setPublicationDate(hdoc2.getProperties().getCoreProperties().getCreated());
        }

        m_currentDoc.createNewSection(SectionAnnotation.CHAPTER);

        // find title
        String title = null;

        if (m_filenameAsTitle) {
            title = m_docPath.trim();
        } else {
            final List<Section> sections = m_currentDoc.getSections();
            if (sections.size() > 0) {
                try {
                    title = sections.get(0).getParagraphs().get(0).getSentences().get(0).getText().trim();
                } catch (IndexOutOfBoundsException e) {
                    LOGGER.debug("Parsed word document " + m_docPath + " is empty.");
                    title = "";
                }
            }
        }
        if (!checkTitle(title)) {
            title = m_docPath.toString();
        }
        m_currentDoc.addTitle(title);

        return m_currentDoc.createDocument();
    } finally {
        is.close();
        if (poifs != null) {
            poifs.close();
        }
        if (hdoc != null) {
            hdoc.close();
        }
        if (hdoc2 != null) {
            hdoc2.close();
        }
        if (extractor != null) {
            extractor.close();
        }
    }
}

From source file:org.nuclos.server.common.ooxml.WordXMLReader.java

License:Open Source License

public WordXMLReader(InputStream is) throws IOException {
    this(new XWPFDocument(is));
}

From source file:org.nuxeo.ecm.platform.template.tests.TestOOoConvert.java

License:Apache License

@Test
public void testOfficeConverter4() throws Exception {
    ConversionService cs = Framework.getService(ConversionService.class);

    BlobHolder bh = getBlobFromPath("data/testMe.html", "text/html");
    String converterName = cs.getConverterName(bh.getBlob().getMimeType(),
            "application/vnd.openxmlformats-officedocument.wordprocessingml.document");
    assertEquals("any2docx", converterName);

    boolean isAvailable = cs.isConverterAvailable(converterName).isAvailable();
    assumeTrue(isAvailable);/*ww  w  . j a  va  2s .  c o m*/

    BlobHolder result = cs.convert(converterName, bh, null);
    File docxFile = Framework.createTempFile("docxfile", "docx");
    result.getBlob().transferTo(docxFile);

    XWPFDocument doc = new XWPFDocument(new FileInputStream(docxFile));
    XWPFWordExtractor extractor = new XWPFWordExtractor(doc);

    String text = extractor.getText();
    assertTrue(text.length() > 0);
    assertTrue(text.contains("Titre 1"));

    docxFile.delete();
}

From source file:org.obeonetwork.m2doc.api.POIServices.java

License:Open Source License

/**
 * Get XWPFDocument from template file./* w w w.j av  a  2  s. c o m*/
 * 
 * @param templateFile
 *            IFile
 * @return XWPFDocument
 * @throws IOException
 *             IOException
 */
public XWPFDocument getXWPFDocument(IFile templateFile) throws IOException {
    OPCPackage oPackage = getOPCPackage(templateFile);
    XWPFDocument document = new XWPFDocument(oPackage);
    return document;
}