Example usage for org.apache.poi.hslf.extractor PowerPointExtractor PowerPointExtractor

List of usage examples for org.apache.poi.hslf.extractor PowerPointExtractor PowerPointExtractor

  1. HOME
  2. Java
  3. org.apache.poi
  4. org.apache.poi.hslf.extractor.*
  5. PowerPointExtractor
  6. PowerPointExtractor

Introduction

In this page you can find the example usage for org.apache.poi.hslf.extractor PowerPointExtractor PowerPointExtractor.

Prototype

public PowerPointExtractor(HSLFSlideShowImpl ss)

Source Link

Document

Creates a PowerPointExtractor, from a HSLFSlideShow

Usage

From source file:com.docdoku.server.esindexer.ESTools.java

License:Open Source License

private static String microsoftPowerPointDocumentToString(InputStream inputStream) throws IOException {
    String strRet;/*  w  ww.j  ava 2  s . co  m*/
    try (InputStream pptStream = new BufferedInputStream(inputStream)) {
        if (POIFSFileSystem.hasPOIFSHeader(pptStream)) {
            PowerPointExtractor pptExtractor = new PowerPointExtractor(pptStream);
            strRet = pptExtractor.getText(true, true);
        } else {
            XSLFPowerPointExtractor pptExtractor = new XSLFPowerPointExtractor(new XMLSlideShow(pptStream));
            strRet = pptExtractor.getText(true, true, true);
        }
    }
    return strRet;
}

From source file:com.docdoku.server.IndexerBean.java

License:Open Source License

@Asynchronous
@Lock(LockType.WRITE)//from   w  w  w  .  j  a  v a2s .  c om
public void addToIndex(String fullName, String pathName) {
    IndexWriter indexWriter = null;
    Directory indexDir = null;
    try {
        indexDir = FSDirectory.open(new File(indexPath));
        indexWriter = new IndexWriter(indexDir, new StandardAnalyzer(Version.LUCENE_30),
                IndexWriter.MaxFieldLength.LIMITED);
        int ext = pathName.lastIndexOf('.');
        String extension = "";
        if (ext != -1) {
            extension = pathName.substring(ext);
        }

        if (extension.equals(".odt") || extension.equals(".ods") || extension.equals(".odp")
                || extension.equals(".odg") || extension.equals(".odc") || extension.equals(".odf")
                || extension.equals(".odb") || extension.equals(".odi") || extension.equals(".odm")) {
            final StringBuilder text = new StringBuilder();
            ZipInputStream zipOpenDoc = new ZipInputStream(
                    new BufferedInputStream(new FileInputStream(pathName)));
            ZipEntry zipEntry;
            while ((zipEntry = zipOpenDoc.getNextEntry()) != null) {
                if (zipEntry.getName().equals("content.xml")) {
                    SAXParserFactory saxParserFactory = SAXParserFactory.newInstance();
                    SAXParser parser = saxParserFactory.newSAXParser();
                    parser.parse(zipOpenDoc, new DefaultHandler() {

                        @Override
                        public void characters(char[] ch, int start, int length) throws SAXException {
                            for (int i = start; i < start + length; i++) {
                                text.append(ch[i]);
                            }
                            text.append("\r\n");
                        }
                    });
                    break;
                }
            }
            zipOpenDoc.close();
            Reader contentReader = new StringReader(text.toString());
            addDoc(indexWriter, contentReader, fullName);
            contentReader.close();
        } else if (extension.equals(".doc")) {
            //MSWord Document
            InputStream wordStream = new BufferedInputStream(new FileInputStream(pathName));
            WordExtractor wordExtractor = new WordExtractor(wordStream);
            Reader contentReader = new StringReader(wordExtractor.getText());
            wordStream.close();
            addDoc(indexWriter, contentReader, fullName);
            contentReader.close();
        } else if (extension.equals(".ppt") || extension.equals(".pps")) {
            //MSPowerPoint Document
            InputStream pptStream = new BufferedInputStream(new FileInputStream(pathName));
            PowerPointExtractor pptExtractor = new PowerPointExtractor(pptStream);
            Reader contentReader = new StringReader(pptExtractor.getText(true, true));
            pptStream.close();
            addDoc(indexWriter, contentReader, fullName);
            pptExtractor.close();
            contentReader.close();
        } else if (extension.equals(".txt")) {
            //Text Document
            Reader contentReader = new BufferedReader(new FileReader(pathName));
            addDoc(indexWriter, contentReader, fullName);
            contentReader.close();
        } else if (extension.equals(".xls")) {
            //MSExcelExtractor Document
            //InputStream excelStream=new BufferedInputStream(new FileInputStream(pathName));
            //ExcelExtractor excelExtractor= new ExcelExtractor(excelStream);
            //Reader contentReader=new StringReader(excelExtractor.getText());
            //excelStream.close();
            //addDoc(indexWriter,contentReader,fullName);
            //excelExtractor.close();
            //contentReader.close();
        } else if (extension.equals(".html") || extension.equals(".htm")) {
        } else if (extension.equals(".csv")) {
        } else if (extension.equals(".xml")) {
        } else if (extension.equals(".rtf")) {
        } else if (extension.equals(".pdf")) {
        } else if (extension.equals(".msg")) {
        }
    } catch (CorruptIndexException ex) {
        throw new EJBException(ex);
    } catch (LockObtainFailedException ex) {
        try {
            if (IndexWriter.isLocked(indexDir)) {
                IndexWriter.unlock(indexDir);
            }
        } catch (IOException pIOEx) {
            throw new EJBException(pIOEx);
        }
        throw new EJBException(ex);
    } catch (ParserConfigurationException ex) {
        throw new EJBException(ex);
    } catch (SAXException ex) {
        throw new EJBException(ex);
    } catch (IOException ex) {
        throw new EJBException(ex);
    } finally {
        try {
            if (indexWriter != null) {
                indexWriter.close();
            }
        } catch (IOException ex) {
            throw new EJBException(ex);
        }
    }
}

From source file:com.frameworkset.platform.cms.searchmanager.extractors.CmsExtractorMsPowerPoint.java

License:Open Source License

/** 
* ?ppt /*from   www.  j  a v  a  2  s .c o  m*/
  * @param path 
  * @return 
  */
public String readPowerPoint(InputStream in) {
    String content = null;
    try {
        HSLFSlideShow slideShow = new HSLFSlideShow(in);
        org.apache.poi.hslf.extractor.PowerPointExtractor extractor = new PowerPointExtractor(slideShow);
        this.m_documentSummary = extractor.getDocSummaryInformation();
        this.m_summary = extractor.getSummaryInformation();
        content = extractor.getText();
        //                 SlideShow ss = new SlideShow(new HSLFSlideShow(in));// is  
        //                // InputStreamSlideShow  
        //                Slide[] slides = ss.getSlides();// ??  
        //                 for (int i = 0; i < slides.length; i++) {  
        //                    TextRun[] t = slides[i].getTextRuns();// ??TextRun  
        //                     for (int j = 0; j < t.length; j++) {  
        //                         content.append(t[j].getText());// content  
        //                    }  
        //                 }  
    } catch (Exception ex) {
        System.out.println(ex.toString());
    }
    return content;
}

From source file:com.krawler.esp.fileparser.pptparser.MsPPTParser.java

License:Open Source License

public String extractText(String filepath) throws Exception {

    InputStream input = new BufferedInputStream(new FileInputStream(filepath));
    String resultText = "";
    PowerPointExtractor ppt = new PowerPointExtractor(input);
    resultText = ppt.getText();//from w  w  w .  j a  v a  2 s .c o m

    if (input != null) {
        input.close();
    }
    return resultText;
}

From source file:com.openkm.extractor.MsPowerPointTextExtractor.java

License:Open Source License

/**
 * {@inheritDoc}/*from w  w  w . j a v  a2  s.  c om*/
 */
public String extractText(InputStream stream, String type, String encoding) throws IOException {
    try {
        PowerPointExtractor extractor = new PowerPointExtractor(stream);
        return extractor.getText(true, true);
    } catch (RuntimeException e) {
        logger.warn("Failed to extract PowerPoint text content", e);
        throw new IOException(e.getMessage(), e);
    } finally {
        try {
            stream.close();
        } catch (IOException ignored) {
        }
    }
}

From source file:com.openkm.util.metadata.MetadataExtractor.java

License:Open Source License

/**
 * Extract metadata from Office Word//from   ww w  .  jav  a2s  .co  m
 */
public static OfficeMetadata officeExtractor(InputStream is, String mimeType) throws IOException {
    POIFSFileSystem fs = new POIFSFileSystem(is);
    OfficeMetadata md = new OfficeMetadata();
    SummaryInformation si = null;

    if (MimeTypeConfig.MIME_MS_WORD.equals(mimeType)) {
        si = new WordExtractor(fs).getSummaryInformation();
    } else if (MimeTypeConfig.MIME_MS_EXCEL.equals(mimeType)) {
        si = new ExcelExtractor(fs).getSummaryInformation();
    } else if (MimeTypeConfig.MIME_MS_POWERPOINT.equals(mimeType)) {
        si = new PowerPointExtractor(fs).getSummaryInformation();
    }

    if (si != null) {
        md.setTitle(si.getTitle());
        md.setSubject(si.getSubject());
        md.setAuthor(si.getAuthor());
        md.setLastAuthor(si.getLastAuthor());
        md.setKeywords(si.getKeywords());
        md.setComments(si.getComments());
        md.setTemplate(si.getTemplate());
        md.setRevNumber(si.getRevNumber());
        md.setApplicationName(si.getApplicationName());
        md.setEditTime(si.getEditTime());
        md.setPageCount(si.getPageCount());
        md.setWordCount(si.getWordCount());
        md.setCharCount(si.getCharCount());
        md.setSecurity(si.getSecurity());

        Calendar createDateTime = Calendar.getInstance();
        createDateTime.setTime(si.getCreateDateTime());
        md.setCreateDateTime(createDateTime);

        Calendar lastSaveDateTime = Calendar.getInstance();
        lastSaveDateTime.setTime(si.getLastSaveDateTime());
        md.setLastSaveDateTime(lastSaveDateTime);

        Calendar lastPrinted = Calendar.getInstance();
        lastPrinted.setTime(si.getLastPrinted());
        md.setLastPrinted(lastPrinted);
    }

    log.info("officeExtractor: {}", md);
    return md;
}

From source file:com.xpn.xwiki.plugin.lucene.textextraction.MSPowerPointTextExtractor.java

License:Open Source License

public String getText(byte[] data) throws Exception {
    PowerPointExtractor ppe = new PowerPointExtractor(new ByteArrayInputStream(data));
    return ppe.getText(true, true);
}

From source file:de.maklerpoint.office.Lucene.Indexer.java

License:Open Source License

private void indexFileorDir(String fileName) throws IOException {
    listFiles(new File(fileName));

    for (File f : queue) {
        FileReader fr = null;/*from  w  w w .  ja va 2  s. c  o m*/
        try {
            if (f.getName().startsWith(".")) {
                //                    System.out.println("Versteckte datei: " + f.getName());
                // TODO add html, xml parsers
            } else if (f.getName().endsWith(".htm") || f.getName().endsWith(".html")
                    || f.getName().endsWith(".xml") || f.getName().endsWith(".txt")) {
                Document doc = new Document();

                //===================================================
                // add contents of file
                //===================================================
                fr = new FileReader(f);
                doc.add(new Field("contents", fr));

                //===================================================
                //adding second field which contains the path of the file
                //===================================================
                doc.add(new Field("path", f.getPath(), Field.Store.YES, Field.Index.ANALYZED));
                /**
                 * Adding Typ
                 */
                doc.add(new Field("type", String.valueOf(FileTypes.TXT), Field.Store.YES,
                        Field.Index.NOT_ANALYZED));

                doc.add(new Field("modified", df.format(f.lastModified()), Field.Store.YES,
                        Field.Index.NOT_ANALYZED));

                doc.add(new Field("filesize",
                        String.valueOf(FormatFileSize.formatSize(f.length(), FormatFileSize.KB)),
                        Field.Store.YES, Field.Index.NOT_ANALYZED));

                writer.addDocument(doc);
            } else if (f.getName().endsWith(".pdf")) {
                PDFParser parser = new PDFParser(new FileInputStream(f));
                parser.parse();
                COSDocument cd = parser.getDocument();
                PDFTextStripper stripper = new PDFTextStripper();

                String text = stripper.getText(new PDDocument(cd));

                Document doc = new Document();

                doc.add(new Field("contents", text, Field.Store.YES, Field.Index.ANALYZED));
                doc.add(new Field("path", f.getPath(), Field.Store.YES, Field.Index.ANALYZED));
                doc.add(new Field("type", String.valueOf(FileTypes.PDF), Field.Store.YES,
                        Field.Index.NOT_ANALYZED));

                doc.add(new Field("modified", df.format(f.lastModified()), Field.Store.YES,
                        Field.Index.NOT_ANALYZED));

                doc.add(new Field("filesize",
                        String.valueOf(FormatFileSize.formatSize(f.length(), FormatFileSize.KB)),
                        Field.Store.YES, Field.Index.NOT_ANALYZED));

                writer.addDocument(doc);
                cd.close();
            } else if (f.getName().endsWith(".doc") || f.getName().endsWith(".docx")) {

                POIFSFileSystem fs = new POIFSFileSystem(new FileInputStream(f));
                WordExtractor extractor = new WordExtractor(fs);
                String wordText = extractor.getText();

                Document doc = new Document();
                doc.add(new Field("contents", wordText, Field.Store.YES, Field.Index.ANALYZED));

                doc.add(new Field("path", f.getPath(), Field.Store.YES, Field.Index.ANALYZED));
                doc.add(new Field("type", String.valueOf(FileTypes.DOC), Field.Store.YES,
                        Field.Index.NOT_ANALYZED));

                doc.add(new Field("modified", df.format(f.lastModified()), Field.Store.YES,
                        Field.Index.NOT_ANALYZED));

                doc.add(new Field("filesize",
                        String.valueOf(FormatFileSize.formatSize(f.length(), FormatFileSize.KB)),
                        Field.Store.YES, Field.Index.NOT_ANALYZED));

                writer.addDocument(doc);
            } else if (f.getName().endsWith(".xls") || f.getName().endsWith(".xlsx")) {
                POIFSFileSystem fs = new POIFSFileSystem(new FileInputStream(f));
                ExcelExtractor extractor = new ExcelExtractor(fs);
                String excelText = extractor.getText();

                Document doc = new Document();
                doc.add(new Field("contents", excelText, Field.Store.YES, Field.Index.ANALYZED));

                doc.add(new Field("path", f.getPath(), Field.Store.YES, Field.Index.ANALYZED));
                doc.add(new Field("type", String.valueOf(FileTypes.XLS), Field.Store.YES,
                        Field.Index.NOT_ANALYZED));

                doc.add(new Field("modified", df.format(f.lastModified()), Field.Store.YES,
                        Field.Index.NOT_ANALYZED));

                doc.add(new Field("filesize",
                        String.valueOf(FormatFileSize.formatSize(f.length(), FormatFileSize.KB)),
                        Field.Store.YES, Field.Index.NOT_ANALYZED));

                writer.addDocument(doc);
            } else if (f.getName().endsWith(".ppt") || f.getName().endsWith(".pptx")) {
                POIFSFileSystem fs = new POIFSFileSystem(new FileInputStream(f));
                PowerPointExtractor extractor = new PowerPointExtractor(fs);
                String ppttext = extractor.getText();

                Document doc = new Document();
                doc.add(new Field("contents", ppttext, Field.Store.YES, Field.Index.ANALYZED));

                doc.add(new Field("path", f.getPath(), Field.Store.YES, Field.Index.ANALYZED));

                doc.add(new Field("modified", df.format(f.lastModified()), Field.Store.YES,
                        Field.Index.NOT_ANALYZED));

                doc.add(new Field("type", String.valueOf(FileTypes.PPT), Field.Store.YES,
                        Field.Index.NOT_ANALYZED));

                doc.add(new Field("filesize",
                        String.valueOf(FormatFileSize.formatSize(f.length(), FormatFileSize.KB)),
                        Field.Store.YES, Field.Index.NOT_ANALYZED));

                writer.addDocument(doc);
            }

            if (Log.logger.isDebugEnabled()) {
                Log.logger.debug("Lucene | Neue Datei indexiert: " + f);
            }
        } catch (Exception e) {
            if (Log.logger.isDebugEnabled()) {
                Log.logger.debug("Datei konnte nicht indexiert werden: " + f, e);
            }
            continue;
        } finally {
            //                fr.close();
        }
    }

    writer.optimize();
    queue.clear();

}

From source file:de.micromata.genome.gwiki.plugin.msotextextractor_1_0.PowerPointTextExtractor.java

License:Apache License

public String extractText(String fileName, InputStream data) {
    try {//from  w  w  w  .j a  va 2 s .  c om
        PowerPointExtractor extr = new PowerPointExtractor(data);
        String text = extr.getText();
        text = WordTextExtractor.reworkWordText(text);
        return text;
    } catch (IOException ex) {
        throw new RuntimeIOException("Failure to extract word from " + fileName + "; " + ex.getMessage(), ex);
    }
}

From source file:dk.defxws.fedoragsearch.server.TransformerToText.java

License:Open Source License

private static Stream getTextFromPPT(InputStream doc) throws GenericSearchException {
    long time = System.currentTimeMillis();
    boolean errorFlag = Boolean.parseBoolean(Config.getCurrentConfig().getIgnoreTextExtractionErrors());
    PowerPointExtractor powerPointExtractor = null;
    try {/*  w  w w.j  a v a 2s.c o  m*/
        powerPointExtractor = new PowerPointExtractor(doc);
        StringBuffer buffer = new StringBuffer(powerPointExtractor.getText(true, true).trim());
        Stream stream = new Stream();
        stream.write(buffer.toString().getBytes(Constants.XML_CHARACTER_ENCODING));
        stream.lock();
        if (logger.isDebugEnabled()) {
            logger.debug("extracting text from ppt needed " + (System.currentTimeMillis() - time));
        }
        return stream;
    } catch (Exception e) {
        if (errorFlag) {
            logger.warn("", e);
            return createErrorStream(pptTextExtractionErrorString);
        } else {
            throw new GenericSearchException("cannot parse ppt-file", e);
        }
    } finally {
        powerPointExtractor = null;
    }
}