Example usage for org.apache.poi.xslf.extractor XSLFPowerPointExtractor getCoreProperties

List of usage examples for org.apache.poi.xslf.extractor XSLFPowerPointExtractor getCoreProperties

Introduction

In this page you can find the example usage for org.apache.poi.xslf.extractor XSLFPowerPointExtractor getCoreProperties.

Prototype

public CoreProperties getCoreProperties() 

Source Link

Document

Returns the core document properties

Usage

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

License:Open Source License

/** 
 * ?ppt //  ww w  .j a  v a 2  s  .  c  o  m
   * @param path 
   * @return 
   */
public String readPowerPoint2007(InputStream in) {
    String content = null;
    try {

        XMLSlideShow xmlslideshow = new XMLSlideShow(in);
        org.apache.poi.xslf.extractor.XSLFPowerPointExtractor extractor = new XSLFPowerPointExtractor(
                xmlslideshow);
        this.cp = extractor.getCoreProperties();
        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.jaeksoft.searchlib.parser.PptxParser.java

License:Open Source License

@Override
protected void parseContent(StreamLimiter streamLimiter, LanguageEnum lang) throws IOException {

    // TODO Optimise if it is already a file
    File tempFile = File.createTempFile("oss", ".pptx");
    FileOutputStream fos = null;//from www.  j  ava2  s.c o m
    try {
        fos = new FileOutputStream(tempFile);
        IOUtils.copy(streamLimiter.getNewInputStream(), fos);
        fos.close();
    } catch (IOException e) {
        IOUtils.close(fos);
        throw e;
    }

    XSLFPowerPointExtractor poiExtractor = null;
    try {
        XSLFSlideShow pptSlideShow = new XSLFSlideShow(tempFile.getAbsolutePath());
        poiExtractor = new XSLFPowerPointExtractor(pptSlideShow);

        ParserResultItem result = getNewParserResultItem();
        CoreProperties info = poiExtractor.getCoreProperties();
        if (info != null) {
            result.addField(ParserFieldEnum.title, info.getTitle());
            result.addField(ParserFieldEnum.creator, info.getCreator());
            result.addField(ParserFieldEnum.subject, info.getSubject());
            result.addField(ParserFieldEnum.description, info.getDescription());
            result.addField(ParserFieldEnum.keywords, info.getKeywords());
        }

        String content = poiExtractor.getText(true, true);
        result.addField(ParserFieldEnum.content, StringUtils.replaceConsecutiveSpaces(content, " "));

        result.langDetection(10000, ParserFieldEnum.content);

    } catch (OpenXML4JException e) {
        throw new IOException(e);
    } catch (XmlException e) {
        throw new IOException(e);
    } finally {
        IOUtils.close(poiExtractor);
    }

}

From source file:com.opensearchserver.extractor.parser.Pptx.java

License:Apache License

@Override
protected void parseContent(File file, String extension, String mimeType) throws Exception {

    XSLFSlideShow pptSlideShow = new XSLFSlideShow(file.getAbsolutePath());
    XMLSlideShow slideshow = new XMLSlideShow(pptSlideShow.getPackage());

    // Extract metadata
    XSLFPowerPointExtractor poiExtractor = null;
    try {//from   w  ww.java 2 s .c  o m
        poiExtractor = new XSLFPowerPointExtractor(slideshow);
        CoreProperties info = poiExtractor.getCoreProperties();
        if (info != null) {
            metas.add(TITLE, info.getTitle());
            metas.add(CREATOR, info.getCreator());
            metas.add(SUBJECT, info.getSubject());
            metas.add(DESCRIPTION, info.getDescription());
            metas.add(KEYWORDS, info.getKeywords());
            metas.add(CREATION_DATE, info.getCreated());
            metas.add(MODIFICATION_DATE, info.getModified());
        }
    } finally {
        poiExtractor.close();
    }
    extractSides(slideshow);
}

From source file:com.opensearchserver.textextractor.parser.Pptx.java

License:Open Source License

@Override
protected void parseContent(File file) throws Exception {

    XSLFSlideShow pptSlideShow = new XSLFSlideShow(file.getAbsolutePath());
    XMLSlideShow slideshow = new XMLSlideShow(pptSlideShow.getPackage());

    // Extract metadata
    XSLFPowerPointExtractor poiExtractor = null;
    try {//from www.j a va 2s .  c o m
        poiExtractor = new XSLFPowerPointExtractor(slideshow);
        CoreProperties info = poiExtractor.getCoreProperties();
        if (info != null) {
            metas.add(TITLE, info.getTitle());
            metas.add(CREATOR, info.getCreator());
            metas.add(SUBJECT, info.getSubject());
            metas.add(DESCRIPTION, info.getDescription());
            metas.add(KEYWORDS, info.getKeywords());
            metas.add(CREATION_DATE, info.getCreated());
            metas.add(MODIFICATION_DATE, info.getModified());
        }
    } finally {
        poiExtractor.close();
    }
    extractSides(slideshow);
}