How to use

CmsExtractorPdf

in

org.opencms.search.extractors

String result = removeControlChars(stripper.getText(pdfDocument));
StringBuffer content = new StringBuffer(result);
if (CmsStringUtil.isNotEmpty(result)) {
combineContentItem(info.getTitle(), I_CmsExtractionResult.ITEM_TITLE, content, contentItems);
combineContentItem(info.getKeywords(), I_CmsExtractionResult.ITEM_KEYWORDS, content, contentItems);
combineContentItem(info.getSubject(), I_CmsExtractionResult.ITEM_SUBJECT, content, contentItems);
combineContentItem(info.getAuthor(), I_CmsExtractionResult.ITEM_AUTHOR, content, contentItems);
combineContentItem(info.getCreator(), I_CmsExtractionResult.ITEM_CREATOR, content, contentItems);
combineContentItem(info.getProducer(), I_CmsExtractionResult.ITEM_PRODUCER, content, contentItems);

  /**
   * @see org.opencms.search.extractors.I_CmsTextExtractor#extractText(java.io.InputStream, java.lang.String)
   */
  @Override
  public I_CmsExtractionResult extractText(InputStream in) throws Exception {

    return extractText(in, new PDFParser());
  }
}

  textExtractor = CmsExtractorPdf.getExtractor();
} else if (path1.endsWith(".doc") && path2.endsWith(".doc")) {
  textExtractor = CmsExtractorMsOfficeOLE2.getExtractor();

  textExtractor = CmsExtractorPdf.getExtractor();
} else if (path1.endsWith(".doc") && path2.endsWith(".doc")) {
  textExtractor = CmsExtractorMsOfficeOLE2.getExtractor();

  textExtractor = CmsExtractorPdf.getExtractor();
} else if (path1.endsWith(".doc") && path2.endsWith(".doc")) {
  textExtractor = CmsExtractorMsWord.getExtractor();

/**
 * Returns the raw text content of a given vfs resource containing Adobe PDF data.<p>
 * 
 * @see org.opencms.search.documents.I_CmsSearchExtractor#extractContent(CmsObject, CmsResource, CmsSearchIndex)
 */
public I_CmsExtractionResult extractContent(CmsObject cms, CmsResource resource, CmsSearchIndex index)
throws CmsIndexException, CmsException {
  CmsFile file = readFile(cms, resource);
  try {
    return CmsExtractorPdf.getExtractor().extractText(file.getContents());
  } catch (Exception e) {
    if (e instanceof CryptographyException) {
      throw new CmsIndexException(Messages.get().container(
        Messages.ERR_DECRYPTING_RESOURCE_1,
        resource.getRootPath()), e);
    }
    if (e instanceof InvalidPasswordException) {
      // default password "" was wrong.
      throw new CmsIndexException(Messages.get().container(
        Messages.ERR_PWD_PROTECTED_1,
        resource.getRootPath()), e);
    }
    throw new CmsIndexException(
      Messages.get().container(Messages.ERR_TEXT_EXTRACTION_1, resource.getRootPath()),
      e);
  }
}

/**
 * Returns the raw text content of a given vfs resource containing Adobe PDF data.<p>
 *
 * @see org.opencms.search.documents.I_CmsSearchExtractor#extractContent(CmsObject, CmsResource, CmsSearchIndex)
 */
public I_CmsExtractionResult extractContent(CmsObject cms, CmsResource resource, CmsSearchIndex index)
throws CmsIndexException, CmsException {
  logContentExtraction(resource, index);
  CmsFile file = readFile(cms, resource);
  try {
    return CmsExtractorPdf.getExtractor().extractText(file.getContents());
  } catch (Exception e) {
    if (e instanceof CryptographyException) {
      throw new CmsIndexException(
        Messages.get().container(Messages.ERR_DECRYPTING_RESOURCE_1, resource.getRootPath()),
        e);
    }
    if (e instanceof InvalidPasswordException) {
      // default password "" was wrong.
      throw new CmsIndexException(
        Messages.get().container(Messages.ERR_PWD_PROTECTED_1, resource.getRootPath()),
        e);
    }
    throw new CmsIndexException(
      Messages.get().container(Messages.ERR_TEXT_EXTRACTION_1, resource.getRootPath()),
      e);
  }
}