"application/x-project",
				"application/vnd.ms-tnef",
				"application/vnd.ms-wmdrm.lic-chlg-req",
				"application/vnd.ms-wmdrm.lic-resp",
				"application/vnd.ms-wmdrm.meter-chlg-req",
				"application/vnd.ms-wmdrm.meter-resp",
				"application/vnd.ms-word.document.macroenabled.12",
				"application/vnd.ms-word.template.macroenabled.12",
				"application/vnd.ms-works",
				"application/vnd.ms-wpl",

            final SearchRequestBuilder builder = c.prepareSearch(index);
            callback.accept(builder);
            builder.setFetchSource(new String[] { "parentUrl", "method", "mimeType", "sessionId", "url", "executionTime", "createTime",
                    "contentLength", "lastModified", "ruleId", "httpStatusCode", "status" }, null);
            return builder.execute();
        });

 * information for authenticating with an SMB server.
 *
 * <p>
 * It provides methods to set and retrieve the server address, port, username,
 * password, and domain. Additionally, it offers a method to construct a path
 * prefix for SMB URLs based on the configured server and port.
 * </p>
 *
 * <p>
 * The path prefix is in the format "smb://server:port/", where the port is

 * <li>TOKEN_NAME - The name of the token parameter.</li>
 * <li>TOKEN_METHOD - The HTTP method to use for the token request (GET or POST).</li>
 * <li>TOKEN_PARAMTERS - The parameters to include in the token request.</li>
 * <li>LOGIN_METHOD - The HTTP method to use for the login request (GET or POST).</li>
 * <li>LOGIN_URL - The URL to send the login request to.</li>

    @Override
    public ResponseData doGet(final String uri) {
        return processRequest(uri, true);
    }

    /**
     * Processes an FTP request to retrieve data from the specified URI.
     * This method handles the complete FTP request lifecycle including timeout management,
     * connection setup, and data retrieval.
     *
     * @param uri The URI to retrieve data from

 * {@link org.codelibs.fess.crawler.exception.CrawlerSystemException} in case of errors.
 * </p>
 *
 * <p>
 * The {@link #storeData(ResponseData, ResultData)} method is the main entry point for storing
 * the content of a crawled resource. The {@link #getData(AccessResultData)} method retrieves
 * the stored file path as a File object.
 * </p>
 */
public class FileTransformer extends HtmlTransformer {
    /** Logger instance for this class */

 * It uses an Extractor to extract the text from the response body based on the MIME type.
 * The extracted text is then converted into a byte array using the specified charset encoding.
 * It also provides a method to retrieve the extracted data as a String from an AccessResultData object.
 *
 * <p>
 * The class handles character encoding issues by attempting to use the specified charset.

 * only one of them (allRequired = false). It also supports a default rule that always matches.
 *
 * <p>
 * The class uses a map of field names to Pattern objects to store the regular expressions.
 * The match method extracts the values of the specified fields from the ResponseData and
 * applies the corresponding regular expressions.
 * </p>
 *
 * <p>
 * Example usage:
 * </p>
 *
 * <pre>
 * {@code

     * Creates a new HtmlXpathExtractor instance.
     */
    public HtmlXpathExtractor() {
        super();
    }

    /**
     * Initializes the XPathAPI cache with a specified cache duration.
     * This method is called to set up the cache for XPathAPI instances.
     */
    @Resource
    public void init() {
        xpathAPICache =

 * <p>
 * The factory maintains a map of keys to an array of {@link Extractor} objects.
 * When multiple extractors are associated with a single key, they are sorted by weight
 * in descending order. The {@link #getExtractor(String)} method returns a composite
 * extractor that iterates through the available extractors until one successfully
 * extracts the data.
 * </p>
 *
 * <p>