import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.impl.TikaExtractor;
import org.codelibs.fess.crawler.processor.ResponseProcessor;
import org.codelibs.fess.crawler.processor.impl.DefaultResponseProcessor;
import org.codelibs.fess.crawler.rule.Rule;

import org.apache.logging.log4j.Logger;
import org.apache.tika.config.TikaConfig;
import org.apache.tika.detect.Detector;
import org.apache.tika.exception.TikaException;
import org.apache.tika.extractor.EmbeddedDocumentExtractor;
import org.apache.tika.extractor.ParsingEmbeddedDocumentExtractor;
import org.apache.tika.io.TemporaryResources;
import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;

    <include path="crawler/client.xml"/>
    <include path="crawler/rule.xml"/>
    <include path="crawler/filter.xml"/>
    <include path="crawler/interval.xml"/>
    <include path="crawler/extractor.xml"/>
    <include path="crawler/mimetype.xml"/>
    <include path="crawler/encoding.xml"/>
    <include path="crawler/urlconverter.xml"/>
    <include path="crawler/log.xml"/>
    <include path="crawler/sitemaps.xml"/>

/**
 * A response processor implementation that handles sitemaps.
 * It parses the response body as a SitemapSet, extracts URLs from the sitemaps,
 * and adds them as child URLs to be crawled.
 *
 * <p>
 * This class uses a {@link SitemapsHelper} to parse the sitemap XML or text.
 * It then iterates through the sitemaps in the SitemapSet, extracts the URL
 * from each sitemap, and creates a new {@link RequestData} object for each URL.

	<include path="crawler/container.xml"/>
	<include path="crawler/client.xml"/>
	<include path="crawler/rule.xml"/>
	<include path="crawler/filter.xml"/>
	<include path="crawler/interval.xml"/>
	<include path="crawler/extractor.xml"/>
	<include path="crawler/mimetype.xml"/>
	<include path="crawler/encoding.xml"/>
	<include path="crawler/urlconverter.xml"/>
	<include path="crawler/log.xml"/>
	<include path="crawler/sitemaps.xml"/>

     */
    FessConfig getFessConfig();

    /**
     * Gets the logger instance for this transformer.
     *
     * @return the logger instance
     */
    Logger getLogger();

    /**
     * Extracts the host name from a URL string.
     * Removes protocol and path components to return just the hostname.
     *
     * @param u the URL string to extract host from

    /**
     * Default constructor for ThemeHelper.
     */
    public ThemeHelper() {
        // Default constructor
    }

    /**
     * Installs a theme from the given artifact.
     * Extracts theme files from the JAR and deploys them to appropriate directories.
     *
     * @param artifact the theme artifact to install
     * @throws ThemeException if installation fails
     */

     */
    public static IntervalControlHelper getIntervalControlHelper() {
        return getComponent(INTERVAL_CONTROL_HELPER);
    }

    /**
     * Gets the extractor factory component.
     * @return The extractor factory.
     */
    public static ExtractorFactory getExtractorFactory() {
        return getComponent(EXTRACTOR_FACTORY);
    }

    /**
     * Gets a job executor by name.

     *
     * @param userPrefix the user prefix to set
     */
    public void setUserPrefix(final String userPrefix) {
        this.userPrefix = userPrefix;
    }

    /**
     * Extracts role type information from SMB (Server Message Block) response data.
     * Processes both SMB and SMB1 protocols to extract allowed and denied SIDs.
     *
     * @param responseData the response data containing SMB metadata

                + "</doc>";

        final ResponseData responseData = new ResponseData();
        responseData.setResponseBody(ResourceUtil.getResourceAsFile("extractor/test.xml"), false);
        responseData.setCharSet(Constants.UTF_8);
        final ResultData resultData = xmlTransformer.transform(responseData);
        assertEquals(result, new String(resultData.getData(), Constants.UTF_8));