import jakarta.annotation.Resource;

/**
 * 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

 * including adding URLs to the queue, filtering URLs, managing crawler threads,
 * and handling the overall crawling lifecycle.
 *
 * <p>It implements the Runnable interface to be executed in a separate thread,
 * and the AutoCloseable interface to ensure resources are properly released after use.
 *
 * <p>The crawler uses several services and components, such as UrlQueueService, DataService,

     * @param settings the settings for the suggest feature
     * @param index    the name of the index where the suggest items will be written
     * @param items    an array of suggest items to be written to the index
     * @param update   a boolean flag indicating whether to update existing items
     * @return a result object containing information about the write operation
     */

     */
    public RequestBuilder(final Client client, final Req request) {
        this.client = client;
        this.request = request;
    }

    /**
     * Executes the request.
     * @return A Promise that will be resolved with the response or rejected with an error.
     */
    public Deferred<Res>.Promise execute() {
        return request.execute(client);
    }

      replaced with your own identifying information. (Don't include
      the brackets!)  The text should be enclosed in the appropriate
      comment syntax for the file format. We also recommend that a
      file or class name and description of purpose be included on the
      same "printed page" as the copyright notice for easier
      identification within third-party archives.

     *
     * @param responseData the data to be transformed
     * @return the transformed ResultData
     */
    ResultData transform(ResponseData responseData);

    /**
     * Retrieves data from the given AccessResultData object.
     *
     * @param accessResultData the AccessResultData object containing the data to be retrieved

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler;

/**
 * Enum representing the status of a crawler.
 * It can be INITIALIZING, RUNNING, or DONE.
 */
public enum CrawlerStatus {
    /**
     * The crawler is initializing.
     */
    INITIALIZING,

    /**
     * The crawler is currently running.
     */

import java.io.Closeable;

/**
 * The {@code QueryLogReader} interface provides methods to read query logs and close the reader.
 * It extends the {@code Closeable} interface, ensuring that resources can be released when no longer needed.
 */
public interface QueryLogReader extends Closeable {
    /**
     * Reads a query log.
     * @return The query log.
     */
    QueryLog read();

    @Override

import java.io.Serializable;

/**
 * The Sitemap interface represents a sitemap entity with location and last modification date.
 * It extends the Serializable interface to allow sitemap objects to be serialized.
 */
public interface Sitemap extends Serializable {

    /**
     * Retrieves the location (URL) of the sitemap.
     *
     * @return the location of the sitemap as a String.
     */

 */
public interface Extractor {

    /**
     * Extracts text data from the given input stream.
     *
     * @param in the input stream to extract text from
     * @param params a map of parameters to be used during extraction
     * @return an ExtractData object containing the extracted text
     */
    ExtractData getText(InputStream in, Map<String, String> params);

    /**
     * Returns the weight of the extractor.