*   <li>Handling exceptions that may occur during the crawling process.</li>
 * </ol>
 *
 * <p>
 * The thread also manages the active thread count using {@code crawlerContext.activeThreadCountLock}
 * and provides methods for logging messages using {@link LogHelper}.
 * </p>
 *
 * <p>
 * The crawling process continues until the crawler status is {@link CrawlerStatus#DONE} or the

        super();
    }

    /**
     * Processes the given response data, extracting URLs from sitemaps.
     * @param responseData The response data.
     */
    @Override
    public void process(final ResponseData responseData) {
        final SitemapsHelper sitemapsHelper = crawlerContainer.getComponent("sitemapsHelper");
        try (final InputStream responseBody = responseData.getResponseBody()) {

 * It encapsulates the process of extracting data from an input stream using a specified or detected extractor.
 * The builder allows setting parameters such as MIME type, filename, extractor name, maximum content length,
 * and cache file size to optimize the extraction process.
 *
 * <p>
 * The main purpose of this class is to simplify the extraction process by providing a fluent interface

            crawlerContext.sessionId = sessionId;
        }
    }

    /**
     * Executes the crawling process.
     * Starts a new thread for the crawler and optionally waits for its termination.
     * @return The session ID of the crawling process.
     */
    public String execute() {
        parentThread = new Thread(this, "Crawler-" + crawlerContext.sessionId);

 * Implementations of this interface are responsible for handling the response data
 * obtained during a crawling process.
 */
public interface ResponseProcessor {

    /**
     * Processes the given response data.
     *
     * @param responseData the response data to be processed
     */
    void process(ResponseData responseData);

package org.codelibs.fess.crawler.exception;

/**
 * MimeTypeException is a custom exception class that extends CrawlerSystemException.
 * It is used to indicate exceptions related to MIME type handling during the crawling process.
 * This exception can be thrown with a message, a cause, or both.
 */
public class MimeTypeException extends CrawlerSystemException {

    private static final long serialVersionUID = 1L;

    /**

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

/**
 * An exception indicating that the execution of a process has timed out.
 * This exception extends {@link org.codelibs.fess.crawler.exception.ExtractException}.
 *
 */
public class ExecutionTimeoutException extends ExtractException {

 * </p>
 *
 * <p>
 * The class provides methods to:
 * </p>
 * <ul>
 *   <li>Initialize the client with SMB authentication details.</li>
 *   <li>Retrieve content and metadata from SMB files.</li>
 *   <li>Process access control entries to determine allowed and denied SIDs (Security Identifiers).</li>
 *   <li>Handle timeouts during SMB operations.</li>
 * </ul>
 *
 * <p>

 * This class provides methods to set and get various parameters related to the crawling process.
 *
 * <p>This class is final and cannot be instantiated.</p>
 *
 * <p>The following parameters are managed:</p>
 * <ul>
 *   <li>{@link UrlQueue} - The queue of URLs to be crawled.</li>
 *   <li>{@link CrawlerContext} - The context of the current crawling process.</li>
 *   <li>{@link UrlQueueService} - The service for managing the URL queue.</li>

 * </p>
 *
 * <p>
 * The class provides methods to:
 * </p>
 * <ul>
 *   <li>Initialize the client with SMB authentication details.</li>
 *   <li>Retrieve content and metadata from SMB files.</li>
 *   <li>Process access control entries to determine allowed and denied SIDs (Security Identifiers).</li>
 *   <li>Handle timeouts during SMB operations.</li>
 * </ul>
 *
 * <p>