}

    /**
     * Creates a temporary file.
     * @param prefix The prefix string to be used in generating the file's name.
     * @param suffix The suffix string to be used in generating the file's name.
     * @param directory The directory in which the file is to be created, or null if the default temporary-file directory is to be used.
     * @return The created temporary file.
     */

 * 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.
     */

/**
 * RegexRule is a rule implementation that uses regular expressions to match against the ResponseData.
 * It allows defining multiple regular expressions for different fields of the ResponseData.
 * The rule can be configured to require all regular expressions to match (allRequired = true) or
 * only one of them (allRequired = false). It also supports a default rule that always matches.
 *
 * <p>

  sources like Apache Nutch, Apache HTTP Server, the file(1) command, etc.

  Notes:
   * Tika supports a wider range of match types than Freedesktop does
   * Glob patterns must be unique, if there's a clash assign to the most
     popular format
   * The main mime type should be the canonical one, use aliases for any
     other widely used forms
   * Where there's a hierarchy in the types, list it via a parent

     * end with a trailing slash, if your web server requires it. This value
     * must be less than 2,048 characters.
     */
    private String loc;

    /**
     * The date of last modification of the file. This date should be in W3C
     * Datetime format. This format allows you to omit the time portion, if
     * desired, and use YYYY-MM-DD.
     *

     * If no extractor exists for the key, a new array containing the extractor is created and associated with the key.
     *
     * @param key       The key associated with the extractor. Must not be null or blank.
     * @param extractor The extractor to add. Must not be null.
     */
    public void addExtractor(final String key, final Extractor extractor) {
        if (StringUtil.isBlank(key)) {

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.
     */

 * 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,

 * This wrapper allows for parameter management and initialization before delegating to the wrapped factory.
 *
 * The wrapper maintains its own parameter map which can be initialized separately from the wrapped factory,
 * and provides access to the wrapped factory instance through getParent().
 *
 * All crawler client management operations (adding, getting clients, setting client map) are delegated

/**
 * NullResponseProcessor is a class that implements the ResponseProcessor interface.
 * It provides a no-op implementation for processing response data.
 * This class can be used when you want to skip the response processing step in a crawler.
 *
 * @author kuma
 */
public class NullResponseProcessor implements ResponseProcessor {

    /**