import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.processor.ResponseProcessor;

/**
 * The Rule interface defines the contract for implementing rules that can be applied to
 * response data in a web crawler. Implementations of this interface should provide logic
 * to determine if a given response data matches the rule, retrieve the rule's identifier,
 * and obtain the associated response processor.
 */

## Overview

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

/**
 * RobotsTxtException is an exception class that represents an error related to robots.txt processing during web crawling.
 * It extends CrawlerSystemException and provides constructors to create instances with a message and/or a cause.
 *
 */
public class RobotsTxtException extends CrawlerSystemException {

 * into a ResultData object, and for retrieving the binary data from an AccessResultData object.
 * It extends the AbstractTransformer class.
 *
 * <p>
 * This transformer extracts the binary content from the response body of a web resource,
 * stores it as a byte array in the ResultData, and provides a method to retrieve this data
 * as a ByteArrayInputStream.
 * </p>
 *
 * <p>

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

/**
 * The {@code IntervalController} interface defines methods for controlling
 * the delay intervals in a web crawler. It includes constants representing
 * different types of processing states and a method to introduce a delay
 * based on the type of processing.
 * <p>
 * Constants:
 * </p>
 * <ul>

package org.codelibs.fess.crawler.client;

import java.util.Map;

import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;

/**
 * Interface representing a client for a web crawler.
 * This client is responsible for executing requests and handling responses.
 * It extends {@link AutoCloseable} to allow for resource management.
 */
public interface CrawlerClient extends AutoCloseable {

    /**

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

/**
 * The UrlQueue interface represents a queue of URLs to be processed by a web crawler.
 * It provides methods to get and set various properties of a URL queue entry.
 *
 * @param <IDTYPE> the type of the identifier for the URL queue entry
 */
public interface UrlQueue<IDTYPE> {

    /**

				"application/vnd.airzip.filesecure.azs",
				"application/vnd.amazon.ebook",
				"application/vnd.americandynamics.acc",
				"application/vnd.amiga.ami",
				"application/vnd.anser-web-certificate-issue-initiation",
				"application/vnd.anser-web-funds-transfer-initiation",
				"application/vnd.antix.game-component",
				"application/vnd.apple.installer+xml",
				"application/vnd.apple.iwork",
				"application/vnd.apple.keynote",

import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.container.CrawlerContainer;

import jakarta.annotation.Resource;

/**
 * Creates and manages crawler clients for web crawling operations.
 * This class handles the registration and loading of crawler client factories and their associated clients.
 * <p>

     */
    public SitemapUrl() {
        super();
    }

    /**
     * URL of the page. This URL must begin with the protocol (such as http) and
     * 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