import org.codelibs.fess.crawler.exception.UnsupportedExtractException;

import jakarta.annotation.Resource;

/**
 * Factory class for managing and retrieving {@link Extractor} instances.
 * This class provides methods to add, retrieve, and manage extractors based on a key.
 * It also includes a builder for creating extractors.
 *
 * <p>
 * The factory maintains a map of keys to an array of {@link Extractor} objects.

import org.codelibs.fess.crawler.container.CrawlerContainer;

import jakarta.annotation.Resource;

/**
 * A factory for creating and managing pooled crawler objects.
 * This class extends {@link BasePooledObjectFactory} and provides
 * methods for creating, wrapping, and destroying crawler components
 * obtained from a {@link CrawlerContainer}.
 *
 * @param <T> the type of the pooled object
 */

 * This class holds information about a single Sitemap, including its location and last modification timestamp.
 * It implements the {@link Sitemap} interface.
 *
 * <p>
 * A Sitemap file provides search engines with a list of URLs available for crawling.
 * This class encapsulates the essential attributes of a Sitemap entry, allowing for efficient management
 * and processing of Sitemap data.
 * </p>
 *
 * <p>

 */
package org.codelibs.fess.crawler.client.http;

import org.apache.http.auth.AuthScheme;
import org.apache.http.auth.AuthScope;
import org.apache.http.auth.Credentials;

/**
 * The Authentication interface provides methods to retrieve authentication details
 * required for HTTP client authentication.
 */
public interface Authentication {

    /**
     * Retrieves the authentication scope associated with this authentication.

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

/**
 * 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
 */

/**
 * Implementation of the {@link UrlFilter} interface.
 * This class provides functionality to filter URLs based on include and exclude patterns.
 * It uses a {@link UrlFilterService} to manage the URL filtering rules.
 * The class supports caching of include and exclude patterns for scenarios where a session ID is not available.
 * It also provides methods to initialize the filter with a session ID, clear the filter,

 */
package org.codelibs.fess.crawler.client.ftp;

import java.util.ArrayList;
import java.util.List;

/**
 * Holds a list of FtpAuthentication objects and provides methods to add and retrieve them based on a given path.
 * This class is designed to manage FTP authentication details for different paths.
 */
public class FtpAuthenticationHolder {

 * in a crawler application. This container supports both singleton and prototype component
 * instantiation patterns.
 *
 * <p>The container provides mechanisms for:
 * <ul>
 *   <li>Registering and retrieving components by name</li>
 *   <li>Managing singleton instances with lifecycle hooks</li>
 *   <li>Creating prototype instances on demand</li>

		</dependency>
		<dependency>
			<groupId>jakarta.transaction</groupId>
			<artifactId>jakarta.transaction-api</artifactId>
			<version>${jakarta.transaction.version}</version>
			<scope>provided</scope>
		</dependency>
		<dependency>
			<groupId>org.codelibs</groupId>
			<artifactId>sai</artifactId>
			<version>${sai.version}</version>
		</dependency>
		<dependency>
			<groupId>junit</groupId>

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

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

/**
 * The RuleManager interface provides methods to manage rules for processing response data.
 * It allows adding, retrieving, and removing rules, as well as checking for their existence.
 */
public interface RuleManager {

    /**