* It implements the {@link Sitemap} interface.
 * </p>
 *
 * <p>
 * The {@code SitemapUrl} class provides getter and setter methods for each of these properties,
 * as well as implementations for {@code equals()}, {@code hashCode()}, and {@code toString()} methods.
 * </p>
 *
 */
public class SitemapUrl implements Sitemap {

    private static final long serialVersionUID = 1L;

    /**

        // The first creation should increment the counter
        assertTrue("Instance count should be at least 1", SingletonTestComponent.getInstanceCount() >= 1);
    }

    /**
     * Test wrap method
     */
    public void test_wrap_basic() {
        TestComponent component = new TestComponent();

        PooledObject<TestComponent> pooledObject = factory.wrap(component);

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

import java.util.Date;

import org.apache.http.client.methods.HttpUriRequest;
import org.codelibs.fess.crawler.CrawlerContext;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.ResponseData;

 * </p>
 *
 * clientConnectionManager the HttpClientConnectionManager used to manage connections
 * idleConnectionTimeout the timeout duration (in milliseconds) for idle connections
 *
 * <p>Methods:</p>
 * <ul>
 *   <li>{@link #expired()}: Handles the expiration of connections by closing expired and idle connections.</li>
 * </ul>
 *
 * <p>Logging:</p>
 * <ul>

 */
package org.codelibs.fess.crawler.service;

import java.util.List;

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

/**
 * Service interface for managing URL queues.
 * Provides methods for adding, retrieving, and managing URLs within a crawling session.
 *
 * @param <QUEUE> the type of URL queue
 */
public interface UrlQueueService<QUEUE extends UrlQueue<?>> {

    /**
     * Updates the session ID.

 * using the Apache Tika library. It extends {@link PasswordBasedExtractor} to handle password-protected files.
 * </p>
 *
 * <p>
 * This class provides methods to extract text from an input stream, handling different scenarios such as:
 * </p>
 * <ul>
 *   <li>Normalizing text content</li>
 *   <li>Handling resource names and content types</li>

import java.io.Serializable;
import java.util.ArrayList;
import java.util.List;

/**
 * Represents a set of Sitemaps, which can be either a UrlSet or an Index.
 * This class provides methods to manage a list of Sitemap objects and determine the type of the SitemapSet.
 *
 */
public class SitemapSet implements Serializable {

    private static final long serialVersionUID = 1L;

 */
package org.codelibs.fess.crawler.helper;

import java.util.HashMap;
import java.util.Locale;
import java.util.Map;

import org.codelibs.core.lang.StringUtil;

/**
 * EncodingHelper provides utility methods for managing and normalizing character encodings.
 * It allows setting a default encoding, mapping various encoding names to preferred ones,

import org.codelibs.fess.crawler.rule.Rule;
import org.codelibs.fess.crawler.rule.RuleManager;

/**
 * Implementation of the {@link RuleManager} interface.
 * Manages a list of rules for the crawler.
 * Provides methods to add, remove, check, and retrieve rules.
 *
 */
public class RuleManagerImpl implements RuleManager {

    /** The list of rules managed by this rule manager. */

 */
package org.codelibs.fess.crawler.service;

import java.util.List;
import java.util.regex.Pattern;

/**
 * Service interface for managing URL filters.
 * Provides methods to add and remove include/exclude URL filters,
 * as well as retrieve the patterns of these filters.
 */
public interface UrlFilterService {

    /**
     * Adds a URL to the include filter list for the specified session.