*
 */
public class SitemapSet implements Serializable {

    private static final long serialVersionUID = 1L;

    /** Constant for UrlSet type. */
    public static final String URLSET = "UrlSet";

    /** Constant for Index type. */
    public static final String INDEX = "Index";

    /** The list of sitemaps in this set. */
    private final List<Sitemap> sitemapList = new ArrayList<>();

 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.entity;

/**
 * Represents the result of accessing a resource.
 *
 * @param <IDTYPE> the type of the identifier for the access result
 */
public interface AccessResult<IDTYPE> {

    /**

 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.processor.impl;

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

        this.url = url;
    }

    /**
     * Gets the HTTP method used for the request.
     *
     * @return the HTTP method (e.g., GET, POST)
     */
    public String getMethod() {
        return method;
    }

    /**
     * Sets the HTTP method used for the request.
     *
     * @param method the HTTP method to set (e.g., GET, POST)
     */

 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.extractor.impl;

import java.io.File;
import java.io.IOException;
import java.util.List;

 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.filter.impl;

import java.util.LinkedHashSet;
import java.util.List;
import java.util.Set;

     * Checks if access to a given path is allowed for a specific user agent according to robots.txt rules.
     *
     * @param path The path to check for access permission
     * @param userAgent The user agent string to check against robots.txt directives
     * @return true if access is allowed, false if access is disallowed by robots.txt rules.
     *         Returns true if no matching directive is found for the user agent.
     */

 *
 * @param <IDTYPE> the type of the identifier for the URL queue entry
 */
public class UrlQueueImpl<IDTYPE> implements UrlQueue<IDTYPE> {
    /** The unique identifier for the URL queue entry. */
    protected IDTYPE id;

    /** The session ID associated with this URL queue. */
    protected String sessionId;

    /** The HTTP method used for the URL in the queue. */
    protected String method;

 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.suggest.index.contents.querylog;

import org.opensearch.common.Nullable;

/**

    /**
     * Service for managing URL queues during crawling.
     */
    @Resource
    protected UrlQueueService<UrlQueue<?>> urlQueueService;

    /**
     * Service for managing access result data.
     */
    @Resource
    protected DataService<AccessResult<?>> dataService;

    /**
     * Filter for URLs to control which URLs are crawled.
     */
    @Resource