}

    @Override
    public ResponseProcessor getResponseProcessor() {
        return responseProcessor;
    }

    /**
     * Sets the response processor for this rule.
     *
     * @param responseProcessor the response processor to set
     */
    public void setResponseProcessor(final ResponseProcessor responseProcessor) {
        this.responseProcessor = responseProcessor;
    }

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.
 */
public interface Rule extends Serializable {

 * 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;

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

/**
 * The ResponseProcessor interface defines a contract for processing response data.

		<property name="ruleId">"sitemapsRule"</property>
		<property name="responseProcessor">
			<component
				class="org.codelibs.fess.crawler.processor.impl.SitemapsResponseProcessor">
			</component>
		</property>
		<postConstruct name="addRule">
			<arg>"url"</arg>
			<arg>".*sitemap.*"</arg>
		</postConstruct>
	</component>

 * 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;
import org.codelibs.fess.crawler.processor.ResponseProcessor;

/**
 * NullResponseProcessor is a class that implements the ResponseProcessor interface.

import org.codelibs.fess.crawler.exception.ChildUrlsException;
import org.codelibs.fess.crawler.helper.SitemapsHelper;
import org.codelibs.fess.crawler.processor.ResponseProcessor;

import jakarta.annotation.Resource;

/**
 * A response processor implementation that handles sitemaps.
 * It parses the response body as a SitemapSet, extracts URLs from the sitemaps,
 * and adds them as child URLs to be crawled.
 *
 * <p>

 *   <li>Processing responses</li>
 *   <li>Handling exceptions during crawling and child URL processing</li>
 *   <li>Handling cases where no URL is in the queue</li>
 *   <li>Handling cases where no response processor or rule is found</li>
 *   <li>Handling system errors</li>
 * </ul>
 *
 * <p>
 * Each logging method checks the log level before logging the message.
 * The log level can be configured in the Log4j2 configuration file.

                .<DefaultResponseProcessor> singleton("defaultResponseProcessor", DefaultResponseProcessor.class, processor -> {
                    processor.setTransformer(container.getComponent("fileTransformer"));
                    processor.setSuccessfulHttpCodes(new int[] { 200 });
                    processor.setNotModifiedHttpCodes(new int[] { 304 });
                })//

 * 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 java.util.ArrayList;
import java.util.HashSet;
import java.util.List;
import java.util.Set;
import java.util.stream.Collectors;

import org.apache.logging.log4j.LogManager;

    NO_URL_IN_QUEUE,
    /** Indicates the start of a crawler thread. */
    START_THREAD,
    /** Indicates the finish of a crawler thread. */
    FINISHED_THREAD,
    /** Indicates no response processor is available. */
    NO_RESPONSE_PROCESSOR,
    /** Indicates no rule is available for processing. */
    NO_RULE,
    /** Indicates a system error occurred. */
    SYSTEM_ERROR