processor.setNotModifiedHttpCodes(new int[] { 304 });

        ResponseData responseData = new ResponseData();
        responseData.setHttpStatusCode(200);
        assertTrue(processor.isSuccessful(responseData));

        responseData.setHttpStatusCode(100);
        assertFalse(processor.isSuccessful(responseData));
        responseData.setHttpStatusCode(304);
        assertFalse(processor.isSuccessful(responseData));

    }

    @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;
    }

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

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

/**
 * The ResponseProcessor interface defines a contract for processing response data.
 * Implementations of this interface are responsible for handling the response data
 * obtained during a crawling process.
 */
public interface ResponseProcessor {

    /**
     * Processes the given response data.
     *

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>

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 {

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

    /**
     * Processes the given response data.
     * This implementation does nothing.
     *
     * @param responseData the response data to process
     */
    @Override
    public void process(final ResponseData responseData) {
        // do nothing
    }

		<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>

package org.codelibs.fess.crawler.log;

/**
 * LogType defines the different types of log messages that can be generated during the crawling process.
 * Each enum constant represents a specific event or state in the crawler's execution.
 */
public enum LogType {
    /** Indicates the start of a crawling process. */
    START_CRAWLING,
    /** Indicates the cleanup phase of crawling. */
    CLEANUP_CRAWLING,

 */
public interface AccessResultCallback<RESULT extends AccessResult<?>> {
    /**
     * Processes the given access result.
     *
     * @param accessResult the result of the access operation to be processed
     */
    /**
     * Processes the given access result.
     *
     * @param accessResult the result of the access operation to be processed
     */
    void iterate(RESULT accessResult);

     *
     * @param urlPattern Regular expression that is not crawled
     */
    void addExclude(String urlPattern);

    /**
     * Process an url when it's added as a seed url.
     *
     * @param url URL
     */
    void processUrl(String url);

    /**
     * Clear this filter.
     */
    void clear();