}

    @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.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.processor.impl.DefaultResponseProcessor;
import org.codelibs.fess.ingest.IngestFactory;

	<component name="sitemapsRule" class="org.codelibs.fess.crawler.rule.impl.RegexRule" >
		<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>"http[s]?:.*sitemap[^/]*\.xml.*|http[s]?:.*sitemap[^/]*\.gz.*|http[s]?:.*sitemap[^/]*\.txt.*"</arg>

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 {

                    java.util.function.BiFunction<org.opensearch.action.update.UpdateRequestBuilder, org.opensearch.search.SearchHit, org.opensearch.action.update.UpdateRequestBuilder> processor) {
                // Return a fixed count for testing
                return 3L;
            }
        };
        ComponentUtil.register(mockSearchEngineClient, "searchEngineClient");

        // Mock FessConfig

    /**
     * Artifact type name for a JAR file that can be placed either on the annotation processor class path
     * or module path. The path (classes or modules) is chosen by the plugin, possibly using heuristic rules.
     */
    String PROCESSOR = "processor";

    /**
     * Artifact type name for a JAR file to unconditionally place on the annotation processor class path.
     * If the JAR is modular, its module information are ignored.
     */

import org.opensearch.index.query.QueryBuilder;

import jakarta.annotation.PostConstruct;

/**
 * Query processor component that handles query filters and commands.
 * This class provides a pipeline for processing Lucene queries by applying
 * a chain of filters and executing registered query commands.
 *
 * <p>The processor maintains a map of query commands indexed by query class names

        connect(con -> {
            final RequestProcessor processor = new RequestProcessor(encoding, threshold);
            processor.accept(con);
            try (final CurlResponse res = processor.getResponse()) {
                actionListener.accept(res);
            } catch (final IOException e) {
                exceptionListener.accept(e);

     * @return The query class name.
     */
    protected abstract String getQueryClassName();

    /**
     * Registers this query command with the query processor.
     * Associates this command with its query class name in the processor.
     */
    public void register() {
        ComponentUtil.getQueryProcessor().add(getQueryClassName(), this);
    }

    /**
     * Gets the query field configuration.

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>