<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>

     */
    public CurlResponse execute() {
        this.threadPool = null;
        final RequestProcessor processor = new RequestProcessor(encoding, threshold);
        connect(processor, e -> {
            throw new CurlException("Failed to process a request.", e);
        });
        return processor.getResponse();
    }

    /**
     * Encodes the specified value using the character encoding.
     *

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>

   *     processor} throws an {@code IOException}
   * @since 16.0
   */
  @CanIgnoreReturnValue // some processors won't return a useful result
  @ParametricNullness
  public <T extends @Nullable Object> T readLines(LineProcessor<T> processor) throws IOException {
    checkNotNull(processor);

    Closer closer = Closer.create();
    try {

   *     processor} throws an {@code IOException}
   * @since 16.0
   */
  @CanIgnoreReturnValue // some processors won't return a useful result
  @ParametricNullness
  public <T extends @Nullable Object> T readLines(LineProcessor<T> processor) throws IOException {
    checkNotNull(processor);

    Closer closer = Closer.create();
    try {

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 {

    /**
     * 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.
     */

     * @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.

     */
    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
    }

 */
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.
     *