* represents a valid sitemap. It uses a SitemapsHelper to validate the response body as an InputStream.
 * The rule checks if the URL matches the defined regex pattern and then validates the content as a sitemap.
 * If any exception occurs during the sitemap validation, it logs the error and returns false.
 *
 */
public class SitemapsRule extends RegexRule {
    /**

 * and provides getter and setter methods for common properties such as
 * {@code ruleId} and {@code responseProcessor}.
 * </p>
 *
 * <p>
 * Subclasses should extend this class and implement the abstract methods
 * defined in the {@link Rule} interface to provide specific rule logic.
 * </p>
 *
 */
public abstract class AbstractRule implements Rule {

    private static final long serialVersionUID = 1L;

    /** The rule ID. */

 *   <li>Loading index settings and mappings from resources.</li>
 *   <li>Checking the availability of analyzers for supported languages.</li>
 * </ul>
 *
 * <p>Supported languages are defined in the SUPPORTED_LANGUAGES array.</p>
 *
 * <p>Inner class:</p>
 * <ul>
 *   <li>DefaultContentsAnalyzer: Implements the SuggestAnalyzer interface to analyze text and retrieve tokens using

 * The class supports caching of include and exclude patterns for scenarios where a session ID is not available.
 * It also provides methods to initialize the filter with a session ID, clear the filter,
 * match a URL against the defined patterns, and process a URL to add include or exclude patterns based on predefined filtering patterns.
 *
 */
/**
 * This class is an implementation of a URL filter.
 */
public class UrlFilterImpl implements UrlFilter {

 * Constants used in the fess-crawler.
 * This class provides a collection of constant values for HTTP methods, status codes,
 * transformer names, boolean values, character encodings, date/time formats, and XML features.
 * It is designed to avoid the instantiation.
 */
public final class Constants {
    /**
     * The GET method.
     */
    public static final String GET_METHOD = "GET";

    /**
     * The HEAD method.
     */

import org.xml.sax.InputSource;

/**
 * {@link XpathTransformer} is a class that transforms HTML content into XML format based on XPath expressions.
 * It extracts data from an HTML document by applying XPath rules defined in {@link #fieldRuleMap}.
 * The extracted data is then formatted into an XML structure and stored in the {@link ResultData}.
 * <p>

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

import org.codelibs.core.lang.StringUtil;

/**
 * Represents a URL entry within a sitemap.
 *
 * <p>
 * This class encapsulates the properties of a URL as defined in the sitemap XML format,
 * including its location, last modification date, change frequency, and priority.
 * It implements the {@link Sitemap} interface.
 * </p>
 *
 * <p>

import java.util.List;
import java.util.Map;
import java.util.regex.Pattern;

import org.codelibs.core.lang.StringUtil;

/**
 * Represents a robots.txt file parser and handler.
 * This class manages the rules defined in a robots.txt file, including user agent directives,
 * allowed/disallowed paths, crawl delays, and sitemap URLs.
 *
 * <p>The robots.txt protocol is implemented according to the standard specification,

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

    /**

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.interval;

/**
 * The {@code IntervalController} interface defines methods for controlling
 * the delay intervals in a web crawler. It includes constants representing
 * different types of processing states and a method to introduce a delay
 * based on the type of processing.
 * <p>