* It uses XPath expressions to extract data from the XML and stores it in a ResultData object.
 * </p>
 *
 * <p>
 * This class provides several configuration options to customize the XML parsing process, such as:
 * </p>
 * <ul>
 *   <li>Namespace awareness</li>
 *   <li>Coalescing</li>
 *   <li>Entity expansion</li>

 * It extends the AbstractTransformer class.
 *
 * <p>
 * This transformer extracts the binary content from the response body of a web resource,
 * stores it as a byte array in the ResultData, and provides a method to retrieve this data
 * as a ByteArrayInputStream.
 * </p>
 *
 * <p>
 * The transform method takes a ResponseData object, checks if it has a response body,

 */
package org.codelibs.fess.crawler;

import java.nio.charset.Charset;
import java.nio.charset.StandardCharsets;

/**
 * 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.
 */

import org.xml.sax.helpers.DefaultHandler;

/**
 * Helper class for parsing and validating sitemaps.
 * It supports XML sitemaps, XML sitemap indexes, and text sitemaps,
 * and can handle GZIP compressed sitemaps.
 * The class provides methods to check if an input stream is a valid sitemap,
 * and to parse an input stream into a {@link SitemapSet} object.
 * It uses SAX parser for XML sitemaps and XML sitemap indexes,

import org.codelibs.fess.crawler.helper.LogHelper;
import org.codelibs.fess.crawler.log.LogType;

/**
 * Implementation of the {@link LogHelper} interface.
 * This class provides methods for logging various events during the crawling process.
 * It uses Log4j2 for logging.
 *
 * <p>
 * The class contains methods for logging different types of events, such as:
 * </p>
 * <ul>

 * including its location, last modification date, change frequency, and priority.
 * It implements the {@link Sitemap} interface.
 * </p>
 *
 * <p>
 * The {@code SitemapUrl} class provides getter and setter methods for each of these properties,
 * as well as implementations for {@code equals()}, {@code hashCode()}, and {@code toString()} methods.
 * </p>
 *
 */
public class SitemapUrl implements Sitemap {

/**
 * Represents SMB1 authentication information, including server details,
 * credentials, and domain. This class is used to encapsulate the necessary
 * information for authenticating with an SMB1 server.
 *
 * <p>
 * It provides methods to set and retrieve the server address, port, username,
 * password, and domain. Additionally, it offers a method to construct a path
 * prefix for SMB1 URLs based on the configured server and port.
 * </p>
 *
 * <p>

import org.codelibs.fess.crawler.rule.Rule;
import org.codelibs.fess.crawler.rule.RuleManager;

/**
 * Implementation of the {@link RuleManager} interface.
 * Manages a list of rules for the crawler.
 * Provides methods to add, remove, check, and retrieve rules.
 *
 */
public class RuleManagerImpl implements RuleManager {

    /** The list of rules managed by this rule manager. */

 * This exception indicates a failure or error that occurred while extracting content from a crawled resource.
 * It extends {@link org.codelibs.fess.crawler.exception.CrawlerSystemException} and provides constructors
 * to handle different scenarios such as wrapping another exception or providing a specific error message.
 */
public class ExtractException extends CrawlerSystemException {

import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.RequestData.Method;

/**
 * Builder class for creating RequestData objects using a fluent interface.
 * This class provides a simple way to construct RequestData objects with method chaining.
 *
 * <p>Usage example:</p>
 * <pre>
 * RequestData request = RequestDataBuilder.newRequestData()
 *     .method("GET")