import org.codelibs.fess.crawler.container.CrawlerContainer;

import jakarta.annotation.Resource;

/**
 * Creates and manages crawler clients for web crawling operations.
 * This class handles the registration and loading of crawler client factories and their associated clients.
 * <p>
 * The class maintains a mapping between regular expressions and component names, and manages a list

 * from FTP servers. The client supports various configurations, including authentication, timeouts,
 * passive/active modes, and encoding settings. It also handles FTP file attributes such as user,
 * group, and symbolic links.
 *
 * <p>
 * The class uses Apache Commons Net library for FTP communication. It maintains a queue of FTPClient

 *
 * <p>
 * This class provides methods to:
 * </p>
 * <ul>
 *   <li>Detect the MIME type based on the input stream and filename.</li>
 *   <li>Normalize the filename to handle special characters.</li>
 *   <li>Configure whether to use the filename for MIME type detection.</li>
 *   <li>Configure whether to use the filename for MIME type detection when the stream is octet-stream.</li>
 * </ul>
 *

import org.apache.http.auth.Credentials;
import org.codelibs.fess.crawler.client.http.Authentication;

/**
 * Implementation of the {@link Authentication} interface.
 * This class provides methods to handle authentication details such as
 * authentication scope, credentials, and authentication scheme.
 *
 * <p>
 * It includes constructors to initialize these details and getter and setter
 * methods to access and modify them.

 *     .method("GET")
 *     .url("https://example.com")
 *     .weight(1.0f)
 *     .build();
 * </pre>
 *
 * <p>The builder is implemented using an inner class {@link RequestDataContext} that handles
 * the actual construction of the RequestData object.</p>
 *
 */
public final class RequestDataBuilder {
    private RequestDataBuilder() {
    }

    /**

     * frequently than that, and they may crawl pages marked "yearly" more
     * frequently than that. Crawlers may periodically crawl pages marked
     * "never" so that they can handle unexpected changes to those pages.
     */
    private String changefreq;

    /**
     * The priority of this URL relative to other URLs on your site. Valid

 *
 * <p>This class uses various utilities such as ReadingConverter, Normalizer, and SuggestAnalyzer
 * to process and analyze the input data.</p>
 *
 * <p>It also handles the exclusion of search words based on certain criteria and manages the
 * maximum length of analyzed content.</p>
 *
 * <p>Methods in this class may throw SuggesterException in case of failures during the parsing process.</p>
 *

<tbody>
<tr>
<td align="left" style="padding:0;margin:0;line-height:1px;font-size:1px;">

import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Abstract base class for XML extractors.
 * Provides common functionality for extracting text content from XML-like documents.
 * It handles encoding detection, HTML entity unescaping, and tag-based content extraction.
 *
 */
public abstract class AbstractXmlExtractor extends AbstractExtractor {

    /**
     * Logger for this class.
     */

 * The extracted text is then converted into a byte array using the specified charset encoding.
 * It also provides a method to retrieve the extracted data as a String from an AccessResultData object.
 *
 * <p>
 * The class handles character encoding issues by attempting to use the specified charset.
 * If the specified charset is invalid, it falls back to UTF-8.
 * </p>
 *
 * <p>