* </p>
 * <ol>
 *   <li>Fetching a URL from the queue using {@link UrlQueueService#poll(String)}.</li>
 *   <li>Checking if the URL is valid using {@link #isValid(UrlQueue)}.</li>
 *   <li>Accessing the content using a {@link CrawlerClient} obtained from {@link CrawlerClientFactory}.</li>
 *   <li>Processing the response using a {@link ResponseProcessor} associated with a {@link Rule}.</li>

                    if (logger.isDebugEnabled()) {
                        logger.debug("Using default extractor {} for MIME type {}", extractorName, mimeType);
                    }
                    extractor = crawlerContainer.getComponent(extractorName);
                } else if (logger.isDebugEnabled()) {
                    logger.debug("Using {} for detected MIME type {}, not {}", extractor.getClass().getName(), detectedMimeType, mimeType);

            }
        } else if (logger.isDebugEnabled()) {
            logger.debug("{} mapping exists.", index);
        }
    }

    /**
     * Extracts a Date object from the source map using the specified field name.
     * Handles various date formats including Date objects, timestamp numbers, and ISO date strings.
     *
     * @param sourceMap The source map containing the date field.

import org.codelibs.jcifs.smb1.util.LogStream;

/**
 * The {@link SmbClient} class is a crawler client implementation for accessing files and directories
 * on SMB (Server Message Block) shares using the SMB1 protocol. It extends {@link AbstractCrawlerClient} and utilizes the JCIFS library
 * to interact with SMB resources.
 *
 * <p>

import org.xml.sax.SAXException;

import jakarta.annotation.PostConstruct;

/**
 * <p>
 * The {@link TikaExtractor} class is responsible for extracting text content and metadata from various file formats
 * using the Apache Tika library. It extends {@link PasswordBasedExtractor} to handle password-protected files.
 * </p>
 *
 * <p>
 * This class provides methods to extract text from an input stream, handling different scenarios such as:

import org.jodconverter.local.LocalConverter;

import jakarta.annotation.PostConstruct;
import jakarta.annotation.PreDestroy;

/**
 * Extracts text content from various document formats using JODConverter.
 */
public class JodExtractor extends AbstractExtractor {
    /** Logger for this class. */
    private static final Logger logger = LogManager.getLogger(JodExtractor.class);

/**
 * Handler for the "storage" protocol, allowing access to objects stored in a MinIO-compatible storage service.
 * This handler extends {@link URLStreamHandler} to provide a way to open connections to storage objects
 * using URLs with the "storage" protocol.
 *
 * <p>
 * The URL format is expected to be: {@code storage://bucketName/objectName}.
 * The bucket name and object name are extracted from the URL.
 * </p>
 *
 * <p>

import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;

/**
 * PdfExtractor extracts text content from PDF files using Apache PDFBox.
 * It supports password-protected PDFs and can extract embedded documents and annotations.
 *
 * <p>The extractor runs text extraction in a separate thread with a configurable timeout

import org.codelibs.fess.crawler.Constants;

/**
 * The FormScheme class implements the AuthScheme interface to provide
 * form-based authentication for HTTP clients. It handles the process of
 * obtaining a token and logging in using the provided credentials.
 *
 * <p>This class supports both GET and POST methods for token and login
 * requests. It also allows for the replacement of placeholders in URLs and
 * parameters with actual credentials.
 *

- **CrawlerContext**: Execution context and configuration
- **CrawlerThread**: Individual crawler thread implementation

#### Client Architecture
- **HcHttpClient**: HTTP/HTTPS client using Apache HttpComponents
- **FileSystemClient**: File system access
- **FtpClient**: FTP protocol support
- **SmbClient**: SMB/CIFS network shares
- **StorageClient**: Cloud storage integration