* Implementations of this interface should provide the logic for reading
 * documents and converting them into a key-value structure.
 *
 * <p>This interface extends {@link java.io.Closeable}, so implementations
 * should also handle resource cleanup when the {@link #close()} method is called.</p>
 */
public interface DocumentReader extends Closeable {
    /**
     * Reads a document and returns its contents as a map.
     *

import org.dbflute.utflute.core.PlainTestCase;
import org.mortbay.jetty.Handler;
import org.mortbay.jetty.HttpConnection;
import org.mortbay.jetty.HttpMethods;
import org.mortbay.jetty.Server;
import org.mortbay.jetty.handler.AbstractHandler;
import org.mortbay.jetty.handler.DefaultHandler;
import org.mortbay.jetty.handler.HandlerList;

/**
 * @author shinsuke
 *
 */

 * 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 {

    private static final long serialVersionUID = 1L;

 *
 * <p>
 * This exception can be thrown when there are problems accessing URLs, files, or any other resources needed for crawling.
 * It includes constructors to handle messages, causes, or both.
 * </p>
 *
 * <p>
 * The log level can be set to DEBUG, INFO, WARN, or ERROR, and the class provides methods to check if a specific log level is enabled.
 * </p>
 *
 * <p>

import org.codelibs.core.timer.TimeoutTarget;

/**
 * HcConnectionMonitorTarget is responsible for monitoring and managing HTTP client connections.
 * It implements the TimeoutTarget interface to handle connection expiration events.
 *
 * <p>This class uses an instance of HttpClientConnectionManager to manage the connections.
 * It closes expired connections and idle connections that have exceeded a specified timeout.
 * </p>

import com.fasterxml.jackson.core.type.TypeReference;
import com.fasterxml.jackson.databind.ObjectMapper;

/**
 * PasswordBasedExtractor is an abstract base class for extractors that can handle password-protected files.
 * It provides functionality to manage passwords for different file patterns using regular expressions.
 *
 * <p>The extractor supports two types of password management:
 * <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.

 *
 * <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>
 *

     * 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

import jakarta.annotation.PostConstruct;
import jakarta.annotation.Resource;

/**
 * A factory class for managing and creating crawler clients based on URL patterns.
 * This class implements AutoCloseable to properly handle resource cleanup.
 *
 * <p>The factory maintains a map of regular expression patterns to crawler clients,
 * allowing for URL-based client selection. Clients can be added with specific patterns