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

import jakarta.annotation.Resource;

/**
 * An abstract base class for implementing Extractor interfaces.
 * Provides common functionality such as access to CrawlerContainer components
 * and registration with the ExtractorFactory.
 *
 * <p>

import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;
import org.codelibs.fess.crawler.util.IgnoreCloseInputStream;

import jakarta.annotation.Resource;

/**
 * Extracts text content from ZIP archives.
 */
public class ZipExtractor extends AbstractExtractor {
    private static final Logger logger = LogManager.getLogger(ZipExtractor.class);

    /**

import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;
import org.codelibs.fess.crawler.util.IgnoreCloseInputStream;

import jakarta.annotation.Resource;

/**
 * Extracts text content from TAR archives.
 */
public class TarExtractor extends AbstractExtractor {
    private static final Logger logger = LogManager.getLogger(TarExtractor.class);

    /**

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.filter.UrlFilter;
import org.codelibs.fess.crawler.service.UrlFilterService;

import jakarta.annotation.Resource;

/**
 * Implementation of the {@link UrlFilter} interface.
 * This class provides functionality to filter URLs based on include and exclude patterns.

import org.codelibs.fess.crawler.exception.ChildUrlsException;
import org.codelibs.fess.crawler.helper.SitemapsHelper;
import org.codelibs.fess.crawler.processor.ResponseProcessor;

import jakarta.annotation.Resource;

/**
 * A response processor implementation that handles sitemaps.
 * It parses the response body as a SitemapSet, extracts URLs from the sitemaps,
 * and adds them as child URLs to be crawled.
 *
 * <p>

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

import jakarta.annotation.Resource;

/**
 * Factory class for managing and retrieving {@link Extractor} instances.
 * This class provides methods to add, retrieve, and manage extractors based on a key.

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

import org.codelibs.fess.crawler.helper.MemoryDataHelper;
import org.codelibs.fess.crawler.service.UrlFilterService;

import jakarta.annotation.Resource;

/**
 * Implementation of the {@link UrlFilterService} interface.
 * This class provides methods for managing URL filtering rules,
 * including adding include and exclude URL patterns, deleting patterns,

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

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.
 *

import org.codelibs.fess.crawler.helper.MemoryDataHelper;
import org.codelibs.fess.crawler.service.DataService;
import org.codelibs.fess.crawler.util.AccessResultCallback;

import jakarta.annotation.Resource;

/**
 * Implementation of the {@link DataService} interface for managing access result data.
 * This class provides methods to store, retrieve, update, and delete access results,

import java.util.List;
import java.util.Map;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
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>