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.
 * It uses a {@link UrlFilterService} to manage the URL filtering rules.

 * supports dependency injection via the {@link Resource} annotation.
 * </p>
 */
public class ExtractorFactory {

    /** Logger instance for this class */
    private static final Logger logger = LogManager.getLogger(ExtractorFactory.class);

    /** Container for managing crawler components */
    @Resource
    protected CrawlerContainer 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.
 *
 * <p>The factory maintains a map of regular expression patterns to crawler clients,

        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }
        try {
            @SuppressWarnings("resource")
            final SlideShowExtractor<HSLFShape, HSLFTextParagraph> extractor = new SlideShowExtractor<>(new HSLFSlideShow(in));
            return new ExtractData(extractor.getText());
        } catch (final IOException e) {

 * </p>
 *
 * <p>
 * Usage:
 * </p>
 * <pre>
 * MimeTypeHelperImpl mimeTypeHelper = new MimeTypeHelperImpl();
 * String contentType = mimeTypeHelper.getContentType(inputStream, filename);
 * </pre>
 */
public class MimeTypeHelperImpl implements MimeTypeHelper {
    /** The resource name for the MIME types configuration file. */

        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }
        try {
            @SuppressWarnings("resource")
            final PublisherTextExtractor publisherTextExtractor = new PublisherTextExtractor(in);
            return new ExtractData(publisherTextExtractor.getText());
        } catch (final IOException e) {

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 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>

        final String outExt = extensionMap.get(extension);
        return outExt == null ? "txt" : outExt;
    }

    /**
     * Extracts the file name from a resource name.
     *
     * @param resourceName the resource name
     * @return the file name
     */
    private String getFileName(final String resourceName) {
        final String name = resourceName.replaceAll("/+$", "");

 * This class provides methods to extract text from an input stream, handling different scenarios such as:
 * </p>
 * <ul>
 *   <li>Normalizing text content</li>
 *   <li>Handling resource names and content types</li>
 *   <li>Retrying extraction without resource name or content type if the initial attempt fails</li>
 *   <li>Extracting text from metadata if the main content extraction fails</li>