* extractor that iterates through the available extractors until one successfully
 * extracts the data.
 * </p>
 *
 * <p>
 * The class uses a {@link CrawlerContainer} for managing crawler components and
 * supports dependency injection via the {@link Resource} annotation.
 * </p>
 */
public class ExtractorFactory {

    /** Logger instance for this class */

import org.xml.sax.SAXNotRecognizedException;
import org.xml.sax.SAXNotSupportedException;
import org.xml.sax.helpers.DefaultHandler;

/**
 * Helper class for parsing and validating sitemaps.
 * It supports XML sitemaps, XML sitemap indexes, and text sitemaps,
 * and can handle GZIP compressed sitemaps.
 * The class provides methods to check if an input stream is a valid sitemap,

     */
    @Override
    public synchronized void mark(final int readlimit) {
        inputStream.mark(readlimit);
    }

    /**
     * Tests if this input stream supports the mark and reset methods.
     *
     * @return true if this stream instance supports the mark and reset methods; false otherwise
     */
    @Override
    public boolean markSupported() {
        return inputStream.markSupported();
    }

    /**

        fileInputStream.mark(readlimit);
    }

    /**
     * Tests if this input stream supports the mark and reset methods.
     * This method delegates to {@link FileInputStream#markSupported()}.
     *
     * @return {@code true} if this stream type supports the mark and reset method; {@code false} otherwise
     */
    @Override
    public boolean markSupported() {

 *
 * <p>
 * The class contains methods for logging different types of events, such as:
 * </p>
 * <ul>
 *   <li>Starting and finishing threads</li>
 *   <li>Starting and cleaning up crawling</li>
 *   <li>Handling unsupported URLs</li>
 *   <li>Checking last modified dates</li>
 *   <li>Getting content</li>
 *   <li>Handling redirects</li>
 *   <li>Processing responses</li>

 *   <li>readTimeout - Read timeout in milliseconds (default: 10000)</li>
 * </ul>
 *
 * <p>The client supports URLs in the format: {@code storage://bucket-name/object-path}
 *
 * <p>Features:
 * <ul>
 *   <li>Automatic initialization of MinIO client</li>
 *   <li>Support for HEAD and GET operations</li>
 *   <li>Content length validation</li>
 *   <li>MIME type detection</li>

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

## Key Features

- **Smart Query Suggestions**: Real-time auto-completion and search suggestions
- **Multi-language Support**: Built-in support for Japanese text processing with Kuromoji analyzer
- **Popular Words Analytics**: Track and analyze frequently searched terms
- **Flexible Text Processing**: Configurable converters and normalizers for text transformation

 */
public enum LogType {
    /** Indicates the start of a crawling process. */
    START_CRAWLING,
    /** Indicates the cleanup phase of crawling. */
    CLEANUP_CRAWLING,
    /** Indicates an unsupported URL was encountered when crawling started. */
    UNSUPPORTED_URL_AT_CRAWLING_STARTED,
    /** Indicates checking the last modified date of a resource. */
    CHECK_LAST_MODIFIED,

    public SuggestWriterResult deleteByQuery(final Client client, final SuggestSettings settings, final String index,
            final QueryBuilder queryBuilder) {
        throw new UnsupportedOperationException("deleteByQuery is unsupported.");
    }