- **Java**: 21+ (requires Java 21 or higher)
- **Build System**: Maven 3.x
- **DI Container**: LastaFlute DI
- **HTTP Client**: Apache HttpComponents
- **Content Extraction**: Apache Tika, Apache POI, PDFBox
- **Testing**: JUnit 4, UTFlute, Testcontainers
- **Storage Backends**: OpenSearch, Memory-based

## Quick Start

### Prerequisites

- Java 21 or higher
- Maven 3.6 or higher

### Installation

 * 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.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */
public class ZipExtractorTest extends PlainTestCase {
    private static final Logger logger = LogManager.getLogger(ZipExtractorTest.class);

    public ZipExtractor zipExtractor;

    @Override
    protected void setUp() throws Exception {
        super.setUp();

 *   <li>{@link #isSuggestIndex(String)}: Checks if the given index name is a suggestion index.</li>
 * </ul>
 */
public class Suggester {
    private static final Logger logger = LogManager.getLogger(Suggester.class);

    /** The OpenSearch client. */
    protected final Client client;
    /** The suggest settings. */
    protected final SuggestSettings suggestSettings;

 *
 * @author shinsuke
 *
 */
public class OpenSearchUrlQueueService extends AbstractCrawlerService implements UrlQueueService<OpenSearchUrlQueue> {
    /**
     * Logger instance.
     */
    private static final Logger logger = LogManager.getLogger(OpenSearchUrlQueueService.class);

    /**
     * Data service for checking access results.
     */
    @Resource
    protected OpenSearchDataService dataService;

 * </ul>
 *
 * <p>Logging:</p>
 * <ul>
 *   <li>Uses {@code Logger} to log debug information when adding, deleting, or deleting all elevate words.</li>
 * </ul>
 */
public class ElevateWordSettings {
    private static final Logger logger = LogManager.getLogger(ElevateWordSettings.class);

    /** Key for elevate word settings. */

 *
 */
public class SitemapsRule extends RegexRule {
    /**
     * Serial version UID for serialization.
     */
    private static final long serialVersionUID = 1L;

    private static final Logger logger = LogManager.getLogger(SitemapsRule.class);

    /**
     * Creates a new SitemapsRule instance.
     */
    public SitemapsRule() {
        super();
    }

    /**

 *   <li>Configurable timeout for extraction process</li>
 * </ul>
 *
 * @author shinsuke
 */
public class PdfExtractor extends PasswordBasedExtractor {
    /** Logger instance for this class. */
    private static final Logger logger = LogManager.getLogger(PdfExtractor.class);

    /** Timeout for PDF extraction in milliseconds (default: 30 seconds). */
    protected long timeout = 30000; // 30sec

 * by using appropriate extractors for each contained file type.
 *
 * @author shinsuke
 */
public class LhaExtractor extends AbstractExtractor {
    /** Logger for this class. */
    private static final Logger logger = LogManager.getLogger(LhaExtractor.class);

    /** Maximum content size for extraction. -1 means no limit. */
    protected long maxContentSize = -1;

    /**

 * <li>{@link #loadIndexSettings()}: Loads the index settings from a JSON file.</li>
 * </ul>
 *
 * <p>Fields:
 * <ul>
 * <li>{@link #logger}: Logger instance for logging debug information.</li>
 * <li>{@link #client}: OpenSearch client instance.</li>
 * <li>{@link #arraySettingsIndexName}: Name of the array settings index.</li>