/**
     * Target indices for OpenSearch.
     */
    public static final String TARGET_INDICES = "crawler.opensearch.target_indices";

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

    /**
     * The OpenSearch client.
     */
    protected Client client;

    /**

 * the stored file path as a File object.
 * </p>
 */
public class FileTransformer extends HtmlTransformer {
    /** Logger instance for this class */
    private static final Logger logger = LogManager.getLogger(FileTransformer.class);

    /**
     * Constructs a new FileTransformer.
     */
    public FileTransformer() {
        // Default constructor
    }

 * It handles encoding detection, HTML entity unescaping, and tag-based content extraction.
 *
 */
public abstract class AbstractXmlExtractor extends AbstractExtractor {

    /**
     * Logger for this class.
     */
    protected static final Logger logger = LogManager.getLogger(AbstractXmlExtractor.class);

    /**
     * UTF-7 Byte Order Mark definition.
     */

 * System.out.println(normalizedText);
 * }</pre>
 *
 * <p>Note: This class is not intended to be instantiated.
 *
 * @see TextNormalizeContext
 */
public final class TextUtil {
    private static final Logger logger = LogManager.getLogger(TextUtil.class);

    private TextUtil() {
    }

    /**
     * This class provides a context for normalizing text.
     */
    public static class TextNormalizeContext {

            case "NoSuchKey", "NoSuchObject":
                if (logger.isDebugEnabled()) {
                    logger.debug("{} is not an object.", path);
                }
                break;
            default:
                logger.warn(path + " is not an object.", e);
                break;
            }
        } catch (final Exception e) {
            logger.warn(path + " is not an object.", e);
        }

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

    /**
     * Constructs a new FtpAuthentication.
     */
    public FtpAuthentication() {
        // Default constructor
    }

    private String server;

    private int port;

    private String username;

        // check url
        if (crawlerContext.getRobotsTxtUrlSet().contains(robotTxtUrl)) {
            if (logger.isDebugEnabled()) {
                logger.debug("{} is already visited.", robotTxtUrl);
            }
            return;
        }

        if (logger.isInfoEnabled()) {
            logger.info("Checking URL: {}", robotTxtUrl);
        }
        // add url to a set

    }

    /**
     * Returns whether the crawler waits on folder operations.
     * @return true if no wait on folder, false otherwise.
     */
    public boolean isNoWaitOnFolder() {
        return noWaitOnFolder;
    }

    /**
     * Sets whether the crawler waits on folder operations.
     * @param noWaitOnFolder true to disable waiting on folder operations.
     */

import org.w3c.dom.Node;
import org.xml.sax.InputSource;

/**
 * Extracts text content from HTML documents.
 */
public class HtmlExtractor extends AbstractXmlExtractor {
    /** Logger for this class. */
    protected static final Logger logger = LogManager.getLogger(HtmlExtractor.class);

    /** Pattern for extracting charset from meta tags. */

data/folder/file.html テスト data/file.txt テキスト...