}

    /**
     * Adds a boost function with a filter to modify document scoring during search.
     * This method adds a boost function that applies only to documents matching the filter.
     *
     * @param filter the query filter to determine which documents the boost applies to
     * @param scoreFunction the score function to add for boosting
     */

        while (!crawlerRunning) {
            ThreadUtil.sleepQuietly(crawlerWaitMillis);
        }
    }

    /**
     * Applies delay based on the configured interval rules.
     * This method calculates the appropriate delay for the current time
     * and applies it by sleeping the current thread.
     */
    public void delayByRules() {
        final long delay = getDelay();
        if (delay > 0) {

 * and processes them to create thumbnail images based on configured dimensions
 * and format settings.
 *
 * <p>The generator validates image MIME types, processes image data through
 * ImageIO operations, and applies scaling and cropping to generate thumbnails
 * that meet the specified size requirements.</p>
 *
 */
public class HtmlTagBasedGenerator extends BaseThumbnailGenerator {

   * FunctionWithIndex)}.
   *
   * @since 33.4.0 (but since 21.0 in the JRE flavor)
   */
  public interface FunctionWithIndex<T extends @Nullable Object, R extends @Nullable Object> {
    /** Applies this function to the given argument and its index within a stream. */
    @ParametricNullness
    R apply(@ParametricNullness T from, long index);
  }

  /*

      delay: Long,
      unit: TimeUnit,
    ): Builder =
      apply {
        headersDelayNanos = unit.toNanos(delay)
      }

    /**
     * Set the delayed time of the response body to [delay]. This applies to the response body
     * only; response headers are not affected.
     */
    public fun bodyDelay(
      delay: Long,
      unit: TimeUnit,
    ): Builder =
      apply {

 *
 * <p>The updater performs the following key operations:
 * <ul>
 * <li>Retrieves crawled documents from the data service</li>
 * <li>Transforms document data using appropriate transformers</li>
 * <li>Applies document boosting rules and click/favorite count enhancements</li>
 * <li>Sends processed documents to the search engine for indexing</li>
 * <li>Manages cleanup of processed crawler session data</li>
 * </ul>
 *

 * SSL socket. For example, if an SSL socket does not have TLS 1.3 enabled, it will not be used even
 * if it is present on the connection spec. The same policy also applies to cipher suites.
 *
 * Use [Builder.allEnabledTlsVersions] and [Builder.allEnabledCipherSuites] to defer all feature
 * selection to the underlying SSL socket.
 *

        }

        return url;
    }

    /**
     * Extracts and processes the site path from a URL with proper encoding handling.
     * Removes protocol, query parameters, and applies URL decoding based on encoding settings.
     *
     * @param u the URL string to process
     * @param encoding the character encoding to use for URL decoding
     * @return the processed site path, abbreviated if necessary

 * the leftmost label.
 *
 * If multiple patterns match a hostname, any match is sufficient. For example, suppose pin A
 * applies to `*.publicobject.com` and pin B applies to `api.publicobject.com`. Handshakes for
 * `api.publicobject.com` are valid if either A's or B's certificate is in the chain.
 *
 * ## Warning: Certificate Pinning is Dangerous!
 *

            }
        } catch (final Exception e) {
            logger.warn("Failed to initiaize TikaExtractor.", e);
        }
    }

    /**
     * Processes and normalizes a document title.
     * Applies text normalization using configured space characters and returns
     * a clean title suitable for indexing.
     *
     * @param responseData the response data from crawling (not currently used)