/**
 * 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
 * to prevent hanging on problematic PDF files. It also extracts metadata from the PDF
 * document and includes it in the extraction result.
 *

 * <li>{@link #addToArrayIndex(String, String, String, Map)}: Adds a map to the array index.</li>
 * <li>{@link #deleteKeyFromArray(String, String, String)}: Deletes all entries associated with the specified key from the array index.</li>
 * <li>{@link #deleteFromArray(String, String, String)}: Deletes a specific entry from the array index based on the ID.</li>

                    builder.addSort(sortBuilder);
                }
            }
            if (from != null) {
                builder.setFrom(from);
            }
            if (size != null) {
                builder.setSize(size);
            }
        });
    }

    /**
     * Retrieves a list of documents from the OpenSearch index using a custom search request builder.
     *

    }

    /**
     * Extracts keywords from the given query string based on the specified fields.
     *
     * @param q the query string to parse and extract keywords from
     * @param fields the fields to consider when extracting keywords
     * @return a list of unique keywords extracted from the query string
     */

    /**
     * Gets the set of child URLs discovered from this response.
     *
     * @return the set of child URLs
     */
    public Set<RequestData> getChildUrlSet() {
        return childUrlSet;
    }

    /**
     * Creates a RequestData object from this response's URL and method.
     *
     * @return a new RequestData object with the URL and method from this response
     */

 * It uses XPath expressions to extract text content from HTML documents.
 * <p>
 * This class provides methods to configure the XPath expressions, parser features, and properties.
 * It also includes caching mechanism for XPathAPI instances to improve performance.
 * </p>
 * <p>
 * The extracted text is obtained from the nodes selected by the {@code targetNodePath} XPath expression.

        }
        return null;
    }

    /**
     * Extracts URLs from HTML tag attributes using XPath.
     *
     * @param url the base URL for resolving relative URLs
     * @param document the document to extract URLs from
     * @param xpath the XPath expression to select elements
     * @param attr the attribute name to extract URLs from
     * @param encoding the character encoding to use

 * </p>
 *
 * <p>
 * The crawling process involves the following steps:
 * </p>
 * <ol>
 *   <li>Fetching a URL from the queue using {@link UrlQueueService#poll(String)}.</li>
 *   <li>Checking if the URL is valid using {@link #isValid(UrlQueue)}.</li>
 *   <li>Accessing the content using a {@link CrawlerClient} obtained from {@link CrawlerClientFactory}.</li>

     * This class handles the authentication, connection management, and data retrieval
     * from storage buckets and objects.
     *
     * <p>
     * The connection extracts bucket and object names from the URL and uses environment
     * variables for authentication and endpoint configuration.
     * </p>
     */

        return processRequest(uri, true);
    }

    /**
     * Processes an FTP request to retrieve data from the specified URI.
     * This method handles the complete FTP request lifecycle including timeout management,
     * connection setup, and data retrieval.
     *
     * @param uri The URI to retrieve data from
     * @param includeContent Whether to include the actual content in the response