* This constructor parses the URL to extract bucket and object names.
         *
         * @param url The GCS URL to connect to
         */
        protected GcsURLConnection(final URL url) {
            super(url);
            // Extract bucket name from host
            bucketName = url.getHost() != null ? url.getHost() : StringUtil.EMPTY;

         * This constructor parses the URL to extract bucket and object names.
         *
         * @param url The S3 URL to connect to
         */
        protected S3URLConnection(final URL url) {
            super(url);
            // Extract bucket name from host
            bucketName = url.getHost() != null ? url.getHost() : StringUtil.EMPTY;

 * 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>

         * This constructor parses the URL to extract bucket and object names.
         *
         * @param url The storage URL to connect to
         */
        protected StorageURLConnection(final URL url) {
            super(url);
            // Extract bucket name from host
            bucketName = url.getHost() != null ? url.getHost() : StringUtil.EMPTY;

    }

    /**
     * Extracts a subset of documents from the full result list based on pagination parameters.
     * Applies proper bounds checking to ensure the extracted range is within the document list size.
     *
     * @param docs the full list of search result documents

        assertEquals("file.txt", file.getName(), "Name should be extracted correctly");
        assertTrue(file.getPath().endsWith("/shared/path/file.txt"), "Path should end correctly");
        assertEquals("shared", file.getShare(), "Share should be extracted correctly");
        assertNotNull(file.getParent(), "Parent should not be null");

            return null;
        }
    }

    /**
     * Retrieves the pipeline configuration parameter for a given config ID.
     * The pipeline parameter is extracted from the crawling configuration's parameter map.
     *
     * @param configId the configuration ID to get the pipeline for
     * @return an OptionalThing containing the pipeline string if found, or empty if not found or blank

                logger.warn("Failed to delete thumbnail file: {}", path, e);
            }
        }

        /**
         * Extracts the document ID from a file path.
         *
         * @param file the file path
         * @return the extracted document ID
         */
        protected String getDocId(final Path file) {
            final String s = file.toUri().toString();

labels.pathmap_title_details=Path Mapping
labels.disabled=Disabled
labels.pathmap_pt_crawling=Crawling
labels.pathmap_pt_displaying=Displaying
labels.pathmap_pt_both=Crawling/Displaying
labels.pathmap_pt_stored=Extracted URL Conversion
labels.regular_name=Regular Name
labels.duplicate_name=Duplicate Name
labels.duplicate_host_configuration=Duplicate Host
labels.duplicate_host_title_details=Duplicate Host

labels.pathmap_title_details=Path Mapping
labels.disabled=Disabled
labels.pathmap_pt_crawling=Crawling
labels.pathmap_pt_displaying=Displaying
labels.pathmap_pt_both=Crawling/Displaying
labels.pathmap_pt_stored=Extracted URL Conversion
labels.regular_name=Regular Name
labels.duplicate_name=Duplicate Name
labels.duplicate_host_configuration=Duplicate Host
labels.duplicate_host_title_details=Duplicate Host