*
 * <p>Features:
 * <ul>
 *   <li>Automatic initialization of MinIO client</li>
 *   <li>Support for HEAD and GET operations</li>
 *   <li>Content length validation</li>
 *   <li>MIME type detection</li>
 *   <li>Handling of large files through temporary file storage</li>
 *   <li>Object metadata and tags retrieval</li>
 *   <li>Directory listing capabilities</li>
 * </ul>
 *

 *   <li>{@link #elevateWord()} - Returns an instance of ElevateWordSettings.</li>
 * </ul>
 *
 * <p>Timeout settings can be accessed via:</p>
 * <ul>
 *   <li>{@link #getScrollTimeout()}</li>
 *   <li>{@link #getSearchTimeout()}</li>
 *   <li>{@link #getIndexTimeout()}</li>
 *   <li>{@link #getIndicesTimeout()}</li>
 *   <li>{@link #getBulkTimeout()}</li>
 *   <li>{@link #getClusterTimeout()}</li>
 * </ul>
 *

 * </ul>
 *
 * <p>Fields:
 * <ul>
 * <li>{@link #logger} - Logger instance.
 * <li>{@link #client} - OpenSearch client.
 * <li>{@link #index} - Index name.
 * <li>{@link #settings} - Suggest settings.
 * <li>{@link #supportedFields} - Supported fields for suggestions.
 * <li>{@link #tagFieldNames} - Tag field names.
 * <li>{@link #roleFieldName} - Role field name.
 * <li>{@link #langFieldName} - Language field name.

 *
 * <p>Constants:</p>
 * <ul>
 *   <li>{@code ELEVATE_WORD_SETTINGD_KEY} - The key for elevate word settings.</li>
 *   <li>{@code ELEVATE_WORD_BOOST} - The key for elevate word boost value.</li>
 *   <li>{@code ELEVATE_WORD_READING} - The key for elevate word readings.</li>
 *   <li>{@code ELEVATE_WORD_FIELDS} - The key for elevate word fields.</li>
 *   <li>{@code ELEVATE_WORD_TAGS} - The key for elevate word tags.</li>

 *   <li>{@link #refresh()}: Refreshes the suggestion indices.</li>
 *   <li>{@link #shutdown()}: Shuts down the thread pool.</li>
 *   <li>{@link #createIndexIfNothing()}: Creates a new index if no index exists.</li>
 *   <li>{@link #createNextIndex()}: Creates a new index and replaces the current update alias with the new index.</li>
 *   <li>{@link #switchIndex()}: Switches the search alias to the current update index.</li>

 *
 * <p>Features:</p>
 * <ul>
 *   <li>Pattern-based client mapping</li>
 *   <li>Ordered client registration</li>
 *   <li>Bulk client registration</li>
 *   <li>Automatic client initialization</li>
 *   <li>Resource cleanup management</li>
 * </ul>
 *
 */
public class CrawlerClientFactory implements AutoCloseable {

 *
 * <p>Features:
 * <ul>
 *   <li>Automatic delimiter detection (comma, tab, semicolon, pipe)</li>
 *   <li>Header row detection and extraction</li>
 *   <li>Column name to data value association</li>
 *   <li>Quoted field handling</li>
 *   <li>Column names as metadata</li>
 *   <li>Configurable encoding and row limits</li>
 * </ul>
 */
public class CsvExtractor extends AbstractExtractor {

 * </ul>
 *
 * <p>The client supports URLs in the format: {@code gcs://bucket-name/object-path}
 *
 * <p>Features:
 * <ul>
 *   <li>Automatic initialization of GCS client</li>
 *   <li>Support for HEAD and GET operations</li>
 *   <li>Content length validation</li>
 *   <li>MIME type detection</li>
 *   <li>Handling of large files through temporary file storage</li>
 *   <li>Object metadata retrieval</li>

 * <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>
 * <li>{@link #settingsId}: ID of the settings.</li>

 *
 * <p>The DataIndexHelper supports:</p>
 * <ul>
 *   <li>Concurrent crawling of multiple data configurations</li>
 *   <li>Thread pool management for crawler execution</li>
 *   <li>Session-based crawling with cleanup operations</li>
 *   <li>Old document deletion after successful crawling</li>
 *   <li>Crawling execution monitoring and timing</li>
 * </ul>
 */
public class DataIndexHelper {