public static final String ROLE_FIELD_NAME = "roleFieldName";
        /** Language field name key. */
        public static final String LANG_FIELD_NAME = "langFieldName";
        /** Parallel processing key. */
        public static final String PARALLEL_PROCESSING = "parallel";
        /** Max content length key. */
        public static final String MAX_CONTENT_LENGTH = "maxContentLength";

 * This class provides functionality for sending documents to the search engine,
 * managing document lifecycle operations (create, update, delete), and handling
 * thumbnail processing during indexing.
 *
 * <p>The IndexingHelper manages bulk operations, handles retries on failures,
 * and provides various query-based operations for document management.

import org.opensearch.index.query.functionscore.FunctionScoreQueryBuilder.FilterFunctionBuilder;
import org.opensearch.search.sort.SortBuilder;

/**
 * Context object that holds query-related information and state during search processing.
 * Contains the query string, query builder, sort criteria, and various metadata.
 */
public class QueryContext {

    /** Prefix for queries that search only in URL fields. */

     * comment: Batch size for search log processing.
     * @return The value of found property. (NotNull: if not found, exception but basically no way)
     */
    String getSearchlogProcessBatchSize();

    /**
     * Get the value for the key 'searchlog.process.batch_size' as {@link Integer}. <br>
     * The value is, e.g. 100 <br>
     * comment: Batch size for search log processing.

**DataService**: Access result persistence, iteration

**Implementations**:
- `UrlQueueServiceImpl`, `DataServiceImpl`: In-memory (default)
- `OpenSearchDataService`: OpenSearch backend (persistent)

### Processing Pipeline

```
CrawlerThread → Client → ResponseProcessor → Transformer → Extractor → ExtractData
                                                                            ↓

import java.util.zip.ZipEntry;
import java.util.zip.ZipInputStream;

import org.codelibs.core.lang.ClassUtil;
import org.codelibs.core.zip.ZipInputStreamUtil;

/**
 * Handler for traversing and processing classes.
 *
 * @author koichik
 * @see ClassHandler
 * @see TraversalUtil
 */
public abstract class ClassTraversalUtil {

    /**
     * Do not instantiate.
     */

                files.add(file);
            } catch (Exception e) {
                log.warn("Error creating SmbFile from cache for {}: {}", fileInfo.getName(), e.getMessage());
                // For testing purposes, continue processing other files
                // In a real scenario, you might want to handle this differently
            }
        }

        return files;
    }

    /**

     * @param includeContent whether to include the actual content in the response
     * @return the response data for the request
     * @throws CrawlingAccessException if an error occurs while processing the request
     */
    protected ResponseData processRequest(final String uri, final boolean includeContent) {
        if (!isInit) {
            init();
        }

        // start

 * <p>
 * The {@link ContentWriter} functional interface is used to abstract the process of writing content to a writer.
 * </p>
 *
 * <p>
 * The class uses temporary files for processing large input streams and ensures that these files are deleted after
 * processing.
 * </p>
 *
 */
public class TikaExtractor extends PasswordBasedExtractor {

    private static final Logger logger = LogManager.getLogger(TikaExtractor.class);

     * The current position in the buffer.
     */
    public int index;

    /**
     * The length of data in the buffer.
     */
    public int length;

    /**
     * Buffer for deferred data processing.
     */
    public NdrBuffer deferred;

    /**
     * Constructs an NdrBuffer with the specified byte array and starting position.
     *
     * @param buf the byte array to use as the buffer