* and to parse an input stream into a {@link SitemapSet} object.
 * It uses SAX parser for XML sitemaps and XML sitemap indexes,
 * and handles potential exceptions during parsing.
 * The class also includes inner classes for handling XML sitemap and sitemap index parsing.
 */
public class SitemapsHelper {
    private static final Logger logger = LogManager.getLogger(SitemapsHelper.class);

 * </p>
 * <ul>
 *   <li>Namespace awareness</li>
 *   <li>Coalescing</li>
 *   <li>Entity expansion</li>
 *   <li>Ignoring comments and whitespace</li>
 *   <li>Validation</li>
 *   <li>XInclude awareness</li>
 * </ul>
 *
 * <p>
 * It also allows defining field rules using XPath expressions to extract specific data from the XML document and map it to fields in the ResultData.

 * This class provides methods to access and modify these attributes, allowing for control and monitoring
 * of the crawler's behavior.
 *
 * <p>
 * The context includes information such as the session ID, active thread count, access count, crawler status,
 * URL filter, rule manager, interval controller, robots.txt URL set, sitemaps, number of threads,

 * 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.

import jakarta.annotation.Resource;

/**
 * Factory class for managing and retrieving {@link Extractor} instances.
 * This class provides methods to add, retrieve, and manage extractors based on a key.
 * It also includes a builder for creating extractors.
 *
 * <p>
 * The factory maintains a map of keys to an array of {@link Extractor} objects.
 * When multiple extractors are associated with a single key, they are sorted by weight

    protected int initialBufferSize = 10000;

    /**
     * If true, duplicated terms are replaced.
     */
    protected boolean replaceDuplication = false;

    /**
     * Space characters. Default includes common space characters.
     */
    protected int[] spaceChars = { '\u0020', '\u00a0', '\u3000', '\ufffd' };

    /**
     * Memory size.
     */
    protected int memorySize = 1024 * 1024; //1mb

 *
 * <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.
 *
 * <p>Features:
 * <ul>
 *   <li>Text extraction from PDF pages</li>
 *   <li>Embedded document extraction</li>
 *   <li>Annotation extraction (file attachments)</li>

            final T bean = BeanUtil.copyMapToNewBean(source, clazz, option -> {
                option.converter(new EsTimestampConverter(), timestampFields).excludeWhitespace();
                option.exclude(OpenSearchAccessResult.ACCESS_RESULT_DATA);
            });
            @SuppressWarnings("unchecked")
            final Map<String, Object> data = (Map<String, Object>) source.get(OpenSearchAccessResult.ACCESS_RESULT_DATA);

                                        crawlerContext.getUrlFilter().addInclude(urlValue);
                                        if (logger.isInfoEnabled()) {
                                            logger.info("Included URL: {}", urlValue);
                                        }
                                    }
                                }
                            }
                        }
                    }