return ROBOT_CONTEXT_THREAD_LOCAL.get();
    }

    /**
     * Sets the current {@link CrawlerContext} for the current thread.
     * If the provided {@code crawlerContext} is {@code null}, the context is removed from the thread-local storage.
     * Otherwise, the provided {@code crawlerContext} is set in the thread-local storage.
     *

 * registering the extractor with the {@link ExtractorFactory}.
 * </p>
 *
 * <p>
 * Subclasses should implement the actual extraction logic in their own
 * methods, leveraging the helper methods provided by this abstract class.
 * </p>
 *
 */
public abstract class AbstractExtractor implements Extractor {

    /** The crawler container. */
    @Resource
    protected CrawlerContainer crawlerContainer;

			<artifactId>opensearch</artifactId>
			<version>${opensearch.version}</version>
			<scope>provided</scope>
		</dependency>
		<dependency>
			<groupId>org.apache.lucene</groupId>
			<artifactId>lucene-queryparser</artifactId>
			<version>${lucene.version}</version>
			<scope>provided</scope>
		</dependency>
		<dependency>
			<groupId>org.apache.logging.log4j</groupId>

      "Work" shall mean the work of authorship, whether in Source or
      Object form, made available under the License, as indicated by a
      copyright notice that is included in or attached to the work
      (an example is provided in the Appendix below).

      "Derivative Works" shall mean any work, whether in Source or Object
      form, that is based on (or derived from) the Work and for which the

 *
 * <p>The extractor supports two types of password management:
 * <ul>
 *   <li>Static passwords configured via {@link #addPassword(String, String)}</li>
 *   <li>Dynamic passwords provided through extraction parameters</li>
 * </ul>
 *
 * <p>Passwords are matched against URLs or resource names using regular expression patterns.

    private AuthScope authScope;

    private Credentials credentials;

    private AuthScheme authScheme;

    /**
     * Initializes the AuthenticationImpl with the provided AuthScope and Credentials,
     * and sets the AuthScheme to null.
     * @param authScope The authentication scope.
     * @param credentials The credentials.
     */

      "Work" shall mean the work of authorship, whether in Source or
      Object form, made available under the License, as indicated by a
      copyright notice that is included in or attached to the work
      (an example is provided in the Appendix below).

      "Derivative Works" shall mean any work, whether in Source or Object
      form, that is based on (or derived from) the Work and for which the

                    || c >= 0x10000 && c <= 0x10FFFF) {
                buf.append(c);
            }
        }
        return buf.toString().trim();
    }

    /**
     * Parses the XML content from the provided {@link AccessResultData} and returns a map of the data.
     *
     * @param accessResultData the data containing the XML content to be parsed
     * @return a map containing the parsed data from the XML content

     * @return the detected content type
     */
    String getContentType(InputStream is, String filename);

    /**
     * Determines the content type of the given input stream using the provided parameters.
     * @param is the input stream to analyze
     * @param params the parameters containing additional information like filename
     * @return the detected content type
     */

import org.apache.logging.log4j.Logger;
import org.codelibs.core.lang.StringUtil;

/**
 * Utility class for text normalization and processing.
 *
 * This class provides methods to normalize text by reading characters from a provided Reader
 * and processing them according to specific rules. The main functionality is encapsulated
 * within the nested {@link TextNormalizeContext} class.
 *
 * <p>The text normalization process includes:
 * <ul>