}
        matcher.appendTail(sb);
        return sb.toString().replaceAll("\\s+", " ").trim();
    }

    /**
     * Returns the current encoding setting.
     * @return The current encoding.
     */
    public String getEncoding() {
        return encoding;
    }

    /**
     * Sets the encoding for content extraction.

            }
        }

    }

    /**
     * Stores child URLs to the crawling queue.
     * @param childUrlList The set of child URLs to store.
     * @param url The parent URL.
     * @param depth The depth of the child URLs.
     */
    protected void storeChildUrls(final Set<RequestData> childUrlList, final String url, final int depth) {

     *
     * @return a hash code value for this object
     */
    @Override
    public int hashCode() {
        return inputStream.hashCode();
    }

    /**
     * Marks the current position in this input stream.
     *
     * @param readlimit the maximum limit of bytes that can be read before the mark position becomes invalid
     */
    @Override
    public synchronized void mark(final int readlimit) {

    protected String sessionId;

    /** The rule ID that matched the accessed resource. */
    protected String ruleId;

    /** The URL of the accessed resource. */
    protected String url;

    /** The parent URL of the accessed resource. */
    protected String parentUrl;

    /** The status of the access result. */
    protected Integer status = Constants.OK_STATUS;

    /** The HTTP status code of the access result. */

     */
    public static final String RULE_ID = "ruleId";

    /**
     * Field name for URL.
     */
    public static final String URL = "url";

    /**
     * Field name for parent URL.
     */
    public static final String PARENT_URL = "parentUrl";

    /**
     * Field name for status.
     */
    public static final String STATUS = "status";

    /**

        }
    }

    /**
     * Generates URL queues from a previous session's access results.
     * @param previousSessionId The previous session ID.
     * @param sessionId The current session ID.
     */
    @Override
    public void generateUrlQueues(final String previousSessionId, final String sessionId) {
        final Queue<UrlQueueImpl<Long>> urlQueueList = dataHelper.getUrlQueueList(sessionId);

 * and cache file size to optimize the extraction process.
 *
 * <p>
 * The main purpose of this class is to simplify the extraction process by providing a fluent interface
 * for configuring the extraction parameters and handling the underlying complexities of content processing,
 * such as MIME type detection, extractor selection, and content length validation.
 * </p>
 *
 * <p>

- **Index Management**: Automatic index creation, switching, and maintenance
- **Customizable Scoring**: User boost, document frequency, and query frequency weighting

## Technology Stack

- **Java**: 21+ (configured via parent POM)
- **OpenSearch**: Latest (provided scope)
- **Apache Lucene**: Query parsing and text analysis
- **ICU4J**: Unicode text processing and normalization
- **JUnit 4**: Testing framework

        }

        return parser;
    }

    /**
     * Gets a thread-local XPathAPI instance for thread-safe XPath evaluation.
     *
     * @return the XPathAPI instance for the current thread
     */
    protected XPathAPI getXPathAPI() {
        XPathAPI cachedXPathAPI = xpathAPI.get();
        if (cachedXPathAPI == null) {
            cachedXPathAPI = new XPathAPI();

    }

    /**
     * Stores child URLs found in the response data.
     *
     * @param crawlerContext the crawler context
     * @param childUrlList the set of child URLs
     * @param url the parent URL
     * @param depth the depth of the child URLs
     * @param encoding the encoding of the child URLs
     */