* The rule checks if the URL matches the defined regex pattern and then validates the content as a sitemap.
 * If any exception occurs during the sitemap validation, it logs the error and returns false.
 *
 */
public class SitemapsRule extends RegexRule {
    /**
     * Serial version UID for serialization.
     */
    private static final long serialVersionUID = 1L;

- **Extractors**: Content extraction from various formats
- **Transformers**: Data transformation and enrichment
- **Filters**: URL filtering with regex patterns
- **Rules**: Content processing rules and validation

## Building and Testing

### Build Commands

```bash
# Build all modules
mvn clean install

# Build without tests
mvn clean install -DskipTests

# Build specific module

 *
 * <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>
 *

 * 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>
 * Example usage:
 * </p>
 *
 * <pre>
 * {@code
 * try (InputStream in = new FileInputStream("example.pdf")) {

    }

    /**
     * Returns the validating.
     *
     * @return the validating
     */
    public boolean isValidating() {
        return validating;
    }

    /**
     * Sets the validating.
     *
     * @param validating the validating to set
     */
    public void setValidating(final boolean validating) {
        this.validating = validating;
    }

    /**

            logger.warn("Could not get urls: (" + xpath + ", " + attr + ")", e);
        }
        return urlList;
    }

    /**
     * Adds a child URL to the URL list after processing and validation.
     *
     * @param urlList the list to add the URL to
     * @param url the base URL for resolving relative URLs
     * @param attrValue the attribute value containing the URL

 *   <li>COOKIES_PROPERTY: Cookie settings.</li>
 *   <li>AUTH_SCHEME_PROVIDERS_PROPERTY: Authentication scheme providers.</li>
 *   <li>IGNORE_SSL_CERTIFICATE_PROPERTY: Ignore SSL certificate validation.</li>
 *   <li>DEFAULT_MAX_CONNECTION_PER_ROUTE_PROPERTY: Default maximum connections per route.</li>
 *   <li>MAX_TOTAL_CONNECTION_PROPERTY: Maximum total connections.</li>

import org.xml.sax.Attributes;
import org.xml.sax.SAXNotRecognizedException;
import org.xml.sax.SAXNotSupportedException;
import org.xml.sax.helpers.DefaultHandler;

/**
 * Helper class for parsing and validating sitemaps.
 * It supports XML sitemaps, XML sitemap indexes, and text sitemaps,
 * and can handle GZIP compressed sitemaps.
 * The class provides methods to check if an input stream is a valid sitemap,