throw new CrawlerSystemException("GET method is not supported.");
    }

    /**
     * Performs a HEAD request.
     * @param url The URL to request.
     * @return The ResponseData.
     */
    protected ResponseData doHead(final String url) {
        throw new CrawlerSystemException("HEAD method is not supported.");
    }

    /**
     * Performs a POST request.

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.exception;

/**
 * UnsupportedExtractException is thrown when the content extraction is not supported.
 * It extends ExtractException and indicates that the requested extraction operation cannot be performed.
 *
 */
public class UnsupportedExtractException extends ExtractException {

/**
 * Represents a request data for crawling.
 * This class encapsulates the HTTP method, URL, and weight associated with a crawling request.
 */
public class RequestData {
    /**
     * HTTP methods supported for crawling requests.
     */
    public enum Method {
        /** HTTP GET method. */
        GET,
        /** HTTP POST method. */
        POST,
        /** HTTP HEAD method. */
        HEAD;
    }

crawler.urlFilter.addInclude(".*\\.pdf$");

// Exclude patterns  
crawler.urlFilter.addExclude(".*\\.js$");
crawler.urlFilter.addExclude(".*login.*");
```

## Supported Protocols and Formats

### Protocols
- **HTTP/HTTPS**: Full web crawling support with cookies, authentication, redirects
- **File System**: Local and network file system access
- **FTP**: FTP server crawling with authentication

        }
    }

    /**
     * Checks if the specified charset is supported.
     *
     * @param charsetName the charset name to check
     * @return true if the charset is supported, false otherwise
     */
    protected boolean isSupportedCharset(final String charsetName) {
        if (charsetName == null) {
            return false;

     * @return The result data body.
     */
    protected String getResultDataBody(final String name, final String value) {
        // TODO: Support other XML footer types
        // TODO: Support other field types and trimming options
        return "<field name=\"" + XmlUtil.escapeXml(name) + "\">" + trimSpace(XmlUtil.escapeXml(value != null ? value : "")) + "</field>\n";
    }

    /**

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,

     */
    @Override
    public synchronized void mark(final int readlimit) {
        inputStream.mark(readlimit);
    }

    /**
     * Tests if this input stream supports the mark and reset methods.
     *
     * @return true if this stream instance supports the mark and reset methods; false otherwise
     */
    @Override
    public boolean markSupported() {
        return inputStream.markSupported();
    }

    /**

 * extractor that iterates through the available extractors until one successfully
 * extracts the data.
 * </p>
 *
 * <p>
 * The class uses a {@link CrawlerContainer} for managing crawler components and
 * supports dependency injection via the {@link Resource} annotation.
 * </p>
 */
public class ExtractorFactory {

    /** Logger instance for this class */

 *   <li>readTimeout - Read timeout in milliseconds (default: 10000)</li>
 * </ul>
 *
 * <p>The client supports URLs in the format: {@code storage://bucket-name/object-path}
 *
 * <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>