* @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
     */

/**
 * {@link ExtractorBuilder} is a builder class for creating and configuring an {@link ExtractData} object.
 * It encapsulates the process of extracting data from an input stream using a specified or detected extractor.
 * The builder allows setting parameters such as MIME type, filename, extractor name, maximum content length,
 * and cache file size to optimize the extraction process.
 *
 * <p>

    protected MimeTypes mimeTypes;

    /** Whether to use the filename for MIME type detection. */
    protected boolean useFilename = false;

    /** Whether to use the filename for MIME type detection when the stream is detected as octet-stream. */
    protected boolean useFilenameOnOctetStream = true;

    /**
     * Creates a new MimeTypeHelperImpl instance.
     * Initializes the MimeTypes instance using the default configuration.

    }

    /**
     * Test protected field access
     */
    public void test_protectedFieldAccess() {
        // Test direct field access (protected fields)
        TestAbstractRule rule = new TestAbstractRule();

        // Direct field assignment
        rule.ruleId = "directFieldAccess";
        TestResponseProcessor processor = new TestResponseProcessor();

        return new ExtractData(extractString(content));
    }

    /**
     * Detects the encoding of the input stream.
     * @param bis The buffered input stream.
     * @return The detected encoding.
     */
    protected String getEncoding(final BufferedInputStream bis) {
        final byte[] b = new byte[preloadSizeForCharset];
        try {
            bis.mark(preloadSizeForCharset);

                }

                return extractData;
            } catch (final TikaException e) {
                if (e.getMessage().indexOf("bomb") >= 0) {
                    throw new ExtractException("Zip bomb detected.", e);
                }
                final Throwable cause = e.getCause();
                if (cause instanceof SAXException) {

        SuggestSettings settings = builder.build(client, id);

        assertNotNull(settings);
        // Verify that the settings object was created with the correct parameters
        // Note: We can't directly verify internal state of SuggestSettings without getters,
        // but we can verify it was created successfully
    }

    @Test
    public void testBuildWithCustomSettings() {

 * It also provides methods to add custom features and properties to the {@link DOMParser}.
 * </p>
 * <p>
 * The encoding of the HTML document is automatically detected using a regular expression that matches the charset attribute in the meta tag.
 * </p>
 *
 */
public class HtmlXpathExtractor extends AbstractXmlExtractor {
    /**

    }

    /**
     * Test protected field access
     */
    public void test_protectedFieldAccess() {
        TestTransformer transformer = new TestTransformer();

        // Direct field access (simulating subclass behavior)
        transformer.name = "directFieldAccess";
        assertEquals("directFieldAccess", transformer.getName());

        // Setter should update the field

        }
        return true;
    }

    /**
     * Loads and detects the character set from the input stream.
     *
     * @param inputStream the input stream to read from
     * @return the detected character set name, or null if not found
     * @throws CrawlingAccessException if an error occurs while reading the content
     */
    protected String loadCharset(final InputStream inputStream) {