/**
     * PDF config file path.
     */
    public static final String TIKA_PDF_CONFIG = "tika.pdf.config";

    /**
     * A parameter key to normalize a text.
     */
    public static final String NORMALIZE_TEXT = "normalize_text";

    private static final String FILE_PASSWORD = "fess.file.password";

    /**
     * Output encoding.
     */

        // Default constructor
    }

    /**
     * Normalizes an encoding string to its preferred form.
     *
     * @param enc the encoding string to normalize
     * @return the normalized encoding or the default encoding if the input is blank
     */
    public String normalize(final String enc) {
        if (StringUtil.isBlank(enc)) {
            return defaultEncoding;
        }

         * This method ensures the URL is in a consistent format for FTP operations.
         *
         * @param s The URL string to normalize
         * @return The normalized URL string
         */
        protected String normalize(final String s) {
            if (s == null) {
                return null;
            }
            String url = s.replaceAll("/+", "/").replace("ftp:/", "ftp://");

 * It uses the Apache Tika library to detect the MIME type.
 *
 * <p>
 * This class provides methods to:
 * </p>
 * <ul>
 *   <li>Detect the MIME type based on the input stream and filename.</li>
 *   <li>Normalize the filename to handle special characters.</li>
 *   <li>Configure whether to use the filename for MIME type detection.</li>
 *   <li>Configure whether to use the filename for MIME type detection when the stream is octet-stream.</li>

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.
 *

        assertEquals("2012-05-18T22:45:00Z", extractData.getValues("dcterms:modified")[0]);
        assertEquals("3", extractData.getValues("meta:character-count")[0]);
        assertEquals("Normal", extractData.getValues("extended-properties:Template")[0]);
        assertEquals("たいとる", extractData.getValues("dc:title")[0]);
        assertEquals("3000000000", extractData.getValues("extended-properties:TotalTime")[0]);

     *
     * @param encoding the encoding name to normalize
     * @return the normalized encoding name
     */
    protected String normalizeEncoding(final String encoding) {
        try {
            final EncodingHelper encodingHelper = crawlerContainer.getComponent("encodingHelper");
            return encodingHelper.normalize(encoding);
        } catch (final Exception e) {
            // NOP
        }

        TestTransformer transformer = new TestTransformer();
        assertNotNull(transformer);
        assertNull(transformer.getName());
    }

    /**
     * Test getName and setName with normal values
     */
    public void test_name_getterSetter() {
        // Initial state
        assertNull(testTransformer.getName());

        // Set name
        testTransformer.setName("testTransformer");

        ContentTransformer transformer = new ContentTransformer("workflowTransformer");
        transformer.addTransformationRule("<[^>]+>", ""); // Remove HTML tags
        transformer.addTransformationRule("\\s+", " "); // Normalize whitespace

        // Simulate crawling response
        ResponseData responseData = new ResponseData();
        responseData.setUrl("http://example.com/page.html");

        try {
            URI uri = new URI(url);
            if (StringUtil.isNotEmpty(location)) {
                uri = uri.resolve(location.replace(" ", "%20"));
            }
            return uri.normalize().toASCIIString();
        } catch (URISyntaxException e) {
            throw new CrawlingAccessException(e);
        }
    }

    /**
     * Sets the connection timeout in milliseconds.
     *