testTransformer.setName("  leadingSpaces");
        assertEquals("  leadingSpaces", testTransformer.getName());

        // Trailing whitespace
        testTransformer.setName("trailingSpaces  ");
        assertEquals("trailingSpaces  ", testTransformer.getName());

        // Both leading and trailing
        testTransformer.setName("  bothSpaces  ");
        assertEquals("  bothSpaces  ", testTransformer.getName());

        extensionMap.put("odp", "pdf");
        extensionMap.put("otp", "pdf");
        extensionMap.put("sxi", "pdf");
        extensionMap.put("ppt", "pdf");
        extensionMap.put("pptx", "pdf");
        // Drawing Formats
        extensionMap.put("odg", "svg");
        extensionMap.put("otg", "svg");

        extractorMap.put("pdf", new PdfExtractor());
        extractorMap.put("svg", new XmlExtractor());
    }

    /**

 * exceptions during retries.</p>
 *
 * <p>Key features:</p>
 * <ul>
 *   <li>Configurable maximum retry attempts</li>
 *   <li>Adjustable interval between retries</li>
 *   <li>Exception tracking and aggregation</li>
 *   <li>Request lifecycle monitoring through listener</li>
 * </ul>
 *
 * <p>By default, it will:</p>
 * <ul>
 *   <li>Retry up to 5 times</li>
 *   <li>Wait 500ms between retries</li>

     * Creates a new SitemapUrl instance.
     */
    public SitemapUrl() {
        super();
    }

    /**
     * URL of the page. This URL must begin with the protocol (such as http) and
     * end with a trailing slash, if your web server requires it. This value
     * must be less than 2,048 characters.
     */
    private String loc;

    /**
     * The date of last modification of the file. This date should be in W3C

    /**
     * Lock object for synchronizing access to active thread count.
     */
    protected Object activeThreadCountLock = new Object();

    /**
     * Atomic counter for tracking the number of accesses made.
     */
    protected AtomicLong accessCount = new AtomicLong(0);

    /**
     * Current status of the crawler.
     */

 * and processing them according to specific rules. The main functionality is encapsulated
 * within the nested {@link TextNormalizeContext} class.
 *
 * <p>The text normalization process includes:
 * <ul>
 *   <li>Treating ISO control characters and specified space characters as spaces.</li>
 *   <li>Appending alphanumeric characters (0-9, A-Z, a-z) to the buffer.</li>
 *   <li>Appending symbol characters (!-/, :-@, [-`, {-~) to the buffer.</li>

    <glob pattern="*.vss"/>
    <glob pattern="*.vsw"/>
    <sub-class-of type="application/x-tika-msoffice"/>
  </mime-type>

  <mime-type type="application/vnd.ms-visio.drawing">
    <_comment>Office Open XML Visio Drawing (macro-free)</_comment>
    <glob pattern="*.vsdx"/>
    <sub-class-of type="application/x-tika-visio-ooxml"/>
  </mime-type>
  <mime-type type="application/vnd.ms-visio.template">

                extractFile(ent.getKey(), embeddedFile, writer);
            }
        }
    }

    /**
     * Gets the embedded file from a file specification, trying different platform-specific variants.
     * @param fileSpec the file specification
     * @return the embedded file, or null if not found
     */

        if (matcher.find()) {
            return matcher.group(1);
        }
        return null;
    }

    /**
     * Gets a duplicate URL by adding or removing a trailing slash.
     *
     * @param requestData the request data to create a duplicate for
     * @return the request data with the duplicate URL
     */