* @param request The HTTP request.
     * @param roleSet The set of roles.
     */
    protected void buildByCookieNameMapping(final HttpServletRequest request, final Set<String> roleSet) {
        final Cookie[] cookies = request.getCookies();
        if (cookies != null) {
            for (final Cookie cookie : cookies) {
                addRoleFromCookieMapping(roleSet, cookie);
            }
        }

            final Cookie[] cookies = req.getCookies();
            if (cookies != null) {
                for (final Cookie cookie : cookies) {
                    if (cookieName.equals(cookie.getName())) {
                        try {
                            final String encoded = cookie.getValue();

        // cookie
        if (cookieSpec != null) {
            requestConfigBuilder.setCookieSpec(cookieSpec);
        }

        // cookie store
        httpClientBuilder.setDefaultCookieStore(cookieStore);
        if (cookieStore != null) {
            final Cookie[] cookies = getInitParameter(COOKIES_PROPERTY, new Cookie[0], Cookie[].class);
            for (final Cookie cookie : cookies) {

cookie.search.parameter.http_only=true
# Whether to set Secure attribute to the search parameter cookie. Should be true in production environments using HTTPS.
cookie.search.parameter.secure=
# Max-Age (in seconds) for the search parameter cookie. Use -1 for session-only cookies.
cookie.search.parameter.max_age=60

    /** The key of the configuration. e.g. true */
    String COOKIE_SEARCH_PARAMETER_http_only = "cookie.search.parameter.http_only";

    /** The key of the configuration. e.g.  */
    String COOKIE_SEARCH_PARAMETER_SECURE = "cookie.search.parameter.secure";

    /** The key of the configuration. e.g. 60 */
    String COOKIE_SEARCH_PARAMETER_max_age = "cookie.search.parameter.max_age";

SITEMAP: http://example.com/sitemap3.xml
Sitemap:    # empty sitemap (should be ignored)
Sitemap: not-a-valid-url

# Case 12: Malformed lines that should be completely ignored
This line is completely invalid
:NoKey
NoValue:
:::
   :

# Case 13: Numeric crawl-delay edge cases
User-agent: NumericBot
Crawl-delay: 0
Crawl-delay: 999999999
Crawl-delay: 1.23e10

# Case 14: Tab characters instead of spaces

- **Extraction**: Apache Tika 3.0+, POI 5.3+, PDFBox 3.0+
- **Testing**: JUnit 4, UTFlute, Mockito 5.7.0
- **Storage**: In-memory (default), OpenSearch (optional)

### Protocols

- **HTTP/HTTPS**: Full crawling, cookies, auth, robots.txt
- **File**: Local/network file systems
- **FTP**: With authentication
- **SMB/CIFS**: Windows shares (SMB1/SMB2+)
- **Storage**: MinIO/S3-compatible

### Content Formats

				"application/vnd.marlin.drm.license+xml",
				"application/vnd.marlin.drm.mdcf",
				"application/vnd.mcd",
				"application/vnd.medcalcdata",
				"application/vnd.mediastation.cdkey",
				"application/vnd.meridian-slingshot",
				"application/vnd.mfer",
				"application/vnd.mfmp",
				"application/vnd.micrografx.flo",
				"application/vnd.micrografx.igx",
				"application/vnd.mif",

    <glob pattern="*.mcd"/>
  </mime-type>
  <mime-type type="application/vnd.medcalcdata">
    <glob pattern="*.mc1"/>
  </mime-type>
  <mime-type type="application/vnd.mediastation.cdkey">
    <glob pattern="*.cdkey"/>
  </mime-type>
  <mime-type type="application/vnd.meridian-slingshot"/>
  <mime-type type="application/vnd.mfer">
    <glob pattern="*.mwf"/>
  </mime-type>