@Override
            public String getIndexFieldHost() {
                return "host";
            }

            @Override
            public String getIndexFieldSite() {
                return "site";
            }

            @Override
            public String getIndexFieldLastModified() {
                return "last_modified";
            }

            @Override

     * Get the value for the key 'crawler.document.max.site.length'. <br>
     * The value is, e.g. 100 <br>
     * comment: Maximum length of site name in documents.
     * @return The value of found property. (NotNull: if not found, exception but basically no way)
     */
    String getCrawlerDocumentMaxSiteLength();

    /**
     * Get the value for the key 'crawler.document.max.site.length' as {@link Integer}. <br>

						>
						</a>
					</div>
					</c:if>
					<div class="description">${doc.content_description}</div>
				</div>
				<div class="site text-truncate">
					<c:if test="${clipboardCopyIcon}"><i class="far fa-copy url-copy d-print-none" data-clipboard-text="${doc.url_link}" aria-hidden="true"></i></c:if>
					<cite>${f:h(doc.site_path)}</cite>
				</div>

                    return "digest";
                case FessConfig.INDEX_FIELD_HOST:
                    return "host";
                case FessConfig.INDEX_FIELD_SITE:
                    return "site";
                case FessConfig.INDEX_FIELD_content_length:
                    return "content_length";
                case FessConfig.INDEX_FIELD_FILETYPE:
                    return "filetype";

     */
    protected ConcurrentHashMap<String, Pair<String, Pattern>> clientRuleCache = new ConcurrentHashMap<>();

    /**
     * Determines whether the content at the given URL has been updated since the last crawl.
     * This method implements incremental crawling by comparing timestamps and checking document
     * expiration. It also handles special cases for different URL schemes (SMB, file, FTP).
     *

        assertTrue(result.contains("Session Id:"));
        assertNotNull(pythonJob.sessionId);
        assertTrue(pythonJob.sessionId.length() >= 10);

        // The test doesn't actually call the real process since ServletContext.getRealPath returns null in test
        // and causes an exception which is caught and added to result
        assertTrue(result.contains("Session Id:"));
    }

    // Test execute with custom session ID

 *
 * <p>Duplicate host configurations allow administrators to define hostname patterns
 * that should be treated as equivalent during crawling. This helps avoid indexing
 * duplicate content from the same logical site that may be accessible via different
 * hostnames (e.g., www.example.com and example.com).</p>
 */
public class DuplicateHostService extends FessAppService {

    /**
     * DBFlute behavior for duplicate host operations.

 * This class contains various helper methods for formatting, parsing, and manipulating data
 * in Fess web templates, including date formatting, localization, file operations, and
 * query parameter handling.
 *
 * @since 1.0
 */
public class FessFunctions {
    /** Logger instance for this class */
    private static final Logger logger = LogManager.getLogger(FessFunctions.class);

    /** Prefix for geographic query parameters */

            // Check that sessionId was generated
            assertNotNull(options.sessionId);
            assertTrue(options.sessionId.matches("\\d{14}"));
        } catch (Exception e) {
            // Expected since we're not setting up the full container
        }
    }

    @Test
    public void test_process_withCustomSessionId() throws Exception {
        // Test that custom sessionId is sanitized

        assertEquals("21T", crawlingConfigHelper.getDefaultConfig(ConfigType.DATA).get().getId());
    }

    @Test
    public void test_getId() {
        // Test getId method through reflection since it's protected
        try {
            java.lang.reflect.Method getIdMethod = CrawlingConfigHelper.class.getDeclaredMethod("getId", String.class);
            getIdMethod.setAccessible(true);