ThreadUtil.sleep(delay);
        }
    }

    /**
     * Calculates the delay in milliseconds based on current time and configured rules.
     * The method checks each rule to see if it applies to the current time and day.
     *
     * @return the delay in milliseconds, or 0 if no rules apply
     */
    protected long getDelay() {
        if (ruleList.isEmpty()) {
            return 0;
        }

            if (values.length > 1) {
                final String[] roles = values[1].split(roleSeparator);
                for (final String role : roles) {
                    if (StringUtil.isNotEmpty(role)) {
                        roleSet.add(role);
                    }
                }
            }
        } else {
            final String[] roles = rolesStr.split(roleSeparator);
            for (final String role : roles) {

            break;
        default:
            break;
        }
        return OptionalEntity.empty();
    }

    /**
     * Get a boost document rule from a form.
     * @param form The create form.
     * @return An optional entity of a boost document rule.
     */
    public static OptionalEntity<BoostDocumentRule> getBoostDocumentRule(final CreateForm form) {

 * hostnames or URLs to be treated as equivalent for crawling and indexing purposes.
 * It maintains a list of DuplicateHost rules and applies them to URLs.
 *
 */
public class DuplicateHostHelper {
    private static final Logger logger = LogManager.getLogger(DuplicateHostHelper.class);

    /** List of duplicate host rules for URL conversion */

- **Index Size**: Storage requirements for search indices
- **Crawl Sources**: URLs, file shares, databases being indexed
- **Custom Configurations**: URL patterns, security rules, metadata fields
- **Search Features**: Facets, suggestions, security filtering, ranking rules
- **Integration Points**: Applications consuming search APIs
- **User Permissions**: Access control and label configurations

### 2. Infrastructure Requirements

    /**
     * Checks if access to a given path is allowed for a specific user agent according to robots.txt rules.
     *
     * @param path The path to check for access permission
     * @param userAgent The user agent string to check against robots.txt directives
     * @return true if access is allowed, false if access is disallowed by robots.txt rules.
     *         Returns true if no matching directive is found for the user agent.
     */

        }

        return node;
    }

    /**
     * Prunes unwanted tags from the node based on configuration.
     *
     * @param node the node to prune
     * @param crawlingConfig the crawling configuration containing pruning rules
     * @return the pruned node
     */
    protected Node pruneNode(final Node node, final CrawlingConfig crawlingConfig) {

     */
    private String version;

    /**
     * The class loading strategy: 'self-first' (the default),
     * 'parent-first' (loads classes from the parent, then from the
     * extension) or 'plugin' (follows the rules from extensions
     * defined as plugins).
     */
    private String classLoadingStrategy = "self-first";

    // -----------/
    // - Methods -/
    // -----------/

    /**

    }

    /**
     * Delays the crawler while waiting for new URLs to be available.
     * This method calibrates CPU load, checks crawler status, applies
     * interval control rules, and then calls the parent implementation.
     * All operations are wrapped in exception handling to ensure robustness
     * in test and production environments.
     */
    @Override

        run: |
          echo 'KERNEL=="kvm", GROUP="kvm", MODE="0666", OPTIONS+="static_node=kvm"' | sudo tee /etc/udev/rules.d/99-kvm4all.rules
          sudo udevadm control --reload-rules
          sudo udevadm trigger --name-match=kvm

      - name: Setup Gradle
        uses: gradle/actions/setup-gradle@v5

      - name: Gradle cache