import org.codelibs.fess.util.ComponentUtil;

/**
 * FessIntervalController extends DefaultIntervalController to provide
 * Fess-specific interval control functionality for web crawling operations.
 * This controller manages delays and timing for various crawling states
 * including processing delays, queue waiting times, and new URL discovery.
 */
public class FessIntervalController extends DefaultIntervalController {

import org.dbflute.optional.OptionalEntity;

import jakarta.annotation.Resource;

/**
 * Service class for managing request headers used in web crawling configurations.
 * This service provides CRUD operations for request headers that are applied
 * during web crawling to configure HTTP request behavior.
 *
 */
public class RequestHeaderService {

    /**
     * Behavior for request header database operations.
     */

You can register crawling targets in the Admin UI on the (Web, File, Data Store) crawler configuration pages, and then start the Crawler manually on the [Scheduler page](https://fess.codelibs.org/15.5/admin/scheduler-guide.html).

## Migration from another search provider

Please see [MIGRATION.md](MIGRATION.md).

## Data Store

import org.codelibs.fess.mylasta.direction.FessConfig;
import org.codelibs.fess.util.ComponentUtil;

import jakarta.annotation.PostConstruct;

/**
 * Helper class for managing and validating URL protocols in Fess crawling system.
 * This class handles the initialization and validation of web and file protocols
 * used by the crawler to determine which URLs can be crawled.
 */
public class ProtocolHelper {

import jakarta.validation.constraints.Size;

/**
 * Form class for creating new duplicate host configuration entries.
 * This form handles the creation of duplicate host mappings that redirect
 * crawling from duplicate hostnames to the regular canonical hostname.
 */
public class CreateForm {

    /**
     * Creates a new CreateForm instance.
     */
    public CreateForm() {
    }

 * including tracking information for optimistic locking and audit trails.
 * Duplicate hosts are used to define which domains should be treated as the same site for crawling purposes.
 *
 */
public class EditForm extends CreateForm {

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

    /**

import org.dbflute.optional.OptionalEntity;

import jakarta.annotation.Resource;

/**
 * Service class for managing web crawling configurations.
 * Provides CRUD operations for web configuration settings including
 * listing, retrieving, storing, and deleting web crawling configurations.
 */
public class WebConfigService extends FessAppService {

    /**
     * Default constructor.
     */

    /**
     * The script data or code for the scheduled job.
     */
    @CustomSize(maxKey = "form.admin.max.input.size")
    public String scriptData;

    /**
     * Whether this job is related to crawling.
     */
    public String crawler;

    /**
     * Whether job logging is enabled.
     */
    public String jobLogging;

    /**
     * Whether the scheduled job is available/enabled.
     */

 * This processor extends DefaultResponseProcessor to provide additional
 * processing capabilities through the ingest framework, allowing for
 * custom data transformation and enrichment during the crawling process.
 *
 * <p>It supports pluggable ingesters that can modify the result data
 * before it is stored in the search index.</p>
 */
public class FessResponseProcessor extends DefaultResponseProcessor {
    /**

import jakarta.annotation.Resource;

/**
 * API action for admin file configuration management.
 * Provides RESTful API endpoints for managing file crawling configuration settings in the Fess search engine.
 * File configurations define settings for crawling file systems, FTP servers, and other file-based data sources.
 *
 */
public class ApiAdminFileconfigAction extends FessApiAdminAction {