*/
package org.codelibs.fess.crawler.exception;

/**
 * RobotsTxtException is an exception class that represents an error related to robots.txt processing during web crawling.
 * It extends CrawlerSystemException and provides constructors to create instances with a message and/or a cause.
 *
 */
public class RobotsTxtException extends CrawlerSystemException {

 */
package org.codelibs.fess.crawler.exception;

/**
 * MimeTypeException is a custom exception class that extends CrawlerSystemException.
 * It is used to indicate exceptions related to MIME type handling during the crawling process.
 * This exception can be thrown with a message, a cause, or both.
 */
public class MimeTypeException extends CrawlerSystemException {

    private static final long serialVersionUID = 1L;

    /**

│   ├── exbhv/                 # Extended behaviors (repositories)
│   └── exentity/              # Extended entities (domain models)
├── helper/                    # Cross-cutting utilities
├── crawler/                   # Crawling engine
├── sso/                       # SSO implementations
└── ds/                        # Data store connectors

src/main/resources/
├── fess_config.properties     # Main config

 */
package org.codelibs.fess.crawler.exception;

import java.util.Set;

import org.codelibs.fess.crawler.entity.RequestData;

/**
 * {@link ChildUrlsException} is thrown when child URLs are found during crawling.
 * It extends {@link CrawlerSystemException} and holds a set of {@link RequestData}
 * representing the child URLs that caused the exception.
 *
 */
public class ChildUrlsException extends CrawlerSystemException {

 * This form extends CreateForm to include fields necessary for updating existing scheduler entries,
 * including tracking information for optimistic locking.
 * Schedulers define automated jobs such as crawling and system maintenance tasks.
 *
 */
public class EditForm extends CreateForm {

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

    /**

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 {

crawler.document.fullstop.chars=u002eu06d4u2e3cu3002
# Encoding for crawling data.
crawler.crawling.data.encoding=UTF-8
# Supported web protocols for crawling.
crawler.web.protocols=http,https
# Supported file protocols for crawling.
crawler.file.protocols=file,smb,smb1,ftp,storage,s3,gcs
# Pattern for environment variable keys in crawling data.
crawler.data.env.param.key.pattern=^FESS_ENV_.*

 * This can help Google News index your articles and display them in Google News search results.
 * </p>
 *
 * @see <a href="https://developers.google.com/search/docs/crawling-indexing/sitemaps/news-sitemap">Google News Sitemaps</a>
 */
public class SitemapNews implements Serializable {

    private static final long serialVersionUID = 1L;

    /**
     * The name of the news publication.

 * including tracking information for optimistic locking and audit trails.
 * File authentication configurations define access control for file system crawling operations.
 *
 */
public class EditForm extends CreateForm {

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

    /**

import org.lastaflute.web.validation.Required;
import org.lastaflute.web.validation.theme.conversion.ValidateTypeFailure;

import jakarta.validation.constraints.Size;

/**
 * Form class for editing web crawling configurations in the admin interface.
 * This form extends CreateForm to include fields necessary for updating existing web config entries,
 * including tracking information for optimistic locking and audit trails.