*/
package org.codelibs.fess.exception;

import org.codelibs.fess.crawler.exception.CrawlingAccessException;

/**
 * Exception thrown when an error occurs during data store crawling operations.
 * This exception provides information about the URL where the error occurred
 * and whether the crawling process should be aborted.
 */
public class DataStoreCrawlingException extends CrawlingAccessException {

    /** The key of the message: Start Crawling */
    public static final String LABELS_wizard_start_crawling_title = "{labels.wizard_start_crawling_title}";

    /** The key of the message: Crawler */
    public static final String LABELS_wizard_start_crawler_title = "{labels.wizard_start_crawler_title}";

    /** The key of the message: You can start crawling now by clicking "Start Crawling" button. */

 * including crawling behavior, authentication, logging, and various system parameters.
 *
 */
public class EditForm {

    /**
     * Creates a new EditForm instance.
     */
    public EditForm() {
        // Default constructor
    }

    /**
     * Enable or disable incremental crawling.
     * When enabled, only new or modified documents are crawled.
     */
    @Size(max = 10)

# 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_.*
# Whether to ignore robots.txt during crawling.
crawler.ignore.robots.txt=false

    public String id;

    /**
     * The URL that failed during crawling.
     * This is a required field containing the actual URL that encountered an error.
     */
    @Required
    public String url;

    /**
     * The name of the crawler thread that encountered the failure.
     * This is a required field used for identifying which crawler process failed.
     */
    @Required
    public String threadName;

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 {
    private static final Logger logger = LogManager.getLogger(ProtocolHelper.class);

    /** The key of the configuration. e.g. u002eu06d4u2e3cu3002 */
    String CRAWLER_DOCUMENT_FULLSTOP_CHARS = "crawler.document.fullstop.chars";

    /** The key of the configuration. e.g. UTF-8 */
    String CRAWLER_CRAWLING_DATA_ENCODING = "crawler.crawling.data.encoding";

    /** The key of the configuration. e.g. http,https */
    String CRAWLER_WEB_PROTOCOLS = "crawler.web.protocols";

/**
 * Integration tests for the Favorites API (/api/v1/favorites and /api/v1/documents/{docId}/favorite)
 * This test requires crawled documents and favorites feature to be properly configured
 */
@Tag("it")
@Disabled("Requires favorites feature to be enabled and crawled documents")
public class FavoritesApiTests extends CrawlTestBase {
    private static final Logger logger = LogManager.getLogger(FavoritesApiTests.class);

     * Creates a new failure URL entry or increments the error count for an existing URL.
     *
     * @param crawlingConfig the crawling configuration associated with the failure
     * @param errorName the name/type of the error that occurred
     * @param url the URL that failed to be crawled
     * @param e the exception that caused the failure

     * 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.
     */