<?xml version="1.0" encoding="UTF-8"?>
<metadata>
  <groupId>org.codelibs.fess</groupId>
  <artifactId>fess-crawler-lasta</artifactId>
  <versioning>
    <latest>14.14.0</latest>
    <release>14.14.0</release>
    <versions>
      <version>1.0.0</version>
      <version>1.0.1</version>
      <version>1.0.2</version>
      <version>1.0.3</version>
      <version>1.0.4</version>
      <version>1.0.5</version>
      <version>1.0.6</version>

import org.dbflute.optional.OptionalEntity;

import jakarta.annotation.Resource;

/**
 * Service class for managing file configuration operations.
 * This service provides CRUD operations for file crawler configurations,
 * including retrieval, storage, deletion, and search functionality.
 * It handles pagination and integrates with the file authentication system.
 */
public class FileConfigService extends FessAppService {

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.rule;

import java.util.regex.Pattern;

import org.codelibs.fess.unit.UnitFessTestCase;
import org.junit.jupiter.api.Test;

/**
 * Test class for MIME type patterns defined in crawler/rule.xml.
 * Verifies that regex patterns correctly match MIME types with special characters.
 *

errors.password_is_blacklisted = To hasło jest niedozwolone. Proszę wybrać inne hasło.
errors.invalid_confirm_password = Potwierdzenie hasła nie pasuje.
errors.cannot_delete_doc_because_of_running = Crawler jest uruchomiony. Nie można usunąć dokumentu.
errors.failed_to_delete_doc_in_admin = Nie można usunąć dokumentu.
errors.failed_to_send_testmail=Nie można wysłać e-maila testowego.

    /** The key of the message: Crawler Start Time */
    public static final String LABELS_crawling_info_CrawlerStartTime = "{labels.crawling_info_CrawlerStartTime}";

    /** The key of the message: Crawler End Time */
    public static final String LABELS_crawling_info_CrawlerEndTime = "{labels.crawling_info_CrawlerEndTime}";

    /** The key of the message: Crawler Execution Time */

/**
 * Service class for managing duplicate host configuration CRUD operations.
 * This service provides functionality to create, read, update, and delete
 * duplicate host configurations used by the Fess crawler system.
 *
 * <p>Duplicate host configurations allow administrators to define hostname patterns
 * that should be treated as equivalent during crawling. This helps avoid indexing

		</dependency>
		<dependency>
			<groupId>org.codelibs.fess</groupId>
			<artifactId>fess-crawler-opensearch</artifactId>
			<version>${crawler.version}</version>
		</dependency>
		<dependency>
			<groupId>org.codelibs.fess</groupId>
			<artifactId>fess-crawler-playwright</artifactId>
			<version>${crawler.playwright.version}</version>
		</dependency>
		<dependency>
			<groupId>args4j</groupId>

    /**
     * Returns the execution type identifier for this job.
     * This type is used for classpath construction, configuration, and logging purposes.
     *
     * @return the execution type (e.g., "crawler", "suggest", etc.)
     */
    protected abstract String getExecuteType();

    /**
     * Executes the job with the specified job executor.

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);

        try {
            final RESULT result = entityType.newInstance();
            result.setAvailable(DfTypeUtil.toBoolean(source.get("available")));
            result.setCrawler(DfTypeUtil.toBoolean(source.get("crawler")));
            result.setCreatedBy(DfTypeUtil.toString(source.get("createdBy")));
            result.setCreatedTime(DfTypeUtil.toLong(source.get("createdTime")));