import org.codelibs.core.misc.DynamicProperties;
import org.codelibs.core.timer.TimeoutManager;
import org.codelibs.core.timer.TimeoutTask;
import org.codelibs.fess.Constants;
import org.codelibs.fess.crawler.client.FesenClient;
import org.codelibs.fess.exception.ContainerNotAvailableException;
import org.codelibs.fess.helper.SuggestHelper;
import org.codelibs.fess.opensearch.client.SearchEngineClient;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.core.misc.Tuple3;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.mylasta.direction.FessConfig;
import org.codelibs.fess.util.ComponentUtil;
import org.codelibs.fess.util.DocumentUtil;

/**

import java.net.URLEncoder;
import java.util.ArrayList;
import java.util.Collections;
import java.util.Date;
import java.util.List;
import java.util.Map;

import org.codelibs.fess.Constants;
import org.codelibs.fess.crawler.util.CharUtil;
import org.codelibs.fess.taglib.FessFunctions;
import org.lastaflute.web.util.LaRequestUtil;

import jakarta.servlet.http.HttpServletRequest;

/**

/**
 * 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);

    }

    /**
     * Gets the crawl delay value for the specified user agent from robots.txt.
     * The crawl delay specifies the time (in seconds) to wait between successive requests.
     *
     * @param userAgent The user agent string to match against robots.txt directives
     * @return The crawl delay value in seconds. Returns 0 if no matching directive is found
     *         or no crawl delay is specified for the matching directive.

import java.util.HashMap;
import java.util.List;
import java.util.Map;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.exception.StorageException;

import com.google.api.gax.paging.Page;
import com.google.auth.oauth2.GoogleCredentials;
import com.google.cloud.NoCredentials;

import java.util.ArrayList;
import java.util.List;
import java.util.concurrent.CountDownLatch;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.atomic.AtomicInteger;

import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * Test class for {@link Handler} and its inner class {@link Handler.GcsURLConnection}.

errors.invalid_str_is_included = {1} is ongeldig in {0}.
errors.blank_password = Wachtwoord is vereist.
errors.invalid_confirm_password = Wachtwoordbevestiging komt niet overeen.
errors.cannot_delete_doc_because_of_running = Crawler is bezig. Document kan niet worden verwijderd.
errors.failed_to_delete_doc_in_admin = Kan document niet verwijderen.
errors.failed_to_send_testmail=Kan test-e-mail niet verzenden.

 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.util;

import java.io.IOException;
import java.io.Reader;
import java.util.HashSet;
import java.util.Set;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;

    /**
     * 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.