super.setUp();

        final int port = 9000;
        logger.info("Creating {}", IMAGE_NAME);
        minioServer = new GenericContainer<>(IMAGE_NAME)//
                .withEnv("MINIO_ACCESS_KEY", ACCESS_KEY)//
                .withEnv("MINIO_SECRET_KEY", SECRET_KEY)//
                .withExposedPorts(port)//
                .withCommand("server /data")//
                .waitingFor(new HttpWaitStrategy()//

     */
    @Override
    protected Pattern getEncodingPattern() {
        return xmlEncodingPattern;
    }

    /**
     * Returns the precompiled {@link Pattern} used to match XML tags within the content.
     * This pattern is utilized by the extractor to identify and process XML elements.
     *
     * @return the {@link Pattern} instance for XML tag matching
     */
    @Override

import java.util.List;

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

/**
 * Service interface for managing URL queues.
 * Provides methods for adding, retrieving, and managing URLs within a crawling session.
 *
 * @param <QUEUE> the type of URL queue
 */
public interface UrlQueueService<QUEUE extends UrlQueue<?>> {

    /**
     * Updates the session ID.
     *

import jp.gr.java_conf.dangan.util.lha.LhaFile;
import jp.gr.java_conf.dangan.util.lha.LhaHeader;

/**
 * Extractor implementation for LHA (LZH) archive files.
 * This extractor can extract text content from files within LHA archives
 * by using appropriate extractors for each contained file type.
 *
 * @author shinsuke
 */
public class LhaExtractor extends AbstractExtractor {
    /** Logger for this class. */

        accessResult.init(responseData, resultData);
        return accessResult;
    }

    /**
     * Checks if the access count is within the allowed limit.
     *
     * @param crawlerContext the crawler context
     * @return true if access count is within limit, false otherwise
     */
    protected boolean checkAccessCount(final CrawlerContext crawlerContext) {
        if (crawlerContext.getMaxAccessCount() > 0) {

##
## CODEOWNERS style rules:
## 1. Prefer team ownership over individual user ownership.
## 2. GBT-related team should be listed first.
## 3. Try to keep paths alphabetically sorted within visual groups.
## 4. List individual owners last.
##

# Build infrastructure
.teamcity/                                  @gradle/bt-developer-productivity

    }

    /**
     * Retrieves metadata information for an object in the specified bucket.
     * @param bucketName the name of the bucket containing the object
     * @param path the path to the object within the bucket
     * @return the object metadata, or null if the object does not exist
     * @throws CrawlingAccessException if the bucket does not exist
     */

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

import org.codelibs.core.lang.StringUtil;

/**
 * Represents a URL entry within a sitemap.
 *
 * <p>
 * This class encapsulates the properties of a URL as defined in the sitemap XML format,
 * including its location, last modification date, change frequency, and priority.

 *
 * This class provides methods to normalize text by reading characters from a provided Reader
 * and processing them according to specific rules. The main functionality is encapsulated
 * within the nested {@link TextNormalizeContext} class.
 *
 * <p>The text normalization process includes:
 * <ul>
 *   <li>Treating ISO control characters and specified space characters as spaces.</li>

 * </ul>
 *
 * <p>
 * The class uses synchronization to ensure thread safety when accessing and modifying the URL queue.
 * It also checks for duplicate URLs before adding them to the queue,
 * both within the queue itself and against previously accessed URLs stored in the {@link MemoryDataHelper}.
 * </p>
 *
 */
/**
 * This class is an implementation of {@link UrlQueueService}.
 */