*/
package org.codelibs.fess.crawler.extractor.impl;

import java.io.InputStream;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.ExtractData;

labels.crawling_info_delete_all_cancel=Annulla
labels.crawling_info_thread_dump=Dump thread
labels.crawling_info_CrawlerStartTime=Ora di inizio crawler
labels.crawling_info_CrawlerEndTime=Ora di fine crawler
labels.crawling_info_CrawlerExecTime=Tempo di esecuzione crawler
labels.crawling_info_CrawlerStatus=Stato crawler
labels.crawling_info_WebFsCrawlExecTime=Tempo di esecuzione scansione (Web/File)

    protected DynamicProperties systemProperties;

    /** Service for managing web crawler configurations */
    @Resource
    protected WebConfigService webConfigService;

    /** Service for managing file crawler configurations */
    @Resource
    protected FileConfigService fileConfigService;

    /** Helper for managing crawler processes */
    @Resource
    protected ProcessHelper processHelper;

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.extractor;

import java.io.InputStream;
import java.util.Map;

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

/**
 * The Extractor interface defines methods for extracting text data from an input stream.

import org.codelibs.fess.crawler.exception.ChildUrlsException;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.helper.impl.MimeTypeHelperImpl;
import org.dbflute.utflute.core.PlainTestCase;
import org.testcontainers.containers.GenericContainer;
import org.testcontainers.containers.wait.strategy.Wait;

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

import java.io.File;
import java.io.FileOutputStream;
import java.io.InputStream;

import org.codelibs.core.io.CopyUtil;
import org.codelibs.core.io.FileUtil;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;

/**
 * Utility class for handling response data.

 */
package org.codelibs.fess.crawler.extractor.impl;

import java.io.BufferedInputStream;
import java.io.ByteArrayInputStream;
import java.io.InputStream;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;

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

/**
 * Configuration class for OpenSearch crawler settings.
 * This class provides configuration for index names, shards, and replicas
 * for the queue, data, and filter indices used by the crawler.
 */
public class OpenSearchCrawlerConfig {
    /**
     * Constructs a new OpenSearchCrawlerConfig.
     */

import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.builder.RequestDataBuilder;
import org.codelibs.fess.crawler.client.AbstractCrawlerClient;
import org.codelibs.fess.crawler.client.AccessTimeoutTarget;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.ChildUrlsException;

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.entity.OpenSearchUrlQueue;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.exception.OpenSearchAccessException;
import org.codelibs.fess.crawler.service.UrlQueueService;
import org.codelibs.fess.crawler.util.OpenSearchCrawlerConfig;