import org.codelibs.fess.crawler.entity.OpenSearchAccessResult;
import org.codelibs.opensearch.runner.OpenSearchRunner;
import org.dbflute.utflute.lastadi.LastaDiTestCase;

import jakarta.annotation.Resource;

/**
 * @author shinsuke
 *
 */
public class OpenSearchDataServiceTest extends LastaDiTestCase {
    @Resource
    private OpenSearchDataService dataService;

    @Resource

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

import com.google.common.base.Charsets;

import jakarta.annotation.PostConstruct;
import jakarta.annotation.PreDestroy;

/**
 * Extract a text by using external http server.
 */
public class ApiExtractor extends AbstractExtractor {

import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
import org.codelibs.fess.crawler.helper.ContentLengthHelper;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;

import jakarta.annotation.Resource;
import org.codelibs.jcifs.smb1.Config;
import org.codelibs.jcifs.smb1.ACE;
import org.codelibs.jcifs.smb1.NtlmPasswordAuthentication;
import org.codelibs.jcifs.smb1.SID;

import org.codelibs.fess.crawler.util.CrawlerWebServer;
import org.codelibs.opensearch.runner.OpenSearchRunner;
import org.dbflute.utflute.lastadi.LastaDiTestCase;

import jakarta.annotation.Resource;

public class CrawlerTest extends LastaDiTestCase {

    @Resource
    private Crawler crawler;

    @Resource
    private DataService dataService;

    @Resource

import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;

import jakarta.annotation.Resource;

/**
 * TextTransformer is a class that transforms a ResponseData object into a ResultData object containing the extracted text content.

import org.w3c.dom.Node;
import org.xml.sax.InputSource;

import com.google.common.cache.CacheBuilder;
import com.google.common.cache.CacheLoader;
import com.google.common.cache.LoadingCache;

import jakarta.annotation.Resource;

/**
 * {@link HtmlXpathExtractor} is an implementation of the {@link org.codelibs.fess.crawler.extractor.Extractor} interface.
 * It uses XPath expressions to extract text content from HTML documents.
 * <p>

import org.opensearch.index.query.QueryBuilders;

import com.google.common.cache.CacheBuilder;
import com.google.common.cache.CacheLoader;
import com.google.common.cache.LoadingCache;

import jakarta.annotation.PostConstruct;

/**
 * OpenSearchUrlFilterService is an implementation of {@link UrlFilterService} for OpenSearch.
 */
public class OpenSearchUrlFilterService extends AbstractCrawlerService implements UrlFilterService {

import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.util.TextUtil;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;

import jakarta.annotation.PostConstruct;

/**
 * <p>
 * The {@link TikaExtractor} class is responsible for extracting text content and metadata from various file formats

import org.codelibs.fess.crawler.entity.UrlQueueImpl;
import org.codelibs.fess.crawler.helper.MemoryDataHelper;
import org.codelibs.fess.crawler.service.UrlQueueService;

import jakarta.annotation.Resource;

/**
 * Implementation of the {@link UrlQueueService} interface.
 * This class provides methods for managing a queue of URLs to be crawled,
 * including adding, deleting, and retrieving URLs from the queue.

import org.opensearch.common.unit.TimeValue;
import org.opensearch.index.query.QueryBuilders;
import org.opensearch.search.SearchHit;
import org.opensearch.search.SearchHits;

import jakarta.annotation.PostConstruct;

/**
 * OpenSearchDataService is an implementation of {@link DataService} for OpenSearch.
 */
public class OpenSearchDataService extends AbstractCrawlerService implements DataService<OpenSearchAccessResult> {