import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */
public class FileTransformerTest extends PlainTestCase {
    public FileTransformer fileTransformer;

    @Override
    protected void setUp() throws Exception {
        super.setUp();
        fileTransformer = new FileTransformer();

import org.dbflute.utflute.core.PlainTestCase;

/**
 * Test class for RuleManager interface.
 * Tests the contract and behavior of RuleManager implementations.
 */
public class RuleManagerTest extends PlainTestCase {

    /**
     * Test implementation of RuleManager for testing purposes
     */
    public static class TestRuleManager implements RuleManager {

/**
 * Represents the response data obtained from a crawled resource.
 * This class encapsulates various details of an HTTP response, including
 * status code, content type, content length, and the response body.
 * It also provides methods for managing metadata, child URLs, and temporary files.
 */
public class ResponseData implements Closeable {

    private String url;

    private int httpStatusCode;

 *   <li>Configurable timeout for extraction process</li>
 * </ul>
 *
 * @author shinsuke
 */
public class PdfExtractor extends PasswordBasedExtractor {
    /** Logger instance for this class. */
    private static final Logger logger = LogManager.getLogger(PdfExtractor.class);

    /** Timeout for PDF extraction in milliseconds (default: 30 seconds). */
    protected long timeout = 30000; // 30sec

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Gets a text from .doc file.
 *
 * @author shinsuke
 *
 */
public class MsWordExtractor extends AbstractExtractor {

    /**
     * Creates a new MsWordExtractor instance.
     */
    public MsWordExtractor() {
        super();
    }

    /**

import org.opensearch.common.unit.TimeValue;
import org.opensearch.env.Environment;
import org.opensearch.index.IndexSettings;
import org.opensearch.index.analysis.AbstractTokenFilterFactory;

public class ReloadableKeywordMarkerFilterFactory extends AbstractTokenFilterFactory {

    private final Path keywordPath;

    private final long reloadInterval;

import org.opensearch.common.unit.TimeValue;
import org.opensearch.env.Environment;
import org.opensearch.index.IndexSettings;
import org.opensearch.index.analysis.AbstractTokenFilterFactory;

public class ReloadableStopFilterFactory extends AbstractTokenFilterFactory {

    private final Path stopwordPath;

    private final long reloadInterval;

    private final boolean ignoreCase;

import org.codelibs.fess.crawler.service.DataService;
import org.codelibs.fess.crawler.service.UrlQueueService;

import jakarta.annotation.Resource;

/**
 * The Crawler class is the main class for web crawling. It manages the crawling process,
 * including adding URLs to the queue, filtering URLs, managing crawler threads,
 * and handling the overall crawling lifecycle.
 *

 */
package org.codelibs.fess.crawler.util;

import java.util.ArrayList;

/**
 * OpenSearchResultList is a list of OpenSearch results.
 *
 * @param <E> The type of elements in this list.
 */
public class OpenSearchResultList<E> extends ArrayList<E> {
    /**
     * Constructs a new OpenSearchResultList.
     */
    public OpenSearchResultList() {
        super();
    }

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Gets a text from .xls file.
 *
 * @author shinsuke
 *
 */
public class MsExcelExtractor extends AbstractExtractor {

    /**
     * Creates a new MsExcelExtractor instance.
     */
    public MsExcelExtractor() {
        super();
    }

    /**