/**
     * Returns the URL of the accessed resource.
     *
     * @return the URL
     */
    String getUrl();

    /**
     * Sets the URL of the accessed resource.
     *
     * @param url the URL
     */
    void setUrl(String url);

    /**
     * Returns the parent URL of the accessed resource.
     *
     * @return the parent URL
     */
    String getParentUrl();

        mimeType = contentType;
    }

    /**
     * Gets the URL of the crawled resource.
     *
     * @return the URL
     */
    public String getUrl() {
        return url;
    }

    /**
     * Sets the URL of the crawled resource.
     *
     * @param url the URL to set
     */
    public void setUrl(final String url) {
        this.url = url;

import org.opensearch.index.query.QueryBuilders;

import jakarta.annotation.Resource;

/**
 * @author shinsuke
 *
 */
public class OpenSearchUrlQueueServiceTest extends LastaDiTestCase {
    @Resource
    private OpenSearchUrlQueueService urlQueueService;

    @Resource
    private FesenClient fesenClient;

    private OpenSearchRunner runner;

    @Override

    /** The session ID associated with the access result. */
    protected String sessionId;

    /** The rule ID that matched the accessed resource. */
    protected String ruleId;

    /** The URL of the accessed resource. */
    protected String url;

    /** The parent URL of the accessed resource. */
    protected String parentUrl;

    /** The status of the access result. */
    protected Integer status = Constants.OK_STATUS;

    UNSUPPORTED_URL_AT_CRAWLING_STARTED,
    /** Indicates checking the last modified date of a resource. */
    CHECK_LAST_MODIFIED,
    /** Indicates the resource has not been modified. */
    NOT_MODIFIED,
    /** Indicates getting content from a resource. */
    GET_CONTENT,
    /** Indicates a redirect location was found. */
    REDIRECT_LOCATION,
    /** Indicates processing a response. */

import org.codelibs.fess.crawler.processor.ResponseProcessor;
import org.codelibs.fess.crawler.rule.Rule;
import org.codelibs.fess.crawler.rule.RuleManager;

import jakarta.annotation.Resource;

/**
 * Abstract base class for implementing {@link Rule} interfaces.
 * Provides common functionality and properties for crawler rules.
 *
 * <p>

        assertTrue(auth.matches("ftp://hostname/path/to/resource.txt"));
        assertFalse(auth.matches("ftp://hostname:22/path/to/resource.txt"));
        assertFalse(auth.matches("ftp://otherhost/path/to/resource.txt"));

        // Test with special characters in path
        assertTrue(auth.matches("ftp://hostname:21/path%20with%20spaces/resource.txt"));

 *   <li>Dynamic passwords provided through extraction parameters</li>
 * </ul>
 *
 * <p>Passwords are matched against URLs or resource names using regular expression patterns.
 * The extractor first tries to match against the URL, then falls back to the resource name if available.
 *
 * @author shinsuke
 */
public abstract class PasswordBasedExtractor extends AbstractExtractor {

/**
 * CrawlingAccessException is an exception class that represents an issue encountered while accessing a resource during the crawling process.
 * It extends CrawlerSystemException and provides functionality to set and check the log level for the exception.
 *
 * <p>
 * This exception can be thrown when there are problems accessing URLs, files, or any other resources needed for crawling.
 * It includes constructors to handle messages, causes, or both.
 * </p>
 *

import jakarta.annotation.Resource;

public class CrawlerTest extends LastaDiTestCase {

    @Resource
    private Crawler crawler;

    @Resource
    private DataService dataService;

    @Resource
    private UrlQueueService urlQueueService;

    @Resource
    private FileTransformer fileTransformer;

    @Resource
    private CrawlerContainer crawlerContainer;