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

    /**
     * Interval in milliseconds between crawler thread executions.
     * Used to control the rate at which new crawler threads are started
     * and the frequency of status checks.
     */
    protected long crawlingExecutionInterval = Constants.DEFAULT_CRAWLING_EXECUTION_INTERVAL;

    /**
     * Thread priority for crawler threads.
     * Defaults to normal thread priority.
     */

    @Size(max = 200)
    public String name;

    /**
     * The description of the web configuration.
     */
    @Size(max = 1000)
    public String description;

    /**
     * The URLs to be crawled by this web configuration.
     */
    @Required
    @UriType(protocolType = ProtocolType.WEB)
    @CustomSize(maxKey = "form.admin.max.input.size")
    public String urls;

    /**

import org.codelibs.fess.app.service.FailureUrlService;
import org.codelibs.fess.crawler.builder.RequestDataBuilder;
import org.codelibs.fess.crawler.client.CrawlerClient;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.log.LogType;
import org.codelibs.fess.exception.ContainerNotAvailableException;

 * This class defines tag patterns that match HTML elements based on tag name, CSS class, ID, or custom attributes.
 * It is used to identify and remove unwanted HTML elements from crawled documents.
 */
public class PrunedTag {
    /** The HTML tag name to match (e.g., "div", "span", "p") */
    private final String tag;
    /** The ID attribute value to match */
    private String id;

/**
 * Helper class for managing and validating URL protocols in Fess crawling system.
 * This class handles the initialization and validation of web and file protocols
 * used by the crawler to determine which URLs can be crawled.
 */
public class ProtocolHelper {
    private static final Logger logger = LogManager.getLogger(ProtocolHelper.class);

     *
     * @param crawlingConfig the crawling configuration associated with the failure
     * @param errorName the name/type of the error that occurred
     * @param url the URL that failed to be crawled
     * @param e the exception that caused the failure
     * @return the stored or updated FailureUrl entity, or null if the exception should be ignored
     */

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.Constants;
import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.util.CrawlingParameterUtil;
import org.codelibs.fess.crawler.util.FieldConfigs;
import org.codelibs.fess.mylasta.direction.FessConfig;

 * </pre>
 */
public class Crawler {

    /**
     * Creates a new instance of Crawler.
     */
    public Crawler() {
        // Default constructor
    }

    /** Logger instance for this class. */
    private static final Logger logger = LogManager.getLogger(Crawler.class);

    /** Thread name for web and file system crawling process. */

    OkHttpClient client = new OkHttpClient.Builder()
        .cache(cache)
        .callTimeout(5, TimeUnit.SECONDS)
        .build();

    Crawler crawler = new Crawler(client, queueLimit, hostLimit);
    crawler.queue.add(HttpUrl.get(args[1]));
    crawler.parallelDrainQueue(threadCount);
  }