* This job launches a separate crawler process that can crawl web sites, file systems,
 * and data sources based on the configured crawling settings.
 *
 * <p>The job supports selective crawling by specifying configuration IDs for different
 * types of crawlers (web, file, data). It manages the crawler process lifecycle,
 * handles timeout scenarios, and ensures proper cleanup of resources.</p>
 *

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

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.processor.impl.DefaultResponseProcessor;

    }

    /**
     * Name of the crawling configuration.
     */
    @Required
    @Size(max = 200)
    public String crawlingConfigName;

    /**
     * Path or URL to be crawled by this configuration.
     */
    @Required
    @Size(max = 1000)
    public String crawlingConfigPath;

    /**
     * Maximum depth for crawling (how many levels deep to follow links).
     */

 * This class extends ArrayList to hold document maps while tracking content size
 * and processing time metrics. It's used throughout the Fess search system to
 * manage collections of search results and crawled documents.
 *
 */
public class DocList extends ArrayList<Map<String, Object>> {

    /** Serial version UID for serialization */
    private static final long serialVersionUID = 1L;

    public void test_urlQueueKeyObject() {
        TestUrlQueue urlQueue = new TestUrlQueue("queue_123", "http://example.com/test");
        crawlerStatsHelper.begin(urlQueue);
        crawlerStatsHelper.record(urlQueue, "crawled");
        crawlerStatsHelper.done(urlQueue);

        String[] values = localLogMsg.get().split("\t");
        assertEquals(4, values.length);
        assertEquals("url:http://example.com/test", values[0]);

import org.codelibs.fess.Constants;
import org.codelibs.fess.crawler.builder.RequestDataBuilder;
import org.codelibs.fess.crawler.client.CrawlerClient;
import org.codelibs.fess.crawler.client.CrawlerClientFactory;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.exception.ChildUrlsException;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

    /**
     * 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.
     */

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;

    @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;

    /**

 * 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;