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

import java.util.LinkedHashMap;
import java.util.LinkedList;
import java.util.List;
import java.util.Map;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.container.CrawlerContainer;

import jakarta.annotation.Resource;

/**
 * Creates and manages crawler clients for web crawling operations.

      }

      socket.sleepWhileOpen(response.headersDelayNanos)
      stream.writeHeaders(response.toHttp2Headers(), outFinished, flushHeaders)

      if (trailers.size > 0) {
        stream.enqueueTrailers(trailers)
      }
      pushPromises(stream, request, response.pushPromises)
      if (body != null) {
        socket.sleepWhileOpen(bodyDelayNanos)
        val responseBodySink =

 */
package org.codelibs.fess.crawler;

/**
 * Enum representing the status of a crawler.
 * It can be INITIALIZING, RUNNING, or DONE.
 */
public enum CrawlerStatus {
    /**
     * The crawler is initializing.
     */
    INITIALIZING,

    /**
     * The crawler is currently running.
     */
    RUNNING,

    /**
     * The crawler has completed its task.
     */
    DONE;

import org.codelibs.core.lang.ThreadUtil;
import org.codelibs.fess.crawler.Crawler;
import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.entity.OpenSearchAccessResult;
import org.codelibs.fess.crawler.entity.OpenSearchUrlQueue;
import org.codelibs.fess.crawler.service.DataService;
import org.codelibs.fess.crawler.service.UrlFilterService;

index.document.suggest.index=fess
# Index name for crawler documents.
index.document.crawler.index=fess_crawler
# Number of primary shards for crawler queue index.
index.document.crawler.queue.number_of_shards=10
# Number of primary shards for crawler data index.
index.document.crawler.data.number_of_shards=10
# Number of primary shards for crawler filter index.
index.document.crawler.filter.number_of_shards=10

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.transformer;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.exception.FessSystemException;

    }

    /** Wait time in milliseconds when crawler is not running */
    protected long crawlerWaitMillis = 10000;

    /** List of interval rules for controlling crawler timing */
    protected List<IntervalRule> ruleList = new ArrayList<>();

    /**
     * Checks the crawler status and waits if the crawler is not running.
     * This method blocks until the crawler is running again.
     */

        this.available = value;
    }

    public Boolean getCrawler() {
        checkSpecifiedProperty("crawler");
        return crawler;
    }

    public void setCrawler(Boolean value) {
        registerModifiedProperty("crawler");
        this.crawler = value;
    }

    public String getCreatedBy() {
        checkSpecifiedProperty("createdBy");

        return resultBuf.toString();

    }

    /**
     * Gets the count of currently running crawler jobs.
     * This method queries the scheduled jobs to count active crawler processes.
     * Used to enforce maximum concurrent crawler limits.
     *
     * @return the number of currently running crawler jobs
     */
    protected int getRunningJobCount() {
        final AtomicInteger counter = new AtomicInteger(0);

        }
        if (1500 <= count) {
            logger.info("Time out: Failed to start crawler)");
            fail(); // Time Out
        }

        logger.info("Crawler is running");
        count = 0;
        isRunning = true;
        sleepTime = 100; // Reset to 100ms for termination wait

        // Wait until the crawler terminates (with exponential backoff)
        while (count < 3000 && isRunning) {