*/
package org.codelibs.fess.crawler.extractor.impl;

import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.io.InputStream;

import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

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

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.interval.IntervalController;

/**
 * An abstract base class for implementing {@link IntervalController}.

    }

    /** 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.
     */

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

/**
 * The {@code IntervalController} interface defines methods for controlling
 * the delay intervals in a web crawler. It includes constants representing
 * different types of processing states and a method to introduce a delay
 * based on the type of processing.
 * <p>

        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");

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

import java.io.InputStream;
import java.util.Map;

import org.codelibs.core.io.InputStreamUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Extracts text content from an input stream as plain text.

 */
package org.codelibs.fess.crawler.transformer.impl;

import java.util.ArrayList;
import java.util.List;
import java.util.Map;

import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.AccessResultDataImpl;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;

    if (flushHeaders) {
      connection.flush()
    }
  }

  fun enqueueTrailers(trailers: Headers) {
    withLock {
      check(!sink.finished) { "already finished" }
      require(trailers.size != 0) { "trailers.size() == 0" }
      this.sink.trailers = trailers
    }
  }

  fun readTimeout(): Timeout = readTimeout

  fun writeTimeout(): Timeout = writeTimeout

  /**

 */
package org.codelibs.fess.crawler.service.impl;

import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.entity.AccessResultImpl;
import org.codelibs.fess.crawler.helper.MemoryDataHelper;
import org.codelibs.fess.crawler.service.DataService;
import org.dbflute.utflute.core.PlainTestCase;

/**

        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);