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

import java.io.InputStream;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

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

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

import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Gets a text from .xls file.
 *
 * @author shinsuke

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

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

import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Gets a text from .doc file.
 *
 * @author shinsuke
 *
 */

 */
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;

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.client;

import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */

    }

    /** 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");

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

import java.util.Set;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
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.exception.CrawlingAccessException;

    /** The key of the configuration. e.g. UTF-8 */
    String CRAWLER_DOCUMENT_SITE_ENCODING = "crawler.document.site.encoding";

    /** The key of the configuration. e.g. unknown */
    String CRAWLER_DOCUMENT_UNKNOWN_HOSTNAME = "crawler.document.unknown.hostname";

    /** The key of the configuration. e.g. false */

        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);