* 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.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Gets a text from .doc file.
 *

    }

    public void setCrawler_Avg(ConditionOptionCall<AvgAggregationBuilder> opLambda) {
        setCrawler_Avg("crawler", opLambda);
    }

    public void setCrawler_Avg(String name, ConditionOptionCall<AvgAggregationBuilder> opLambda) {
        AvgAggregationBuilder builder = regAvgA(name, "crawler");
        if (opLambda != null) {
            opLambda.callback(builder);
        }
    }

 */
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.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Gets a text from .xls file.

import org.codelibs.core.lang.StringUtil;
import org.codelibs.core.lang.SystemUtil;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.util.CrawlingParameterUtil;

/**
 * HostIntervalController is an implementation of {@link org.codelibs.fess.crawler.interval.IntervalController}
 * that controls the interval between requests to the same host.

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.impl.MimeTypeHelperImpl;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */
public class PdfExtractorTest extends PlainTestCase {
    private static final Logger logger = LogManager.getLogger(PdfExtractorTest.class);

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

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

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.lang.ThreadUtil;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;

* [LastaFlute](https://github.com/lastaflute/lastaflute "LastaFlute"): Web Framework
* [Lasta Job](https://github.com/lastaflute/lasta-job "Lasta Job"): Job Scheduler
* [Fess Crawler](https://github.com/codelibs/fess-crawler "Fess Crawler"): Web Crawler

import jakarta.annotation.PreDestroy;

/**
 * Helper class for managing system processes in Fess.
 * This class provides functionality to start, stop, and manage external processes
 * such as crawler processes, with proper resource cleanup and lifecycle management.
 */
public class ProcessHelper {
    /** Logger instance for this class */
    private static final Logger logger = LogManager.getLogger(ProcessHelper.class);

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

import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.helper.MemoryDataHelper;
import org.codelibs.fess.crawler.service.impl.DataServiceImpl;
import org.codelibs.fess.crawler.service.impl.UrlFilterServiceImpl;
import org.dbflute.utflute.core.PlainTestCase;

/**

    /** 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 */