* @return The list of compiled include patterns.
     * @throws CrawlerSystemException if the patterns cannot be loaded.
     */
    @Override
    public List<Pattern> getIncludeUrlPatternList(final String sessionId) {
        try {
            return includeFilterCache.get(sessionId);
        } catch (final ExecutionException e) {
            throw new CrawlerSystemException(e);
        }
    }

    /**

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}

            resultData.removeUrl(requestData);
            resultData.removeUrl(getDuplicateUrl(requestData));
        } catch (final CrawlerSystemException e) {
            throw e;
        } catch (final Exception e) {
            throw new CrawlerSystemException("Could not store data.", e);
        }
    }

    /**
     * Gets the child URL extraction rules as a stream of tag-attribute pairs.
     *

        try {
            server.start();
        } catch (final Exception e) {
            throw new CrawlerSystemException(e);
        }
    }

    public void stop() {
        try {
            server.stop();
            server.join();
        } catch (final Exception e) {
            throw new CrawlerSystemException(e);
        } finally {
            if (tempDocRoot) {
                docRoot.delete();
            }

    }

    /**
     * Initializes the extractor by starting the office manager.
     *
     * @throws CrawlerSystemException if the office manager is null or fails to start
     */
    @PostConstruct
    public void init() {
        if (officeManager == null) {
            throw new CrawlerSystemException("officeManager is null.");
        }
        try {
            officeManager.start();

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.
 *
 * @author shinsuke
 *
 */
public class MsWordExtractor extends AbstractExtractor {

    /**

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;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */
public class TextExtractorTest extends PlainTestCase {

import java.io.File;
import java.io.IOException;
import java.util.List;

import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;

import jakarta.annotation.Resource;

import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;

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.
 *
 * @author shinsuke
 *
 */
public class MsExcelExtractor extends AbstractExtractor {