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 org.slf4j.Logger;

        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();
            }

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

import java.util.LinkedHashMap;
import java.util.Map;

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

/**
 * @author shinsuke
 *
 */
public class UrlConvertHelper {

    protected Map<String, String> convertMap = new LinkedHashMap<>();

    public String convert(final String url) {

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

/**
 * @author shinsuke
 *
 */
public class TextExtractor extends AbstractExtractor {

    protected String encoding = Constants.UTF_8;

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 {

    /*

            throw new CrawlerSystemException("MimeTypeHelper is unavailable.");
        }
        return mimeTypeHelper;
    }

    protected ExtractorFactory getExtractorFactory() {
        final ExtractorFactory extractorFactory = crawlerContainer.getComponent("extractorFactory");
        if (extractorFactory == null) {
            throw new CrawlerSystemException("ExtractorFactory is unavailable.");
        }

    public void addMaxLength(final String mimeType, final long maxLength) {
        if (StringUtil.isBlank(mimeType)) {
            throw new CrawlerSystemException("MIME type is a blank.");
        }
        if (maxLength < 0) {
            throw new CrawlerSystemException("The value of maxLength is invalid.");
        }
        maxLengthMap.put(mimeType, maxLength);
    }

    public long getMaxLength(final String mimeType) {

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 {
    /*

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;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

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

import org.apache.poi.hslf.usermodel.HSLFTextParagraph;
import org.apache.poi.sl.extractor.SlideShowExtractor;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * @author shinsuke
 *
 */
public class MsPowerPointExtractor extends AbstractExtractor {

    /*
     * (non-Javadoc)
     *