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 {

    /**
     * Creates a new MsWordExtractor instance.
     */
    public MsWordExtractor() {

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 {

    /**
     * Creates a new MsExcelExtractor instance.
     */

        }
        return buf.toString();
    }

    /**
     * Gets the character set for the given file.
     *
     * @param file the file to get the character set for
     * @return the character set
     */
    protected String getCharSet(final File file) {
        return charset;
    }

    /**
     * Gets the character encoding used for files.
     *
     * @return the character encoding

import jakarta.mail.Part;
import jakarta.mail.Session;
import jakarta.mail.internet.MailDateFormat;
import jakarta.mail.internet.MimeMessage;
import jakarta.mail.internet.MimeUtility;

/**
 * Gets a text from .eml file.
 *
 * @author shinsuke
 *
 */
public class EmlExtractor extends AbstractExtractor {
    /** Array of day of week abbreviations used for parsing received dates */

        if (!childList.isEmpty()) {
            CrawlingParameterUtil.getUrlQueueService().offerAll(crawlerContext.getSessionId(), childList);
        }
    }

    /**
     * Gets the transformer.
     *
     * @return the transformer
     */
    public Transformer getTransformer() {
        return transformer;
    }

    /**
     * Sets the transformer.
     *

    public void delete(final String sessionId) {
        deleteBySessionId(sessionId);
        includeFilterCache.invalidate(sessionId);
        excludeFilterCache.invalidate(sessionId);
    }

    /**
     * Gets the list of include URL patterns for the specified session.
     *
     * @param sessionId The session ID.
     * @return The list of compiled include patterns.

        } catch (final Exception e) {
            throw new OpenSearchAccessException("Failed to check if " + sessionId + ":" + url + " exists.", e);
        }
    }

    /**
     * Gets the count of documents matching the search criteria.
     *
     * @param callback The callback to configure the search request.
     * @return The number of matching documents.
     */

        if (resultData != null) {
            BeanUtil.copyBeanToBean(resultData, accessResultData);
        }
        setAccessResultData(accessResultData);
    }

    /**
     * Gets the access result data, loading it from the data service if not already initialized.
     *
     * @return The access result data.
     */
    @Override
    public AccessResultData<String> getAccessResultData() {

        if (limitNumber < 0) {
            return percentNum;
        }
        return percentNum < limitNumber ? percentNum : limitNumber;
    }

    /**
     * Gets the total number of documents.
     * @return The total number of documents.
     */
    protected long getTotal() {
        final SearchResponse response = client.prepareSearch()
                .setIndices(indexName)

        // Default constructor
    }

    /*
     * (non-Javadoc)
     *
     * @see org.codelibs.fess.crawler.rule.RuleManager#getRule(org.codelibs.fess.crawler.entity.ResponseData)
     */
    /**
     * Gets the first rule that matches the given response data.
     * @param responseData the response data to match against
     * @return the first matching rule, or null if no rule matches
     */
    @Override