/**
 * <p>
 * The {@link TikaExtractor} class is responsible for extracting text content and metadata from various file formats
 * using the Apache Tika library. It extends {@link PasswordBasedExtractor} to handle password-protected files.
 * </p>
 *
 * <p>
 * This class provides methods to extract text from an input stream, handling different scenarios such as:
 * </p>
 * <ul>
 *   <li>Normalizing text content</li>

     */
    public void setMailProperties(final Properties mailProperties) {
        this.mailProperties = mailProperties;
    }

    /**
     * Extracts the body text from a MIME message.
     *
     * @param message the MIME message to extract text from
     * @return the extracted body text
     * @throws ExtractException if extraction fails
     */
    protected String getBodyText(final MimeMessage message) {

                    fields, 0, score, -1, tags, roles, langs, SuggestItem.Kind.QUERY);
        } catch (final IOException e) {
            throw new SuggesterException("Failed to create SuggestItem from search words.", e);
        }
    }

    @Override
    public List<SuggestItem> parseQueryLog(final QueryLog queryLog, final String[] fields, final String[] tagFieldNames,

    /**
     * Private constructor to prevent instantiation of this utility class.
     */
    private ResponseDataUtil() {
    }

    /**
     * Creates a temporary file containing the response body from the given ResponseData.
     *
     * @param responseData the response data containing the response body
     * @return a temporary file containing the response body

     *
     * @param index the position at which the rule should be added
     * @param rule the rule to be added
     */
    void addRule(int index, Rule rule);

    /**
     * Removes the specified rule from the rule manager.
     *
     * @param rule the rule to be removed
     * @return true if the rule was successfully removed, false otherwise
     */
    boolean removeRule(Rule rule);

    /**

import jp.gr.java_conf.dangan.util.lha.LhaFile;
import jp.gr.java_conf.dangan.util.lha.LhaHeader;

/**
 * Extractor implementation for LHA (LZH) archive files.
 * This extractor can extract text content from files within LHA archives
 * by using appropriate extractors for each contained file type.
 *
 * @author shinsuke
 */
public class LhaExtractor extends AbstractExtractor {
    /** Logger for this class. */

 *   <li>Limiting the number of results (size).</li>
 *   <li>Filtering by tags, roles, fields, and languages.</li>
 *   <li>Excluding specific words from the results.</li>
 *   <li>Building the OpenSearch query and rescorer for the popular words search.</li>
 *   <li>Creating a {@link PopularWordsResponse} from the OpenSearch search response.</li>
 * </ul>
 *
 * @see Request
 * @see PopularWordsResponse
 */

### Key Features

- **Multi-Protocol Support**: HTTP/HTTPS, File System, FTP, SMB/CIFS, Cloud Storage (MinIO, S3)

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() {
        super();
    }

    /**
     * Extracts text from the Word input stream.
     * @param in The input stream.

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.
     */
    public MsExcelExtractor() {
        super();
    }

    /**
     * Extracts text from the Excel input stream.
     * @param in The input stream.