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.ExtractException;

/**
 * Gets a text from .doc file.
 *
 * @author shinsuke
 *
 */
public class MsWordExtractor extends AbstractExtractor {

    /**
     * Creates a new MsWordExtractor instance.
     */

package org.codelibs.fess.crawler.exception;

/**
 * UnsupportedExtractException is thrown when the content extraction is not supported.
 * It extends ExtractException and indicates that the requested extraction operation cannot be performed.
 *
 */
public class UnsupportedExtractException extends ExtractException {

    private static final long serialVersionUID = 1L;

    /**
     * Constructor.
     * @param message The error message.

import org.apache.logging.log4j.Logger;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;

import jakarta.mail.Address;

import org.apache.poi.hpbf.extractor.PublisherTextExtractor;
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 . file.
 *
 * @author shinsuke
 *
 */
public class MsPublisherExtractor extends AbstractExtractor {

    /**
     * Creates a new MsPublisherExtractor instance.

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;

/**
 * Abstract base class for XML extractors.
 * Provides common functionality for extracting text content from XML-like documents.

import org.codelibs.core.lang.ThreadUtil;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;

/**

import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
import org.codelibs.fess.crawler.helper.ContentLengthHelper;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;

/**

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;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.jodconverter.core.office.OfficeException;
import org.jodconverter.core.office.OfficeManager;
import org.jodconverter.local.LocalConverter;

import org.codelibs.fess.crawler.client.http.Authentication;
import org.codelibs.fess.crawler.client.http.RequestHeader;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.ExtractException;

import com.google.common.base.Charsets;

import jakarta.annotation.PostConstruct;
import jakarta.annotation.PreDestroy;

/**
 * Extract a text by using external http server.
 */

        try {
            zipExtractor.getText(invalidStream, null);
            fail("Expected ExtractException");
        } catch (final ExtractException e) {
            assertTrue("Error message should mention ZIP archive", e.getMessage().contains("ZIP archive"));
            assertTrue("Error message should indicate failure",