</dependency>
		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>poi-ooxml</artifactId>
			<version>${poi.version}</version>
			<exclusions>
				<exclusion>
					<groupId>stax</groupId>
					<artifactId>stax-api</artifactId>
				</exclusion>
				<exclusion>
					<groupId>xml-apis</groupId>
					<artifactId>xml-apis</artifactId>
				</exclusion>
			</exclusions>
		</dependency>
		<dependency>

     */
    public static final String FEATURE_EXTERNAL_GENERAL_ENTITIES = "http://xml.org/sax/features/external-general-entities";

    /**
     * Feature for external parameter entities in XML.
     */
    public static final String FEATURE_EXTERNAL_PARAMETER_ENTITIES = "http://xml.org/sax/features/external-parameter-entities";

    static {
        DEFAULT_CHARSET = Charset.defaultCharset();
    }

import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.exception.SitemapsException;
import org.xml.sax.Attributes;
import org.xml.sax.SAXNotRecognizedException;
import org.xml.sax.SAXNotSupportedException;
import org.xml.sax.helpers.DefaultHandler;

/**
 * Helper class for parsing and validating sitemaps.
 * It supports XML sitemaps, XML sitemap indexes, and text sitemaps,

import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.xml.sax.Attributes;
import org.xml.sax.InputSource;
import org.xml.sax.helpers.DefaultHandler;

/**
 * Utility class for XML-related operations.
 *
 * This class provides methods to escape special characters in XML strings,

        {
            xpathTransformer = new XpathTransformer();
            xpathTransformer.setName("xpathTransformer");
            Map<String, String> featureMap = newHashMap();
            featureMap.put("http://xml.org/sax/features/namespaces", "false");
            xpathTransformer.setFeatureMap(featureMap);
            Map<String, String> propertyMap = newHashMap();
            xpathTransformer.setPropertyMap(propertyMap);

import org.apache.tika.parser.PasswordProvider;
import org.apache.tika.parser.ocr.TesseractOCRConfig;
import org.apache.tika.parser.pdf.PDFParserConfig;
import org.apache.tika.sax.BodyContentHandler;
import org.apache.tika.sax.SecureContentHandler;
import org.codelibs.core.beans.util.BeanUtil;
import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.CopyUtil;
import org.codelibs.core.io.FileUtil;

		instance="singleton">
		<property name="name">"binaryTransformer"</property>
	</component>

	<component name="defaultFeatureMap" class="java.util.LinkedHashMap">
		<postConstruct name="put">
			<arg>"http://xml.org/sax/features/namespaces"</arg>
			<arg>"false"</arg>
		</postConstruct>
	</component>

	<component name="defaultPropertyMap" class="java.util.LinkedHashMap">
	</component>

        super.setUp();
        fileTransformer = new FileTransformer();
        fileTransformer.setName("fileTransformer");
        Map<String, String> featureMap = newHashMap();
        featureMap.put("http://xml.org/sax/features/namespaces", "false");
        fileTransformer.setFeatureMap(featureMap);
        Map<String, String> propertyMap = newHashMap();
        fileTransformer.setPropertyMap(propertyMap);

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.util.XPathAPI;
import org.codelibs.nekohtml.parsers.DOMParser;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.xml.sax.InputSource;

/**
 * Extracts text content from HTML documents.
 */
public class HtmlExtractor extends AbstractXmlExtractor {
    /** Logger for this class. */

import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.util.XPathAPI;
import org.codelibs.nekohtml.parsers.DOMParser;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.xml.sax.InputSource;

import com.google.common.cache.CacheBuilder;
import com.google.common.cache.CacheLoader;
import com.google.common.cache.LoadingCache;

import jakarta.annotation.Resource;

/**