/**
     * Extracts text from file attachments in PDF annotations.
     * @param doc the PDF document
     * @param writer the writer to append extracted text to
     */
    protected void extractAnnotations(final PDDocument doc, final StringWriter writer) {
        for (final PDPage page : doc.getPages()) {
            try {
                for (final PDAnnotation annotation : page.getAnnotations()) {

			<artifactId>httpclient-cache</artifactId>
			<version>${httpcomponents.version}</version>
		</dependency>
		<dependency>
			<groupId>jakarta.annotation</groupId>
			<artifactId>jakarta.annotation-api</artifactId>
			<version>${jakarta.annotation.api.version}</version>
		</dependency>
		<dependency>
			<groupId>org.codelibs</groupId>
			<artifactId>nekohtml</artifactId>

      "Derivative Works" shall mean any work, whether in Source or Object
      form, that is based on (or derived from) the Work and for which the
      editorial revisions, annotations, elaborations, or other modifications
      represent, as a whole, an original work of authorship. For the purposes
      of this License, Derivative Works shall not include works that remain

      "Derivative Works" shall mean any work, whether in Source or Object
      form, that is based on (or derived from) the Work and for which the
      editorial revisions, annotations, elaborations, or other modifications
      represent, as a whole, an original work of authorship. For the purposes
      of this License, Derivative Works shall not include works that remain

import org.codelibs.core.lang.ClassUtil;
import org.codelibs.core.lang.FieldUtil;
import org.codelibs.core.lang.MethodUtil;

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

/**
 * A container implementation that manages the lifecycle and dependency injection of components

import org.opensearch.search.SearchHits;
import org.opensearch.search.sort.SortBuilders;
import org.opensearch.search.sort.SortOrder;

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

/**
 * OpenSearchUrlQueueService is an implementation of {@link UrlQueueService} for OpenSearch.
 *
 * @author shinsuke
 *
 */

import org.jodconverter.core.office.OfficeException;
import org.jodconverter.core.office.OfficeManager;
import org.jodconverter.local.LocalConverter;

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

/**
 * Extracts text content from various document formats using JODConverter.
 */
public class JodExtractor extends AbstractExtractor {
    /** Logger for this class. */

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.
 */
public class ApiExtractor extends AbstractExtractor {

import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
import org.codelibs.fess.crawler.helper.ContentLengthHelper;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;

import jakarta.annotation.Resource;
import org.codelibs.jcifs.smb1.Config;
import org.codelibs.jcifs.smb1.ACE;
import org.codelibs.jcifs.smb1.NtlmPasswordAuthentication;
import org.codelibs.jcifs.smb1.SID;

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;

/**
 * {@link HtmlXpathExtractor} is an implementation of the {@link org.codelibs.fess.crawler.extractor.Extractor} interface.
 * It uses XPath expressions to extract text content from HTML documents.
 * <p>