import jakarta.annotation.Resource;

/**
 * Extracts text content from ZIP archives.
 */
public class ZipExtractor extends AbstractExtractor {
    private static final Logger logger = LogManager.getLogger(ZipExtractor.class);

    /**
     * The archive stream factory.
     */
    @Resource
    protected ArchiveStreamFactory archiveStreamFactory;

    /**

import jakarta.annotation.Resource;

/**
 * Extracts text content from TAR archives.
 */
public class TarExtractor extends AbstractExtractor {
    private static final Logger logger = LogManager.getLogger(TarExtractor.class);

    /**
     * The archive stream factory.
     */
    @Resource
    protected ArchiveStreamFactory archiveStreamFactory;

    /**
     * Maximum content size.

 *
 * @author shinsuke
 */
public abstract class PasswordBasedExtractor extends AbstractExtractor {

    /** Logger instance for this class. */
    private static final Logger logger = LogManager.getLogger(PasswordBasedExtractor.class);

    /** Map of regex patterns to passwords for static password configuration. */

import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */
public class TarExtractorTest extends PlainTestCase {
    private static final Logger logger = LogManager.getLogger(TarExtractorTest.class);

    public TarExtractor tarExtractor;

    @Override
    protected void setUp() throws Exception {
        super.setUp();

 *     System.out.println(document);
 * }
 *
 * reader.close(); // Close the reader to release resources
 * }
 * </pre>
 */
public class ESSourceReader implements DocumentReader {
    private static final Logger logger = LogManager.getLogger(ESSourceReader.class);

    /** Queue of documents. */
    protected final Queue<Map<String, Object>> queue = new ConcurrentLinkedQueue<>();
    /** Flag indicating if reading is finished. */

 * @see org.codelibs.fess.crawler.entity.AccessResultData
 * @see org.codelibs.core.lang.StringUtil
 */
public final class XmlUtil {

    private static final Logger logger = LogManager.getLogger(XmlUtil.class);

    private XmlUtil() {
    }

    /**
     * Escapes special characters in the given XML string to their corresponding

import jakarta.annotation.PreDestroy;

/**
 * Extracts text content from various document formats using JODConverter.
 */
public class JodExtractor extends AbstractExtractor {
    /** Logger for this class. */
    private static final Logger logger = LogManager.getLogger(JodExtractor.class);

    /** Office manager for document conversion. */
    protected OfficeManager officeManager;

    /** Temporary directory for file operations. */

 * and handles potential exceptions during parsing.
 * The class also includes inner classes for handling XML sitemap and sitemap index parsing.
 */
public class SitemapsHelper {
    private static final Logger logger = LogManager.getLogger(SitemapsHelper.class);

    /** The size of the preload buffer for checking file format. */
    protected int preloadSize = 512;

    /**
     * Creates a new SitemapsHelper instance.
     */

public class XpathTransformer extends HtmlTransformer {

    /**
     * Creates a new XpathTransformer instance.
     */
    public XpathTransformer() {
        super();
    }

    private static final Logger logger = LogManager.getLogger(XpathTransformer.class);

    private static final Pattern SPACE_PATTERN = Pattern.compile("\\s+", Pattern.MULTILINE);

    /**

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.FileUtil;

/**
 * A custom InputStream that wraps a temporary file. This class ensures that the temporary file
 * is deleted when the stream is closed.
 */
public class TemporaryFileInputStream extends InputStream {
    private static final Logger logger = LogManager.getLogger(TemporaryFileInputStream.class);