throw new ExtractException(e);
            }
        }

        return encoding;
    }

    /**
     * Extracts text content from the given content by removing tags and processing attributes.
     * @param content The content to extract from.
     * @return The extracted text.
     */
    protected String extractString(final String content) {
        String input = content.replaceAll("[\\r\\n]", " ");

     * @return The extracted data.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        validateInputStream(in);
        try (final HSLFSlideShow slideShow = new HSLFSlideShow(in);
                final SlideShowExtractor<HSLFShape, HSLFTextParagraph> extractor = new SlideShowExtractor<>(slideShow)) {
            return new ExtractData(extractor.getText());

    @Test
    @DisplayName("readSecurityBuffer correctly extracts data")
    void testReadSecurityBuffer() {
        byte[] buf = new byte[8 + 4];
        byte[] payload = { 0x11, 0x22, 0x33, 0x44 };
        NtlmMessage.writeSecurityBuffer(buf, 0, 8, payload);
        byte[] extracted = NtlmMessage.readSecurityBuffer(buf, 0);
        assertArrayEquals(payload, extracted, "Payload should match original");
    }

    @Test

            dfos = out;
            CopyUtil.copy(in, out);
            out.flush();

            Extractor extractor = StringUtil.isBlank(mimeType) ? null : extractorFactory.getExtractor(mimeType);
            if (extractor == null) {
                final String detectedMimeType = getMimeType(out);
                extractor = extractorFactory.getExtractor(detectedMimeType);

                final org.apache.poi.hssf.extractor.ExcelExtractor excelExtractor =
                        new org.apache.poi.hssf.extractor.ExcelExtractor(workbook)) {
            return new ExtractData(excelExtractor.getText());
        } catch (final IOException e) {
            throw new ExtractException("Failed to extract text from Excel document.", e);
        }
    }

        super();
    }

    /**
     * Extracts text from the Word input stream.
     * @param in The input stream.
     * @param params The parameters.
     * @return The extracted data.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        validateInputStream(in);

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

    /**
     * Extracts text from the Visio input stream.
     * @param in The input stream.
     * @param params The parameters.
     * @return The extracted data.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        if (in == null) {

    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) {

 * Negotiation Protocol) authentication. It contains the username extracted from the
 * SPNEGO authentication process, typically from a Kerberos ticket.
 */
public class SpnegoCredential implements LoginCredential, FessCredential {

    /** The username extracted from SPNEGO authentication. */
    private final String username;

    /**

import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
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.util.IgnoreCloseInputStream;

import jakarta.annotation.Resource;

/**
 * Extracts text content from ZIP archives.
 */
public class ZipExtractor extends AbstractExtractor {