*/
    protected final List<String> readings;

    /**
     * The list of fields associated with the elevate word.
     */
    protected final List<String> fields;

    /**
     * The list of tags associated with the elevate word.
     */
    protected final List<String> tags;

    /**
     * The list of roles associated with the elevate word.
     */

				"application/vnd.ms-wmdrm.lic-resp",
				"application/vnd.ms-wmdrm.meter-chlg-req",
				"application/vnd.ms-wmdrm.meter-resp",
				"application/vnd.ms-word.document.macroenabled.12",
				"application/vnd.ms-word.template.macroenabled.12",
				"application/vnd.ms-works",
				"application/vnd.ms-wpl",
				"application/vnd.ms-xpsdocument",
				"application/vnd.mseq",
				"application/vnd.msign",

    <alias type="application/vnd.ms-word"/>
    <_comment>Microsoft Word Document</_comment>
    <tika:link>http://en.wikipedia.org/wiki/.doc</tika:link>
    <tika:uti>com.microsoft.word.doc</tika:uti>
    <magic priority="50">
      <match value="Microsoft\ Word\ 6.0\ Document" type="string" offset="2080"/>
      <match value="Documento\ Microsoft\ Word\ 6" type="string" offset="2080"/>

public class MsWordExtractor extends AbstractExtractor {

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

    /**
     * Extracts text from the Word input stream.
     * @param in The input stream.
     * @param params The parameters.
     * @return The extracted data.
     */
    @Override

- **FTP**: FTP server crawling with authentication
- **SMB/CIFS**: Windows network shares
- **Storage**: Cloud storage systems (MinIO, S3-compatible)

### Content Formats

#### Office Documents
- Microsoft Office (Word, Excel, PowerPoint)
- OpenOffice/LibreOffice documents
- RTF, WordPerfect

#### PDFs and Images
- PDF documents (text and metadata extraction)
- Images (JPEG, PNG, GIF, TIFF, BMP)

 *
 * <p>This class provides methods to initialize settings, get and set individual settings,
 * and manage various types of settings such as array settings, analyzer settings, bad word settings,
 * and elevate word settings.</p>
 *
 * <p>It also includes a nested TimeoutSettings class to manage various timeout configurations.</p>
 *
 * <p>Usage example:</p>
 * <pre>
 * {@code
 * Client client = ...;

        assertEquals("こめんと", extractData.getValues("w:Comments")[0]);
        assertEquals("たぐ|さぶたいとる", String.join("|", extractData.getValues("dc:subject")));
        assertEquals("Microsoft Office Word", extractData.getValues("extended-properties:Application")[0]);
        assertEquals("sugaya", extractData.getValues("meta:last-author")[0]);
        assertEquals("太郎", extractData.getValues("dc:creator")[0]);

        // Test convert with long text
        converter.init();
        StringBuilder sb = new StringBuilder();
        for (int i = 0; i < 1000; i++) {
            sb.append("word").append(i).append(" ");
        }
        String text = sb.toString();
        String field = "content";

        List<String> readings = converter.convert(text, field, "en");

        assertNotNull(readings);

        // Test empty query
        String[] emptyKeywords = SuggestUtil.parseQuery("", field);
        assertNotNull(emptyKeywords);
        assertEquals(0, emptyKeywords.length);

        // Test single word query
        String[] singleKeyword = SuggestUtil.parseQuery("single", field);
        assertNotNull(singleKeyword);
        assertEquals(1, singleKeyword.length);
        assertEquals("single", singleKeyword[0]);
    }

        pdfExtractor = container.getComponent("pdfExtractor");
        pdfExtractorForPdfPassword = container.getComponent("pdfExtractorForPdfPassword");
        pdfExtractorForPdfPassword.addPassword(".*test_.*.pdf", "word");
    }

    public void test_getText() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test.pdf");
        final ExtractData extractData = pdfExtractor.getText(in, null);