* The {@link TikaExtractor} class is responsible for extracting text content and metadata from various file formats
 * using the Apache Tika library. It extends {@link PasswordBasedExtractor} to handle password-protected files.
 * </p>
 *
 * <p>
 * This class provides methods to extract text from an input stream, handling different scenarios such as:
 * </p>
 * <ul>
 *   <li>Normalizing text content</li>

<map version="0.7.1">
<node TEXT="&#12479;&#12452;&#12488;&#12523;">
<node TEXT="&#12486;&#12473;&#12488;" MODIFIED="1237874353965" STYLE="fork"/>
</node>

        assertNotNull(accessResult2);

        accessResult2.setMimeType("text/html");
        dataService.update(accessResult2);

        final AccessResult accessResult3 = dataService.getAccessResult("id1", "http://www.id1.com/");
        assertNotNull(accessResult3);
        assertEquals("text/html", accessResult3.getMimeType());

        dataService.delete("id1");

            return keywords;
        }
        for (final TermQuery tq : termQueryList) {
            final String text = tq.getTerm().text();
            if (0 == text.length() || keywords.contains(text)) {
                continue;
            }
            keywords.add(text);
        }
        return keywords;
    }

    /**

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. */

        assertNotNull(responseData.getLastModified());
        assertEquals(Constants.GET_METHOD, responseData.getMethod());
        assertEquals("text/plain", responseData.getMimeType());
        assertTrue(responseData.getUrl().endsWith("test/text%203.txt"));
        final String content = new String(InputStreamUtil.getBytes(responseData.getResponseBody()), "UTF-8");
        assertEquals("test3\n", content);
    }

        return new ExtractData(getTextInternal(in, mimeTypeHelper, extractorFactory));
    }

    /**
     * Returns a text from the input stream.
     *
     * @param in The input stream.
     * @param mimeTypeHelper The mime type helper.
     * @param extractorFactory The extractor factory.
     * @return A text.
     */

        rule.addCondition("mimeType", "text/.*");

        ResponseData responseData1 = new ResponseData();
        responseData1.setMimeType("text/html");
        assertTrue(rule.match(responseData1));

        ResponseData responseData2 = new ResponseData();
        responseData2.setMimeType("text/plain");
        assertTrue(rule.match(responseData2));

    public static final String USER_DICT_ENCODING = "fess.user.dict.encoding";

    /** The system property name for user dictionary path. */
    public static final String USER_DICT_PATH = "fess.user.dict.path";

    /** The text separator. */
    public static final String TEXT_SEPARATOR = " ";

    /** The default role for guest users. */
    public static final String DEFAULT_ROLE = "_guest_";

    /** The default document type. */

import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Gets a text from . file.
 *
 * @author shinsuke
 *
 */
public class MsPublisherExtractor extends AbstractExtractor {

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

    /**
     * Extracts text from the Publisher input stream.
     * @param in The input stream.