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.
     */

        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");

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.

        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));

                    TarExtractor tarExtractor = container.getComponent("tarExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                    factory.addExtractor("application/tar", tarExtractor);
                })//
        ;

import org.xml.sax.SAXNotSupportedException;
import org.xml.sax.helpers.DefaultHandler;

/**
 * Helper class for parsing and validating sitemaps.
 * It supports XML sitemaps, XML sitemap indexes, and text sitemaps,
 * and can handle GZIP compressed sitemaps.
 * The class provides methods to check if an input stream is a valid sitemap,
 * and to parse an input stream into a {@link SitemapSet} object.

        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);
    }

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

/**
 * Extracts text content from Microsoft PowerPoint documents.
 */
public class MsPowerPointExtractor extends AbstractExtractor {

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

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

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

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

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

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

     */
    public LhaExtractor() {
        super();
    }

    /**
     * Extracts text content from an LHA archive input stream.
     *
     * @param in the input stream containing the LHA archive
     * @param params extraction parameters
     * @return the extracted text data
     * @throws CrawlerSystemException if the input stream is null