}

    public void test_getText_mswordx() {
        InputStream in = ResourceUtil.getResourceAsStream("extractor/msoffice/test.docx");
        Map<String, String> params = new HashMap<String, String>();
        params.put("resourceName", "test.docx");
        ExtractData extractData = jodExtractor.getText(in, params);
        String content = extractData.getContent();
        CloseableUtil.closeQuietly(in);

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

/**
 * Robots.txt Specifications:
 * <ul>
 * <li><a href=
 * "https://developers.google.com/webmasters/control-crawl-index/docs/robots_txt"
 * >https://developers.google.com/webmasters/control-crawl-index/docs/robots_txt
 * </a></li>
 * </ul>
 *
 * @author bowez
 * @author shinsuke
 *
 */
public class RobotsTxtHelper {

    /** Pattern for parsing user-agent records. */

import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

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

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

        msWordExtractor = container.getComponent("msWordExtractor");
    }

    public void test_getText() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/msoffice/test.doc");
        final String content = msWordExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }