zipExtractor.setMaxContentSize(100);
            zipExtractor.getText(in, null);
            fail();
        } catch (MaxLengthExceededException e) {
            // pass
        }
        zipExtractor.setMaxContentSize(-1);
    }

    public void test_getText_null() {
        try {
            zipExtractor.getText(null, null);
            fail();
        } catch (final CrawlerSystemException e) {

 *
 */
public class MsWordExtractor extends AbstractExtractor {

    /*
     * (non-Javadoc)
     *
     * @see org.codelibs.fess.crawler.extractor.Extractor#getText(java.io.InputStream,
     * java.util.Map)
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }

public class MsExcelExtractor extends AbstractExtractor {
    /*
     * (non-Javadoc)
     *
     * @see
     * org.codelibs.fess.crawler.extractor.impl.Extractor#getText(java.io.InputStream,
     * java.util.Map)
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }

    }

    public void test_getText() throws IOException {
        try (final InputStream in = ResourceUtil.getResourceAsStream("extractor/eml/sample1.eml")) {
            ExtractData data = emlExtractor.getText(in, null);
            final String content = data.getContent();
            logger.info(content);
            assertTrue(content.contains("プレイステーション"));
            assertTrue(data.getValues("Subject")[0].contains("ダイジェスト"));

            lhaExtractor.setMaxContentSize(100);
            lhaExtractor.getText(in, null);
            fail();
        } catch (MaxLengthExceededException e) {
            // pass
        }
        lhaExtractor.setMaxContentSize(-1);
    }

    public void test_getText_null() {
        try {
            lhaExtractor.getText(null, null);
            fail();
        } catch (final CrawlerSystemException e) {

            @Override
            public ExtractData getText(InputStream in, Map<String, String> params) {
                return null;
            }
        });
        assertEquals(1, extractorFactory.getExtractor(key).getWeight());
        extractorFactory.addExtractor(key, new Extractor() {
            @Override
            public ExtractData getText(InputStream in, Map<String, String> params) {
                return null;

        extractor.command = getCommand(scriptFile);
        final Map<String, String> params = new HashMap<String, String>();
        final ExtractData text = extractor.getText(new FileInputStream(contentFile), params);
        assertEquals(content, text.getContent());
    }

    public void test_getText_withUrl() throws IOException {
        final File scriptFile = createScriptTempFile(3);

          if (last == UNSET) {
            // we need to update the root link from table[]
            table[tableIndex] = getNext(entries[next]);
          } else {
            // we need to update the link from the chain
            entries[last] = swapNext(entries[last], getNext(entries[next]));
          }

          moveLastEntry(next);
          size--;
          modCount++;
          return oldValue;

    }

    public void test_getHtml_utf8() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_utf8.html");
        final ExtractData data = htmlExtractor.getText(in, null);
        final String content = data.getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));

 */
public class MsPublisherExtractor extends AbstractExtractor {

    /*
     * (non-Javadoc)
     *
     * @see org.codelibs.fess.crawler.extractor.Extractor#getText(java.io.InputStream,
     * java.util.Map)
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }