final String content = textExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

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

    /**
     * Extracts text from the Excel input stream.
     * @param in The input stream.
     * @param params The parameters.
     * @return The extracted data.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        validateInputStream(in);
        try (final HSSFWorkbook workbook = new HSSFWorkbook(in);

     * @return The extracted data.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        validateInputStream(in);
        try (final org.apache.poi.hwpf.extractor.WordExtractor wordExtractor = new org.apache.poi.hwpf.extractor.WordExtractor(in)) {
            return new ExtractData(wordExtractor.getText());
        } catch (final IOException e) {

    /**
     * Extracts text from the Publisher input stream.
     * @param in The input stream.
     * @param params The parameters.
     * @return The extracted data.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        if (in == null) {
            throw new CrawlerSystemException("Microsoft Publisher input stream is null. Cannot extract text from null input.");
        }

        final String content = msWordExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

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

        final String content = pdfExtractorForPdfPassword.getText(in, params).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

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

        assertEquals(0L, controller.getDelayMillisBeforeProcessing());
        assertEquals(1000L, controller.getDelayMillisForWaitingNewUrl());
    }

    /**
     * Test setters
     */
    public void test_setters() {
        final DefaultIntervalController controller = new DefaultIntervalController();

        controller.setDelayMillisAfterProcessing(111L);

        }
        return new Extractor() {
            @Override
            public ExtractData getText(final InputStream in, final Map<String, String> params) {
                for (final Extractor extractor : extractors) {
                    try {
                        return extractor.getText(in, params);
                    } catch (final UnsupportedExtractException e) {

        final Map<String, String> params = new HashMap<String, String>();
        //final ExtractData text = extractor.getText(new ByteArrayInputStream(FileUtils.readFileToByteArray(new File(filePath))), params);
        final ExtractData text = extractor.getText(new ByteArrayInputStream(testStr.getBytes()), params);
        assertEquals(content, text.getContent());
    }

    // TODO other tests

 * Provides common functionality and properties for crawler rules.
 *
 * <p>
 * This class handles the registration of rules with the {@link RuleManager}
 * and provides getter and setter methods for common properties such as
 * {@code ruleId} and {@code responseProcessor}.
 * </p>
 *
 * <p>
 * Subclasses should extend this class and implement the abstract methods