final Session mailSession = Session.getDefaultInstance(props, null);
            final MimeMessage message = new MimeMessage(mailSession, in);
            final String content = getBodyText(message);
            final ExtractData data = new ExtractData(content != null ? content : StringUtil.EMPTY);
            final Enumeration<Header> headers = message.getAllHeaders();
            while (headers.hasMoreElements()) {

        if (count <= 0) {
            return;
        }

        final String content = getHtmlContent(count);

        final File indexFile = new File(dir, "index.html");
        indexFile.deleteOnExit();
        FileUtil.writeBytes(indexFile.getAbsolutePath(), content.getBytes("UTF-8"));

        for (int i = 1; i <= 10; i++) {

        assertEquals("http://hoge.com/http/fuga.html", urlConvertHelper.convert(url));

        url = "tp://hoge.com/http/fuga.html";
        assertEquals("tp://hoge.com/http/fuga.html", urlConvertHelper.convert(url));

        urlConvertHelper.add("^tp:", "http:");

        url = "http://hoge.com/http/fuga.html";
        assertEquals("http://hoge.com/http/fuga.html", urlConvertHelper.convert(url));

        url = "tp://hoge.com/http/fuga.html";

                byte[] bytes = is.readAllBytes();
                String content = new String(bytes);
                for (Map.Entry<String, String> rule : transformationRules.entrySet()) {
                    content = content.replaceAll(rule.getKey(), rule.getValue());
                }
                resultData.setData(content.getBytes());
            } catch (Exception e) {
                throw new RuntimeException(e);

        final InputStream in = ResourceUtil.getResourceAsStream("extractor/lha/test.lzh");
        final String content = lhaExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
        assertTrue(content.contains("テキスト"));
    }

    public void test_getText_maxSize() throws IOException {

    private static final Logger logger = LogManager.getLogger(StorageClient.class);

    /**
     * The character encoding to use for content. Defaults to UTF-8.
     */
    protected String charset = Constants.UTF_8;

    /**
     * Helper for managing content length validation and limits.
     */
    @Resource
    protected ContentLengthHelper contentLengthHelper;

    /**

    }

    public void test_getText() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test.txt");
        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);

    /**
     * Returns the content length of the accessed resource.
     *
     * @return the content length
     */
    Long getContentLength();

    /**
     * Sets the content length of the accessed resource.
     *
     * @param contentLength the content length
     */
    void setContentLength(Long contentLength);

    /**

        params.put(ExtractData.RESOURCE_NAME_KEY, getResourceName(responseData));
        params.put(ExtractData.CONTENT_TYPE, responseData.getMimeType());
        String content = null;
        try (final InputStream in = responseData.getResponseBody()) {
            content = extractor.getText(in, params).getContent();
        } catch (final Exception e) {
            throw new CrawlingAccessException("Could not extract data.", e);
        }

        final ExtractData extractData = pdfExtractor.getText(in, null);
        final String content = extractData.getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
        assertEquals("Writer", extractData.getValues("Creator")[0]);
        assertEquals("OpenOffice.org 3.0", extractData.getValues("Producer")[0]);