// public ResponseData call() throws Exception {
    // String[] urls =
    // new String[] {
    // "http://.../",
    // "http://.../test.pdf",
    // "http://.../test.doc",
    // "http://.../test.xls",
    // "http://.../test.ppt",
    // "http://.../test.txt", };
    // for (String url : urls) {
    // ResponseData responseData = httpClient.doGet(url);

    private char replacement;

    public ProlongedSoundMarkCharFilterFactory(final IndexSettings indexSettings, final Environment env, final String name,
            final Settings settings) {
        super(indexSettings, name);
        final String value = settings.get("replacement");
        if (value == null || value.length() == 0) {
            replacement = '\u30fc';
        } else {

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

     */
    @Override
    public int hashCode() {
        return java.util.Objects.hash(loc, lastmod);
    }

    /**
     * Returns a string representation of this SitemapFile.
     * @return A string representation.
     */
    @Override
    public String toString() {
        return "SitemapFile [loc=" + loc + ", lastmod=" + lastmod + "]";
    }

     * @param field the field associated with the text
     * @param lang the language of the text
     * @return a list of analyzed tokens
     */
    List<AnalyzeToken> analyze(String text, String field, String lang);

    /**
     * Analyzes the given text and returns a list of tokens along with their readings.
     *
     * @param text the text to analyze
     * @param field the field associated with the text

 * SuggestSettings settings = // Obtain SuggestSettings
 * String indexName = "your_index_name";
 *
 * ESSourceReader reader = new ESSourceReader(client, settings, indexName);
 * reader.setScrollSize(1000); // Set the scroll size
 * reader.setLimitOfDocumentSize(1024 * 1024); // Limit document size to 1MB
 * reader.setQuery(QueryBuilders.termQuery("field", "value")); // Set a query
 *
 * Map<String, Object> document;

        // Test convert with empty language array
        String text = "test text";
        String field = "content";
        String[] langs = new String[0];

        List<String> results = converter.convert(text, field, langs);

        assertNotNull(results);
        // Results may vary based on analyzer configuration
    }

    @Test
    public void testConvertWithSingleLanguage() throws IOException {

     */
    void init(String sessionId);

    /**
     * Check if a given url is a target.
     *
     * @param url URL
     * @return true if url is matched
     */
    boolean match(String url);

    /**
     * Add an url pattern as a target.
     *
     * @param urlPattern Regular expression that is crawled
     */
    void addInclude(String urlPattern);

    /**

                }
                final String filename = entry.getName();
                final String mimeType = mimeTypeHelper.getContentType(null, filename);
                if (mimeType != null) {
                    final Extractor extractor = extractorFactory.getExtractor(mimeType);
                    if (extractor != null) {
                        try {
                            final Map<String, String> map = new HashMap<>();

     */
    protected void parseTokenPage(final String tokenPattern, final List<Pair<String, String>> responseParams, final HttpEntity entity) {
        try {
            final String tokenName = getParameter(TOKEN_NAME);
            final String content = new String(InputStreamUtil.getBytes(entity.getContent()), Constants.UTF_8_CHARSET);
            final String tokenValue = getTokenValue(tokenPattern, content);