fieldRuleMap.put("url", "//address/item/access[@kind='url']");
            fieldRuleMap.put("tel", "//address/item/access[@kind='tel']");
            xmlTransformer.setFieldRuleMap(fieldRuleMap);
            xmlTransformer.init();
        }
        {
            xmlNsTransformer = new XmlTransformer();
            xmlNsTransformer.setName("xmlNsTransformer");
            xmlNsTransformer.setNamespaceAware(true);

    public SmbClient() {
        super();
    }

    @Override
    public synchronized void init() {
        if (smbAuthenticationHolder != null) {
            return;
        }

        if (logger.isDebugEnabled()) {
            logger.debug("Initializing SmbClient...");
        }

        super.init();

        // smb auth
        final SmbAuthenticationHolder holder = new SmbAuthenticationHolder();

     *
     * @return the maximum number of readings, default is 10.
     */
    default int getMaxReadingNum() {
        return 10;
    }

    /**
     * Initializes the converter.
     *
     * @throws IOException if an I/O error occurs during initialization.
     */
    void init() throws IOException;

    /**

        /*
         * TODO ReadingConverterChain chain = new ReadingConverterChain(); chain.addConverter(new KatakanaConverter());
         * chain.addConverter(new KatakanaToAlphabetConverter()); chain.init();
         *
         * List<String> list = chain.convert("検索"); assertTrue(list.contains("ケンサク"));
         * assertTrue(list.contains("kennsaku"));
         */
    }

            getUrlFilterService().delete(sessionId);
        }
    }

    /*
     * (non-Javadoc)
     *
     * @see org.codelibs.fess.crawler.filter.UrlFilter#init(java.lang.String)
     */
    @Override
    public void init(final String sessionId) {
        this.sessionId = sessionId;
        if (!cachedIncludeSet.isEmpty()) {
            try {

            final CrawlerContext crawlerContext = new CrawlerContext();
            final String sessionId = "id1";
            urlFilter.init(sessionId);
            crawlerContext.setUrlFilter(urlFilter);
            CrawlingParameterUtil.setCrawlerContext(crawlerContext);
            httpClient.init();
            httpClient.processRobotsTxt(url);
            assertEquals(1, crawlerContext.getRobotsTxtUrlSet().size());

 *
 * @author shinsuke
 *
 */
public interface UrlFilter {

    /**
     * Initialize a url filter by sessionId.
     *
     * @param sessionId Session ID
     */
    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);

    /**

    * @see org.codelibs.fess.crawler.client.AbstractCrawlerClient#init()
    */
    @Override
    public synchronized void init() {
        if (smbAuthenticationHolder != null) {
            return;
        }

        if (logger.isDebugEnabled()) {
            logger.debug("Initializing SmbClient...");
        }

        super.init();

        final Properties props = new Properties();

    }

    /**
     * Retrieves a setting value as an int.
     * @param key The key of the setting.
     * @param defaultValue The default value if the setting is not found.
     * @return The setting value as an int.
     */
    public int getAsInt(final String key, final int defaultValue) {
        final Object obj = get(key);

        final int value;
        if (obj == null) {
            value = defaultValue;

        StandardCrawlerContainer container = new StandardCrawlerContainer().singleton("htmlXpathExtractor", HtmlXpathExtractor.class);
        htmlXpathExtractor = container.getComponent("htmlXpathExtractor");
        htmlXpathExtractor.init();
    }

    public void test_getHtml_utf8() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_utf8.html");
        final String content = htmlXpathExtractor.getText(in, null).getContent();