public PatternConcatenationFilterFactory(final IndexSettings indexSettings, final Environment environment, final String name,
            final Settings settings) {
        super(indexSettings, name, settings);

        final String pattern1Str = settings.get("pattern1");
        final String pattern2Str = settings.get("pattern2", ".*");

        if (logger.isDebugEnabled()) {

public class KuromojiPartOfSpeechFilterFactory extends AbstractTokenFilterFactory {

    private final Set<String> stopTags = new HashSet<>();

    public KuromojiPartOfSpeechFilterFactory(IndexSettings indexSettings, Environment env, String name, Settings settings) {
        super(indexSettings, name, settings);
        List<String> wordList = Analysis.parseWordList(env, settings, "stoptags", s -> s);
        if (wordList != null) {

     * @return the detected content type
     */
    String getContentType(InputStream is, String filename);

    /**
     * Determines the content type of the given input stream using the provided parameters.
     * @param is the input stream to analyze
     * @param params the parameters containing additional information like filename
     * @return the detected content type
     */
    String getContentType(InputStream is, Map<String, String> params);

        // Default constructor
    }

    /**
     * Queue index name.
     */
    protected String queueIndex = ".crawler.queue";

    /**
     * Data index name.
     */
    protected String dataIndex = ".crawler.data";

    /**
     * Filter index name.
     */
    protected String filterIndex = ".crawler.filter";

    /**
     * Number of shards for the queue index.
     */

     * Normalizes the given text.
     * @param text The text to normalize
     * @param field The field name
     * @param langs The language
     * @return The normalized text
     */
    String normalize(String text, String field, String... langs);

    /**
     * Retrieves the location (URL) of the sitemap.
     *
     * @return the location of the sitemap as a String.
     */
    String getLoc();

    /**
     * Retrieves the last modification date of the sitemap.
     *
     * @return A string representing the last modification date.
     */
    String getLastmod();

         */
        @Override
        public void connect() throws IOException {
            final String endpoint = System.getenv().get("STORAGE_ENDPOINT");
            final String accessKey = System.getenv().get("STORAGE_ACCESS_KEY");
            final String secretKey = System.getenv().get("STORAGE_SECRET_KEY");
            final String region = System.getenv().get("STORAGE_SECRET_KEY");
            try {

     */
    protected void storeChildUrls(final CrawlerContext crawlerContext, final Set<RequestData> childUrlList, final String url,
            final int depth, final String encoding) {
        // add url and filter
        final Set<String> urlSet = new HashSet<>();
        final List<UrlQueue<?>> childList = childUrlList.stream()

                }
            }
        }

        return result;
    }

    @Override
    public SuggestWriterResult delete(final Client client, final SuggestSettings settings, final String index, final String id) {
        final SuggestWriterResult result = new SuggestWriterResult();
        try {
            client.prepareDelete().setIndex(index).setId(id).execute().actionGet(settings.getIndexTimeout());

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

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