firstLineInnerMap.put("_index", index);
        firstLineInnerMap.put("_type", type);
        firstLineInnerMap.put("_id", item.getId());
        firstLineMap.put("index", firstLineInnerMap);

        final Map<String, Object> secondLine = new HashMap<>();

        secondLine.put("text", item.getText());

        // reading
        final String[][] readings = item.getReadings();

    /**
     * This class is a parser that detects the document type.
     */
    protected class TikaDetectParser extends CompositeParser {
        private static final long serialVersionUID = 1L;

        /**
         * The type detector used by this parser to auto-detect the type of a
         * document.
         */

 * The builder allows setting parameters such as MIME type, filename, extractor name, maximum content length,
 * and cache file size to optimize the extraction process.
 *
 * <p>
 * The main purpose of this class is to simplify the extraction process by providing a fluent interface
 * for configuring the extraction parameters and handling the underlying complexities of content processing,

        if (logger.isDebugEnabled()) {
            logger.debug("SID:{}", sid);
        }
        final int type = sid.getType();
        sidSet.add(sid);
        if (type == SID.SID_TYPE_DOM_GRP || type == SID.SID_TYPE_ALIAS) {
            try {
                final SID[] children = sid.getGroupMemberSids(file.getServer(), (NtlmPasswordAuthentication) file.getPrincipal(),

    /**
     * Get values from array index.
     * @param index Index
     * @param type Type
     * @param key Key
     * @return Values
     */
    @SuppressWarnings("unchecked")
    protected Map<String, Object>[] getFromArrayIndex(final String index, final String type, final String key) {
        final String actualIndex = index + "." + type.toLowerCase(Locale.ENGLISH);
        try {

                .put("analysis.analyzer.test_reading_analyzer.type", "custom")
                .put("analysis.analyzer.test_reading_analyzer.tokenizer", "standard")
                .put("analysis.analyzer.test_reading_term_analyzer.type", "custom")
                .put("analysis.analyzer.test_reading_term_analyzer.tokenizer", "standard")
                .put("analysis.analyzer.test_reading_analyzer_ja.type", "custom")

                namespace = "http://www.w3.org/XML/1998/namespace";
            } else {
                int type;
                while (null != parent && null == namespace
                        && ((type = parent.getNodeType()) == Node.ELEMENT_NODE || type == Node.ENTITY_REFERENCE_NODE)) {
                    if (type == Node.ELEMENT_NODE) {
                        if (parent.getNodeName().indexOf(prefix + ":") == 0) {

    }

    /**
     * Gets the MIME type of the response.
     *
     * @return the MIME type, or null if not specified
     */
    public String getMimeType() {
        return mimeType;
    }

    /**
     * Sets the MIME type of the response.
     *
     * @param contentType the MIME type to set
     */
    public void setMimeType(final String contentType) {

    }

    public void test_getTika_text_sjis() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_sjis.txt");
        Map<String, String> params = new HashMap<>();
        params.put("Content-Type", "text/plain");
        final ExtractData extractData = tikaExtractor.getText(in, params);
        final String content = extractData.getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);

        if (logger.isDebugEnabled()) {
            logger.debug("SID:{}", sid);
        }
        final int type = sid.getType();
        sidSet.add(sid);
        if (type == SID.SID_TYPE_DOM_GRP || type == SID.SID_TYPE_ALIAS) {
            try {
                final CIFSContext context = file.getContext();
                final SID[] children = context.getSIDResolver()