}
        final StringBuilder sb = new StringBuilder(s);
        int i;
        for (i = 0; i < sb.length() - 1; i++) {
            final char originalChar1 = sb.charAt(i);
            final char originalChar2 = sb.charAt(i + 1);
            final char margedChar = mergeChar(originalChar1, originalChar2);
            if (margedChar != originalChar1) {
                sb.setCharAt(i, margedChar);

        final char[] chars = new char[text.length()];
        for (int i = 0; i < chars.length; i++) {
            final char c = text.charAt(i);
            if (c >= 'ａ' && c <= 'ｚ') {
                chars[i] = (char) (c - 'ａ' + 'a');
            } else if (c >= 'Ａ' && c <= 'Ｚ') {
                chars[i] = (char) (c - 'Ａ' + 'A');
            } else if (c >= '１' && c <= '０') {

        if (value == null || value.length() == 0) {
            replacement = '\u30fc';
        } else {
            replacement = value.charAt(0);
        }
    }

    @Override
    public Reader create(final Reader tokenStream) {
        return new ProlongedSoundMarkCharFilter(tokenStream, replacement);
    }

        if (StringUtil.isEmpty(in)) {
            return in;
        }

        final StringBuilder buf = new StringBuilder(in.length());
        char c;
        for (int i = 0; i < in.length(); i++) {
            c = in.charAt(i);
            if (c == 0x9 || c == 0xA || c == 0xD || c >= 0x20 && c <= 0xD7FF || c >= 0xE000 && c <= 0xFFFD
                    || c >= 0x10000 && c <= 0x10FFFF) {

            return filename;
        }
        final StringBuilder buf = new StringBuilder(filename.length() + 10);
        for (int i = 0; i < filename.length(); i++) {
            final char c = filename.charAt(i);
            switch (c) {
            case '?':
                buf.append("%3f");
                break;
            case '#':
                buf.append("%23");
                break;

    }

    private static boolean isLastSpaceChar(final StringBuilder buf) {
        if (buf.length() == 0) {
            return false;
        }
        return buf.charAt(buf.length() - 1) == ' ';
    }

    private static boolean removeLastDuplication(final StringBuilder buf, final int size, final boolean isSpace,
            final Set<String> termCache) {

         * @param charset The charset to use for reading.
         * @param maxOutputLineBuffer The maximum number of lines to buffer.
         */
        public InputStreamThread(final InputStream is, final String charset, final int maxOutputLineBuffer) {
            try {
                br = new BufferedReader(new InputStreamReader(is, charset));
            } catch (final UnsupportedEncodingException e) {

        String text = "Test123 ABC-456";
        String field = "content";
        String lang = "en";

        List<AnalyzeToken> tokens = analyzer.analyzeAndReading(text, field, lang);

        assertNotNull(tokens);
        assertEquals(2, tokens.size()); // "Test123" and "ABC-456" (hyphen is not a split char in our tokenizer)

        if (matchWordFirst && !hiraganaQuery && singleWordQuery && text.contains(query)) {
            if (query.length() == 1) {
                return UnicodeBlock.of(query.charAt(0)) != UnicodeBlock.HIRAGANA;
            }
            return true;
        }
        return false;
    }

    /**
     * Checks if the query is a hiragana query.

     */
    protected String convertRobotsTxtPatternToRegex(final String path) {
        String newPath = path.replace(".", "\\.").replace("?", "\\?").replace("*", ".*");
        if (newPath.charAt(0) != '/') {
            newPath = ".*" + newPath;
        }
        if (!newPath.endsWith("$") && !newPath.endsWith(".*")) {
            newPath = newPath + ".*";
        }