* @return the detected delimiter character
     */
    protected Character detectDelimiter(final String line) {
        final char[] candidates = { ',', '\t', ';', '|' };
        int maxCount = 0;
        char bestDelimiter = ',';

        for (final char candidate : candidates) {
            final int count = countOccurrences(line, candidate);
            if (count > maxCount) {

        if (initialCapacity > 0 && initialCapacity <= MAX_BUF_SIZE) {
            bufferSize = initialCapacity;
        } else {
            bufferSize = DEFAULT_BUF_SIZE;
        }
        char[] buf = new char[bufferSize];
        int size = 0;
        int len;
        try {
            while ((len = reader.read(buf, size, bufferSize - size)) != -1) {
                size += len;

        String input = "Test" + String.valueOf((char) 0x0020) // space
                + String.valueOf((char) 0x0009) // tab
                + String.valueOf((char) 0x000A) // line feed
                + String.valueOf((char) 0x000D) // carriage return
                + String.valueOf((char) 0xD7FF) + String.valueOf((char) 0xE000) + String.valueOf((char) 0xFFFD);
        String result = XmlUtil.stripInvalidXMLCharacters(input);

    public void testNewStringUnsafe() {
        assertNull(StringUtil.newStringUnsafe(null));
        char[] chars = new char[0];
        assertThat(StringUtil.newStringUnsafe(chars), is(""));
        chars = new char[] { 'a', 'b', 'c' };
        assertThat(StringUtil.newStringUnsafe(chars), is("abc"));
        chars = new char[] { 'a', 'b', 'c', ' ' };
        assertThat(StringUtil.newStringUnsafe(chars), is("abc "));
    }

    private static boolean isAsciiPrintable(final char ch) {
        return ch >= 32 && ch < 127;
    }

    /**
     * Creates a new String from a char array.
     * <p>
     * Note: This method no longer uses internal JDK APIs for safety and compatibility.
     * It now uses the standard String constructor.
     * </p>
     *
     * @param chars
     *            the char array

        }

        // normalize
        final StringBuilder buf = new StringBuilder(1000);
        for (int i = 0; i < configPath.length(); i++) {
            final char c = configPath.charAt(i);
            if (c == '\\') {
                buf.append('/');
            } else if (c == ' ') {
                buf.append("%20");
            } else if (CharUtil.isUrlChar(c)) {

     *
     * @param c the character to check
     * @return {@code true} if the character is a valid URL character, {@code false} otherwise
     */
    public static boolean isUrlChar(final char c) {
        return (c >= 'a' && c <= 'z') //
                || (c >= 'A' && c <= 'Z') //
                || (c >= '0' && c <= '9') //
                || c == '.' || c == '-' || c == '*' || c == '_' //

            final StringBuilder regex = new StringBuilder();
            regex.append("^"); // Match from the start

            for (int i = 0; i < pattern.length(); i++) {
                final char c = pattern.charAt(i);
                if (c == '*') {
                    // Wildcard: matches any sequence of characters
                    regex.append(".*");
                } else if (c == '$') {

    /** Logger instance for this class */
    private static final Logger logger = LogManager.getLogger(PopularWordHelper.class);

    /** Character used to separate cache key components */
    protected static final char CACHE_KEY_SPLITTER = '\n';

    /** Cache for storing popular word lists */
    protected Cache<String, List<String>> cache;

    /** Fess configuration instance */
    protected FessConfig fessConfig;

    /**

    public static String stripInvalidXMLCharacters(final String in) {
        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)