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') {

            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);
                sb.deleteCharAt(i + 1);
            } else {

     *
     * @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) {
        if (c >= 'a' && c <= 'z' //
                || c >= 'A' && c <= 'Z' //
                || c >= '0' && c <= '9' //
                || c == '.' //
                || c == '-' //
                || c == '*' //

    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

                    || PRIORITY_ELEMENT.equals(qName)) {
                buf = new StringBuilder();
            }
        }

        @Override
        public void characters(final char[] ch, final int offset, final int length) {
            if (buf != null) {
                buf.append(new String(ch, offset, length));
            }
        }

        @Override

        final StringBuilder buf = new StringBuilder(100);
        boolean singleQuote = false;
        boolean doubleQuote = false;
        char prevChar = ' ';
        for (int i = 0; i < cmd.length(); i++) {
            final char c = cmd.charAt(i);
            if (c == ' ' && !singleQuote && !doubleQuote && buf.length() > 0) {
                cmdList.add(getCommandValue(buf.toString(), params));

            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;

        map.put("シュ", new String[] { "syu", "shu" });
        map.put("ショ", new String[] { "syo", "sho" });
        map.put("シェ", new String[] { "sye", "she" });

        map.put("チャ", new String[] { "tya", "cha" });
        map.put("チュ", new String[] { "tyu", "chu" });
        map.put("チョ", new String[] { "tyo", "cho" });
        map.put("チェ", new String[] { "tye", "che" });

        map.put("ニャ", new String[] { "nya" });

        if (!filePath.startsWith("file:")) {
            filePath = "file://" + filePath;
        }

        final StringBuilder buf = new StringBuilder(filePath.length() + 100);
        try {
            for (final char c : filePath.toCharArray()) {
                if (c == ' ') {
                    buf.append("%20");
                } else {
                    final String str = String.valueOf(c);

			<artifactId>tika-parser-audiovideo-module</artifactId>
			<version>${tika.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.tika</groupId>
			<artifactId>tika-parser-cad-module</artifactId>
			<version>${tika.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.tika</groupId>
			<artifactId>tika-parser-code-module</artifactId>
			<version>${tika.version}</version>