* @param readlimit the maximum limit of bytes that can be read before the mark position becomes invalid
     */
    @Override
    public synchronized void mark(final int readlimit) {
        inputStream.mark(readlimit);
    }

    /**
     * Tests if this input stream supports the mark and reset methods.
     *
     * @return true if this stream instance supports the mark and reset methods; false otherwise
     */
    @Override

     * This method delegates to {@link FileInputStream#mark(int)}.
     *
     * @param readlimit the maximum limit of bytes that can be read before the mark position becomes invalid
     */
    @Override
    public synchronized void mark(final int readlimit) {
        fileInputStream.mark(readlimit);
    }

    /**
     * Tests if this input stream supports the mark and reset methods.

    /**
     * Logger for this class.
     */
    protected static final Logger logger = LogManager.getLogger(AbstractXmlExtractor.class);

    /**
     * UTF-7 Byte Order Mark definition.
     */
    protected static final ByteOrderMark BOM_UTF_7 = new ByteOrderMark("UTF-7", 0x2B, 0x2F, 0x76);

    /**
     * HTML4 unescape translator.
     */

     * Gets the replacement string for question marks in URLs.
     *
     * @return the question mark replacement string
     */
    public String getQuestionStr() {
        return questionStr;
    }

    /**
     * Sets the replacement string for question marks in URLs.
     *
     * @param questionStr the question mark replacement string to set
     */
    public void setQuestionStr(final String questionStr) {

 * the ICUNormalizer instance.</p>
 *
 * <p>Example usage:</p>
 * <pre>
 * ICUNormalizer normalizer = new ICUNormalizer("Any-Latin; NFD; [:Nonspacing Mark:] Remove; NFC");
 * String normalizedText = normalizer.normalize("text to normalize", "field");
 * </pre>
 *
 * @see com.ibm.icu.text.Transliterator
 */
public class ICUNormalizer implements Normalizer {

     */
    protected boolean isValid(final InputStream in, final boolean recursive) {
        final BufferedInputStream bis = new BufferedInputStream(in);
        bis.mark(preloadSize);

        final byte[] bytes = new byte[preloadSize];
        try {
            if (bis.read(bytes) == -1) {
                return false;
            }

        }

        final File tempFile;
        final boolean isByteStream = inputStream instanceof ByteArrayInputStream;
        if (isByteStream) {
            inputStream.mark(0); // ByteArrayInputStream
            tempFile = null;
        } else {
            tempFile = createTempFile("tikaExtractor-", ".out", null);
        }

        try {

        // Test escaping asterisk
        String query1 = "test*query";
        String escaped1 = SuggestUtil.escapeWildcardQuery(query1);
        assertEquals("test\\*query", escaped1);

        // Test escaping question mark
        String query2 = "test?query";
        String escaped2 = SuggestUtil.escapeWildcardQuery(query2);
        assertEquals("test\\?query", escaped2);

        // Test escaping both

    <tika:uti>com.adobe.pdf</tika:uti>
    <magic priority="50">
      <!-- Normally just %PDF- -->
      <match value="%PDF-" type="string" offset="0"/>
      <!-- Sometimes has a UTF-8 Byte Order Mark first -->
      <match value="\xef\xbb\xbf%PDF-" type="string" offset="0"/>
    </magic>
    <magic priority="40">
      <!-- Higher priority than matlab's priority=20 %% match