return readingList;
    }

    /**
     * Converts the input string to Katakana.
     * @param inputStr The input string.
     * @return The Katakana representation of the input string.
     * @throws IOException If an I/O error occurs.
     */
    protected String toKatakana(final String inputStr) throws IOException {
        final StringBuilder kanaBuf = new StringBuilder();

import java.util.Map;

/**
 * MimeTypeHelper provides methods to determine the content type of a given input stream or file.
 * It allows content type detection based on the stream's content and/or filename.
 */
public interface MimeTypeHelper {
    /**
     * Determines the content type of the given input stream and filename.
     * @param is the input stream to analyze
     * @param filename the filename to help determine the content type

        String tokenPattern = "name=\"authenticity_token\" +value=\"([^\"]+)\"";
        String content = "<input name=\"authenticity_token\" value=\"abcdefg\">";
        assertEquals("abcdefg", formScheme.getTokenValue(tokenPattern, content));

        tokenPattern = "name=\"authenticity_token\" +value=\"[^\"]+\"";
        content = "<input name=\"authenticity_token\" value=\"abcdefg\">";
        assertNull(formScheme.getTokenValue(tokenPattern, content));

    protected String extractString(final String content) {
        String input = content.replaceAll("[\\r\\n]", " ");
        if (ignoreCommentTag) {
            input = input.replaceAll("<!--[^>]+-->", "");
        } else {
            input = input.replace("<!--", "").replace("-->", "");
        }
        final Matcher matcher = getTagPattern().matcher(input);
        final StringBuffer sb = new StringBuffer();

/**
 * The Extractor interface defines methods for extracting text data from an input stream.
 * Implementations of this interface should provide the logic for extracting text and
 * optionally override the default weight value.
 */
public interface Extractor {

    /**
     * Extracts text data from the given input stream.
     *
     * @param in the input stream to extract text from

    /**
     * Creates a new MsVisioExtractor instance.
     */
    public MsVisioExtractor() {
        super();
    }

    /**
     * Extracts text from the Visio input stream.
     * @param in The input stream.
     * @param params The parameters.
     * @return The extracted data.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {

            return mimeTypeHelper.getContentType(is, filename);
        }
    }

    /**
     * Gets an input stream for the content in the deferred file output stream.
     *
     * @param out the deferred file output stream
     * @return the input stream for the content
     * @throws IOException if an I/O error occurs
     */

    /**
     * Creates a new MsWordExtractor instance.
     */
    public MsWordExtractor() {
        super();
    }

    /**
     * Extracts text from the Word input stream.
     * @param in The input stream.
     * @param params The parameters.
     * @return The extracted data.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {

    /**
     * Creates a new MsExcelExtractor instance.
     */
    public MsExcelExtractor() {
        super();
    }

    /**
     * Extracts text from the Excel input stream.
     * @param in The input stream.
     * @param params The parameters.
     * @return The extracted data.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {

 *
 * <p>All other methods delegate to the wrapped input stream.</p>
 *
 */
public class IgnoreCloseInputStream extends InputStream {

    /** The wrapped input stream. */
    private transient InputStream inputStream;

    /**
     * Constructs a new IgnoreCloseInputStream that wraps the specified input stream.
     *