*
 * <p>
 * The class handles character encoding issues by attempting to use the specified charset.
 * If the specified charset is invalid, it falls back to UTF-8.
 * </p>
 *
 * <p>
 * The class also provides methods to set and get the charset name used for encoding and decoding the text content.
 * </p>
 *
 * <p>

 * strip invalid XML characters, and parse XML content into a map of data.
 *
 * <p>
 * The class is final and cannot be instantiated.
 * </p>
 *
 * <h2>Methods:</h2>
 * <ul>
 *   <li>{@link #escapeXml(String)}: Escapes special characters in an XML string.</li>
 *   <li>{@link #stripInvalidXMLCharacters(String)}: Strips invalid XML characters from a string.</li>

        if (StringUtil.isBlank(mimeType)) {
            throw new CrawlerSystemException("MIME type is a blank.");
        }
        if (maxLength < 0) {
            throw new CrawlerSystemException("The value of maxLength is invalid.");
        }
        maxLengthMap.put(mimeType, maxLength);
    }

    /**
     * Gets the maximum content length for a specific MIME type.

    public void addExclude(final String urlPattern) {
        try {
            Pattern.compile(urlPattern);
        } catch (final Exception e) {
            if (logger.isWarnEnabled()) {
                logger.warn("Invalid exclude pattern: {}", urlPattern);
            }
            return;
        }
        if (sessionId == null) {
            cachedExcludeSet.add(urlPattern);
        } else {

                return false;
            }
            return true;
        } catch (final Exception e) {
            // Log the exception at debug level because an invalid URI is not critical and can be ignored.
            logger.debug("Invalid URI: {}", path, e);
        }
        return false;
    }

        // check transformer name
        if (!getName().equals(accessResultData.getTransformerName())) {
            throw new CrawlerSystemException(
                    "Transformer is invalid. Use " + accessResultData.getTransformerName() + ". This transformer is " + getName() + ".");
        }
        final byte[] data = accessResultData.getData();
        if (data == null) {
            return null;
        }

     * 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.

        final Reader rd = new StringReader(inputStr);
        try (TokenStream stream = createTokenStream(rd)) {
            if (stream == null) {
                throw new IOException("Invalid tokenizer.");
            }
            stream.reset();

            int offset = 0;
            while (stream.incrementToken()) {

        return inputStream.hashCode();
    }

    /**
     * Marks the current position in this input stream.
     *
     * @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.
     *

    }

    /**
     * Creates and configures a DOM parser for parsing HTML content.
     *
     * @return a configured DOMParser instance
     * @throws CrawlerSystemException if the parser configuration is invalid
     */
    protected DOMParser getDomParser() {
        final DOMParser parser = new DOMParser();
        try {
            // feature