* @param regex The regular expression for the client.
     * @param client The CrawlerClient instance.
     */
    @Override
    public void addClient(final String regex, final CrawlerClient client) {
        factory.addClient(regex, client);
    }

    /**
     * Adds a client to the wrapped factory at a specific position.
     * @param regex The regular expression for the client.

     * (java.lang.String)
     */
    /**
     * Retrieves a list of URL patterns to be excluded for a given session.
     * @param sessionId The ID of the session.
     * @return A list of compiled regular expression patterns.
     */
    @Override
    public List<Pattern> getExcludeUrlPatternList(final String sessionId) {
        return dataHelper.getExcludeUrlPatternList(sessionId);
    }

    private static final Pattern SPACE_PATTERN = Pattern.compile("\\s+", Pattern.MULTILINE);

    /**
     * A map of field rules, where the key is the field name and the value is the XPath expression.
     */
    protected Map<String, String> fieldRuleMap = new LinkedHashMap<>();

    /** Flag to enable or disable trimming of whitespace characters. */
    protected boolean trimSpaceEnabled = true;

    }

    /**
     * Retrieves a list of XPath nodes from the document.
     *
     * @param doc The XML document.
     * @param xpath The XPath expression.
     * @return A list of XPath nodes.
     * @throws XPathExpressionException if an XPath expression error occurs.
     */
    protected XPathNodes getNodeList(final Document doc, final String xpath) throws XPathExpressionException {

 *   <li><b>preloadSizeForCharset:</b> The number of bytes to read from the input
 *       stream to determine the character set encoding.</li>
 *   <li><b>invalidUrlPattern:</b> A regular expression pattern used to identify
 *       invalid URLs.</li>
 * </ul>
 *
 * <p>
 * <b>Usage:</b>
 * </p>
 * <p>
 * The {@code transform} method is the main entry point for transforming an HTML

            }
        }
        return null;
    }

    /**
     * Adds a directive to the robots.txt rules.
     * The user-agent pattern in the directive is converted to a regular expression pattern,
     * where '*' is replaced with '.*' for pattern matching, and stored case-insensitively.
     *
     * @param directive The directive to add to the robots.txt rules
     */

        } finally {
            EntityUtils.consumeQuietly(httpEntity);
        }
    }

    /**
     * Converts a robots.txt pattern to a regular expression.
     *
     * @param path The robots.txt pattern to convert
     * @return The equivalent regular expression
     */
    protected String convertRobotsTxtPatternToRegex(final String path) {

e=d.attrHandle[b.toLowerCase()],f=e&&E.call(d.attrHandle,b.toLowerCase())?e(a,b,!p):void 0;return void 0!==f?f:c.attributes||!p?a.getAttribute(b):(f=a.getAttributeNode(b))&&f.specified?f.value:null},fb.error=function(a){throw new Error("Syntax error, unrecognized expression: "+a)},fb.uniqueSort=function(a){var b,d=[],e=0,f=0;if(l=!c.detectDuplicates,k=!c.sortStable&&a.slice(0),a.sort(B),l){while(b=a[f++])b===a[f]&&(e=d.push(f));while(e--)a.splice(d[e],1)}return k=null,a},e=fb.getText=function(a){var b,c="",d=0,f=a...