import org.codelibs.fess.crawler.entity.ResponseData;

/**
 * RegexRule is a rule implementation that uses regular expressions to match against the ResponseData.
 * It allows defining multiple regular expressions for different fields of the ResponseData.
 * The rule can be configured to require all regular expressions to match (allRequired = true) or
 * only one of them (allRequired = false). It also supports a default rule that always matches.
 *

     *  @param expression A valid XPath string.
     *  @return A XPathNodes, should never be null.
     *
     * @throws XPathExpressionException if an XPath expression error occurs.
     */
    public XPathNodes selectNodeList(final Node contextNode, final String expression) throws XPathExpressionException {
        return xPath.evaluateExpression(expression, contextNode, XPathNodes.class);
    }

    /**

 *
 * <p>The extractor supports two types of password management:
 * <ul>
 *   <li>Static passwords configured via {@link #addPassword(String, String)}</li>
 *   <li>Dynamic passwords provided through extraction parameters</li>
 * </ul>
 *
 * <p>Passwords are matched against URLs or resource names using regular expression patterns.

            clientFactoryList.remove(0);
        }
    }

    /**
     * Registers a client component with a regular expression.
     * The component will be loaded into all registered CrawlerClientFactories.
     * @param regex The regular expression to match URLs.
     * @param componentName The name of the component to register.
     */

     * Adds a client with a list of regular expression patterns.
     * @param regexList The list of regular expressions to match URLs.
     * @param client The CrawlerClient instance.
     */
    public void addClient(final List<String> regexList, final CrawlerClient client) {
        if (regexList == null || regexList.isEmpty()) {
            throw new CrawlerSystemException("A regular expression list is null or empty.");
        }

import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.xml.sax.InputSource;

/**
 * {@link XpathTransformer} is a class that transforms HTML content into XML format based on XPath expressions.
 * It extracts data from an HTML document by applying XPath rules defined in {@link #fieldRuleMap}.
 * The extracted data is then formatted into an XML structure and stored in the {@link ResultData}.
 * <p>

 * It uses XPath expressions to extract text content from HTML documents.
 * <p>
 * This class provides methods to configure the XPath expressions, parser features, and properties.
 * It also includes caching mechanism for XPathAPI instances to improve performance.
 * </p>
 * <p>
 * The extracted text is obtained from the nodes selected by the {@code targetNodePath} XPath expression.

     * @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.

    /** Map of parser properties. */
    protected Map<String, String> propertyMap = new HashMap<>();

    /** XPath expression for extracting content from the document body. */
    protected String contentXpath = "//BODY";

    /** Map of metadata field names to their corresponding XPath expressions. */
    protected Map<String, String> metadataXpathMap = new HashMap<>();

    }

    /**
     * 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 {