* 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.

    /**
     * Returns the most specific directive matching the given user agent.
     * The method finds the longest matching user agent pattern in the directives,
     * excluding the general "*" pattern which matches all bots.
     *
     * @param userAgent the user agent string to match against directives,
     *                 can be null (treated as empty string)
     * @return the most specific matching directive, or null if no directive matches

        TestRule rule = new TestRule("rule1", true);

        ruleManager.addRule(rule);

        assertFalse(ruleManager.hasRule(null));
    }

    /**
     * Test getRule with matching rule
     */
    public void test_getRule_matching() {
        TestRule rule1 = new TestRule("rule1", false);
        TestRule rule2 = new TestRule("rule2", true);
        TestRule rule3 = new TestRule("rule3", false);

        }
    }

    /**
     * Gets the count of documents matching the search criteria.
     *
     * @param callback The callback to configure the search request.
     * @return The number of matching documents.
     */
    public int getCount(final Consumer<SearchRequestBuilder> callback) {
        final TotalHits totalHits = getClient().get(c -> {

        conditionalRule.setMimeTypePattern("text/.*");

        // Test matching
        ResponseData responseData1 = new ResponseData();
        responseData1.setUrl("http://www.example.com/page");
        responseData1.setMimeType("text/html");
        assertTrue(conditionalRule.match(responseData1));

        // Test non-matching URL
        ResponseData responseData2 = new ResponseData();

        // Clear conditions
        rule.clearConditions();

        // Should match after clearing conditions
        assertTrue(rule.match(responseData));
    }

    /**
     * Test rule matching with various ResponseData states
     */
    public void test_matchWithVariousResponseDataStates() {
        ConfigurableRule rule = new ConfigurableRule();
        rule.setRuleId("stateRule");

        for (int i = 0; i < 1000; i++) {
            urlFilter.addInclude("https://site" + i + ".com/.*");
            urlFilter.addExclude(".*\\.exclude" + i + "$");
        }

        // Test matching performance
        assertTrue(urlFilter.match("https://site500.com/page"));
        assertFalse(urlFilter.match("https://site500.com/file.exclude500"));
        assertFalse(urlFilter.match("https://unknown.com/page"));

            return (T) Long.valueOf(value.longValue());
        }
        return (T) field;
    }

    /**
     * Iterates through all access results for a session, calling the callback for each result.
     * Uses OpenSearch scroll API for efficient iteration over large result sets.
     *
     * @param sessionId The session ID.

     */
    @Override
    public void close() {
        clientFactory.close();
    }

    /**
     * Adds an include filter for URLs.
     * Only URLs matching this regular expression will be crawled.
     * @param regexp The regular expression for the include filter.
     */
    public void addIncludeFilter(final String regexp) {
        if (StringUtil.isNotBlank(regexp)) {

        assertEquals(original.getCause().getClass(), deserialized.getCause().getClass());
    }

    /**
     * Test throwing and catching the exception
     */
    public void test_throwAndCatch() {
        try {
            throw new CrawlerSystemException("Test throw");
        } catch (CrawlerSystemException e) {