- **Java**: 21+ (requires Java 21 or higher)
- **Build System**: Maven 3.x
- **DI Container**: LastaFlute DI
- **HTTP Client**: Apache HttpComponents
- **Content Extraction**: Apache Tika, Apache POI, PDFBox
- **Testing**: JUnit 4, UTFlute, Testcontainers
- **Storage Backends**: OpenSearch, Memory-based

## Quick Start

### Prerequisites

- Java 21 or higher
- Maven 3.6 or higher

### Installation

    @Override
    protected void setUp() throws Exception {
        super.setUp();
        crawlerContext = new CrawlerContext();
    }

    /**
     * Test implementation of UrlFilter for testing
     */
    private static class TestUrlFilter implements UrlFilter {
        @Override
        public void init(String sessionId) {
        }

        @Override
        public void addInclude(String urlPattern) {

        factory = new CrawlerPooledObjectFactory<>();
        factory.crawlerContainer = container;
    }

    /**
     * Test component class for testing factory operations
     */
    public static class TestComponent {
        private static AtomicInteger instanceCounter = new AtomicInteger(0);
        private final int id;
        private boolean destroyed = false;

        StringBuilder longId = new StringBuilder();
        for (int i = 0; i < 1000; i++) {
            longId.append("verylongruleid");
        }
        testRule.setRuleId(longId.toString());
        assertEquals(longId.toString(), testRule.getRuleId());

        // Special characters in rule ID
        testRule.setRuleId("rule-id_with.special@chars#123");

        for (int i = 0; i < 1000; i++) {
            maxName.append("0123456789");
        }
        testTransformer.setName(maxName.toString());
        assertEquals(10000, testTransformer.getName().length());
        assertEquals(maxName.toString(), testTransformer.getName());
    }

    /**
     * Test complete workflow
     */
    public void test_completeWorkflow() {

        list.add("item1");
        list.add("item2");
        TestAccessResultData<String> listData = new TestAccessResultData<>(list.toString().getBytes());
        Object retrievedList = testTransformer.getData(listData);
        assertEquals(list.toString(), retrievedList);

        // Null data
        TestAccessResultData<Object> nullData = new TestAccessResultData<>();

        for (int i = 0; i < 1000; i++) {
            longId.append("verylongruleid_");
        }

        TestRule rule = new TestRule(longId.toString(), new TestResponseProcessor("longProcessor"), true);

        assertEquals(longId.toString(), rule.getRuleId());

        ResponseData responseData = new ResponseData();
        assertTrue(rule.match(responseData));
    }

    /**

 * Test class for RuleManager interface.
 * Tests the contract and behavior of RuleManager implementations.
 */
public class RuleManagerTest extends PlainTestCase {

    /**
     * Test implementation of RuleManager for testing purposes
     */
    public static class TestRuleManager implements RuleManager {
        private final List<Rule> rules = new ArrayList<>();
        private int getRuleCallCount = 0;

        @Override

 * and provides access to the wrapped factory instance through getParent().
 *
 * All crawler client management operations (adding, getting clients, setting client map) are delegated
 * to the wrapped factory instance.
 *
 * This class implements the decorator pattern to extend CrawlerClientFactory functionality while
 * maintaining the same interface.
 *
 */

 *
 * <p>Key properties and configurations:</p>
 * <ul>
 *   <li>CONNECTION_TIMEOUT_PROPERTY: Connection timeout setting.</li>
 *   <li>SO_TIMEOUT_PROPERTY: Socket timeout setting.</li>
 *   <li>PROXY_HOST_PROPERTY: Proxy host setting.</li>
 *   <li>PROXY_PORT_PROPERTY: Proxy port setting.</li>
 *   <li>PROXY_AUTH_SCHEME_PROPERTY: Proxy authentication scheme.</li>
 *   <li>PROXY_CREDENTIALS_PROPERTY: Proxy credentials.</li>