* This class provides methods for managing URL filtering rules,
 * including adding include and exclude URL patterns, deleting patterns,
 * and retrieving lists of compiled URL patterns. It utilizes a
 * {@link MemoryDataHelper} to store and manage the URL patterns in memory.
 *
 */
public class UrlFilterServiceImpl implements UrlFilterService {

    /**
     * Creates a new UrlFilterServiceImpl instance.

        assertFalse(urlFilter.match("https://other.com/page.html"));
    }

    /**
     * Test match with no patterns configured
     */
    public void test_match_noPatterns() {
        String sessionId = "test-session-009";
        urlFilter.init(sessionId);

        // Without any patterns, all URLs should match
        assertTrue(urlFilter.match("https://example.com/"));

/**
 * A factory class for managing and creating crawler clients based on URL patterns.
 * This class implements AutoCloseable to properly handle resource cleanup.
 *
 * <p>The factory maintains a map of regular expression patterns to crawler clients,
 * allowing for URL-based client selection. Clients can be added with specific patterns
 * and optionally at specific positions in the processing order.</p>
 *

    /**
     * Retrieves a list of URL patterns to include for a given session.
     *
     * @param sessionId the ID of the session for which to retrieve the include URL patterns
     * @return a list of compiled regular expression patterns representing the URLs to include
     */
    List<Pattern> getIncludeUrlPatternList(String sessionId);

    /**
     * Retrieves a list of URL patterns to be excluded for a given session.
     *

        excludeFilterCache.invalidate(sessionId);
    }

    /**
     * Gets the list of include URL patterns for the specified session.
     *
     * @param sessionId The session ID.
     * @return The list of compiled include patterns.
     * @throws CrawlerSystemException if the patterns cannot be loaded.
     */
    @Override
    public List<Pattern> getIncludeUrlPatternList(final String sessionId) {

    protected volatile Map<String, Map<String, AccessResultImpl<Long>>> sessionMap = new HashMap<>();

    /** Map of session IDs to include URL patterns for filtering URLs. */
    protected volatile Map<String, List<Pattern>> includeUrlPatternMap = new HashMap<>();

    /** Map of session IDs to exclude URL patterns for filtering URLs. */
    protected volatile Map<String, List<Pattern>> excludeUrlPatternMap = new HashMap<>();

    /**

 * It uses a {@link UrlFilterService} to manage the URL filtering rules.
 * The class supports caching of include and exclude patterns for scenarios where a session ID is not available.
 * It also provides methods to initialize the filter with a session ID, clear the filter,
 * match a URL against the defined patterns, and process a URL to add include or exclude patterns based on predefined filtering patterns.
 *

 *
 * <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.

     * @return true if all patterns must match, false if only one needs to match
     */
    public boolean isAllRequired() {
        return allRequired;
    }

    /**
     * Sets whether all regular expressions must match for this rule to match.
     * @param allRequired true if all patterns must match, false if only one needs to match
     */

crawler.crawlerContext.setDefaultIntervalTime(1000); // 1 second
```

### URL Filtering

```java
// Include patterns
crawler.urlFilter.addInclude("https://example.com/.*");
crawler.urlFilter.addInclude(".*\\.pdf$");

// Exclude patterns  
crawler.urlFilter.addExclude(".*\\.js$");
crawler.urlFilter.addExclude(".*login.*");
```

## Supported Protocols and Formats