}

    /**
     * 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) {
        try {

        String sessionId = "test-session-024";
        urlFilter.init(sessionId);

        // Test empty pattern
        urlFilter.addInclude("");
        urlFilter.addExclude("");

        // Test single character pattern
        urlFilter.addInclude(".");
        urlFilter.addExclude("*");

        // Test patterns with only special characters
        urlFilter.addInclude("^$");
        urlFilter.addExclude(".*");

                .getTotalHits()
                .value() > 0);

        // Verify pattern can be retrieved
        final List<Pattern> patterns = urlFilterService.getIncludeUrlPatternList(sessionId);
        assertEquals(1, patterns.size());
        assertTrue(patterns.get(0).matcher("http://example.com/page1").matches());
        assertFalse(patterns.get(0).matcher("http://other.com/page1").matches());

# Based on RFC 9309 specification

# Test wildcard patterns
User-agent: WildcardBot
Disallow: /*.pdf$
Disallow: /admin/*.php
Disallow: /*/private/
Allow: /public/*.html

# Test end-of-path ($) patterns
User-agent: EndPathBot
Disallow: /fish$
Disallow: /temp$
Allow: /fishing

# Test complex patterns
User-agent: ComplexBot
Disallow: /
Allow: /$
Allow: /index.html$
Allow: /public/

/**
 * 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>
 *

        private final int priorityLength;

        /**
         * Constructs a new PathPattern from the given robots.txt path pattern.
         * @param pattern the path pattern string from robots.txt (may contain * and $)
         */
        public PathPattern(final String pattern) {
            this.pattern = pattern;

					symmetry = uint64(len(p.Seq))%ss == 0
				} else {
					symmetry = ss%uint64(len(p.Seq)) == 0
				}
			}
		}
		// With no arg patterns, it is expected that user knows
		// the right symmetry, so either ellipses patterns are
		// provided (recommended) or no ellipses patterns.
		if _, ok := newSetCounts[ss]; !ok && (symmetry || argPatterns == nil) {
			newSetCounts[ss] = struct{}{}
		}
	}

	setCounts = []uint64{}

    }

    /**
     * Converts a GSA URL pattern into a regular expression pattern suitable for Fess.
     * Handles various GSA pattern formats including regexp, contains, and URL-based patterns.
     *
     * @param s the input GSA pattern string
     * @return a regular expression pattern string, or empty string for comments/invalid patterns
     */
    protected String getFilterPath(final String s) {

/**
 */
class FilterHashEqualsTest {

    @Test
    void testIncludesExcludesArtifactFilter() {
        List<String> patterns = Arrays.asList("c", "d", "e");

        IncludesArtifactFilter f1 = new IncludesArtifactFilter(patterns);

        IncludesArtifactFilter f2 = new IncludesArtifactFilter(patterns);

        assertTrue(f1.equals(f2), "Expected " + f1 + " to equal " + f2);

**Flow**: Poll URL → Validate → Get client → Delay → Check last-modified → Execute → Process → Extract children → Queue children → Delay

### CrawlerClientFactory

Pattern-based client selection using `LinkedHashMap<Pattern, CrawlerClient>`.

**Standard Patterns**:
```java
"^https?://.*"     → httpClient
"^file:.*"         → fileSystemClient
"^ftp://.*"        → ftpClient
"^smb://.*"        → smbClient