}

    /**
     * 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 {

                .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());

    }

    /**
     * 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) {

        Pattern pattern = Pattern.compile(FS_FILE_RULE_PATTERN);
        assertTrue(pattern.matcher("text/html").matches());
    }

    @Test
    public void test_fsFileRulePattern_lhaTypes() {
        Pattern pattern = Pattern.compile(FS_FILE_RULE_PATTERN);
        assertTrue(pattern.matcher("application/lha").matches());
        assertTrue(pattern.matcher("application/x-lha").matches());

     * - Second: List of regex pattern matches (Pattern -> content template)
     */
    protected Map<String, Pair<Map<String, String>, List<Pair<Pattern, String>>>> relatedContentMap = Collections.emptyMap();

    /**
     * Prefix used to identify regex patterns in related content terms.
     * When a term starts with this prefix, it is treated as a regular expression
     * pattern rather than an exact match term.
     */

    init {
      require(
        (pattern.startsWith("*.") && pattern.indexOf("*", 1) == -1) ||
          (pattern.startsWith("**.") && pattern.indexOf("*", 2) == -1) ||
          pattern.indexOf("*") == -1,
      ) {
        "Unexpected pattern: $pattern"
      }

      this.pattern =
        pattern.toCanonicalHost() ?: throw IllegalArgumentException("Invalid pattern: $pattern")

      when {

        final Set<String> valueSet = new HashSet<>();
        for (final LabelTypePattern pattern : labelTypePatternList) {
            if (pattern.match(path)) {
                valueSet.add(pattern.getValue());
            }
        }
        return valueSet;
    }

    /**
     * Builds a list of label type patterns.
     *
     * @param labelTypeList The list of label types.
     */

     * @throws FessSystemException if the input string contains invalid tag patterns
     */
    public static PrunedTag[] parse(final String value) {
        return split(value, ",").get(stream -> stream.filter(StringUtil::isNotBlank).map(v -> {
            final Pattern pattern = Pattern.compile("(\\w+)(\\[[^\\]]+\\])?(\\.[\\w\\-]+)?(#[\\w\\-]+)?");
            final Matcher matcher = pattern.matcher(v.trim());
            if (matcher.matches()) {

        assertTrue(pattern.match("/test/path"));

        // Should not match excluded path
        assertFalse(pattern.match("/exclude/path"));
    }

    @Test
    public void test_labelTypePattern_match_noPatterns() {
        LabelTypePattern pattern = new LabelTypePattern("test", null, null);

        // Should match everything when no patterns
        assertTrue(pattern.match("/any/path"));

    /**
     * Cache for client rules mapping client names to their corresponding URL patterns.
     * This cache improves performance by avoiding repeated parsing of client configuration rules.
     * The key is the rule string, and the value is a pair containing the client name and compiled pattern.
     */
    protected ConcurrentHashMap<String, Pair<String, Pattern>> clientRuleCache = new ConcurrentHashMap<>();

    /**