*   <li>Manages crawl delay settings per user agent</li>
 *   <li>Stores sitemap URLs listed in robots.txt</li>
 * </ul>
 *
 * <p>The class uses case-insensitive pattern matching for user agents and supports
 * wildcard characters (*) in user agent strings. When multiple directives match a user agent,
 * the most specific (longest) match is used.</p>
 *
 */
public class RobotsTxt {

        RobotsTxt robotsTxt;
        final InputStream in = new java.io.ByteArrayInputStream(robotsTxtContent.getBytes());
        try {
            robotsTxt = robotsTxtHelper.parse(in);
        } finally {
            CloseableUtil.closeQuietly(in);
        }

        // Directives before User-agent should be ignored

 * </ul>
 *
 * @author bowez
 * @author shinsuke
 *
 */
public class RobotsTxtHelper {

    /** Pattern for parsing user-agent records. */
    protected static final Pattern USER_AGENT_RECORD =
            Pattern.compile("^user-agent:\\s*([^\\t\\n\\x0B\\f\\r]+)\\s*$", Pattern.CASE_INSENSITIVE);

    /** Pattern for parsing disallow records. */

        this.authSchemeProviderMap = authSchemeProviderMap;
    }

    /**
     * Sets the user agent string.
     * @param userAgent The user agent string.
     */
    public void setUserAgent(final String userAgent) {
        this.userAgent = userAgent;
    }

    /**
     * Sets the credentials provider.

    // ============================================================
    // User Agent Configuration
    // ============================================================

    /** Prefix for Fess crawler user agent string. */
    public static final String CRAWLING_USER_AGENT_PREFIX = "Mozilla/5.0 (compatible; Fess/";

    /** Suffix for Fess crawler user agent string with bot information URL. */

        Directive retrieved = robotsTxt.getDirective("OtherBot");
        assertNull(retrieved);
    }

    public void test_getDirectiveWithNull() {
        // Test getDirective with null user agent
        RobotsTxt robotsTxt = new RobotsTxt();

        Directive retrieved = robotsTxt.getDirective(null);
        assertNull(retrieved);
    }

    public void test_getMatchedDirectiveWithExactMatch() {

```bash
# Format code (Eclipse formatter)
mvn formatter:format

# Check/apply license headers
mvn license:check
mvn license:format

# Generate test coverage report
mvn jacoco:prepare-agent test jacoco:report

# Generate API documentation
mvn javadoc:javadoc
```

### Testing

The project uses JUnit 4 with embedded OpenSearch for integration testing:

```bash
# Run all tests

			</plugin>
			<plugin>
				<groupId>org.jacoco</groupId>
				<artifactId>jacoco-maven-plugin</artifactId>
				<version>0.8.13</version>
				<executions>
					<execution>
						<goals>
							<goal>prepare-agent</goal>
						</goals>
					</execution>
					<execution>
						<id>report</id>
						<phase>prepare-package</phase>
						<goals>
							<goal>report</goal>
						</goals>
					</execution>

extractorFactory.addExtractor("text/html", htmlExtractor, 2);  // Weight 2
extractorFactory.addExtractor("text/html", tikaExtractor, 1);  // Fallback
```

### Helpers

**RobotsTxtHelper**: RFC 9309 parsing, user-agent matching, crawl-delay, sitemaps
**SitemapsHelper**: Sitemap XML parsing, index handling
**MimeTypeHelper**: MIME detection via Tika
**EncodingHelper**: Charset detection with BOM
**UrlConvertHelper**: URL normalization

     */
    public static WebApiManagerFactory getWebApiManagerFactory() {
        return getComponent(WEB_API_MANAGER_FACTORY);
    }

    /**
     * Gets the user agent helper component.
     * @return The user agent helper.
     */
    public static UserAgentHelper getUserAgentHelper() {
        return getComponent(USER_AGENT_HELPER);
    }

    /**
     * Gets the data store factory component.