// Add file URL
crawler.addUrl("file:///path/to/directory");
crawler.urlFilter.addInclude("file:///path/to/directory/.*");
```

## Configuration

### XML Configuration

Fess Crawler uses XML-based configuration with LastaFlute DI. Place configuration files in your classpath:

```xml
<!-- crawler.xml -->
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"

        super();
    }

    /**
     * Adds an SMB authentication configuration to the holder.
     * @param auth The SMB authentication configuration to add.
     */
    public void add(final SmbAuthentication auth) {
        authMap.put(auth.getPathPrefix(), auth);
    }

    /**
     * Retrieves an SMB authentication configuration that matches the given path.
     * @param path The path to match.

 * </ul>
 *
 * <p>
 * The class also supports configuration options such as:
 * </p>
 * <ul>
 *   <li>Output encoding</li>
 *   <li>Maximum compression ratio and uncompression size</li>
 *   <li>Initial buffer size</li>
 *   <li>Memory size for temporary file storage</li>
 *   <li>Maximum term sizes for alphanumeric and symbolic terms</li>
 *   <li>Custom Tika configuration</li>

 *   <li>Handling system errors</li>
 * </ul>
 *
 * <p>
 * Each logging method checks the log level before logging the message.
 * The log level can be configured in the Log4j2 configuration file.
 * </p>
 *
 */
public class LogHelperImpl implements LogHelper {

    /** Logger for this class. */
    private static final Logger logger = LogManager.getLogger(LogHelperImpl.class);

    /**

    protected boolean useFilenameOnOctetStream = true;

    /**
     * Creates a new MimeTypeHelperImpl instance.
     * Initializes the MimeTypes instance using the default configuration.
     * @throws CrawlerSystemException if the MIME types configuration cannot be loaded
     */
    public MimeTypeHelperImpl() {
        try {
            mimeTypes = MimeTypesFactory.create(MIME_TYPES_RESOURCE_NAME);

			</plugin>
			<plugin>
				<artifactId>maven-source-plugin</artifactId>
			</plugin>
			<plugin>
				<artifactId>maven-surefire-plugin</artifactId>
				<configuration>
					<excludes>
						<exclude>**/JodExtractorTest.java</exclude>
					</excludes>
				</configuration>
			</plugin>
			<plugin>
				<groupId>org.jacoco</groupId>
				<artifactId>jacoco-maven-plugin</artifactId>
			</plugin>
			<plugin>

    private static final Logger logger = LogManager.getLogger(PasswordBasedExtractor.class);

    /** Map of regex patterns to passwords for static password configuration. */
    protected Map<Pattern, String> passwordMap = new HashMap<>();

    /** Cache for parsed password configurations from extraction parameters. */
    private final Map<String, List<Pair<Pattern, String>>> configPasswordMap = new ConcurrentHashMap<>();

    /**

 * <p>
 * The URL format is expected to be: {@code storage://bucketName/objectName}.
 * The bucket name and object name are extracted from the URL.
 * </p>
 *
 * <p>
 * The handler relies on environment variables for configuration:
 * </p>
 * <ul>
 *   <li>{@code STORAGE_ENDPOINT}: The endpoint URL of the MinIO service.</li>
 *   <li>{@code STORAGE_ACCESS_KEY}: The access key for authentication.</li>

    /** Map of path prefixes to SMB authentication configurations. */
    private final Map<String, SmbAuthentication> authMap = new HashMap<>();

    /**
     * Creates a new SmbAuthenticationHolder instance.
     */
    public SmbAuthenticationHolder() {
        super();
    }

    /**
     * Adds an SMB authentication configuration to the holder.
     *

			</plugin>
			<plugin>
				<artifactId>maven-jar-plugin</artifactId>
				<configuration>
					<archive>
						<manifestEntries>
							<Automatic-Module-Name>org.codelibs.fess.crawler.lasta</Automatic-Module-Name>
						</manifestEntries>
					</archive>
				</configuration>
			</plugin>
			<plugin>
				<groupId>com.mycila</groupId>
				<artifactId>license-maven-plugin</artifactId>