* </p>
 * <ul>
 *   <li>ftpConfigSystemKey: The system key used to configure the FTPClientConfig.</li>
 *   <li>ftpConfigServerLanguageCode: The language code used by the FTP server.</li>
 *   <li>ftpConfigServerTimeZoneId: The time zone ID of the FTP server.</li>
 *   <li>activeExternalHost: The external IP address to use for active mode FTP.</li>
 *   <li>activeMinPort: The minimum port number for active mode FTP.</li>

                .withEnv("MINIO_ACCESS_KEY", ACCESS_KEY)//
                .withEnv("MINIO_SECRET_KEY", SECRET_KEY)//
                .withExposedPorts(port)//
                .withCommand("server /data")//
                .waitingFor(new HttpWaitStrategy()//
                        .forPath("/minio/health/ready")//
                        .forPort(port)//

```

## Supported Protocols and Formats

### Protocols
- **HTTP/HTTPS**: Full web crawling support with cookies, authentication, redirects
- **File System**: Local and network file system access
- **FTP**: FTP server crawling with authentication
- **SMB/CIFS**: Windows network shares
- **Storage**: Cloud storage systems (MinIO, S3-compatible)

### Content Formats

#### Office Documents

import com.google.common.base.Charsets;

import jakarta.annotation.PostConstruct;
import jakarta.annotation.PreDestroy;

/**
 * Extract a text by using external http server.
 */
public class ApiExtractor extends AbstractExtractor {

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

    /** The URL of the API endpoint. */
    protected String url;

        // Process URL should handle different URL formats
        urlFilter.processUrl("https://example.com/");
        urlFilter.processUrl("http://test.com/path/to/page");
        urlFilter.processUrl("ftp://files.server.com/documents/");
        urlFilter.processUrl("file:///local/path/file.txt");

        // Should complete without errors
        assertNotNull(urlFilter);
    }

    /**

import org.codelibs.jcifs.smb1.SmbFileInputStream;
import org.codelibs.jcifs.smb1.util.LogStream;

/**
 * The {@link SmbClient} class is a crawler client implementation for accessing files and directories
 * on SMB (Server Message Block) shares using the SMB1 protocol. It extends {@link AbstractCrawlerClient} and utilizes the JCIFS library
 * to interact with SMB resources.
 *
 * <p>

#   M2_HOME - location of maven2's installed home dir
#   MAVEN_OPTS - parameters passed to the Java VM when running Maven
#     e.g. to debug Maven itself, use
#       set MAVEN_OPTS=-Xdebug -Xrunjdwp:transport=dt_socket,server=y,suspend=y,address=8000
#   MAVEN_SKIP_RC - flag to disable loading of mavenrc files
# ----------------------------------------------------------------------------

if [ -z "$MAVEN_SKIP_RC" ] ; then

    os: Os,
    arch: Arch = Arch.AMD64,
) {
    params {
        param("env.BOT_TEAMCITY_GITHUB_TOKEN", "%github.bot-teamcity.token%")
        param("env.GRADLE_CACHE_REMOTE_SERVER", "%gradle.cache.remote.server%")

        param("env.JAVA_HOME", javaHome(buildJvm, os, arch))
        param("env.ANDROID_HOME", os.androidHome)
        param("env.ANDROID_SDK_ROOT", os.androidHome)

 * This client supports operations on object storage systems compatible with S3 protocol.
 *
 * <p>This client requires the following initialization parameters:
 * <ul>
 *   <li>endpoint - The URL of the MinIO server</li>
 *   <li>accessKey - The access key for authentication</li>
 *   <li>secretKey - The secret key for authentication</li>
 *   <li>connectTimeout - Connection timeout in milliseconds (default: 10000)</li>

import org.codelibs.jcifs.smb.impl.SmbFile;
import org.codelibs.jcifs.smb.impl.SmbFileInputStream;

/**
 * The {@link SmbClient} class is a crawler client implementation for accessing files and directories
 * on SMB (Server Message Block) shares. It extends {@link AbstractCrawlerClient} and utilizes the JCIFS library
 * to interact with SMB resources.
 *
 * <p>