/**
 * A crawler client implementation for accessing and retrieving content from S3-compatible storage systems
 * using AWS SDK v2. This client supports operations on Amazon S3 and S3-compatible storage systems.
 *
 * <p>This client requires the following initialization parameters:
 * <ul>
 *   <li>endpoint - The URL of the S3-compatible server</li>
 *   <li>accessKey - The access key for authentication</li>

package org.codelibs.fess.storage;

/**
 * Enum for supported storage types.
 */
public enum StorageType {

    /** Amazon S3 */
    S3,

    /** Google Cloud Storage */
    GCS,

    /** S3-compatible storage (MinIO, etc.) */
    S3_COMPAT

import software.amazon.awssdk.services.s3.model.Tag;
import software.amazon.awssdk.services.s3.model.Tagging;

/**
 * S3-compatible storage client implementation using AWS SDK v2.
 * Supports Amazon S3, MinIO, and other S3-compatible storage systems.
 */
public class S3StorageClient implements StorageClient {

    private static final Logger logger = LogManager.getLogger(S3StorageClient.class);

import java.io.InputStream;
import java.io.OutputStream;
import java.util.List;
import java.util.Map;

/**
 * Interface for cloud storage operations.
 * Implementations provide access to S3-compatible storage, GCS, or other cloud storage systems.
 */
public interface StorageClient extends AutoCloseable {

    /**
     * Uploads an object to storage.
     *
     * @param objectName the name/path for the object

 * <p>
 * This class now uses the standard {@link java.util.Base64} implementation
 * instead of a custom implementation, providing better security and performance.
 * The API remains backward compatible with previous versions.
 * </p>
 *
 * @author higa
 */
public abstract class Base64Util {

    /**
     * Do not instantiate.
     */
    protected Base64Util() {
    }

    /**

import software.amazon.awssdk.services.s3.model.HeadObjectResponse;
import software.amazon.awssdk.services.s3.model.S3Exception;

/**
 * Handler for the "s3" protocol, allowing access to objects stored in S3-compatible storage services.
 * This handler extends {@link URLStreamHandler} to provide a way to open connections to S3 objects
 * using URLs with the "s3" protocol.
 *
 * <p>

        // S3 patterns
        if (lowerEndpoint.contains(".amazonaws.com") || lowerEndpoint.contains("s3.") || lowerEndpoint.contains("s3-")) {
            return StorageType.S3;
        }

        // Default to S3-compatible (MinIO, etc.)
        return StorageType.S3_COMPAT;
    }

    /**
     * Creates a StorageClient based on FessConfig.
     *
     * @param fessConfig the Fess configuration

### Protocols

- **HTTP/HTTPS**: Full crawling, cookies, auth, robots.txt
- **File**: Local/network file systems
- **FTP**: With authentication
- **SMB/CIFS**: Windows shares (SMB1/SMB2+)
- **Storage**: MinIO/S3-compatible

### Content Formats

Office (Word, Excel, PowerPoint), PDF, Archives (ZIP, TAR, GZ), HTML, XML, JSON, Media (audio/video metadata), Images (EXIF/IPTC/XMP)

---

## Architecture

### Module Structure

import jakarta.annotation.Resource;

/**
 * A crawler client implementation for accessing and retrieving content from storage systems using MinIO.
 * 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>

    // ============================================================

    /** 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. */
    public static final String CRAWLING_USER_AGENT_SUFFIX = "; +http://fess.codelibs.org/bot.html)";