config/app_config.py

"""
BackgroundFX Pro Configuration Module
Centralizes all application configuration and environment variable handling

Note: Named 'app_config.py' to avoid conflicts with existing 'Configs/' folder
"""

import os
from dataclasses import dataclass, asdict, field
from typing import Dict, Any, Optional, List
from pathlib import Path
import logging
import json
import yaml

logger = logging.getLogger(__name__)

@dataclass
class ProcessingConfig:
    """
    Main processing configuration with environment variable defaults
    """
    # Application info
    app_name: str = "BackgroundFX Pro"
    version: str = "2.0.0"
    
    # Frame processing settings
    keyframe_interval: int = int(os.getenv('KEYFRAME_INTERVAL', '5'))
    frame_skip: int = int(os.getenv('FRAME_SKIP', '1'))
    
    # Memory management
    memory_cleanup_interval: int = int(os.getenv('MEMORY_CLEANUP_INTERVAL', '30'))
    memory_threshold_mb: int = int(os.getenv('MEMORY_THRESHOLD_MB', '1024'))
    
    # Video constraints
    max_video_length: int = int(os.getenv('MAX_VIDEO_LENGTH', '300'))  # seconds
    max_video_resolution: str = os.getenv('MAX_VIDEO_RESOLUTION', '1920x1080')
    min_video_fps: int = int(os.getenv('MIN_VIDEO_FPS', '15'))
    max_video_fps: int = int(os.getenv('MAX_VIDEO_FPS', '60'))
    
    # Quality settings
    quality_preset: str = os.getenv('QUALITY_PRESET', 'balanced')
    
    # Model settings
    sam2_model_size: str = os.getenv('SAM2_MODEL_SIZE', 'large')  # tiny, small, base, large
    matanyone_precision: str = os.getenv('MATANYONE_PRECISION', 'fp32')  # fp16, fp32
    model_device: str = os.getenv('MODEL_DEVICE', 'auto')  # auto, cuda, cpu
    
    # Processing settings
    temporal_consistency: bool = os.getenv('TEMPORAL_CONSISTENCY', 'true').lower() == 'true'
    edge_refinement: bool = os.getenv('EDGE_REFINEMENT', 'true').lower() == 'true'
    mask_blur_radius: int = int(os.getenv('MASK_BLUR_RADIUS', '5'))
    confidence_threshold: float = float(os.getenv('CONFIDENCE_THRESHOLD', '0.85'))
    background_preset: str = os.getenv('BACKGROUND_PRESET', 'minimalist')
    
    # Output settings
    output_dir: str = os.getenv('OUTPUT_DIR', 'outputs')
    output_format: str = os.getenv('OUTPUT_FORMAT', 'mp4')
    output_quality: str = os.getenv('OUTPUT_QUALITY', 'high')  # low, medium, high
    output_codec: str = os.getenv('OUTPUT_CODEC', 'h264')
    write_fps: Optional[float] = None
    preserve_audio: bool = os.getenv('PRESERVE_AUDIO', 'true').lower() == 'true'
    
    # Cache settings
    model_cache_dir: str = os.getenv('MODEL_CACHE_DIR', 'models/cache')
    temp_dir: str = os.getenv('TEMP_DIR', 'temp')
    cleanup_temp_files: bool = os.getenv('CLEANUP_TEMP_FILES', 'true').lower() == 'true'
    cache_size_limit_gb: float = float(os.getenv('CACHE_SIZE_LIMIT_GB', '10.0'))
    
    # Performance settings
    max_concurrent_processes: int = int(os.getenv('MAX_CONCURRENT_PROCESSES', '1'))
    gpu_memory_fraction: float = float(os.getenv('GPU_MEMORY_FRACTION', '0.8'))
    batch_size: int = int(os.getenv('BATCH_SIZE', '4'))
    num_workers: int = int(os.getenv('NUM_WORKERS', '4'))
    
    # API settings
    api_enabled: bool = os.getenv('API_ENABLED', 'false').lower() == 'true'
    api_host: str = os.getenv('API_HOST', '0.0.0.0')
    api_port: int = int(os.getenv('API_PORT', '8000'))
    api_key: Optional[str] = os.getenv('API_KEY', None)
    
    # Web UI settings
    gradio_server_name: str = os.getenv('GRADIO_SERVER_NAME', '0.0.0.0')
    gradio_server_port: int = int(os.getenv('GRADIO_SERVER_PORT', '7860'))
    gradio_share: bool = os.getenv('GRADIO_SHARE', 'false').lower() == 'true'
    gradio_auth: Optional[str] = os.getenv('GRADIO_AUTH', None)  # username:password
    
    # Debug settings
    debug_mode: bool = os.getenv('DEBUG_MODE', 'false').lower() == 'true'
    save_intermediate_results: bool = os.getenv('SAVE_INTERMEDIATE_RESULTS', 'false').lower() == 'true'
    log_level: str = os.getenv('LOG_LEVEL', 'INFO')
    profile_performance: bool = os.getenv('PROFILE_PERFORMANCE', 'false').lower() == 'true'
    
    # Feature flags
    enable_two_stage: bool = os.getenv('ENABLE_TWO_STAGE', 'true').lower() == 'true'
    enable_preview_modes: bool = os.getenv('ENABLE_PREVIEW_MODES', 'true').lower() == 'true'
    enable_batch_processing: bool = os.getenv('ENABLE_BATCH_PROCESSING', 'false').lower() == 'true'
    
    # Legacy compatibility
    legacy_mode: bool = os.getenv('LEGACY_MODE', 'true').lower() == 'true'
    legacy_configs_dir: str = os.getenv('LEGACY_CONFIGS_DIR', 'Configs')
    
    def __post_init__(self):
        """Validate configuration after initialization"""
        self._validate_config()
        self._create_directories()
        self._setup_logging()
        if self.debug_mode:
            self._log_config()
    
    def _validate_config(self):
        """Validate configuration values"""
        # Validate frame settings
        self.keyframe_interval = max(1, self.keyframe_interval)
        self.frame_skip = max(1, self.frame_skip)
        
        # Validate memory settings
        self.memory_cleanup_interval = max(1, self.memory_cleanup_interval)
        self.memory_threshold_mb = max(256, self.memory_threshold_mb)
        
        # Validate video constraints
        self.max_video_length = max(1, self.max_video_length)
        self.min_video_fps = max(1, min(self.min_video_fps, 60))
        self.max_video_fps = max(self.min_video_fps, min(self.max_video_fps, 120))
        
        # Validate resolution format
        if 'x' not in self.max_video_resolution:
            logger.warning(f"Invalid resolution format: {self.max_video_resolution}. Setting to 1920x1080.")
            self.max_video_resolution = '1920x1080'
        
        # Validate quality preset
        valid_presets = ['fast', 'balanced', 'high', 'ultra']
        if self.quality_preset not in valid_presets:
            logger.warning(f"Invalid quality preset: {self.quality_preset}. Setting to 'balanced'.")
            self.quality_preset = 'balanced'
        
        # Validate model settings
        valid_sam2_sizes = ['tiny', 'small', 'base', 'large']
        if self.sam2_model_size not in valid_sam2_sizes:
            logger.warning(f"Invalid SAM2 model size: {self.sam2_model_size}. Setting to 'large'.")
            self.sam2_model_size = 'large'
        
        valid_precisions = ['fp16', 'fp32']
        if self.matanyone_precision not in valid_precisions:
            logger.warning(f"Invalid precision: {self.matanyone_precision}. Setting to 'fp32'.")
            self.matanyone_precision = 'fp32'
        
        # Validate output settings
        valid_formats = ['mp4', 'avi', 'mov', 'webm', 'mkv']
        if self.output_format not in valid_formats:
            logger.warning(f"Invalid output format: {self.output_format}. Setting to 'mp4'.")
            self.output_format = 'mp4'
        
        valid_qualities = ['low', 'medium', 'high', 'ultra']
        if self.output_quality not in valid_qualities:
            logger.warning(f"Invalid output quality: {self.output_quality}. Setting to 'high'.")
            self.output_quality = 'high'
        
        # Validate performance settings
        self.max_concurrent_processes = max(1, self.max_concurrent_processes)
        self.gpu_memory_fraction = max(0.1, min(1.0, self.gpu_memory_fraction))
        self.batch_size = max(1, self.batch_size)
        self.num_workers = max(0, self.num_workers)
        
        # Validate API settings
        self.api_port = max(1024, min(65535, self.api_port))
        
        # Validate confidence threshold
        self.confidence_threshold = max(0.0, min(1.0, self.confidence_threshold))
        
        # Validate cache size
        self.cache_size_limit_gb = max(0.1, self.cache_size_limit_gb)
    
    def _create_directories(self):
        """Create necessary directories if they don't exist"""
        directories = [
            self.model_cache_dir,
            self.temp_dir,
            self.output_dir,
            Path(self.output_dir) / 'masks',
            Path(self.output_dir) / 'greenscreen',
            Path(self.output_dir) / 'final',
            Path(self.output_dir) / 'two_stage'
        ]
        
        for directory in directories:
            try:
                Path(directory).mkdir(parents=True, exist_ok=True)
                logger.debug(f"Ensured directory exists: {directory}")
            except Exception as e:
                logger.error(f"Failed to create directory {directory}: {e}")
    
    def _setup_logging(self):
        """Setup logging based on configuration"""
        log_levels = {
            'DEBUG': logging.DEBUG,
            'INFO': logging.INFO,
            'WARNING': logging.WARNING,
            'ERROR': logging.ERROR,
            'CRITICAL': logging.CRITICAL
        }
        
        level = log_levels.get(self.log_level.upper(), logging.INFO)
        logging.getLogger().setLevel(level)
    
    def _log_config(self):
        """Log current configuration in debug mode"""
        logger.info("=" * 60)
        logger.info(f"{self.app_name} v{self.version} Configuration")
        logger.info("=" * 60)
        config_dict = self.to_dict()
        # Hide sensitive information
        if config_dict.get('api_key'):
            config_dict['api_key'] = '***hidden***'
        if config_dict.get('gradio_auth'):
            config_dict['gradio_auth'] = '***hidden***'
        
        for key, value in config_dict.items():
            logger.info(f"{key}: {value}")
        logger.info("=" * 60)
    
    def to_dict(self) -> Dict[str, Any]:
        """Convert configuration to dictionary"""
        return asdict(self)
    
    def to_json(self, filepath: Optional[str] = None) -> str:
        """Export configuration to JSON"""
        config_dict = self.to_dict()
        if filepath:
            with open(filepath, 'w') as f:
                json.dump(config_dict, f, indent=2)
            logger.info(f"Configuration saved to {filepath}")
        return json.dumps(config_dict, indent=2)
    
    def to_yaml(self, filepath: Optional[str] = None) -> str:
        """Export configuration to YAML"""
        config_dict = self.to_dict()
        if filepath:
            with open(filepath, 'w') as f:
                yaml.dump(config_dict, f, default_flow_style=False)
            logger.info(f"Configuration saved to {filepath}")
        return yaml.dump(config_dict, default_flow_style=False)
    
    @classmethod
    def from_json(cls, filepath: str) -> 'ProcessingConfig':
        """Load configuration from JSON file"""
        with open(filepath, 'r') as f:
            config_dict = json.load(f)
        return cls(**config_dict)
    
    @classmethod
    def from_yaml(cls, filepath: str) -> 'ProcessingConfig':
        """Load configuration from YAML file"""
        with open(filepath, 'r') as f:
            config_dict = yaml.safe_load(f)
        return cls(**config_dict)
    
    def get_quality_settings(self) -> Dict[str, Any]:
        """Get quality-specific settings based on preset"""
        quality_maps = {
            'fast': {
                'keyframe_interval': max(self.keyframe_interval, 10),
                'frame_skip': max(self.frame_skip, 2),
                'edge_refinement': False,
                'temporal_consistency': False,
                'model_precision': 'fp16',
                'batch_size': min(self.batch_size * 2, 16),
                'output_quality_params': '-preset ultrafast -crf 28'
            },
            'balanced': {
                'keyframe_interval': self.keyframe_interval,
                'frame_skip': self.frame_skip,
                'edge_refinement': True,
                'temporal_consistency': True,
                'model_precision': 'fp32',
                'batch_size': self.batch_size,
                'output_quality_params': '-preset medium -crf 23'
            },
            'high': {
                'keyframe_interval': max(self.keyframe_interval // 2, 1),
                'frame_skip': 1,
                'edge_refinement': True,
                'temporal_consistency': True,
                'model_precision': 'fp32',
                'batch_size': max(self.batch_size // 2, 1),
                'output_quality_params': '-preset slow -crf 18'
            },
            'ultra': {
                'keyframe_interval': 1,
                'frame_skip': 1,
                'edge_refinement': True,
                'temporal_consistency': True,
                'model_precision': 'fp32',
                'batch_size': 1,
                'output_quality_params': '-preset veryslow -crf 15'
            }
        }
        
        return quality_maps.get(self.quality_preset, quality_maps['balanced'])
    
    def get_resolution_limits(self) -> tuple[int, int]:
        """Get max width and height from resolution setting"""
        try:
            width, height = map(int, self.max_video_resolution.split('x'))
            return width, height
        except ValueError:
            logger.error(f"Invalid resolution format: {self.max_video_resolution}")
            return 1920, 1080
    
    def get_output_params(self) -> Dict[str, str]:
        """Get FFmpeg output parameters based on settings"""
        quality_settings = self.get_quality_settings()
        codec_map = {
            'h264': 'libx264',
            'h265': 'libx265',
            'vp9': 'libvpx-vp9',
            'av1': 'libaom-av1'
        }
        
        return {
            'codec': codec_map.get(self.output_codec, 'libx264'),
            'quality': quality_settings['output_quality_params'],
            'format': self.output_format,
            'audio': '-c:a copy' if self.preserve_audio else '-an'
        }
    
    def is_high_performance_mode(self) -> bool:
        """Check if configuration is set for high performance"""
        return (
            self.quality_preset in ['high', 'ultra'] and
            self.edge_refinement and
            self.temporal_consistency and
            self.keyframe_interval <= 3
        )
    
    def get_memory_limits(self) -> Dict[str, Any]:
        """Get memory-related limits"""
        return {
            'gpu_memory_fraction': self.gpu_memory_fraction,
            'cleanup_interval': self.memory_cleanup_interval,
            'max_concurrent': self.max_concurrent_processes,
            'threshold_mb': self.memory_threshold_mb,
            'cache_size_gb': self.cache_size_limit_gb
        }
    
    def validate_for_production(self) -> List[str]:
        """Validate configuration for production deployment"""
        warnings = []
        
        if self.debug_mode:
            warnings.append("Debug mode is enabled in production")
        
        if self.save_intermediate_results:
            warnings.append("Intermediate results saving is enabled (disk usage)")
        
        if not self.cleanup_temp_files:
            warnings.append("Temp file cleanup is disabled (disk usage)")
        
        if self.gradio_share:
            warnings.append("Gradio share is enabled (security risk)")
        
        if not self.api_key and self.api_enabled:
            warnings.append("API is enabled without authentication")
        
        if self.gpu_memory_fraction > 0.9:
            warnings.append("GPU memory fraction is very high (>90%)")
        
        if self.max_concurrent_processes > 4:
            warnings.append("High concurrent processes may cause instability")
        
        return warnings

# Singleton instance for application-wide use
_config_instance: Optional[ProcessingConfig] = None

def get_config() -> ProcessingConfig:
    """Get global configuration instance"""
    global _config_instance
    if _config_instance is None:
        _config_instance = ProcessingConfig()
    return _config_instance

def reload_config() -> ProcessingConfig:
    """Reload configuration from environment variables"""
    global _config_instance
    _config_instance = ProcessingConfig()
    logger.info("Configuration reloaded from environment variables")
    return _config_instance

def update_config(**kwargs) -> ProcessingConfig:
    """Update configuration with new values"""
    global _config_instance
    if _config_instance is None:
        _config_instance = ProcessingConfig()
    
    for key, value in kwargs.items():
        if hasattr(_config_instance, key):
            setattr(_config_instance, key, value)
            logger.debug(f"Updated config: {key} = {value}")
        else:
            logger.warning(f"Unknown configuration key: {key}")
    
    # Re-validate after updates
    _config_instance._validate_config()
    return _config_instance

def load_config_from_file(filepath: str) -> ProcessingConfig:
    """Load configuration from file (JSON or YAML)"""
    global _config_instance
    
    file_path = Path(filepath)
    if not file_path.exists():
        raise FileNotFoundError(f"Configuration file not found: {filepath}")
    
    if file_path.suffix.lower() in ['.json']:
        _config_instance = ProcessingConfig.from_json(filepath)
    elif file_path.suffix.lower() in ['.yaml', '.yml']:
        _config_instance = ProcessingConfig.from_yaml(filepath)
    else:
        raise ValueError(f"Unsupported configuration file format: {file_path.suffix}")
    
    logger.info(f"Configuration loaded from {filepath}")
    return _config_instance