# config.py
"""
Configuration file for Mistral OCR processing.
Contains API key and other settings.
"""
import os
import logging
from dotenv import load_dotenv

# Configure logging
logger = logging.getLogger("config")

# Load environment variables from .env file if it exists
load_dotenv()

# Mistral API key handling - get from Hugging Face secrets or environment variable
# The priority order is: 
# 1. HF_MISTRAL_API_KEY environment var (for Hugging Face deployment)
# 2. MISTRAL_API_KEY environment var (standard environment variable)
# 3. Empty string (will show warning in app)
MISTRAL_API_KEY = os.environ.get("HF_MISTRAL_API_KEY", 
                  os.environ.get("MISTRAL_API_KEY", "sfSLqRdW31yxodeYFz3m7Ky83X2V7jUH")).strip()

# Check if we're in test mode (allows operation without valid API key)
# Set to False to use actual API calls
TEST_MODE = False

# Just check if API key exists
if not MISTRAL_API_KEY and not TEST_MODE:
    logger.warning("No Mistral API key found. OCR functionality will not work unless TEST_MODE is enabled.")

if TEST_MODE:
    logger.info("TEST_MODE is enabled. Using mock responses instead of actual API calls.")

# Model settings with fallbacks
OCR_MODEL = os.environ.get("MISTRAL_OCR_MODEL", "mistral-ocr-latest")
TEXT_MODEL = os.environ.get("MISTRAL_TEXT_MODEL", "mistral-small-latest")  # Updated from ministral-8b-latest
VISION_MODEL = os.environ.get("MISTRAL_VISION_MODEL", "mistral-small-latest")  # Using faster model that supports vision

# Image preprocessing settings optimized for historical documents
# These can be customized from environment variables
IMAGE_PREPROCESSING = {
    "enhance_contrast": float(os.environ.get("ENHANCE_CONTRAST", "1.8")),  # Increased contrast for better text recognition
    "sharpen": os.environ.get("SHARPEN", "True").lower() in ("true", "1", "yes"),
    "denoise": os.environ.get("DENOISE", "True").lower() in ("true", "1", "yes"),
    "max_size_mb": float(os.environ.get("MAX_IMAGE_SIZE_MB", "12.0")),    # Increased size limit for better quality
    "target_dpi": int(os.environ.get("TARGET_DPI", "300")),               # Target DPI for scaling
    "compression_quality": int(os.environ.get("COMPRESSION_QUALITY", "95")),  # Higher quality for better OCR results
    # Enhanced settings for handwritten documents
    "handwritten": {
        "contrast": float(os.environ.get("HANDWRITTEN_CONTRAST", "1.2")),  # Lower contrast for handwritten text
        "block_size": int(os.environ.get("HANDWRITTEN_BLOCK_SIZE", "21")), # Larger block size for adaptive thresholding
        "constant": int(os.environ.get("HANDWRITTEN_CONSTANT", "5")),      # Lower constant for adaptive thresholding
        "use_dilation": os.environ.get("HANDWRITTEN_DILATION", "True").lower() in ("true", "1", "yes"),  # Connect broken strokes
        "clahe_limit": float(os.environ.get("HANDWRITTEN_CLAHE_LIMIT", "2.0")),  # CLAHE limit for local contrast
        "bilateral_d": int(os.environ.get("HANDWRITTEN_BILATERAL_D", "5")), # Bilateral filter window size
        "bilateral_sigma1": int(os.environ.get("HANDWRITTEN_BILATERAL_SIGMA1", "25")),  # Color sigma
        "bilateral_sigma2": int(os.environ.get("HANDWRITTEN_BILATERAL_SIGMA2", "45"))   # Space sigma
    }
}

# OCR settings optimized for single-page performance
OCR_SETTINGS = {
    "timeout_ms": int(os.environ.get("OCR_TIMEOUT_MS", "45000")),         # Shorter timeout for single pages (45 seconds)
    "max_retries": int(os.environ.get("OCR_MAX_RETRIES", "2")),           # Fewer retries to avoid rate-limiting
    "retry_delay": int(os.environ.get("OCR_RETRY_DELAY", "1")),           # Shorter initial retry delay for faster execution
    "include_image_base64": os.environ.get("INCLUDE_IMAGE_BASE64", "True").lower() in ("true", "1", "yes"),
    "thread_count": int(os.environ.get("OCR_THREAD_COUNT", "2"))          # Lower thread count to prevent API rate limiting
}