import os
import json
import logging
from datetime import datetime
from typing import Dict, Any, List

from .config import config

def setup_logging():
    """Seadista logimine"""
    log_file = os.path.join(config.log_dir, f"processing_{datetime.now().strftime('%Y%m%d_%H%M%S')}.log")
    
    logging.basicConfig(
        level=logging.INFO,
        format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
        handlers=[
            logging.FileHandler(log_file, encoding='utf-8'),
            logging.StreamHandler()
        ]
    )
    
    return logging.getLogger(__name__)

def save_processed_article(data: Dict[str, Any]):
    """Salvesta töödeldud artikkel JSON failina"""
    try:
        # Genereeri failinimi
        timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
        filename = f"article_{timestamp}.json"
        filepath = os.path.join(config.processed_dir, filename)
        
        # Salvesta JSON failina
        with open(filepath, 'w', encoding='utf-8') as f:
            json.dump(data, f, ensure_ascii=False, indent=2)
        
        logger = logging.getLogger(__name__)
        logger.info(f"Töödeldud andmed salvestatud: {filepath}")
        
    except Exception as e:
        logger = logging.getLogger(__name__)
        logger.error(f"Viga andmete salvestamisel: {str(e)}")

def load_processed_articles() -> List[Dict]:
    """Lae töödeldud artiklid"""
    articles = []
    
    for filename in os.listdir(config.processed_dir):
        if filename.endswith('.json'):
            filepath = os.path.join(config.processed_dir, filename)
            try:
                with open(filepath, 'r', encoding='utf-8') as f:
                    articles.append(json.load(f))
            except:
                continue
    
    return articles

def clean_filename(filename: str) -> str:
    """Puhasta failinimi erimärkidest"""
    import re
    # Eemalda erimärgid, jäta ainult tähed, numbrid, tühikud, punktid ja sidekriipsud
    clean = re.sub(r'[^\w\s\.\-]', '', filename)
    # Asenda mitmik tühikud ühega
    clean = re.sub(r'\s+', ' ', clean)
    return clean.strip()