"""
Simple Keyword-Based Email Classifier
Fallback when AI classification is unavailable
"""

import logging
from typing import Dict, Optional
import re

logger = logging.getLogger(__name__)


class SimpleEmailClassifier:
    """Simple rule-based email classifier using keywords"""
    
    def __init__(self):
        self.keyword_rules = {
            'invoice': [
                'faktura', 'invoice', 'kreditnota', 'credit note', 
                'ordrenr', 'order number', 'betalingspåmindelse', 'payment reminder',
                'fakturanr', 'invoice number', 'betaling', 'payment'
            ],
            'freight_note': [
                'fragtbrev', 'tracking', 'forsendelse', 'shipment',
                'levering', 'delivery', 'pakke', 'package', 'fragtbreve'
            ],
            'order_confirmation': [
                'ordrebekræftelse', 'order confirmation', 'bestilling bekræftet',
                'ordre modtaget', 'order received'
            ],
            'time_confirmation': [
                'timer', 'hours', 'tidsforbrug', 'time spent',
                'tidsregistrering', 'time registration'
            ],
            'case_notification': [
                'cc[0-9]{4}', 'case #', 'sag ', 'ticket', 'support'
            ],
            'bankruptcy': [
                'konkurs', 'bankruptcy', 'rekonstruktion', 'insolvency',
                'betalingsstandsning', 'administration'
            ],
            'spam': [
                'unsubscribe', 'click here', 'free offer', 'gratis tilbud',
                'vind nu', 'win now', 'limited time'
            ]
        }
    
    def classify(self, email_data: Dict) -> Dict:
        """
        Classify email using simple keyword matching
        Returns: {classification: str, confidence: float, reasoning: str}
        """
        subject = (email_data.get('subject', '') or '').lower()
        sender = (email_data.get('sender_email', '') or '').lower()
        body = (email_data.get('body_text', '') or '').lower()[:500]  # First 500 chars
        
        logger.info(f"🔍 simple_classifier: subject='{subject}', body_len={len(body)}, sender='{sender}'")
        
        # Combine all text for analysis
        text = f"{subject} {body}"
        
        # Check each category
        scores = {}
        for category, keywords in self.keyword_rules.items():
            matches = 0
            matched_keywords = []
            
            for keyword in keywords:
                # Use regex for patterns like CC[0-9]{4}
                if re.search(keyword, text, re.IGNORECASE):
                    matches += 1
                    matched_keywords.append(keyword)
            
            if matches > 0:
                scores[category] = {
                    'matches': matches,
                    'keywords': matched_keywords
                }
        
        # Determine best match
        if not scores:
            return {
                'classification': 'general',
                'confidence': 0.5,
                'reasoning': 'No specific keywords matched - classified as general'
            }
        
        # Get category with most matches
        best_category = max(scores.items(), key=lambda x: x[1]['matches'])
        category_name = best_category[0]
        match_count = best_category[1]['matches']
        matched_keywords = best_category[1]['keywords']
        
        # Calculate confidence (0.6-0.9 based on matches)
        confidence = min(0.9, 0.6 + (match_count * 0.1))
        
        reasoning = f"Matched {match_count} keyword(s): {', '.join(matched_keywords[:3])}"
        
        logger.info(f"✅ Keyword classification: {category_name} (confidence: {confidence:.2f})")
        
        return {
            'classification': category_name,
            'confidence': confidence,
            'reasoning': reasoning
        }


# Global instance
simple_classifier = SimpleEmailClassifier()