"""
Validation utilities for agricultural keyword tagging system
"""

import re
from typing import List, Dict, Tuple
import pandas as pd

class KeywordValidator:
    """Validates and scores keyword quality for agricultural photos"""
    
    def __init__(self):
        self.agricultural_terms = {
            'high_value': [
                'farmer', 'rancher', 'dairy farmer', 'chicken farmer',
                'tractor', 'combine', 'harvester', 'cattle', 'livestock',
                'corn', 'wheat', 'soybean', 'cotton', 'rice'
            ],
            'medium_value': [
                'field', 'farm', 'barn', 'agriculture', 'farming',
                'rural', 'crop', 'harvest', 'planting', 'irrigation'
            ],
            'low_value': [
                'outdoor', 'green', 'sunny', 'large', 'small', 'old', 'new'
            ]
        }
    
    def validate_keywords(self, keywords: List[str]) -> Dict[str, any]:
        """Validate keyword quality and relevance"""
        if not keywords:
            return {'score': 0, 'issues': ['No keywords provided']}
        
        issues = []
        score = 0
        
        # Check keyword count
        if len(keywords) < 5:
            issues.append(f'Only {len(keywords)} keywords (minimum 5 recommended)')
        elif len(keywords) > 10:
            issues.append(f'{len(keywords)} keywords (maximum 10 recommended)')
        
        # Score keywords based on agricultural relevance
        for keyword in keywords:
            if keyword in self.agricultural_terms['high_value']:
                score += 3
            elif keyword in self.agricultural_terms['medium_value']:
                score += 2
            elif keyword in self.agricultural_terms['low_value']:
                score += 1
            else:
                score += 0.5  # Generic terms
        
        # Check for required agricultural content
        has_agricultural_term = any(
            keyword in self.agricultural_terms['high_value'] + self.agricultural_terms['medium_value']
            for keyword in keywords
        )
        
        if not has_agricultural_term:
            issues.append('No clear agricultural terms detected')
            score *= 0.5
        
        # Normalize score (0-100)
        max_possible_score = len(keywords) * 3
        normalized_score = min(100, (score / max_possible_score) * 100) if max_possible_score > 0 else 0
        
        return {
            'score': round(normalized_score, 1),
            'issues': issues,
            'keyword_count': len(keywords),
            'agricultural_relevance': has_agricultural_term
        }
    
    def validate_title(self, title: str) -> Dict[str, any]:
        """Validate title quality for stock photos"""
        issues = []
        score = 100
        
        if not title:
            return {'score': 0, 'issues': ['No title provided']}
        
        # Check length
        if len(title) < 10:
            issues.append('Title too short (minimum 10 characters)')
            score -= 20
        elif len(title) > 100:
            issues.append('Title too long (maximum 100 characters)')
            score -= 10
        
        # Check for agricultural content
        agricultural_words = [
            'farm', 'agriculture', 'crop', 'livestock', 'rural',
            'farmer', 'rancher', 'tractor', 'field', 'barn'
        ]
        
        has_ag_content = any(word in title.lower() for word in agricultural_words)
        if not has_ag_content:
            issues.append('Title lacks agricultural context')
            score -= 30
        
        # Check capitalization
        if not title[0].isupper():
            issues.append('Title should start with capital letter')
            score -= 5
        
        return {
            'score': max(0, score),
            'issues': issues,
            'length': len(title),
            'agricultural_content': has_ag_content
        }

class DataQualityChecker:
    """Check data quality for batch processing"""
    
    @staticmethod
    def validate_csv_output(csv_path: str) -> Dict[str, any]:
        """Validate CSV output format and content"""
        try:
            df = pd.read_csv(csv_path)
            
            required_columns = ['filename', 'human_keywords', 'ai_keywords', 'ai_title', 'location']
            missing_columns = [col for col in required_columns if col not in df.columns]
            
            if missing_columns:
                return {
                    'valid': False,
                    'error': f'Missing required columns: {missing_columns}'
                }
            
            # Check for empty critical fields
            empty_ai_keywords = df['ai_keywords'].isna().sum()
            empty_ai_titles = df['ai_title'].isna().sum()
            
            return {
                'valid': True,
                'total_rows': len(df),
                'empty_ai_keywords': empty_ai_keywords,
                'empty_ai_titles': empty_ai_titles,
                'completion_rate': {
                    'keywords': round((len(df) - empty_ai_keywords) / len(df) * 100, 1),
                    'titles': round((len(df) - empty_ai_titles) / len(df) * 100, 1)
                }
            }
            
        except Exception as e:
            return {
                'valid': False,
                'error': f'Error reading CSV: {str(e)}'
            }
    
    @staticmethod
    def check_batch_performance(processing_times: List[float], image_count: int) -> Dict[str, any]:
        """Analyze batch processing performance"""
        if not processing_times:
            return {'error': 'No processing times provided'}
        
        avg_time = sum(processing_times) / len(processing_times)
        total_time = sum(processing_times)
        
        # Performance thresholds
        target_time_per_image = 5.0  # seconds
        performance_rating = 'excellent' if avg_time <= 2 else 'good' if avg_time <= 5 else 'needs_improvement'
        
        return {
            'total_images': image_count,
            'total_time_seconds': round(total_time, 2),
            'average_time_per_image': round(avg_time, 2),
            'performance_rating': performance_rating,
            'estimated_time_for_500': round(avg_time * 500 / 60, 1),  # minutes
            'estimated_time_for_1000': round(avg_time * 1000 / 60, 1)  # minutes
        }

def validate_image_file(file_path: str) -> bool:
    """Quick validation that file is a valid image"""
    try:
        from PIL import Image
        with Image.open(file_path) as img:
            img.verify()
        return True
    except:
        return False