import pandas as pd
import re

def load_csv_data(file_path):
    """Load CSV data from file path"""
    try:
        return pd.read_csv(file_path)
    except Exception as e:
        print(f"Error loading CSV: {str(e)}")
        # Return a minimal dataframe for demonstration
        return pd.DataFrame({
            'Crop': ['Tomato', 'Apple'],
            'Disease': ['Early Blight', 'Apple Scab'],
            'Symptoms': ['Yellow spots on leaves', 'Dark scab-like lesions'],
            'Treatment': ['Remove affected leaves', 'Prune affected branches'],
            'Medicine/Chemical Control': ['Copper fungicide', 'Sulfur spray']
        })

def analyze_csv_data(df):
    """Analyze CSV data and return statistics"""
    stats = {
        "total_entries": len(df),
        "unique_crops": df['Crop'].nunique(),
        "unique_diseases": df['Disease'].nunique(),
        "crops": df['Crop'].unique().tolist()
    }
    return stats

def search_disease_info(df, query):
    """Search for disease information in the dataframe"""
    query = query.lower()
    results = []
    
    # Search in all columns
    for _, row in df.iterrows():
        score = 0
        if query in str(row['Crop']).lower():
            score += 3
        if query in str(row['Disease']).lower():
            score += 5
        if query in str(row['Symptoms']).lower():
            score += 2
        if query in str(row['Treatment']).lower():
            score += 1
        if query in str(row['Medicine/Chemical Control']).lower():
            score += 1
            
        if score > 0:
            results.append({
                'score': score,
                'Crop': row['Crop'],
                'Disease': row['Disease'],
                'Symptoms': row['Symptoms'],
                'Treatment': row['Treatment'],
                'Medicine/Chemical Control': row['Medicine/Chemical Control']
            })
    
    # Sort by relevance score
    results.sort(key=lambda x: x['score'], reverse=True)
    return results

def extract_entities_from_question(question, df):
    """Extract crop and disease entities from a question"""
    question = question.lower()
    
    # Get all crops and diseases from the dataframe
    crops = set(df['Crop'].str.lower())
    diseases = set(df['Disease'].str.lower())
    
    # Find matches in the question
    found_crop = None
    found_disease = None
    
    for crop in crops:
        if crop in question:
            found_crop = crop
            break
            
    for disease in diseases:
        if disease in question:
            found_disease = disease
            break
    
    return found_crop, found_disease

def get_treatment_for_disease(df, crop, disease):
    """Get treatment information for a specific crop and disease"""
    if crop and disease:
        matches = df[(df['Crop'].str.lower() == crop.lower()) & 
                     (df['Disease'].str.lower() == disease.lower())]
        
        if not matches.empty:
            row = matches.iloc[0]
            return {
                'crop': row['Crop'],
                'disease': row['Disease'],
                'symptoms': row['Symptoms'],
                'treatment': row['Treatment'],
                'medicine': row['Medicine/Chemical Control']
            }
    
    return None