import pandas as pd
import gradio as gr
from retriever import get_relevant_passages
from reranker import rerank

# Load and clean CSV
def clean_df(df):
    df = df.copy()
    
    # Ensure clean URLs
    # Check if the second column contains URLs or just IDs
    second_col = df.iloc[:, 1].astype(str)
    if second_col.str.contains('http').any() or second_col.str.contains('www').any():
        df["url"] = second_col  # Already has full URLs
    else:
        # Create full URLs from IDs
        df["url"] = "https://www.shl.com/" + second_col.str.replace(r'^[\s/]*', '', regex=True)
    
    df["remote_support"] = df.iloc[:, 2].map(lambda x: "Yes" if x == "T" else "No")
    df["adaptive_support"] = df.iloc[:, 3].map(lambda x: "Yes" if x == "T" else "No")
    
    # Handle test_type with error checking
    df["test_type"] = df.iloc[:, 4].astype(str).str.split("\\n")
    
    df["description"] = df.iloc[:, 5]
    
    # Extract duration with error handling
    df["duration"] = pd.to_numeric(
        df.iloc[:, 8].astype(str).str.extract(r'(\d+)')[0], 
        errors='coerce'
    )
    
    return df[["url", "adaptive_support", "remote_support", "description", "duration", "test_type"]]

try:
    df = pd.read_csv("assesments.csv")
    df_clean = clean_df(df)
except Exception as e:
    print(f"Error loading or cleaning data: {e}")
    # Create an empty DataFrame with required columns as fallback
    df_clean = pd.DataFrame(columns=["url", "adaptive_support", "remote_support", 
                                     "description", "duration", "test_type"])

def validate_and_fix_urls(candidates):
    """Validates and fixes URLs in candidate assessments."""
    for candidate in candidates:
        # Ensure URL exists
        if 'url' not in candidate or not candidate['url']:
            candidate['url'] = 'https://www.shl.com/missing-url'
            continue
            
        url = str(candidate['url'])
        
        # Fix URLs that are just numbers
        if url.isdigit() or (url.startswith('https://www.shl.com') and url[len('https://www.shl.com'):].isdigit()):
            candidate['url'] = f"https://www.shl.com/{url.replace('https://www.shl.com', '')}"
            continue
            
        # Add protocol if missing
        if not url.startswith(('http://', 'https://')):
            candidate['url'] = f"https://{url}"
            
    return candidates

def recommend(query):
    if not query.strip():
        return {"error": "Please enter a job description"}
    
    try:
        # Print some debug info
        print(f"Processing query: {query[:50]}...")
        
        top_k_df = get_relevant_passages(query, df_clean, top_k=20)
        
        # Debug: Check URLs in retrieved data
        print(f"Retrieved {len(top_k_df)} assessments")
        if not top_k_df.empty:
            print(f"Sample URLs from retrieval: {top_k_df['url'].iloc[:3].tolist()}")
        
        candidates = top_k_df.to_dict(orient="records")
        
        # Additional URL validation before sending to reranker
        for c in candidates:
            if 'url' in c:
                if not str(c['url']).startswith(('http://', 'https://')):
                    c['url'] = f"https://www.shl.com/{str(c['url']).lstrip('/')}"
        
        result = rerank(query, candidates)
        
        # Post-process result to ensure URLs are properly formatted
        if 'recommended_assessments' in result:
            result['recommended_assessments'] = validate_and_fix_urls(result['recommended_assessments'])
            
        return result
    except Exception as e:
        import traceback
        error_details = traceback.format_exc()
        print(f"Error: {str(e)}\n{error_details}")
        return {"error": f"Error processing request: {str(e)}"}

iface = gr.Interface(
    fn=recommend,
    inputs=gr.Textbox(label="Enter Job Description", lines=4),
    outputs="json",
    title="SHL Assessment Recommender",
    description="Paste a job description to get the most relevant SHL assessments."
)

if __name__ == "__main__":
    iface.launch()