import pandas as pd
import gradio as gr
import json
from fastapi import FastAPI, Request
from fastapi.responses import JSONResponse
from gradio.routes import mount_gradio_app

from retriever import get_relevant_passages
from reranker import rerank

# --- Initialize FastAPI ---
app = FastAPI()

# --- Load and clean CSV ---
def clean_df(df):
    df = df.copy()
    second_col = df.iloc[:, 2].astype(str)

    if second_col.str.contains('http').any() or second_col.str.contains('www').any():
        df["url"] = second_col
    else:
        df["url"] = "https://www.shl.com" + second_col.str.replace(r'^(?!/)', '/', regex=True)

    df["remote_support"] = df.iloc[:, 3].map(lambda x: "Yes" if x == "T" else "No")
    df["adaptive_support"] = df.iloc[:, 4].map(lambda x: "Yes" if x == "T" else "No")
    df["test_type"] = df.iloc[:, 5].apply(lambda x: eval(x) if isinstance(x, str) else x)
    df["description"] = df.iloc[:, 6]
    df["duration"] = pd.to_numeric(df.iloc[:, 9].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", encoding='utf-8')
    df_clean = clean_df(df)
except Exception as e:
    print(f"Error loading data: {e}")
    df_clean = pd.DataFrame(columns=["url", "adaptive_support", "remote_support", "description", "duration", "test_type"])

# --- Fix URLs ---
def validate_and_fix_urls(candidates):
    for candidate in candidates:
        if not isinstance(candidate, dict):
            continue
        if 'url' not in candidate or not candidate['url']:
            candidate['url'] = 'https://www.shl.com/missing-url'
            continue
        url = str(candidate['url'])
        if url.isdigit():
            candidate['url'] = f"https://www.shl.com/{url}"
            continue
        if not url.startswith(('http://', 'https://')):
            candidate['url'] = f"https://www.shl.com{url}" if url.startswith('/') else f"https://www.shl.com/{url}"
    return candidates

# --- Recommendation Logic ---
def recommend(query):
    if not query.strip():
        return {"error": "Please enter a job description"}
    try:
        top_k_df = get_relevant_passages(query, df_clean, top_k=20)
        if top_k_df.empty:
            return {"error": "No matching assessments found"}
        top_k_df['test_type'] = top_k_df['test_type'].apply(
            lambda x: x if isinstance(x, list) else
            (eval(x) if isinstance(x, str) and x.startswith('[') else [str(x)])
        )
        top_k_df['duration'] = top_k_df['duration'].fillna(-1).astype(int)
        top_k_df.loc[top_k_df['duration'] == -1, 'duration'] = None
        candidates = top_k_df.to_dict(orient="records")
        candidates = validate_and_fix_urls(candidates)
        result = rerank(query, candidates)
        if 'recommended_assessments' in result:
            result['recommended_assessments'] = validate_and_fix_urls(result['recommended_assessments'])
        return result
    except Exception as e:
        import traceback
        print(traceback.format_exc())
        return {"error": f"Error processing request: {str(e)}"}

# --- Gradio Interface ---
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."
)

# ✅ Mount Gradio UI without overwriting `app`
mount_gradio_app(app, iface, path="/")

# --- Health Endpoint ---
@app.get("/health")
async def health_check():
    return JSONResponse(
        content={"status": "healthy"},
        media_type="application/json",
        status_code=200
    )

# --- API Recommendation Endpoint ---
@app.post("/recommend")
async def recommend_api(request: Request):
    try:
        body = await request.json()
        query = body.get("query", "").strip()
        if not query:
            return JSONResponse(
                content={"error": "Missing 'query' in request body"},
                media_type="application/json",
                status_code=400
            )
        result = recommend(query)
        return JSONResponse(
            content=result,
            media_type="application/json",
            status_code=200
        )
    except Exception as e:
        return JSONResponse(
            content={"error": str(e)},
            media_type="application/json",
            status_code=500
        )