import numpy as np
import scipy
from scipy.signal import savgol_filter
from typing import Dict, List
import matplotlib.pyplot as plt
import io
import base64
import google.generativeai as genai
import faiss
from openai import OpenAI
import json
import os
import pandas as pd

genai.configure(
    api_key=os.environ.get("GOOGLE_API_KEY")
)
model = genai.GenerativeModel("gemini-2.5-flash")

BASE_DIR = os.path.dirname(os.path.abspath(__file__))
csv_path = os.path.join(BASE_DIR, "..", "data", "CATHODES_DATASET.csv")
csv_path = os.path.abspath(csv_path)

df_base = pd.read_csv(csv_path)

def query_faiss_index(query_text, 
                      faiss_index_path=None,
                      metadata_path=None,
                      top_k=5):
    openai_api_key = os.getenv("OPENAI_API_KEY")
    if not openai_api_key:
        raise ValueError("OPENAI_API_KEY is not set")

    client = OpenAI(api_key=openai_api_key)
    
    BASE_DIR = os.path.dirname(os.path.abspath(__file__))

    if faiss_index_path is None:
        faiss_index_path = os.path.join(BASE_DIR, "../sentiment/faiss_index.idx")
    if metadata_path is None:
        metadata_path = os.path.join(BASE_DIR, "../sentiment/metadata.json")

    # Load index and metadata
    index = faiss.read_index(faiss_index_path)
    with open(metadata_path, "r", encoding="utf-8") as f:
        metadata = json.load(f)

    # Get embedding for query
    response = client.embeddings.create(
        input=query_text.lower(),
        model="text-embedding-3-large"
    )
    query_embedding = response.data[0].embedding
    query_embedding_np = np.array([query_embedding]).astype("float32")
    faiss.normalize_L2(query_embedding_np)

    # Search index
    distances, indices = index.search(query_embedding_np, top_k)
    results = []
    for dist, idx in zip(distances[0], indices[0]):
        meta = metadata[idx]
        results.append({
            "score": float(dist),
            "source_pdf": meta["source_pdf"],
            "page": meta["page"],
            "chunk_index": meta["chunk_index"],
            "text_snippet": meta["text"]
        })
    return results


def calculate_cv(input_data: Dict) -> Dict:
    V_start = input_data["V_start"]
    V_switch = input_data["V_switch"]
    scan_rate = input_data["scan_rate"]
    dt = input_data["dt"]
    sigma = input_data["sigma"]
    E0 = input_data["E0"]
    Ip = input_data["Ip"]

    # --- Time & Voltage Arrays ---
    t_up = np.arange(0, (V_switch - V_start) / scan_rate, dt)
    t_down = np.arange(0, (V_switch - V_start) / scan_rate, dt)
    V_up = V_start + scan_rate * t_up
    V_down = V_switch - scan_rate * t_down
    V = np.concatenate([V_up, V_down])

    # --- Simulated CV current ---
    I_ox = Ip * np.exp(-((V - E0) ** 2) / (2 * sigma ** 2))
    I_red = -Ip * np.exp(-((V - (E0 - 0.06)) ** 2) / (2 * sigma ** 2))
    I = I_ox + I_red

    # --- Peak Analysis ---
    idx_ox = np.argmax(I)
    idx_red = np.argmin(I)
    V_ox = float(V[idx_ox])
    V_red = float(V[idx_red])
    delta_V_peak = V_ox - V_red

    # --- Integrated Charge (Coulombs) ---
    # ∫ I dt = ∫ I dV × (1/scan_rate)  ⇒ simps(I, V) / scan_rate
    Q = float(scipy.integrate.simpson(I, V) / scan_rate)

    return {
        "t": np.concatenate([t_up, t_down]).tolist(),
        "V": V.tolist(),
        "I": I.tolist(),
        "V_ox": V_ox,
        "V_red": V_red,
        "delta_V_peak": delta_V_peak,
        "Q_integrated": Q
    }

def calculate_eis(data: Dict) -> Dict:
    freqs = np.array(data["frequencies"], dtype=float)
    Rs, Rct, Cdl, sigma_w = data["Rs"], data["Rct"], data["Cdl"], data["sigma_w"]
    omega = 2*np.pi*freqs
    j     = 1j

    # Warburg impedance
    Zw = sigma_w*(1 - j)/np.sqrt(omega)

    # Admittances
    Y_Rct = 1/Rct
    Y_Cdl = j * omega * Cdl
    Y_W   = 1/Zw

    Y_par     = Y_Rct + Y_Cdl + Y_W
    Z_parallel= 1/Y_par
    Z_total   = Rs + Z_parallel

    # Return real & imag parts separately
    return {
        "frequencies": freqs.tolist(),
        "Z_real":      np.real(Z_total).tolist(),
        "Z_imag":      np.imag(Z_total).tolist()
    }

def compute_d2QdV2(
    V: List[float],
    Q: List[float],
    window: int = 21,
    poly: int = 3
) -> Dict[str, List[float]]:
    V = np.array(V, dtype=float)
    Q = np.array(Q, dtype=float)

    # Ensure monotonic V
    if not np.all(np.diff(V) > 0):
        idx = np.argsort(V)
        V = V[idx]
        Q = Q[idx]

    # Smooth and differentiate
    Qs = savgol_filter(Q, window_length=window, polyorder=poly)
    dQdV   = np.gradient(Qs, V)
    d2QdV2 = np.gradient(dQdV, V)

    return {"dQdV": dQdV.tolist(), "d2QdV2": d2QdV2.tolist()}

def plot_cv(V, I):
    fig, ax = plt.subplots()
    ax.plot(V, I, color='blue')
    ax.set_title("Cyclic Voltammetry")
    ax.set_xlabel("Voltage (V)")
    ax.set_ylabel("Current (A)")
    ax.grid(True)
    return fig_to_base64(fig)

def plot_eis(Z_real, Z_imag):
    fig, ax = plt.subplots()
    ax.plot(Z_real, -np.array(Z_imag), 'o-', color='green')
    ax.set_title("Nyquist Plot (EIS)")
    ax.set_xlabel("Z' (Ω)")
    ax.set_ylabel("-Z'' (Ω)")
    ax.grid(True)
    return fig_to_base64(fig)

def plot_dqdv(V, dQdV, d2QdV2):
    fig, ax = plt.subplots()
    ax.plot(V, dQdV, label="dQ/dV", color='orange')
    ax.plot(V, d2QdV2, label="d²Q/dV²", color='red')
    ax.set_title("Q–V Derivatives")
    ax.set_xlabel("Voltage (V)")
    ax.set_ylabel("Derivative")
    ax.legend()
    ax.grid(True)
    return fig_to_base64(fig)

def fig_to_base64(fig):
    buf = io.BytesIO()
    fig.savefig(buf, format="png", bbox_inches="tight")
    buf.seek(0)
    img_base64 = base64.b64encode(buf.read()).decode("utf-8")
    plt.close(fig)
    return img_base64

def image_to_part(base64_str: str) -> dict:
    return {
        "inline_data": {
            "mime_type": "image/png",
            "data": base64_str
        }
    }

def analyze_plots_with_gemini(cv_img: str, eis_img: str, qv_img: str, cathode_name: str, faiss_results: list) -> str:
    prompt = (
        f"""Remove the underscores and .pdf from the source_pdf field in the RAG section below and put it as References at the end of the explanation.
        You are to explain the results of the calculations of a sodium-ion full cell battery using hard carbon and {cathode_name}. You are a RAG system  that takes information only from the RAG section below.
        And respond with extensive/long explanation in a scientific way and straight to the point without any additional text. Do not include opinions just explanations
        of the results of the calculations.
        Lastly shortly analyze the performance of the full cell battery.

        These are three plots from sodium-ion battery electrochemical analysis.
        Please summarize the main features observed in:
        1. Cyclic Voltammetry (CV)
        2. Electrochemical Impedance Spectroscopy (EIS)
        3. Q–V and d²Q/dV² analysis
        Include observations on redox peaks, charge transfer resistance, and plateau features.
        
        Remove the underscores and .pdf from the source_pdf field in the RAG section below and put it as References at the end of the explanation. Do not include the PDF file name directly in the explanation.
        At the end of the explanation, list the full source_pdf file names used as references.
        RAG Section, use only the information from this section to explain the results:
        {json.dumps(faiss_results, indent=2)}"""
    )

    try:
        response = model.generate_content([
            prompt,
            image_to_part(cv_img),
            image_to_part(eis_img),
            image_to_part(qv_img),
        ])

        if response.candidates:
            parts = response.candidates[0].content.parts
            text_output = " ".join(
                p.text for p in parts if hasattr(p, "text") and p.text
            )
            return text_output.strip()
        else:
            return "Gemini returned no candidates."

    except Exception as e:
        return f"Error from Gemini API: {e}"

def calculate_all_c(cathode_name: str, input_data: Dict) -> Dict:

    query_text = (
        f"Sodium-ion battery with hard carbon anode and cathode {cathode_name}. "
    )

    faiss_results = query_faiss_index(query_text, top_k=5)

    cv  = calculate_cv(input_data)
    eis = calculate_eis(input_data)
    deriv = compute_d2QdV2(
        V      = input_data["V_qv"],
        Q      = input_data["Q_qv"],
        window = input_data["window"],
        poly   = input_data["poly"]
    )

    cv_plot  = plot_cv(cv["V"], cv["I"])
    eis_plot = plot_eis(eis["Z_real"], eis["Z_imag"])
    qv_plot  = plot_dqdv(input_data["V_qv"], deriv["dQdV"], deriv["d2QdV2"])

    summary = analyze_plots_with_gemini(cv_plot, eis_plot, qv_plot, cathode_name, faiss_results)

    return {
        "plots": {
            "cv_plot":  cv_plot,
            "eis_plot": eis_plot,
            "qv_plot":  qv_plot,
        },
        "Gemini_Explanation": summary
    }