#!/usr/bin/env python
# coding=utf-8
import datetime
import re
from fpdf import FPDF
from langdetect import detect
import gradio as gr

from tools.common import prepend_metadata_questions  # ✅ Import helper

# === PDF Export Function ===
def export_text_to_pdf(text, metadata=None, output_path=None, language="en"):
    if output_path is None:
        timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
        output_path = f"data_governance_record_{timestamp}.pdf"

    pdf = FPDF()
    pdf.add_page()
    pdf.set_auto_page_break(auto=True, margin=15)

    # Title
    pdf.set_font("Arial", 'B', 16)
    pdf.set_text_color(0, 51, 102)
    title = "Data Governance and Quality Record" if language == "en" else "Dossier de Gouvernance et Qualité des Données"
    pdf.cell(0, 15, title, ln=True, align='C')
    pdf.ln(10)

    # Metadata block
    if metadata:
        pdf.set_font("Arial", '', 12)
        pdf.set_text_color(90, 90, 90)
        pdf.multi_cell(0, 10, f"Organization: {metadata.get('organization', 'N/A')}")
        pdf.multi_cell(0, 10, f"Completed by: {metadata.get('completed_by', 'N/A')} ({metadata.get('role', 'N/A')})")
        pdf.multi_cell(0, 10, f"Timestamp: {metadata.get('timestamp', 'N/A')}")
        pdf.ln(5)

    # Body
    pdf.set_font("Arial", '', 12)
    pdf.set_text_color(0, 0, 0)
    for line in text.strip().split('\n'):
        line = line.strip()
        if line.startswith("## "):
            section_title = line.replace("## ", "").strip()
            pdf.set_font("Arial", 'B', 13)
            pdf.set_text_color(30, 30, 120)
            pdf.ln(8)
            pdf.cell(0, 10, section_title, ln=True)
            pdf.set_font("Arial", '', 12)
            pdf.set_text_color(0, 0, 0)
        elif line.startswith("- **"):
            match = re.match(r"- \*\*(.+?)\*\*: (.+)", line)
            if match:
                label, answer = match.groups()
                pdf.set_font("Arial", 'B', 12)
                pdf.cell(0, 10, f"{label}:", ln=True)
                pdf.set_font("Arial", '', 12)
                pdf.multi_cell(0, 10, answer)
        elif line == "---":
            pdf.line(10, pdf.get_y(), 200, pdf.get_y())
            pdf.ln(5)
        else:
            pdf.multi_cell(0, 10, line)

    pdf.output(output_path)
    return output_path


# === Core Questions ===
BASE_QUESTIONS = [
    ("dataset_description", "Please describe the dataset(s) used."),
    ("data_sources", "What are the sources of the data?"),
    ("data_collection_method", "How was the data collected?"),
    ("preprocessing", "What preprocessing steps were applied?"),
    ("representativeness", "Is the data representative of the use case?"),
    ("bias_handling", "How are biases identified and mitigated?"),
    ("data_split", "How is the data split (training/testing/validation)?"),
    ("missing_data", "How is missing or incomplete data handled?"),
    ("updates", "How is data kept up-to-date or refreshed?"),
    ("access_control", "Who has access to the data and under what conditions?")
]

QUESTIONS = prepend_metadata_questions(BASE_QUESTIONS)  # ✅ Prepend metadata

def get_questions():
    return QUESTIONS

# === Run Tool ===
def run_tool():
    state = {"step": 0, "answers": {}}

    def step_by_step_agent(user_input, state):
        step = state["step"]
        answers = state["answers"]

        if step > 0:
            key, _ = QUESTIONS[step - 1]
            answers[key] = user_input

        if step < len(QUESTIONS):
            next_q = QUESTIONS[step][1]
            state["step"] += 1
            return next_q, state, None

        content = "\n".join([f"- **{label}**: {answers.get(key, '')}" for key, label in QUESTIONS])
        detected_lang = detect(content)

        # ✅ Extract metadata from prepended fields
        metadata = {
            "organization": answers.get("organization_name", "N/A"),
            "completed_by": answers.get("user_name", "N/A"),
            "role": answers.get("user_role", "N/A"),
            "timestamp": datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
        }

        pdf_path = export_text_to_pdf(content, metadata=metadata, language=detected_lang)
        return "✅ Documentation complete. Download below.", {"done": True}, pdf_path

    with gr.Blocks(title="Data Governance Tool") as demo:
        chatbot = gr.Chatbot(
            label="📊 Data Governance Assistant",
            value=[{"role": "assistant", "content": QUESTIONS[0][1]}],
            type="messages"
        )
        msg = gr.Textbox(label="Your answer")
        state_var = gr.State(state)
        file_output = gr.File(label="Download PDF")
        reset_btn = gr.Button("🔁 Restart")

        def chat_logic(msg_in, state_in):
            reply, updated_state, file = step_by_step_agent(msg_in, state_in)
            messages = [{"role": "user", "content": msg_in}]
            if reply:
                messages.append({"role": "assistant", "content": reply})
            return messages, updated_state, file

        def reset():
            return [{"role": "assistant", "content": QUESTIONS[0][1]}], {"step": 0, "answers": {}}, None

        msg.submit(chat_logic, [msg, state_var], [chatbot, state_var, file_output])
        reset_btn.click(reset, outputs=[chatbot, state_var, file_output])

    demo.launch(show_api=False)