# app.py
import gradio as gr
from pipeline import process_answers_pipeline  # Import the centralized pipeline function
from questions import questions  # Import questions list

def process_answers(
    sleep,
    exercise,
    mood,
    stress_level,
    wellness_goals,
    dietary_restrictions,
    eating_habits,
    relaxation_time,
    health_issues,
    stress_management,
    daily_routine,
    bedtime_routine,
    water_intake,
    mindfulness_frequency,
    mindset,
    personal_growth_reflection,
    break_frequency,
    relaxation_activities,
    self_care_time,
    outdoor_activity_frequency,
    gratitude_practice,
    home_cooked_meals,
    uninterrupted_sleep,
    gratitude_feelings,
    connection_rating,
    activity_tracking,
    strength_training,
    energy_rating
):
    # Explicit mapping of responses to corresponding questions
    responses = {
        questions[0]: sleep,
        questions[1]: exercise,
        questions[2]: mood,
        questions[3]: stress_level,
        questions[4]: wellness_goals,
        questions[5]: dietary_restrictions,
        questions[6]: eating_habits,
        questions[7]: relaxation_time,
        questions[8]: health_issues,
        questions[9]: stress_management,
        questions[10]: daily_routine,
        questions[11]: bedtime_routine,
        questions[12]: water_intake,
        questions[13]: mindfulness_frequency,
        questions[14]: mindset,
        questions[15]: personal_growth_reflection,
        questions[16]: break_frequency,
        questions[17]: relaxation_activities,
        questions[18]: self_care_time,
        questions[19]: outdoor_activity_frequency,
        questions[20]: gratitude_practice,
        questions[21]: home_cooked_meals,
        questions[22]: uninterrupted_sleep,
        questions[23]: gratitude_feelings,
        questions[24]: connection_rating,
        questions[25]: activity_tracking,
        questions[26]: strength_training,
        questions[27]: energy_rating
    }

    # Process responses using the centralized pipeline
    results = process_answers_pipeline(responses)

    # Format outputs using results from the pipeline
    wellness_report = f"**Wellness Report**\n------------------\n{results['report'].strip()}"

    # Updated Identified Problems section to display eight new themes
    identified_problems = (
        "**Identified Problems**\n"
        "-----------------------\n"
        f"Stress Management: {results['problems'].get('stress_management', 'N/A')}%\n"
        f"Low Therapy: {results['problems'].get('low_therapy', 'N/A')}%\n"
        f"Balanced Weight: {results['problems'].get('balanced_weight', 'N/A')}%\n"
        f"Restless Night: {results['problems'].get('restless_night', 'N/A')}%\n"
        f"Lack of Motivation: {results['problems'].get('lack_of_motivation', 'N/A')}%\n"
        f"Gut Health: {results['problems'].get('gut_health', 'N/A')}%\n"
        f"Anxiety: {results['problems'].get('anxiety', 'N/A')}%\n"
        f"Burnout: {results['problems'].get('burnout', 'N/A')}%"
    )

    recommendations = (
        "**Recommendations**\n"
        "--------------------\n"
        f"{results['recommendation'].strip()}"
    )

    summary_shown = (
        "**Summary (SHOWN TO USER)**\n"
        "-----------------\n"
        f"{results['final_summary'].strip()}"
    )

    final_summary_video = (
        "**Final Summary (FOR VIDEO CREATION)**\n"
        "-----------------\n"
        f"{results['shortened_summary'].strip()}"
    )

    return wellness_report, identified_problems, recommendations, summary_shown, final_summary_video

iface = gr.Interface(
    fn=process_answers,
    inputs=[gr.Textbox(label=q) for q in questions],
    outputs=[
        gr.Markdown(label="Wellness Report"),
        gr.Markdown(label="Identified Problems"),
        gr.Markdown(label="Recommendations"),
        gr.Markdown(label="Summary (SHOWN TO USER)"),
        gr.Markdown(label="Final Summary (FOR VIDEO CREATION)")
    ],
    title="Wellness Report Generator",
    description="Answer the questions to generate a wellness report, problem analysis, recommendations, and a final summary."
)

iface.launch()