import gradio as gr
import pandas as pd
import PyPDF2
import json
import re

# Parse uploaded transcript file
def parse_transcript(file):
    if file.name.endswith('.csv'):
        df = pd.read_csv(file.name)
    elif file.name.endswith(('.xls', '.xlsx')):
        df = pd.read_excel(file.name)
    elif file.name.endswith('.pdf'):
        reader = PyPDF2.PdfReader(file)
        text = ""
        for page in reader.pages:
            text += page.extract_text() or ""
        df = pd.DataFrame({'Transcript_Text': [text]})
    else:
        raise ValueError("Unsupported file format. Use .csv, .xlsx, or .pdf")
    return df

# Extract student info
def extract_transcript_info(df):
    transcript_text = df['Transcript_Text'].iloc[0] if 'Transcript_Text' in df.columns else ''
    info = {}
    name_match = re.search(r"Name[:\s]+([A-Z][a-z]+\s[A-Z][a-z]+)", transcript_text)
    if name_match:
        info['Name'] = name_match.group(1)
    gpa_match = re.findall(r'(GPA|Grade Point Average)[^\d]*(\d+\.\d+)', transcript_text, re.IGNORECASE)
    if gpa_match:
        if len(gpa_match) == 1:
            info['GPA'] = gpa_match[0][1]
        elif len(gpa_match) >= 2:
            info['Unweighted_GPA'] = gpa_match[0][1]
            info['Weighted_GPA'] = gpa_match[1][1]
    grade_match = re.search(r'Grade:?[\s]*(\d{1,2})', transcript_text, re.IGNORECASE)
    if grade_match:
        info['Grade_Level'] = grade_match.group(1)
    courses = re.findall(r'(?i)\b([A-Z][a-zA-Z\s&/]+)\s+(\d{1,3})\b', transcript_text)
    if courses:
        info['Courses'] = list(set([c[0].strip() for c in courses]))
    return info

# Learning style questions - from educationplanner.org
learning_style_questions = [
    "When you are learning something new, you prefer to:",
    "When you are at home, you like to:",
    "When you spell a word, you remember it by:",
    "When you read, you:",
    "When you write, you:",
    "When you listen to music, you:",
    "When you work at solving a problem, you:",
    "When you give someone directions, you:",
    "When you are concentrating, you:",
    "When you meet someone new, you remember them by:"
]

learning_style_answers = [
    ["Watch someone do it", "Listen to someone explain it", "Read about it"],
    ["Watch TV or play video games", "Listen to music or talk to people", "Read books or write stories"],
    ["Seeing the word in your mind", "Saying the word out loud", "Writing the word down"],
    ["See the action in your mind", "Hear the characters talk", "Focus on the written words"],
    ["Use diagrams or doodles", "Talk about ideas", "Write detailed notes"],
    ["Appreciate the rhythm and melodies", "Easily remember lyrics", "Analyze the lyrics"],
    ["Visualize the solution", "Discuss the problem", "Write out the steps"],
    ["Draw a map", "Give spoken directions", "Write directions"],
    ["Picture things", "Say things out loud", "Write or read quietly"],
    ["Remember faces", "Remember names or voices", "Remember what you wrote about them"]
]

style_count_map = {0: "visual", 1: "auditory", 2: "reading/writing"}

def learning_style_quiz(*answers):
    scores = {'visual': 0, 'auditory': 0, 'reading/writing': 0}

    for i, ans in enumerate(answers):
        if i < len(learning_style_answers):
            options = learning_style_answers[i]
            if ans in options:
                index = options.index(ans)
                style = style_count_map[index]
                scores[style] += 1

    max_score = max(scores.values())
    best_styles = [style.capitalize() for style, score in scores.items() if score == max_score]

    return ", ".join(best_styles)

# PanoramaEd categories and multiple choice questions
get_to_know_categories = {
    "All About Me": [
        ("What’s your favorite way to spend a day off?", []),
        ("If you could only eat one food for the rest of your life, what would it be?", []),
        ("Do you have any pets? If so, what are their names?", []),
        ("If you could travel anywhere in the world, where would you go?", []),
        ("What’s your favorite holiday or tradition?", []),
        ("What are some of your favorite movies or shows?", []),
        ("Do you have a favorite book or book series? Why?", []),
        ("Who is a character from a show, book, or movie that you relate to? Why?", []),
        ("If you could be any fictional character, who would you be and why?", [])
    ],
    "Hopes and Dreams": [
        ("What do you want to be when you grow up?", []),
        ("What’s something you hope to achieve this year?", []),
        ("If you could change the world in one way, what would you do?", []),
        ("What are you most proud of?", []),
        ("What’s a big dream you have for your future?", [])
    ],
    "School Life": [
        ("What’s your favorite subject in school?", []),
        ("What’s something that makes learning easier for you?", []),
        ("Do you prefer working alone or in groups?", []),
        ("What helps you feel confident in class?", []),
        ("What’s something you’re good at in school?", [])
    ],
    "Relationships": [
        ("Who do you look up to and why?", []),
        ("Who is someone that makes you feel safe and supported?", []),
        ("Do you have a best friend? What do you like to do together?", []),
        ("What’s one thing you wish people knew about you?", []),
        ("What’s something kind you’ve done for someone else?", [])
    ]
}

def generate_learning_plan(info):
    level = info.get("Grade_Level", "unknown")
    courses = info.get("Courses", [])
    gpa = info.get("GPA", info.get("Unweighted_GPA", "N/A"))
    return f"""
📘 **Personalized Learning Plan**
- Grade Level: {level}
- GPA: {gpa}
- Suggested Focus Areas: {', '.join(courses[:3]) if courses else 'N/A'}
- Goals: Strengthen key subjects, explore interests, and build study habits.
"""

def generate_learning_style_summary(style):
    return f"""
🧠 **Learning Style Summary**
You are a **{style}** learner. That means you learn best through {"visual aids like charts and images" if "Visual" in style else "listening and verbal instruction" if "Auditory" in style else "reading and writing-based methods"}.
"""

def generate_motivation_section(responses):
    hopes = [ans for q, ans in responses.items() if "hope" in q.lower() or "dream" in q.lower()]
    return f"""
💡 **Motivational Summary**
Your dreams are powerful: {'; '.join(hopes) if hopes else 'You are filled with potential!'}. 
Believe in yourself and keep moving forward.
"""

def save_profile(file, *inputs):
    try:
        if not file:
            return "⚠️ Please upload your transcript."

        quiz_answers = inputs[:len(learning_style_questions)]
        if any(ans is None for ans in quiz_answers):
            return "⚠️ Please answer all the learning style questions."

        blog_checkbox = inputs[len(learning_style_questions)]
        blog_text = inputs[len(learning_style_questions)+1]
        category_answers = inputs[len(learning_style_questions)+2:]

        if any(ans.strip() == "" for ans in category_answers):
            return "⚠️ Please complete all 'Get to Know You' sections before saving."

        if blog_checkbox and blog_text.strip() == "":
            return "⚠️ You checked the blog option but didn’t write anything. Please write your mini blog or uncheck the option."

        df = parse_transcript(file)
        transcript_info = extract_transcript_info(df)
        learning_type = learning_style_quiz(*quiz_answers)

        question_texts = [q for cat in get_to_know_categories.values() for q, _ in cat]
        responses = dict(zip(question_texts, category_answers))

        profile = {
            "transcript": df.to_dict(orient='records'),
            "transcript_info": transcript_info,
            "learning_style": learning_type,
            "get_to_know_answers": responses,
            "blog": blog_text if blog_checkbox else "[User chose to skip this section]"
        }

        summary = {
            "Learning_Plan": generate_learning_plan(transcript_info),
            "Style_Summary": generate_learning_style_summary(learning_type),
            "Motivation": generate_motivation_section(responses)
        }

        with open("student_profile.json", "w") as f:
            json.dump(profile, f, indent=4)

        with open("student_summary.md", "w") as f:
            f.write(summary["Learning_Plan"] + '\n' + summary["Style_Summary"] + '\n' + summary["Motivation"])

        return f"✅ Profile saved! Your learning style is: {learning_type}"
    
    except Exception as e:
        return f"❌ Error: {str(e)}"

# Build Gradio UI
with gr.Blocks() as demo:
    gr.Markdown("## 🎓 Personalized AI Student Assistant")

    with gr.Row():
        file = gr.File(label="📄 Upload Your Transcript (.csv, .xlsx, .pdf)")

    with gr.Column():
        gr.Markdown("### 🧠 Learning Style Discovery")
        quiz_components = []
        for i, (question, options) in enumerate(zip(learning_style_questions, learning_style_answers)):
            quiz_components.append(gr.Radio(
                choices=options,
                label=f"{i+1}. {question}"
            ))

    category_inputs = []
    for category, questions in get_to_know_categories.items():
        gr.Markdown(f"### 📘 {category}")
        for q_text, _ in questions:
            category_inputs.append(gr.Textbox(label=q_text))

    blog_checkbox = gr.Checkbox(label="📝 I'd like to write a mini blog about myself")
    blog_text = gr.Textbox(lines=5, label="✍️ Mini Blog", visible=False)

    blog_checkbox.change(fn=lambda x: gr.update(visible=x), inputs=blog_checkbox, outputs=blog_text)

    submit = gr.Button("🗕️ Save My Profile")
    output = gr.Textbox(label="Status")

    submit.click(fn=save_profile,
                 inputs=[file, *quiz_components, blog_checkbox, blog_text, *category_inputs],
                 outputs=[output])

if __name__ == '__main__':
    demo.launch()