from flask import Flask, request, jsonify
from flask_cors import CORS
import os
from datetime import datetime
import numpy as np
from PIL import Image
from tensorflow.keras.models import load_model

app = Flask(__name__)
CORS(app)

UPLOAD_FOLDER = os.path.join(os.path.dirname(__file__), 'uploads')
os.makedirs(UPLOAD_FOLDER, exist_ok=True)

# 1. Sesuaikan nama file model!
MODEL_PATH = os.path.join(os.path.dirname(__file__), 'model_padi.h5')

# 2. Sesuaikan dengan urutan class di Colab kamu (4 class)
CLASS_NAMES = [
    'Healthy',
    'Blast',
    'Blight',
    'Tungro'
]

DESCRIPTIONS = {
    'Healthy': {
        'deskripsi': 'Kondisi tanaman sehat.',
        'solusi': 'Lanjutkan perawatan normal dan pemantauan rutin.'
    },
    'Blast': {
        'deskripsi': 'Blast adalah penyakit daun padi akibat jamur Pyricularia oryzae.',
        'solusi': 'Lakukan pengendalian jamur dan semprot fungisida sesuai anjuran.'
    },
    'Blight': {
        'deskripsi': 'Blight merupakan hawar daun bakteri.',
        'solusi': 'Gunakan varietas tahan dan sanitasi lahan yang baik.'
    },
    'Tungro': {
        'deskripsi': 'Tungro adalah penyakit virus yang ditularkan oleh wereng.',
        'solusi': 'Lakukan pengendalian hama wereng dan gunakan benih sehat.'
    }
}

# Load model
model = None

try:
    model = load_model(MODEL_PATH)
    print('Model berhasil dimuat dari', MODEL_PATH)
except Exception as e:
    print("Gagal load model:", e)

def preprocess_image(path):

    image = Image.open(path).convert('RGB')

    image = image.resize((224, 224))

    image_array = np.array(image).astype('float32') / 255.0

    image_array = np.expand_dims(image_array, axis=0)

    return image_array

@app.route('/prediksi', methods=['POST'])
def prediksi():
    # 3. Menerima request dengan key 'gambar'
    if 'gambar' not in request.files:
        return jsonify({
            'error': 'Tidak ada gambar'
        }), 400

    file = request.files['gambar']

    if file.filename == '':
        return jsonify({
            'error': 'File kosong'
        }), 400

    # Simpan gambar
    filename = datetime.now().strftime('%Y%m%d%H%M%S_') + file.filename

    filepath = os.path.join(UPLOAD_FOLDER, filename)

    file.save(filepath)

    print("Gambar diterima:", filename)

    if model is None:
        return jsonify({'error': 'Model tidak tersedia. Pastikan file .h5 ada.'}), 500

    try:

        # Preprocessing
        image_array = preprocess_image(filepath)
        predictions = model.predict(image_array, verbose=0)
        predicted_index = int(np.argmax(predictions, axis=1)[0])
        confidence = float(np.max(predictions, axis=1)[0]) * 100.0
        label = CLASS_NAMES[predicted_index] if predicted_index < len(CLASS_NAMES) else f'Kelas {predicted_index + 1}'

        confidence_display = f'{confidence:.2f}%'
        all_predictions = {
            CLASS_NAMES[i]: float(predictions[0][i] * 100.0)
            for i in range(len(CLASS_NAMES))
        }
        description_data = DESCRIPTIONS.get(label, {
            'deskripsi': 'Tidak ada deskripsi tersedia.',
            'solusi': 'Tidak ada solusi tersedia.'
        })

        return jsonify({
            'penyakit': label,
            'confidence': confidence_display,
            'all_predictions': all_predictions,
            'deskripsi': description_data['deskripsi'],
            'solusi': description_data['solusi']
        })

    except Exception as e:

        print("ERROR:", e)

        return jsonify({
            'error': str(e)
        }), 500


if __name__ == '__main__':
    print('=' * 50)
    print('Klasifikasi Penyakit Daun Padi')
    print('=' * 50)
    app.run(host='127.0.0.1', port=5000, debug=False)