import gradio as gr
import face_recognition
import cv2
import numpy as np
import os
from PIL import Image
import io
import firebase_admin
from firebase_admin import credentials
from firebase_admin import db
from firebase_admin import storage
from datetime import datetime

# Initialize Firebase
cred = credentials.Certificate("path/to/serviceAccountKey.json") # Update the path to your Firebase credentials
firebase_admin.initialize_app(cred, {
    'databaseURL': 'https://faceantendancerealtime-default-rtdb.firebaseio.com/',
    'storageBucket': 'faceantendancerealtime.appspot.com'
})
bucket = storage.bucket()

# Load the known face encodings and their IDs from Firebase
def load_known_encodings():
    # Code to download the 'EncodeFile.p' from Firebase Storage
    # Assume 'EncodeFile.p' is already uploaded to Firebase Storage
    blob = bucket.blob('EncodeFile.p')
    blob.download_to_filename('/tmp/EncodeFile.p')
    with open('/tmp/EncodeFile.p', 'rb') as file:
        encodeListKnownWithIds = pickle.load(file)
    return encodeListKnownWithIds

encodeListKnownWithIds = load_known_encodings()
encodeListKnown, studentsIds = encodeListKnownWithIds

def recognize_face(input_image):
    # Convert the PIL Image to a numpy array
    img = np.array(input_image)
    
    # Convert the image to RGB
    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
    
    # Resize image for faster processing
    img_small = cv2.resize(img, (0, 0), None, 0.25, 0.25)
    
    # Find faces in the image
    face_locations = face_recognition.face_locations(img_small)
    face_encodings = face_recognition.face_encodings(img_small, face_locations)
    
    # Convert the coordinates to full scale since the image was scaled to 1/4 size
    face_locations = [(top*4, right*4, bottom*4, left*4) for top, right, bottom, left in face_locations]
    
    # Recognize faces
    for face_encoding, (top, right, bottom, left) in zip(face_encodings, face_locations):
        matches = face_recognition.compare_faces(encodeListKnown, face_encoding)
        name = "Unknown"
        
        # Use the known face with the smallest distance to the new face
        face_distances = face_recognition.face_distance(encodeListKnown, face_encoding)
        best_match_index = np.argmin(face_distances)
        if matches[best_match_index]:
            name = studentsIds[best_match_index]
        
        # Draw rectangles and names on the original image
        cv2.rectangle(img, (left, top), (right, bottom), (0, 0, 255), 2)
        cv2.putText(img, name, (left + 6, bottom - 6), cv2.FONT_HERSHEY_COMPLEX, 0.5, (255, 255, 255), 1)
    
    # Convert the image back to PIL format
    return Image.fromarray(img)

# Define the Gradio interface
iface = gr.Interface(
    fn=recognize_face,
    inputs=gr.inputs.Image(type="pil"),
    outputs=gr.outputs.Image(type="pil"),
    title="Face Recognition Attendance System",
    description="Upload an image to identify registered students."
)

# Run the Gradio app
if __name__ == "__main__":
    iface.launch()