from fastapi import FastAPI, File, UploadFile, HTTPException
from PIL import Image
import numpy as np
from io import BytesIO
import math
import pickle
import os

app = FastAPI(title="Fingerprint detection API")

som_model = None
classification_matrix = None

def sobel(I):
    m, n = I.shape
    Gx = np.zeros([m-2, n-2], np.float32)
    Gy = np.zeros([m-2, n-2], np.float32)
    gx = [[-1, 0, 1], [-2, 0, 2], [-1, 0, 1]]
    gy = [[1, 2, 1], [0, 0, 0], [-1, -2, -1]]

    for j in range(1, m-2):
        for i in range(1, n-2):
            Gx[j-1, i-1] = sum(sum(I[j-1:j+2, i-1:i+2] * gx))
            Gy[j-1, i-1] = sum(sum(I[j-1:j+2, i-1:i+2] * gy))

    return Gx, Gy

def medfilt2(G, d=3):
    m, n = G.shape
    temp = np.zeros([m+2*(d//2), n+2*(d//2)], np.float32)
    salida = np.zeros([m, n], np.float32)
    temp[1:m+1, 1:n+1] = G

    for i in range(1, m):
        for j in range(1, n):
            A = np.asarray(temp[i-1:i+2, j-1:j+2]).reshape(-1)
            salida[i-1, j-1] = np.sort(A)[d+1]

    return salida

def orientacion(patron, w):
    Gx, Gy = sobel(patron)
    Gx = medfilt2(Gx)
    Gy = medfilt2(Gy)
    m, n = Gx.shape
    mOrientaciones = np.zeros([m//w, n//w], np.float32)

    for i in range(m//w):
        for j in range(n//w):
            YY = sum(sum(2*Gx[i*w:(i+1)*w, j*w:(j+1)*w]*Gy[i*w:(i+1)*w, j*w:(j+1)*w]))
            XX = sum(sum(Gx[i*w:(i+1)*w, j*w:(j+1)*w]**2-Gy[i*w:(i+1)*w, j*w:(j+1)*w]**2))
            mOrientaciones[i, j] = (0.5*math.atan2(YY, XX) + math.pi/2.0)*(180.0/math.pi)

    return mOrientaciones

def representativo(image_array):
    if isinstance(image_array, np.ndarray):
        if len(image_array.shape) == 3:
            image_array = np.mean(image_array, axis=2)
        im = Image.fromarray(image_array.astype(np.uint8))
    else:
        im = image_array

    im = im.resize((256, 256))
    m, n = im.size
    imarray = np.array(im, np.float32)
    patron = imarray[1:m-1, 1:n-1]
    EE = orientacion(patron, 14)

    return np.asarray(EE).reshape(-1)

def is_valid_fingerprint_features(features):
    if features is None or len(features) != 324:
        return False

    if np.any(np.isnan(features)) or np.any(np.isinf(features)):
        return False

    if np.min(features) < 0 or np.max(features) > 180:
        return False

    orientation_variance = np.var(features)
    if orientation_variance < 100:
        return False

    bins = np.histogram(features, bins=18, range=(0, 180))[0]
    non_empty_bins = np.sum(bins > 0)

    if non_empty_bins < 6:
        return False

    return True

def load_trained_model():
    global som_model, classification_matrix

    try:
        if os.path.exists('somhuella.pkl'):
            with open('somhuella.pkl', 'rb') as f:
                som_model = pickle.load(f)
            print("OK model")
        else:
            print("cargar somhuella.pkl")
            return False

        if os.path.exists('matrizMM.txt'):
            classification_matrix = np.loadtxt('matrizMM.txt')
            print("OK matrix")
        else:
            print("load matrix")
            return False

        return True
    except Exception as e:
        print(f"error {e}")
        return False

def detect_and_classify_fingerprint(features):
    global som_model, classification_matrix

    if not is_valid_fingerprint_features(features):
        return False, "no fingerprint patterns"

    if som_model is None or classification_matrix is None:
        return True, "Fingerprint pattern detected"

    try:
        winner = som_model.winner(features)

        classification_value = classification_matrix[winner]
        if classification_value == -1:
            return False, "no pattern"

        class_names = {
            0: "LEFT_LOOP",
            1: "RIGHT_LOOP", 
            2: "WHORL",
            3: "ARCO"
        }

        class_name = class_names.get(int(classification_value), "UNKNOWN")

        return True, f"{class_name} fingerprint detected (class {int(classification_value)})"

    except Exception as e:
        print(f"Error in SOM class: {e}")
        return True, "Fingerprint pattern detected (classification error)"

load_trained_model()

@app.post("/detect_fingerprint/")
async def detect_fingerprint(file: UploadFile = File(...)):
    try:
        contents = await file.read()
        image = Image.open(BytesIO(contents))
        image_array = np.array(image)
        features = representativo(image_array)
        is_fingerprint, details = detect_and_classify_fingerprint(features)

        return {
            "fingerprint_detected": is_fingerprint,
            "details": details
        }

    except Exception as e:
        raise HTTPException(status_code=500, detail=f"error processing image: {str(e)}")