import os
import shutil
from datetime import datetime

import cv2
import matplotlib.pyplot as plt
import numpy as np
from fastapi import UploadFile
from PIL import Image
from ultralytics import YOLO

# Models loaded once at import time
car_detection_model = YOLO(r"car_detection.pt")
part_detection_model = YOLO(r"car_part.pt")

DRIVER_SIDE = "Driver Side View"
PASSENGER_SIDE = "Passenger Side View"
FRONT_DRIVER_CORNER = "Front Driver Side Corner View"
FRONT_PASSENGER_CORNER = "Front Passenger Side Corner View"
REAR_DRIVER_CORNER = "Rear Driver Side Corner View"
REAR_PASSENGER_CORNER = "Rear Passenger Side Corner View"

CORNER_SWAP = {
    FRONT_PASSENGER_CORNER: FRONT_DRIVER_CORNER,
    FRONT_DRIVER_CORNER: FRONT_PASSENGER_CORNER,
    REAR_PASSENGER_CORNER: REAR_DRIVER_CORNER,
    REAR_DRIVER_CORNER: REAR_PASSENGER_CORNER,
}


def _enforce_side(label, desired_side):
    """Return label with the correct driver/passenger side applied."""
    if not desired_side or not label or label == "NA":
        return label
    if label in (DRIVER_SIDE, PASSENGER_SIDE):
        return desired_side if label != desired_side else label
    if label in CORNER_SWAP:
        wrong_keyword = "Passenger" if desired_side == DRIVER_SIDE else "Driver"
        return CORNER_SWAP[label] if wrong_keyword in label else label
    return label

MIN_RATIO = {
    # Front
    "Front-bumper": 0.015,
    "Grille": 0.010,
    "Headlight": 0.005,      # small but important
    "Hood": 0.020,
    "License-plate": 0.002,  # very small

    # Side
    "Front-door": 0.030,
    "Back-door": 0.030,
    "Front-wheel": 0.010,
    "Back-wheel": 0.010,
    "Mirror": 0.001,         # small but always relevant
    "Quarter-panel": 0.010,
    "Rocker-panel": 0.010,
    "Roof": 0.020,

    # Windows
    "Windshield": 0.020,
    "Front-window": 0.015,
    "Back-window": 0.015,
    "Back-windshield": 0.020,

    # Rear
    "Back-bumper": 0.015,
    "Tail-light": 0.005,     # small but important
    "Trunk": 0.020,

    # Catch-all fallback
    "default": 0.01
}

viewing_angle_rules = {
    "Front Right": {
        "must_be_visible": ["Front-bumper", "Grille", "Headlight", "Front-wheel", "Windshield", "Front-door", "Front-window", "Fender", "Mirror", "Rocker-panel"],
        "optional_parts": ["Hood", "Roof", "Back-door", "Back-wheel", "Back-window", "Quarter-panel"],
        "conflict_parts": ["Tail-light", "Back-bumper", "Back-windshield", "Trunk"]
    },
    "Right": {
        "must_be_visible": ["Front-door", "Back-door", "Mirror", "Quarter-panel", "Fender", "Rocker-panel", "Front-wheel", "Back-wheel", "Back-window", "Front-window"],
        "optional_parts": ["Roof", "Front-bumper", "Back-bumper", "Headlight", "Tail-light", "Hood", "Back-windshield", "Windshield", "Trunk", "Grille", "License-plate"],
        "conflict_parts": []
    },
    "Rear Right": {
        "must_be_visible": ["Back-bumper", "Tail-light", "Back-wheel", "Back-door", "Back-window", "Quarter-panel", "Back-windshield", "Rocker-panel", "Trunk"],
        "optional_parts": ["Roof", "License-plate", "Front-wheel", "Front-door", "Fender", "Mirror", "Front-window"],
        "conflict_parts": ["Front-bumper", "Headlight", "Grille", "Windshield", "Hood"]
    },
    "Rear Left": {
        "must_be_visible": ["Back-bumper", "Tail-light", "Back-wheel", "Back-door", "Back-window", "Quarter-panel", "Back-windshield", "Rocker-panel", "Trunk"],
        "optional_parts": ["Roof", "License-plate", "Front-wheel", "Front-door", "Fender", "Mirror", "Front-window"],
        "conflict_parts": ["Front-bumper", "Headlight", "Grille", "Windshield", "Hood"]
    },
    "Left": {
        "must_be_visible": ["Front-door", "Back-door", "Mirror", "Quarter-panel", "Fender", "Rocker-panel", "Front-wheel", "Back-wheel", "Back-window", "Front-window"],
        "optional_parts": ["Roof", "Front-bumper", "Back-bumper", "Headlight", "Tail-light", "Hood", "Back-windshield", "Windshield", "Trunk", "Grille", "License-plate"],
        "conflict_parts": []
    },
    "Front Left": {
        "must_be_visible": ["Front-bumper", "Grille", "Headlight", "Front-wheel", "Windshield", "Front-door", "Front-window", "Fender", "Mirror", "Rocker-panel"],
        "optional_parts": ["Hood", "Roof", "Back-door", "Back-wheel", "Back-window", "Quarter-panel"],
        "conflict_parts": ["Tail-light", "Back-bumper", "Back-windshield", "Trunk"]
    }
}


def compute_direction_mirror_refined(detected, fixed_label="Mirror"):
    if fixed_label not in detected:
        return "Unknown", None, None

    mirror_box = detected[fixed_label][0]
    mirror_center = ((mirror_box[0] + mirror_box[2]) / 2, (mirror_box[1] + mirror_box[3]) / 2)

    groupA = ["Windshield", "Hood", "Headlight", "Front-bumper", "Front-wheel"]
    groupB = ["Back-wheel", "Back-door", "Quarter-panel", "Rocker-panel", "Back-window"]

    offsets_A = []
    offsets_B = []
    radial_lines = []

    for part in groupA:
        if part in detected:
            for box in detected[part]:
                part_center = ((box[0] + box[2]) / 2, (box[1] + box[3]) / 2)
                offset = part_center[0] - mirror_center[0]
                offsets_A.append(offset)
                radial_lines.append((mirror_center, part_center))

    for part in groupB:
        if part in detected:
            for box in detected[part]:
                part_center = ((box[0] + box[2]) / 2, (box[1] + box[3]) / 2)
                offset = part_center[0] - mirror_center[0]
                offsets_B.append(offset)
                radial_lines.append((mirror_center, part_center))

    voteA = None
    voteB = None

    if offsets_A:
        avg_A = sum(offsets_A) / len(offsets_A)
        voteA = "Right" if avg_A > 0 else "Left"

    if offsets_B:
        avg_B = sum(offsets_B) / len(offsets_B)
        voteB = "Right" if avg_B < 0 else "Left"

    if voteA and voteB:
        if voteA == voteB:
            direction = f"{voteA} side view"
        else:
            if len(offsets_A) > len(offsets_B):
                direction = f"{voteA} side view"
            elif len(offsets_B) > len(offsets_A):
                direction = f"{voteB} side view"
            else:
                direction = f"{voteB} side view"
    elif voteA:
        direction = f"{voteA} side view"
    elif voteB:
        direction = f"{voteB} side view"
    else:
        direction = "Unknown"

    if voteA and voteB:
        consensus = (voteA == voteB)
    elif voteA or voteB:
        consensus = True
    else:
        consensus = None

    return direction, radial_lines, consensus


def compute_direction_front_wheel_refined(detected, fixed_label="Front-wheel"):
    if fixed_label not in detected:
        return "Unknown", None, None

    front_wheel_box = detected[fixed_label][0]
    front_wheel_center = ((front_wheel_box[0] + front_wheel_box[2]) / 2, (front_wheel_box[1] + front_wheel_box[3]) / 2)

    groupA = ["Front-bumper", "Headlight", "Fender", "Grille"]
    groupB = ["Front-door", "Back-door", "Rocker-panel", "Front-window", "Back-window", "Back-wheel", "Quarter-panel", "Mirror", "Windshield"]

    offsets_A = []
    offsets_B = []
    radial_lines = []

    for part in groupA:
        if part in detected:
            for box in detected[part]:
                part_center = ((box[0] + box[2]) / 2, (box[1] + box[3]) / 2)
                offset = part_center[0] - front_wheel_center[0]
                offsets_A.append(offset)
                radial_lines.append((front_wheel_center, part_center))

    for part in groupB:
        if part in detected:
            for box in detected[part]:
                part_center = ((box[0] + box[2]) / 2, (box[1] + box[3]) / 2)
                offset = part_center[0] - front_wheel_center[0]
                offsets_B.append(offset)
                radial_lines.append((front_wheel_center, part_center))

    voteA = None
    voteB = None

    if offsets_A:
        avg_A = sum(offsets_A) / len(offsets_A)
        voteA = "Right" if avg_A > 0 else "Left"

    if offsets_B:
        avg_B = sum(offsets_B) / len(offsets_B)
        voteB = "Right" if avg_B < 0 else "Left"

    if voteA and voteB:
        if voteA == voteB:
            direction = f"{voteA} side view"
        else:
            if len(offsets_A) > len(offsets_B):
                direction = f"{voteA} side view"
            elif len(offsets_B) > len(offsets_A):
                direction = f"{voteB} side view"
            else:
                direction = f"{voteB} side view"
    elif voteA:
        direction = f"{voteA} side view"
    elif voteB:
        direction = f"{voteB} side view"
    else:
        direction = "Unknown"

    if voteA and voteB:
        consensus = (voteA == voteB)
    elif voteA or voteB:
        consensus = True
    else:
        consensus = None

    return direction, radial_lines, consensus


def compute_direction_back_wheel_refined(detected, fixed_label="Back-wheel"):
    if fixed_label not in detected:
        return "Unknown", None, None

    back_wheel_box = detected[fixed_label][0]
    back_wheel_center = ((back_wheel_box[0] + back_wheel_box[2]) / 2,
                         (back_wheel_box[1] + back_wheel_box[3]) / 2)

    groupA = ["Back-bumper", "Tail-light", "Quarter-panel", "Trunk"]
    groupB = ["Front-wheel", "Rocker-panel", "Back-door", "Front-door",
              "Back-window", "Front-window", "Mirror", "Fender"]

    offsets_A = []
    offsets_B = []
    radial_lines = []

    for part in groupA:
        if part in detected:
            for box in detected[part]:
                part_center = ((box[0] + box[2]) / 2, (box[1] + box[3]) / 2)
                offset = part_center[0] - back_wheel_center[0]
                offsets_A.append(offset)
                radial_lines.append((back_wheel_center, part_center))

    for part in groupB:
        if part in detected:
            for box in detected[part]:
                part_center = ((box[0] + box[2]) / 2, (box[1] + box[3]) / 2)
                offset = part_center[0] - back_wheel_center[0]
                offsets_B.append(offset)
                radial_lines.append((back_wheel_center, part_center))

    voteA = None
    voteB = None

    if offsets_A:
        avg_A = sum(offsets_A) / len(offsets_A)
        voteA = "Right" if avg_A < 0 else "Left"
    if offsets_B:
        avg_B = sum(offsets_B) / len(offsets_B)
        voteB = "Left" if avg_B < 0 else "Right"

    if voteA and voteB:
        if voteA == voteB:
            direction = f"{voteA} side view"
        else:
            if len(offsets_A) > len(offsets_B):
                direction = f"{voteA} side view"
            elif len(offsets_B) > len(offsets_A):
                direction = f"{voteB} side view"
            else:
                direction = f"{voteB} side view"
    elif voteA:
        direction = f"{voteA} side view"
    elif voteB:
        direction = f"{voteB} side view"
    else:
        direction = "Unknown"

    if voteA and voteB:
        consensus = (voteA == voteB)
    elif voteA or voteB:
        consensus = True
    else:
        consensus = None

    return direction, radial_lines, consensus


def compute_direction_headlight_refined(detected, fixed_label="Headlight"):
    if fixed_label not in detected:
        return "Unknown", None, None

    headlight_box = detected[fixed_label][0]
    headlight_center = ((headlight_box[0] + headlight_box[2]) / 2, (headlight_box[1] + headlight_box[3]) / 2)

    groupA = ["Front-wheel", "Fender", "Mirror", "Rocker-panel", "Front-door", "Front-window"]
    groupB = ["Front-bumper", "Grille", "Hood", "Windshield"]

    offsets_A = []
    offsets_B = []
    radial_lines = []

    for part in groupA:
        if part in detected:
            for box in detected[part]:
                part_center = ((box[0] + box[2]) / 2, (box[1] + box[3]) / 2)
                offset = part_center[0] - headlight_center[0]
                offsets_A.append(offset)
                radial_lines.append((headlight_center, part_center))

    for part in groupB:
        if part in detected:
            for box in detected[part]:
                part_center = ((box[0] + box[2]) / 2, (box[1] + box[3]) / 2)
                offset = part_center[0] - headlight_center[0]
                offsets_B.append(offset)
                radial_lines.append((headlight_center, part_center))

    voteA = None
    voteB = None

    if offsets_A:
        avg_A = sum(offsets_A) / len(offsets_A)
        voteA = "Right" if avg_A < 0 else "Left"
    if offsets_B:
        avg_B = sum(offsets_B) / len(offsets_B)
        voteB = "Right" if avg_B > 0 else "Left"

    if voteA and voteB:
        if voteA == voteB:
            direction = f"{voteA} side view"
        else:
            if len(offsets_A) > len(offsets_B):
                direction = f"{voteA} side view"
            elif len(offsets_B) > len(offsets_A):
                direction = f"{voteB} side view"
            else:
                direction = f"{voteB} side view"
    elif voteA:
        direction = f"{voteA} side view"
    elif voteB:
        direction = f"{voteB} side view"
    else:
        direction = "Unknown"

    if voteA and voteB:
        consensus = (voteA == voteB)
    elif voteA or voteB:
        consensus = True
    else:
        consensus = None

    return direction, radial_lines, consensus


def compute_direction_tail_refined(detected, fixed_label="Tail-light"):
    if fixed_label not in detected:
        return "Unknown", None, None

    tail_box = detected[fixed_label][0]
    tail_center = ((tail_box[0] + tail_box[2]) / 2, (tail_box[1] + tail_box[3]) / 2)

    groupA = ["Trunk", "Back-bumper", "Back-windshield"]
    groupB = ["Back-wheel", "Quarter-panel", "Back-door", "Back-window"]

    offsets_A = []
    offsets_B = []
    radial_lines = []

    for part in groupA:
        if part in detected:
            for box in detected[part]:
                part_center = ((box[0] + box[2]) / 2, (box[1] + box[3]) / 2)
                offset = part_center[0] - tail_center[0]
                offsets_A.append(offset)
                radial_lines.append((tail_center, part_center))

    for part in groupB:
        if part in detected:
            for box in detected[part]:
                part_center = ((box[0] + box[2]) / 2, (box[1] + box[3]) / 2)
                offset = part_center[0] - tail_center[0]
                offsets_B.append(offset)
                radial_lines.append((tail_center, part_center))

    voteA = None
    voteB = None
    if offsets_A:
        avg_A = sum(offsets_A) / len(offsets_A)
        voteA = "Right" if avg_A < 0 else "Left"
    if offsets_B:
        avg_B = sum(offsets_B) / len(offsets_B)
        voteB = "Right" if avg_B > 0 else "Left"

    if voteA and voteB:
        if voteA == voteB:
            direction = f"{voteA} side view"
        else:
            if len(offsets_A) > len(offsets_B):
                direction = f"{voteA} side view"
            elif len(offsets_B) > len(offsets_A):
                direction = f"{voteB} side view"
            else:
                direction = f"{voteB} side view"
    elif voteA:
        direction = f"{voteA} side view"
    elif voteB:
        direction = f"{voteB} side view"
    else:
        direction = "Unknown"

    if voteA and voteB:
        consensus = (voteA == voteB)
    elif voteA or voteB:
        consensus = True
    else:
        consensus = None

    return direction, radial_lines, consensus


def determine_vehicle_directions(detected):
    directions = {}
    radial_lines_all = {}
    consensus_flags = {}

    mirror_direction, mirror_radials, mirror_consensus = compute_direction_mirror_refined(detected, fixed_label="Mirror")
    directions["Mirror"] = mirror_direction
    radial_lines_all["Mirror"] = mirror_radials
    consensus_flags["Mirror"] = mirror_consensus

    tail_direction, tail_radials, tail_consensus = compute_direction_tail_refined(detected, fixed_label="Tail-light")
    directions["Tail-light"] = tail_direction
    radial_lines_all["Tail-light"] = tail_radials
    consensus_flags["Tail-light"] = tail_consensus

    front_wheel_direction, front_wheel_radials, front_wheel_consensus = compute_direction_front_wheel_refined(detected, fixed_label="Front-wheel")
    directions["Front-wheel"] = front_wheel_direction
    radial_lines_all["Front-wheel"] = front_wheel_radials
    consensus_flags["Front-wheel"] = front_wheel_consensus

    back_wheel_direction, back_wheel_radials, back_wheel_consensus = compute_direction_back_wheel_refined(detected, fixed_label="Back-wheel")
    directions["Back-wheel"] = back_wheel_direction
    radial_lines_all["Back-wheel"] = back_wheel_radials
    consensus_flags["Back-wheel"] = back_wheel_consensus

    headlight_direction, headlight_radials, headlight_consensus = compute_direction_headlight_refined(detected, fixed_label="Headlight")
    directions["Headlight"] = headlight_direction
    radial_lines_all["Headlight"] = headlight_radials
    consensus_flags["Headlight"] = headlight_consensus

    return directions, radial_lines_all, consensus_flags


def find_best_combination(pil_image):
    """
    Runs car + part detection on pil_image.
    Returns (pil_image, detected_parts_dict, detections_dict).
    Returns (pil_image, {}, {}) if no car is found.
    """
    image_array = cv2.cvtColor(np.array(pil_image), cv2.COLOR_RGB2BGR)
    car_results = car_detection_model(image_array)

    car_detections_to_plot = []
    main_car_bbox = None
    best_area = 0
    for result in car_results:
        for box in result.boxes.data:
            conf = float(box[4])
            if conf < 0.50:
                continue
            x1, y1, x2, y2 = box[0], box[1], box[2], box[3]
            car_detections_to_plot.append((x1, y1, x2, y2, "Car", conf))
            area = (x2 - x1) * (y2 - y1)
            if area > best_area:
                best_area = area
                main_car_bbox = (x1, y1, x2, y2)

    if main_car_bbox is None:
        return pil_image, {}, {}

    results = part_detection_model(image_array)
    part_detections_to_plot = []
    detected = {}

    car_area = (main_car_bbox[2] - main_car_bbox[0]) * (main_car_bbox[3] - main_car_bbox[1])

    for result in results:
        for box in result.boxes.data:
            conf = float(box[4])
            if conf < 0.65:
                continue

            x1, y1, x2, y2, conf, class_id = box
            label = result.names[int(class_id)]

            width = max(0, x2 - x1)
            height = max(0, y2 - y1)
            area = width * height
            part_ratio = area / car_area

            min_ratio = MIN_RATIO.get(label, MIN_RATIO["default"])

            if part_ratio < min_ratio and conf < 0.8:
                continue

            margin = 5
            if (x1 <= main_car_bbox[0] + margin or x2 >= main_car_bbox[2] - margin or
                    y1 <= main_car_bbox[1] + margin or y2 >= main_car_bbox[3] - margin):
                if part_ratio < min_ratio * 3:
                    continue

            detected.setdefault(label, []).append((x1, y1, x2, y2))
            part_detections_to_plot.append((x1, y1, x2, y2, label, conf))

    detections = {
        "car_detection": {
            "image_array": image_array,
            "detections_to_plot": car_detections_to_plot,
            "title": "Car Detections",
        },
        "part_detection": {
            "image_array": image_array,
            "detections_to_plot": part_detections_to_plot,
            "title": "Part Detections",
        },
    }

    return pil_image, detected, detections


def determine_viewing_angle(detected):
    need_review = False
    detected_parts = set(detected.keys())

    angle_scores = []
    critical_parts = {
        "Front Right": {"Front-bumper", "Headlight", "Front-door"},
        "Right": {"Front-door", "Back-door", "Front-wheel", "Back-wheel"},
        "Rear Right": {"Tail-light", "Trunk", "Back-windshield", "Back-door"},
        "Rear Left": {"Tail-light", "Trunk", "Back-windshield", "Back-door"},
        "Left": {"Front-door", "Back-door", "Front-wheel", "Back-wheel"},
        "Front Left": {"Front-bumper", "Headlight", "Front-door"}
    }

    for angle, rules in viewing_angle_rules.items():
        if angle in critical_parts:
            total_critical = len(critical_parts[angle])
            detected_critical = len(critical_parts[angle].intersection(detected_parts))
            critical_ratio = detected_critical / total_critical
        else:
            critical_ratio = None

        ess_score = sum(3 for part in rules['must_be_visible'] if part in detected_parts)
        opt_score = sum(1 for part in rules['optional_parts'] if part in detected_parts)
        conf_pen = sum(-3 for part in rules['conflict_parts'] if part in detected_parts)
        raw_score = ess_score + opt_score + conf_pen
        total_defined = len(rules['must_be_visible']) + len(rules['optional_parts']) + len(rules['conflict_parts'])
        stage2_score = raw_score / total_defined if total_defined > 0 else 0.0
        angle_scores.append((angle, critical_ratio, stage2_score))

    print(angle_scores)
    score_map = {angle.lower(): score for (angle, _, score) in angle_scores}

    eps = 1e-6
    stage_2_thresold = 0.75
    sorted_all = sorted(angle_scores, key=lambda x: x[2], reverse=True)
    symmetric_view = {
        "Front Right": "Front Left",
        "Front Left": "Front Right",
        "Right": "Left",
        "Left": "Right",
        "Rear Right": "Rear Left",
        "Rear Left": "Rear Right"
    }
    top_2_predictions = ["", ""]
    if sorted_all:
        top1 = sorted_all[0]
        top1_key = top1[0].lower()
        top1_score = top1[2]
        top_2_predictions[0] = top1_key

        second_key = ""
        for angle, _, score in sorted_all[1:]:
            if score <= top1_score and score >= stage_2_thresold and symmetric_view.get(angle, "").lower() != top1_key:
                second_key = angle.lower()
                break
            if top1_score > 0.25 and score / (top1_score - eps) >= 0.60 and symmetric_view.get(angle, "").lower() != top1_key:
                second_key = angle.lower()
                break
        top_2_predictions[1] = second_key

    angles_above_60 = [item for item in angle_scores if item[1] is not None and item[1] >= 0.60]
    if len(angles_above_60) >= 3:
        need_review = True
        best_angle, *_ = max(angle_scores, key=lambda x: x[2])
    else:
        candidates = [item for item in angle_scores if item[1] is not None and item[1] >= 0.9]
        if candidates:
            best_angle, *_ = max(candidates, key=lambda x: x[1])
        else:
            best_angle, *_ = max(angle_scores, key=lambda x: x[2])

    if best_angle in ["Front", "Rear"]:
        directions = {"Selected": best_angle}
    else:
        directions_all, _, consensus_all = determine_vehicle_directions(detected)
        print(directions_all)

        consensus_votes = {
            ref: directions_all[ref]
            for ref, flag in consensus_all.items()
            if flag is True and directions_all[ref] != "Unknown"
        }

        if consensus_votes:
            _, chosen_dir = next(iter(consensus_votes.items()))
            majority_side = chosen_dir.split()[0]
        else:
            votes = {}
            weights = {"Front-wheel": 1, "Back-wheel": 1, "Mirror": 1, "Headlight": 0.5, "Tail-light": 0.5}
            for ref, dir_val in directions_all.items():
                if dir_val != "Unknown":
                    side = dir_val.split()[0]
                    weight = weights.get(ref, 1)
                    votes[side] = votes.get(side, 0) + weight
            majority_side = max(votes, key=votes.get) if votes else "Unknown"

        if best_angle.startswith("Front"):
            final_side_classification = "Front " + majority_side
        elif best_angle.startswith("Rear"):
            final_side_classification = "Rear " + majority_side
        else:
            final_side_classification = majority_side

        directions = {"Selected": final_side_classification}

    return directions, detected_parts, need_review, top_2_predictions, score_map


def deskew_image(pil_image: Image.Image) -> Image.Image:
    img = cv2.cvtColor(np.array(pil_image), cv2.COLOR_RGB2BGR)
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    edges = cv2.Canny(gray, 50, 150, apertureSize=3)
    lines = cv2.HoughLines(edges, 1, np.pi / 180, 200)

    angles = []
    if lines is not None:
        for _, theta in lines[:, 0]:
            angle = (theta * 180 / np.pi) - 90
            if angle < -90:
                angle += 180
            if angle > 90:
                angle -= 180
            angles.append(angle)

    median_angle = np.median(angles) if len(angles) > 0 else 0

    (h, w) = img.shape[:2]
    center = (w // 2, h // 2)
    M = cv2.getRotationMatrix2D(center, median_angle, 1.0)
    rotated = cv2.warpAffine(img, M, (w, h), flags=cv2.INTER_CUBIC, borderMode=cv2.BORDER_REPLICATE)

    return Image.fromarray(cv2.cvtColor(rotated, cv2.COLOR_BGR2RGB))


async def yolo_rule_based_classification(pil_image, image_name, img_file: UploadFile):
    """
    Returns (final_secondaries, final_review, final_scores, file_details).
    Tries each rotation (0, 90, -90) and also a deskewed variant — picks the
    image variant that yields the most detected parts.
    """
    rotations = [0, 90, -90]
    best_raw_direction = None
    final_review = False
    fail_count = 0
    best_top_predictions = [False, False]
    best_score_map = {}
    max_detected_labels = 0
    detected_labels = {}
    final_detections = {}

    for rotation in rotations:
        rotated_image = pil_image.rotate(rotation, expand=True) if rotation != 0 else pil_image

        # Try original orientation
        _, detected, detections = find_best_combination(rotated_image)
        print(detected)
        if len(detected.keys()) > max_detected_labels:
            max_detected_labels = len(detected.keys())
            detected_labels = detected
            final_detections = detections

        # Try deskewed version of this rotation
        deskewed_image = deskew_image(rotated_image)
        _, detected, detections = find_best_combination(deskewed_image)
        print(detected)
        if len(detected.keys()) > max_detected_labels:
            max_detected_labels = len(detected.keys())
            detected_labels = detected
            final_detections = detections

    print(detected_labels)
    direction, detected_labels, need_review, top_predictions, score_map = determine_viewing_angle(detected_labels)

    best_raw_direction = direction['Selected']
    final_review = need_review
    best_top_predictions = top_predictions
    best_score_map = score_map

    viewing_angle_map = {
        "front": "Front View",
        "rear": "Rear View",
        "left": DRIVER_SIDE,
        "right": PASSENGER_SIDE,
        "left side view": DRIVER_SIDE,
        "right side view": PASSENGER_SIDE,
        "front right": FRONT_PASSENGER_CORNER,
        "front left": FRONT_DRIVER_CORNER,
        "rear right": REAR_PASSENGER_CORNER,
        "rear left": REAR_DRIVER_CORNER,
        "unknown": "NA",
    }

    desired_side = None
    if isinstance(best_raw_direction, str):
        raw = best_raw_direction.lower()
        if "left" in raw:
            desired_side = "Driver Side View"
        elif "right" in raw:
            desired_side = "Passenger Side View"

    stage1_top1_key = best_top_predictions[0] if isinstance(best_top_predictions, (list, tuple)) and len(best_top_predictions) > 0 else False
    stage1_top2_key = best_top_predictions[1] if isinstance(best_top_predictions, (list, tuple)) and len(best_top_predictions) > 1 else False

    mapped_primary = "NA"
    if stage1_top1_key and isinstance(stage1_top1_key, str):
        mapped_primary = viewing_angle_map.get(stage1_top1_key.lower(), "NA")
    elif isinstance(best_raw_direction, str):
        mapped_primary = viewing_angle_map.get(best_raw_direction.lower(), "NA")


    mapped_primary = _enforce_side(mapped_primary, desired_side)

    final_secondaries = [False, False]
    threshold = 0.75
    eps = 1e-6

    if stage1_top1_key and isinstance(stage1_top1_key, str):
        mapped_top1 = viewing_angle_map.get(stage1_top1_key.lower(), "NA")
    else:
        mapped_top1 = mapped_primary if mapped_primary != "NA" else False

    mapped_top1 = _enforce_side(mapped_top1, desired_side)
    final_secondaries[0] = mapped_top1 if mapped_top1 != "NA" else False

    mapped_top2 = False
    if isinstance(stage1_top2_key, str):
        top2_score = best_score_map.get(stage1_top2_key.lower(), -999.0)
        top1_score = best_score_map.get(stage1_top1_key.lower(), -999.0) if isinstance(stage1_top1_key, str) else -999.0
        if (top2_score >= threshold and top2_score <= top1_score) or (top2_score / (top1_score - eps) >= 0.60 and top1_score > 0.25):
            mapped_top2 = _enforce_side(viewing_angle_map.get(stage1_top2_key.lower(), "NA"), desired_side)
        else:
            mapped_top2 = False

    final_secondaries[1] = mapped_top2 if mapped_top2 and mapped_top2 != "NA" else False

    if mapped_primary == "NA" and final_secondaries[0]:
        mapped_primary = final_secondaries[0]

    if fail_count >= 3:
        final_review = True

    final_scores = [0, 0]
    if isinstance(stage1_top1_key, str):
        final_scores[0] = best_score_map.get(stage1_top1_key.lower(), 0)
    if isinstance(stage1_top2_key, str) and final_secondaries[1]:
        final_scores[1] = best_score_map.get(stage1_top2_key.lower(), 0)
    final_secondaries = [item for item in final_secondaries if isinstance(item, str)]
    print(final_secondaries)

    file_details = await store_images(final_detections, image_name, img_file)

    return final_secondaries, final_review, final_scores, file_details


async def store_images(final_detections, image_name, img_file):
    os.makedirs("./output_files", exist_ok=True)

    img_folder, extension = os.path.splitext(image_name)
    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
    ff = f"{img_folder}_{timestamp}"
    output_folder = f"./output_files/{ff}"
    os.makedirs(output_folder, exist_ok=True)
    output_file_car = f"car_detection{extension}"
    output_file_part = f"part_detection{extension}"

    main_img_path = os.path.join(output_folder, img_file.filename)
    await img_file.seek(0)
    with open(main_img_path, "wb") as buffer:
        shutil.copyfileobj(img_file.file, buffer)

    try:
        save_detection_img(
            final_detections["car_detection"]["image_array"],
            final_detections["car_detection"]["detections_to_plot"],
            output_folder,
            output_file_car,
            final_detections["car_detection"]["title"],
        )
    except Exception as e:
        print("Error Saving Car detections", e)

    try:
        save_detection_img(
            final_detections["part_detection"]["image_array"],
            final_detections["part_detection"]["detections_to_plot"],
            output_folder,
            output_file_part,
            final_detections["part_detection"]["title"],
        )
    except Exception as e:
        print("Error Saving Part detections", e)

    return {
        "main_img_name": f"{ff}/{img_file.filename}",
        "part_detection": f"{ff}/{output_file_part}",
        "car_detection": f"{ff}/{output_file_car}",
    }


def save_detection_img(image_array, detections, save_folder, filename, title="Detections"):
    vis_img = image_array.copy()

    for x1, y1, x2, y2, label, conf in detections:
        cv2.rectangle(vis_img, (int(x1), int(y1)), (int(x2), int(y2)), (0, 255, 0), 3)
        text = f"{label} {conf:.2f}"
        text_size = cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, 0.6, 2)[0]
        cv2.rectangle(
            vis_img,
            (int(x1), int(y1) - text_size[1] - 10),
            (int(x1) + text_size[0], int(y1)),
            (0, 255, 0),
            -1,
        )
        cv2.putText(vis_img, text, (int(x1), int(y1) - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 0), 2)

    os.makedirs(save_folder, exist_ok=True)

    if not filename.endswith((".png", ".jpg", ".jpeg")):
        filename += ".png"
    filepath = os.path.join(save_folder, filename)

    plt.figure(figsize=(12, 8), dpi=300)
    plt.imshow(cv2.cvtColor(vis_img, cv2.COLOR_BGR2RGB))
    plt.title(title, fontsize=16, fontweight="bold")
    plt.axis("off")
    plt.tight_layout()
    plt.savefig(filepath, bbox_inches="tight", dpi=300, format="png", facecolor="white", edgecolor="none")
    plt.close()

    print(f"High quality image saved: {filepath}")
    return filepath