#!/opt/homebrew/bin/python3.11
"""
Search for "vase" in the video using OWL-ViT on a subset of frames.
"""

import os
import cv2
import glob
from PIL import Image
import torch
from transformers import OwlViTProcessor, OwlViTForObjectDetection

BASE_DIR = "output/384b0ff44aaaa1f1/full_video_scans"
RESULTS_DIR = "output/384b0ff44aaaa1f1/vase_search_results"
os.makedirs(RESULTS_DIR, exist_ok=True)

print("🔍 Searching for vases...")

# Load model
processor = OwlViTProcessor.from_pretrained("google/owlvit-base-patch32")
model = OwlViTForObjectDetection.from_pretrained("google/owlvit-base-patch32")
model.eval()

# Search terms
SEARCH_TERMS = ["vase", "flower vase", "urn", "pottery", "glass jar"]

frames = sorted(glob.glob(os.path.join(BASE_DIR, "frame_*.jpg")))
print(f"📸 Scanning {len(frames)} frames...")

found_count = 0

for frame_path in frames:
    frame_name = os.path.basename(frame_path)
    sec = frame_name.replace("frame_", "").replace("s.jpg", "")

    image = Image.open(frame_path).convert("RGB")
    h, w = image.height, image.width
    target_sizes = torch.Tensor([[h, w]])

    for term in SEARCH_TERMS:
        inputs = processor(text=[[term]], images=image, return_tensors="pt")

        with torch.no_grad():
            outputs = model(**inputs)

        results = processor.post_process_object_detection(
            outputs=outputs, target_sizes=target_sizes, threshold=0.05
        )

        for score, label, box in zip(
            results[0]["scores"], results[0]["labels"], results[0]["boxes"]
        ):
            s = float(score)
            if s > 0.08:  # Threshold for visualization
                x1, y1, x2, y2 = map(int, box.tolist())
                img = cv2.imread(frame_path)
                crop = img[y1:y2, x1:x2]

                if crop.size > 0:
                    crop_name = f"vase_{sec}s_{term.replace(' ', '_')}_{s:.2f}.jpg"
                    cv2.imwrite(os.path.join(RESULTS_DIR, crop_name), crop)

                    # Annotate
                    cv2.rectangle(img, (x1, y1), (x2, y2), (0, 0, 255), 3)
                    cv2.putText(
                        img,
                        f"{term} {s:.2f}",
                        (x1, y1 - 10),
                        cv2.FONT_HERSHEY_SIMPLEX,
                        0.7,
                        (0, 0, 255),
                        2,
                    )
                    ann_name = f"annotated_{sec}s.jpg"
                    cv2.imwrite(os.path.join(RESULTS_DIR, ann_name), img)

                    print(f"  📍 {sec}s | {term} | {s:.2f}")
                    found_count += 1

print(f"\n🏁 Done. Found {found_count} candidates.")