#!/opt/homebrew/bin/python3.11
"""
Push existing embeddings from face.json to Qdrant _faces collection.
This is faster than recomputing embeddings with face_processor.py.

Usage:
    python scripts/push_existing_embeddings.py --file-uuid <uuid>
    python scripts/push_existing_embeddings.py --all
"""

import os
import sys
import json
import argparse
from pathlib import Path

sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from utils.qdrant_faces import (
    ensure_faces_collection,
    push_face_embeddings_batch,
)

OUTPUT_DIR = os.environ.get("MOMENTRY_OUTPUT_DIR", "/Users/accusys/momentry/output")


def push_embeddings_for_file(file_uuid: str) -> int:
    """Push embeddings from face.json to Qdrant"""
    face_json_path = Path(OUTPUT_DIR) / f"{file_uuid}.face.json"
    if not face_json_path.exists():
        print(f"ERROR: {face_json_path} not found")
        return 0
    
    with open(face_json_path) as f:
        data = json.load(f)
    
    faces = []
    for frame_data in data.get("frames", []):
        frame = frame_data.get("frame", 0)
        for face in frame_data.get("faces", []):
            embedding = face.get("embedding")
            if not embedding:
                continue
            
            faces.append({
                "frame": frame,
                "trace_id": face.get("trace_id"),
                "bbox": {
                    "x": face.get("x", 0),
                    "y": face.get("y", 0),
                    "width": face.get("width", 0),
                    "height": face.get("height", 0),
                },
                "confidence": face.get("confidence", 0),
                "embedding": embedding,
            })
    
    if faces:
        count = push_face_embeddings_batch(file_uuid, faces)
        print(f"Pushed {count} embeddings for {file_uuid}")
        return count
    
    return 0


def main():
    parser = argparse.ArgumentParser(description="Push existing embeddings to Qdrant")
    parser.add_argument("--file-uuid", help="File UUID to process")
    parser.add_argument("--all", action="store_true", help="Process all files in output dir")
    args = parser.parse_args()
    
    if args.all:
        total = 0
        for face_json in Path(OUTPUT_DIR).glob("*.face.json"):
            # Extract UUID from filename like "uuid.face.json"
            filename = face_json.name
            file_uuid = filename.replace(".face.json", "")
            count = push_embeddings_for_file(file_uuid)
            total += count
        print(f"\nTotal: {total} embeddings pushed")
    elif args.file_uuid:
        push_embeddings_for_file(args.file_uuid)
    else:
        parser.print_help()


if __name__ == "__main__":
    main()