mediaproc/tests/detect/manual/seed_scenario.py

#!/usr/bin/env python3
"""
Seed a scenario checkpoint from a video chunk.

Extracts frames via ffmpeg, uploads to MinIO, creates a StageCheckpoint
in Postgres marked as a scenario. No pipeline, no Redis, no SSE.

Prerequisites:
  - Postgres reachable (port-forward or local)
  - MinIO reachable (port-forward or local)

Usage:
    # With K8s port-forwards:
    kubectl port-forward svc/postgres 5432:5432 &
    kubectl port-forward svc/minio 9000:9000 &

    python tests/detect/manual/seed_scenario.py

    # Custom video:
    python tests/detect/manual/seed_scenario.py --video media/mpr/out/chunks/.../chunk_0001.mp4

Then open:
    http://mpr.local.ar/detection/?job=<JOB_ID>#/editor/detect_edges
"""

from __future__ import annotations

import argparse
import logging
import os
import sys
import uuid

parser = argparse.ArgumentParser(description="Seed a scenario checkpoint")
parser.add_argument("--video",
                    default="media/mpr/out/chunks/95043d50-4df6-4ac8-bbd5-2ba873117c6e/chunk_0000.mp4")
parser.add_argument("--label", default="chelsea_edges_default",
                    help="Scenario label for bookmarking")
parser.add_argument("--fps", type=float, default=2.0, help="Frames per second to extract")
parser.add_argument("--max-frames", type=int, default=20, help="Max frames to extract")
parser.add_argument("--db-url",
                    default=os.environ.get("DATABASE_URL", "postgresql://mpr:mpr@localhost:5432/mpr"))
parser.add_argument("--s3-url",
                    default=os.environ.get("S3_ENDPOINT_URL", "http://localhost:9000"))
args = parser.parse_args()

# Set env before imports
os.environ["DATABASE_URL"] = args.db_url
os.environ["S3_ENDPOINT_URL"] = args.s3_url
os.environ.setdefault("AWS_ACCESS_KEY_ID", "minioadmin")
os.environ.setdefault("AWS_SECRET_ACCESS_KEY", "minioadmin")

sys.path.insert(0, ".")

logging.basicConfig(level=logging.INFO, format="%(levelname)-7s %(name)s — %(message)s")
logger = logging.getLogger(__name__)


def extract_frames_ffmpeg(video_path: str, fps: float, max_frames: int):
    """Extract frames using ffmpeg subprocess — no pipeline dependencies."""
    import subprocess
    import tempfile
    from pathlib import Path

    import numpy as np
    from PIL import Image

    from detect.models import Frame

    tmpdir = tempfile.mkdtemp(prefix="scenario_")
    pattern = os.path.join(tmpdir, "frame_%04d.jpg")

    cmd = [
        "ffmpeg", "-i", video_path,
        "-vf", f"fps={fps}",
        "-frames:v", str(max_frames),
        "-q:v", "2",
        pattern,
        "-y", "-loglevel", "error",
    ]
    subprocess.run(cmd, check=True)

    frames = []
    for jpg in sorted(Path(tmpdir).glob("frame_*.jpg")):
        seq = int(jpg.stem.split("_")[1]) - 1  # 0-indexed
        img = Image.open(jpg).convert("RGB")
        image_array = np.array(img)
        frame = Frame(
            sequence=seq,
            chunk_id=0,
            timestamp=seq / fps,
            image=image_array,
        )
        frames.append(frame)
        jpg.unlink()

    Path(tmpdir).rmdir()
    return frames


def main():
    job_id = str(uuid.uuid4())
    video_path = args.video

    if not os.path.exists(video_path):
        logger.error("Video not found: %s", video_path)
        sys.exit(1)

    logger.info("Video: %s", video_path)
    logger.info("Job ID: %s", job_id)
    logger.info("Label: %s", args.label)

    # Ensure DB tables exist
    from core.db.connection import create_tables
    create_tables()

    # Extract frames
    logger.info("Extracting frames (fps=%.1f, max=%d)...", args.fps, args.max_frames)
    frames = extract_frames_ffmpeg(video_path, args.fps, args.max_frames)
    logger.info("Extracted %d frames", len(frames))

    # Upload frames to MinIO
    from detect.checkpoint.frames import save_frames
    logger.info("Uploading frames to MinIO...")
    manifest = save_frames(job_id, frames)
    logger.info("Uploaded %d frames", len(manifest))

    # Build frame metadata
    frames_meta = [
        {
            "sequence": f.sequence,
            "chunk_id": f.chunk_id,
            "timestamp": f.timestamp,
            "perceptual_hash": "",
        }
        for f in frames
    ]

    # All frames are "filtered" (no scene filter ran)
    filtered_sequences = [f.sequence for f in frames]

    # Save checkpoint as scenario
    from core.db.detect import save_stage_checkpoint
    from detect.checkpoint.frames import CHECKPOINT_PREFIX

    checkpoint = save_stage_checkpoint(
        job_id=job_id,
        stage="filter_scenes",
        stage_index=1,
        frames_prefix=f"{CHECKPOINT_PREFIX}/{job_id}/frames/",
        frames_manifest={str(k): v for k, v in manifest.items()},
        frames_meta=frames_meta,
        filtered_frame_sequences=filtered_sequences,
        stage_output_key="",
        stats={"frames_extracted": len(frames), "frames_after_scene_filter": len(frames)},
        config_snapshot={},
        config_overrides={},
        video_path=video_path,
        profile_name="soccer_broadcast",
        is_scenario=True,
        scenario_label=args.label,
    )

    logger.info("")
    logger.info("Scenario created:")
    logger.info("  ID: %s", checkpoint.id)
    logger.info("  Job: %s", job_id)
    logger.info("  Label: %s", args.label)
    logger.info("  Frames: %d", len(frames))
    logger.info("")
    logger.info("Open in editor:")
    logger.info("  http://mpr.local.ar/detection/?job=%s#/editor/detect_edges", job_id)


if __name__ == "__main__":
    main()