scripts/test_opening_kickoff_fix.py

#!/usr/bin/env python3
"""
Test script to verify the opening kickoff detection fix.

Tests:
1. Tennessee: Opening kickoff should be detected around 117s
2. Oregon: Opening kickoff should be detected around 332s
3. Texas: Should REJECT the fake kickoff at 20.5s and detect real game start around 444s

The fix requires:
- k=3 consecutive clock readings to confirm kickoff start
- Maximum kickoff duration of 90s (rejects if too long)
"""

import sys
import logging
from pathlib import Path

# Add src to path
sys.path.insert(0, str(Path(__file__).parent.parent / "src"))

from config import SessionConfig, load_session_config, get_video_basename, OUTPUT_DIR
from pipeline import run_extraction

# Configure logging
logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
logger = logging.getLogger(__name__)


def test_video(video_name: str, video_path: str, start_time: float, end_time: float, expected_kickoff_start: float, expected_kickoff_tolerance: float = 30.0):
    """
    Test opening kickoff detection on a video segment.

    Args:
        video_name: Name for display
        video_path: Path to video file
        start_time: Start time in seconds
        end_time: End time in seconds
        expected_kickoff_start: Expected kickoff start time (within video segment)
        expected_kickoff_tolerance: Tolerance for kickoff timing match
    """
    print(f"\n{'=' * 60}")
    print(f"Testing: {video_name}")
    print(f"Video: {video_path}")
    print(f"Time range: {start_time}s - {end_time}s")
    print(f"Expected kickoff around: {expected_kickoff_start}s (±{expected_kickoff_tolerance}s)")
    print("=" * 60)

    try:
        # Load existing session config for this video
        video_basename = get_video_basename(video_path, testing_mode=False)
        config_path = OUTPUT_DIR / f"{video_basename}_config.json"

        if not config_path.exists():
            logger.error(f"Config not found: {config_path}")
            logger.error("Run main.py with --use-saved-regions first")
            return False

        # Load config and update time bounds
        session_config = load_session_config(str(config_path))
        session_config.video_path = video_path
        session_config.start_time = start_time
        session_config.end_time = end_time
        session_config.video_basename = video_basename

        # Run extraction
        results = run_extraction(session_config, OUTPUT_DIR, num_workers=1)

        # Analyze results - plays are dicts, not objects
        plays = results.get("plays", [])
        kickoff_plays = [p for p in plays if p.get("play_type") == "kickoff"]

        print(f"\nResults:")
        print(f"  Total plays detected: {len(plays)}")
        print(f"  Kickoff plays: {len(kickoff_plays)}")

        success = True
        if kickoff_plays:
            for kp in kickoff_plays:
                start = kp.get("start_time", 0)
                end = kp.get("end_time", 0)
                print(f"\n  Kickoff found:")
                print(f"    Start: {start:.1f}s")
                print(f"    End: {end:.1f}s")
                print(f"    Duration: {end - start:.1f}s")

                # Check if within expected range
                diff = abs(start - expected_kickoff_start)
                if diff <= expected_kickoff_tolerance:
                    print(f"    ✅ PASS: Within expected range ({diff:.1f}s from expected)")
                else:
                    print(f"    ❌ FAIL: Outside expected range ({diff:.1f}s from expected)")
                    success = False
        else:
            print(f"\n  ❌ No kickoff detected!")
            success = False

        # Show first few plays for context
        print(f"\nFirst 5 plays:")
        for p in plays[:5]:
            pnum = p.get("play_number", "?")
            pstart = p.get("start_time", 0)
            pend = p.get("end_time", 0)
            ptype = p.get("play_type", "?")
            pmethod = p.get("start_method", "?")
            print(f"  Play #{pnum}: {pstart:.1f}s - {pend:.1f}s ({ptype}, {pmethod})")

        return success

    except Exception as e:
        logger.error(f"Error testing {video_name}: {e}")
        import traceback
        traceback.print_exc()
        return False


def main():
    """Run all tests."""
    base_path = Path("/Users/andytaylor/Documents/Personal/cfb40/full_videos")

    # Test configurations
    tests = [
        {
            "video_name": "Tennessee (baseline - should pass)",
            "video_path": str(base_path / "OSU vs Tenn 12.21.24.mkv"),
            "start_time": 0,
            "end_time": 300,  # First 5 minutes
            "expected_kickoff_start": 117,  # ~1:57 video time
            "expected_kickoff_tolerance": 30,
        },
        {
            "video_name": "Oregon (baseline - should pass)",
            "video_path": str(base_path / "OSU vs Oregon 01.01.25.mkv"),
            "start_time": 200,
            "end_time": 500,  # Around kickoff time
            "expected_kickoff_start": 332,  # ~5:32 video time
            "expected_kickoff_tolerance": 30,
        },
        {
            "video_name": "Texas (fix test - should reject fake kickoff at 20s)",
            "video_path": str(base_path / "OSU vs Texas 01.10.25.mkv"),
            "start_time": 0,
            "end_time": 600,  # First 10 minutes
            "expected_kickoff_start": 444,  # Real game starts ~7:24
            "expected_kickoff_tolerance": 30,
        },
    ]

    print("\n" + "=" * 60)
    print("OPENING KICKOFF DETECTION FIX TEST")
    print("=" * 60)

    results = []
    for test_config in tests:
        success = test_video(**test_config)
        results.append((test_config["video_name"], success))

    # Summary
    print("\n" + "=" * 60)
    print("TEST SUMMARY")
    print("=" * 60)
    for name, success in results:
        status = "✅ PASS" if success else "❌ FAIL"
        print(f"  {status}: {name}")


if __name__ == "__main__":
    main()