momentry_core/scripts/cut_benchmark_runner.py

#!/opt/homebrew/bin/python3.11
"""
CUT Processor Benchmark Runner
测试场景辨识的性能和质量

测试版本:
A. cut_processor.py (PySceneDetect)
B. cut_processor_contract_v1.py (Contract v1.0)

测试指标:
- 处理时间
- 内存峰值 (MB)
- 检测场景数
- 场景平均时长
"""

import os
import sys
import json
import time
import subprocess
from pathlib import Path
from datetime import datetime

SCRIPTS_DIR = Path(__file__).parent
OUTPUT_DIR = SCRIPTS_DIR.parent / "output" / "benchmark" / "cut_processor"

def get_memory_peak(pid):
    """获取进程内存峰值"""
    try:
        cmd = ["ps", "-p", str(pid), "-o", "rss="]
        result = subprocess.run(cmd, capture_output=True, text=True)
        if result.returncode == 0:
            return int(result.stdout.strip()) / 1024
    except:
        pass
    return 0

def run_processor(script_name, video_path, output_path, uuid=""):
    """运行指定 CUT processor"""
    
    script_path = SCRIPTS_DIR / script_name
    if not script_path.exists():
        print(f"❌ 脚本不存在: {script_path}")
        return None
    
    cmd = [sys.executable, str(script_path), video_path, output_path]
    if uuid:
        cmd.extend(["--uuid", uuid])
    
    print(f"\n执行: {script_name}")
    print(f"命令: {' '.join(cmd)}")
    
    start_time = time.time()
    
    process = subprocess.Popen(
        cmd,
        stdout=subprocess.PIPE,
        stderr=subprocess.PIPE,
        text=True
    )
    
    peak_memory = 0
    while process.poll() is None:
        mem = get_memory_peak(process.pid)
        if mem > peak_memory:
            peak_memory = mem
        time.sleep(0.5)
    
    stdout, stderr = process.communicate()
    elapsed_time = time.time() - start_time
    
    if process.returncode != 0:
        print(f"❌ 处理失败: {stderr}")
        return None
    
    if os.path.exists(output_path):
        with open(output_path) as f:
            result = json.load(f)
        
        scenes = result.get("scenes", [])
        total_scenes = len(scenes)
        
        # 计算场景统计
        avg_scene_duration = 0
        min_scene_duration = 0
        max_scene_duration = 0
        
        if scenes:
            durations = [s.get("end_time", 0) - s.get("start_time", 0) for s in scenes]
            avg_scene_duration = sum(durations) / len(durations)
            min_scene_duration = min(durations)
            max_scene_duration = max(durations)
        
        file_size_kb = os.path.getsize(output_path) / 1024
        
        return {
            "elapsed_time": elapsed_time,
            "peak_memory_mb": peak_memory,
            "total_scenes": total_scenes,
            "avg_scene_duration": avg_scene_duration,
            "min_scene_duration": min_scene_duration,
            "max_scene_duration": max_scene_duration,
            "file_size_kb": file_size_kb,
            "fps": result.get("fps", 0),
            "frame_count": result.get("frame_count", 0),
            "stdout": stdout,
            "stderr": stderr,
        }
    
    return None

def main():
    print("=" * 80)
    print("CUT Processor Benchmark 测试")
    print("=" * 80)
    
    OUTPUT_DIR.mkdir(parents=True, exist_ok=True)
    
    # 测试视频
    video_path = "/Users/accusys/momentry/var/sftpgo/data/demo/Gamma Carry Saves the World..mp4"
    
    if not os.path.exists(video_path):
        print(f"❌ 测试视频不存在: {video_path}")
        sys.exit(1)
    
    # 获取视频信息
    cmd = [
        "ffprobe",
        "-v", "quiet",
        "-print_format", "json",
        "-show_format",
        "-show_streams",
        video_path
    ]
    
    try:
        result = subprocess.run(cmd, capture_output=True, text=True, check=True)
        video_info = json.loads(result.stdout)
        
        video_stream = next((s for s in video_info["streams"] if s["codec_type"] == "video"), None)
        
        print(f"\n测试视频:")
        print(f"  文件: {int(video_info['format'].get('size', 0)) / 1024 / 1024:.1f} MB")
        print(f"  时长: {float(video_info['format'].get('duration', 0)):.1f} 秒")
        print(f"  分辨率: {video_stream.get('width', 0)}x{video_stream.get('height', 0)}")
        print(f"  FPS: {video_stream.get('r_frame_rate', 'unknown')}")
    except:
        print("⚠️ 无法获取视频信息")
    
    processors = [
        ("A", "cut_processor.py", "PySceneDetect"),
        ("B", "cut_processor_contract_v1.py", "Contract v1.0"),
    ]
    
    results = []
    
    for scheme_id, script_name, description in processors:
        print(f"\n{'=' * 80}")
        print(f"方案 {scheme_id}: {description}")
        print(f"{'=' * 80}")
        
        output_path = OUTPUT_DIR / f"scheme_{scheme_id}_{script_name.replace('.py', '.json')}"
        
        if os.path.exists(output_path):
            os.remove(output_path)
        
        result = run_processor(
            script_name,
            video_path,
            str(output_path),
            uuid=f"cut_bench_{scheme_id}"
        )
        
        if result:
            results.append({
                "scheme": scheme_id,
                "script": script_name,
                "description": description,
                "elapsed_time": result["elapsed_time"],
                "peak_memory_mb": result["peak_memory_mb"],
                "total_scenes": result["total_scenes"],
                "avg_scene_duration": result["avg_scene_duration"],
                "min_scene_duration": result["min_scene_duration"],
                "max_scene_duration": result["max_scene_duration"],
                "fps": result["fps"],
                "frame_count": result["frame_count"],
                "file_size_kb": result["file_size_kb"],
            })
            
            print(f"\n✅ 处理完成:")
            print(f"  时间: {result['elapsed_time']:.2f}秒")
            print(f"  内存峰值: {result['peak_memory_mb']:.1f} MB")
            print(f"  检测场景数: {result['total_scenes']}")
            print(f"  场景平均时长: {result['avg_scene_duration']:.2f}秒")
            print(f"  场景最短时长: {result['min_scene_duration']:.2f}秒")
            print(f"  场景最长时长: {result['max_scene_duration']:.2f}秒")
            print(f"  FPS: {result['fps']}")
            print(f"  输出大小: {result['file_size_kb']:.1f} KB")
        else:
            print(f"❌ 方案 {scheme_id} 处理失败")
            results.append({
                "scheme": scheme_id,
                "script": script_name,
                "description": description,
                "error": "processing failed"
            })
    
    # 保存报告
    report = {
        "test_date": datetime.now().isoformat(),
        "video_path": video_path,
        "results": results,
    }
    
    report_path = OUTPUT_DIR / "CUT_BENCHMARK_REPORT.json"
    with open(report_path, "w") as f:
        json.dump(report, f, indent=2, ensure_ascii=False)
    
    print(f"\n{'=' * 80}")
    print("测试报告已保存:")
    print(f"  {report_path}")
    print(f"{'=' * 80}")
    
    print("\n【对比总结】")
    print(f"\n| 方案 | 脚本 | 时间(秒) | 内存(MB) | 场景数 | 平均时长(秒) |")
    print("|------|------|---------|---------|--------|-------------|")
    
    for r in results:
        if "error" not in r:
            print(f"| {r['scheme']} | {r['script']} | {r['elapsed_time']:.2f} | {r['peak_memory_mb']:.1f} | {r['total_scenes']} | {r['avg_scene_duration']:.2f} |")
        else:
            print(f"| {r['scheme']} | {r['script']} | - | - | - | - |")

if __name__ == "__main__":
    main()