fix: 添加工作流
This commit is contained in:
root
@@ -1,23 +1,26 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
PySceneDetect 场景检测命令行工具
|
||||
PySceneDetect 场景检测命令行工具 - LangGraph增强版
|
||||
"""
|
||||
|
||||
import os
|
||||
import json
|
||||
import time
|
||||
from pathlib import Path
|
||||
from typing import Optional, List
|
||||
from typing import Optional, List, Literal, Dict, Any
|
||||
from enum import Enum
|
||||
from dataclasses import dataclass, asdict
|
||||
|
||||
import typer
|
||||
from python_core.cli.const import progress_reporter, console, project_root
|
||||
from python_core.cli.const import progress_reporter
|
||||
|
||||
# 检查 PySceneDetect 依赖
|
||||
# PySceneDetect 依赖
|
||||
from scenedetect import open_video, SceneManager
|
||||
from scenedetect.detectors import ContentDetector, ThresholdDetector
|
||||
from scenedetect.video_splitter import split_video_ffmpeg
|
||||
|
||||
# LangGraph 依赖
|
||||
from langgraph.graph import StateGraph, START, END
|
||||
from langgraph.graph.state import CompiledStateGraph
|
||||
from langgraph.checkpoint.memory import MemorySaver
|
||||
from langchain_anthropic import ChatAnthropic
|
||||
|
||||
class DetectorType(str, Enum):
|
||||
"""检测器类型"""
|
||||
@@ -55,11 +58,59 @@ class DetectionResult:
|
||||
success: bool
|
||||
error: Optional[str] = None
|
||||
|
||||
# LangGraph 工作流状态
|
||||
@dataclass
|
||||
class SceneDetectionWorkflowState:
|
||||
"""场景检测工作流状态"""
|
||||
# 输入参数
|
||||
video_path: str = ""
|
||||
detector_type: str = "content"
|
||||
threshold: float = 30.0
|
||||
min_scene_length: float = 1.0
|
||||
output_path: Optional[str] = None
|
||||
output_format: str = "json"
|
||||
enable_ai_analysis: bool = True
|
||||
|
||||
# 工作流状态
|
||||
current_stage: str = "init"
|
||||
progress: int = 0
|
||||
total_steps: int = 5
|
||||
|
||||
# 中间结果
|
||||
video_info: Dict[str, Any] = None
|
||||
raw_scenes: List[Any] = None
|
||||
processed_scenes: List[SceneInfo] = None
|
||||
|
||||
# 最终结果
|
||||
detection_result: Optional[DetectionResult] = None
|
||||
ai_analysis: Optional[str] = None
|
||||
|
||||
# 错误处理
|
||||
errors: List[str] = None
|
||||
|
||||
def __post_init__(self):
|
||||
if self.video_info is None:
|
||||
self.video_info = {}
|
||||
if self.raw_scenes is None:
|
||||
self.raw_scenes = []
|
||||
if self.processed_scenes is None:
|
||||
self.processed_scenes = []
|
||||
if self.errors is None:
|
||||
self.errors = []
|
||||
|
||||
class SceneDetector:
|
||||
"""场景检测器"""
|
||||
|
||||
|
||||
def __init__(self):
|
||||
self.supported_formats = {'.mp4', '.avi', '.mov', '.mkv', '.wmv', '.flv', '.webm', '.m4v'}
|
||||
|
||||
# 初始化AI分析器（如果可用）
|
||||
try:
|
||||
self.llm = ChatAnthropic(model="claude-3-5-sonnet-20241022")
|
||||
self.ai_enabled = True
|
||||
except Exception as e:
|
||||
progress_reporter.warning(f"⚠️ AI分析器初始化失败: {e}")
|
||||
self.ai_enabled = False
|
||||
|
||||
def detect_scenes(self, video_path: Path, detector_type: DetectorType = DetectorType.CONTENT,
|
||||
threshold: float = 30.0, min_scene_length: float = 1.0) -> DetectionResult:
|
||||
@@ -361,5 +412,460 @@ class SceneDetector:
|
||||
|
||||
f.write("\n")
|
||||
|
||||
# ==================== LangGraph 工作流方法 ====================
|
||||
|
||||
def create_detection_workflow(self) -> Optional[CompiledStateGraph]:
|
||||
"""创建场景检测工作流"""
|
||||
|
||||
# 定义工作流节点
|
||||
def validate_input(state: SceneDetectionWorkflowState) -> Dict[str, Any]:
|
||||
"""验证输入参数"""
|
||||
progress_reporter.info("🔍 验证输入参数...")
|
||||
|
||||
video_path = Path(state.video_path)
|
||||
errors = []
|
||||
|
||||
# 验证文件存在
|
||||
if not video_path.exists():
|
||||
errors.append(f"视频文件不存在: {video_path}")
|
||||
|
||||
# 验证文件格式
|
||||
if video_path.suffix.lower() not in self.supported_formats:
|
||||
errors.append(f"不支持的文件格式: {video_path.suffix}")
|
||||
|
||||
# 验证参数范围
|
||||
if not (0 <= state.threshold <= 100):
|
||||
errors.append(f"阈值超出范围 (0-100): {state.threshold}")
|
||||
|
||||
if state.min_scene_length < 0:
|
||||
errors.append(f"最小场景长度不能为负数: {state.min_scene_length}")
|
||||
|
||||
return {
|
||||
"current_stage": "validated" if not errors else "error",
|
||||
"progress": 1,
|
||||
"errors": errors
|
||||
}
|
||||
|
||||
def extract_video_info(state: SceneDetectionWorkflowState) -> Dict[str, Any]:
|
||||
"""提取视频信息"""
|
||||
progress_reporter.info("📊 提取视频信息...")
|
||||
|
||||
try:
|
||||
import cv2
|
||||
cap = cv2.VideoCapture(state.video_path)
|
||||
|
||||
if not cap.isOpened():
|
||||
raise Exception("无法打开视频文件")
|
||||
|
||||
fps = cap.get(cv2.CAP_PROP_FPS)
|
||||
frame_count = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
|
||||
width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
|
||||
height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
|
||||
duration = frame_count / fps if fps > 0 else 0
|
||||
|
||||
cap.release()
|
||||
|
||||
video_info = {
|
||||
"fps": fps,
|
||||
"frame_count": frame_count,
|
||||
"width": width,
|
||||
"height": height,
|
||||
"duration": duration,
|
||||
"resolution": f"{width}x{height}"
|
||||
}
|
||||
|
||||
progress_reporter.info(f"📹 视频信息: {video_info['resolution']}, {fps:.2f}fps, {duration:.2f}s")
|
||||
|
||||
return {
|
||||
"current_stage": "info_extracted",
|
||||
"progress": 2,
|
||||
"video_info": video_info
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
return {
|
||||
"current_stage": "error",
|
||||
"errors": state.errors + [f"提取视频信息失败: {e}"]
|
||||
}
|
||||
|
||||
def detect_scenes(state: SceneDetectionWorkflowState) -> Dict[str, Any]:
|
||||
"""执行场景检测"""
|
||||
progress_reporter.info("🎯 执行场景检测...")
|
||||
|
||||
try:
|
||||
# 使用现有的检测逻辑
|
||||
result = self.detect_scenes(
|
||||
Path(state.video_path),
|
||||
DetectorType(state.detector_type),
|
||||
state.threshold,
|
||||
state.min_scene_length
|
||||
)
|
||||
|
||||
return {
|
||||
"current_stage": "scenes_detected",
|
||||
"progress": 3,
|
||||
"detection_result": result,
|
||||
"processed_scenes": result.scenes
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
return {
|
||||
"current_stage": "error",
|
||||
"errors": state.errors + [f"场景检测失败: {e}"]
|
||||
}
|
||||
|
||||
def analyze_with_ai(state: SceneDetectionWorkflowState) -> Dict[str, Any]:
|
||||
"""AI分析场景结果"""
|
||||
if not self.ai_enabled or not state.enable_ai_analysis:
|
||||
progress_reporter.info("⚠️ AI分析已禁用，跳过此步骤")
|
||||
return {
|
||||
"current_stage": "analysis_skipped",
|
||||
"progress": 4,
|
||||
"ai_analysis": "AI分析已禁用"
|
||||
}
|
||||
|
||||
progress_reporter.info("🧠 AI分析场景结果...")
|
||||
|
||||
try:
|
||||
result = state.detection_result
|
||||
video_info = state.video_info
|
||||
|
||||
analysis_prompt = f"""
|
||||
请分析以下视频场景检测结果：
|
||||
|
||||
视频信息:
|
||||
- 文件: {result.filename}
|
||||
- 分辨率: {video_info.get('resolution', 'Unknown')}
|
||||
- 时长: {result.total_duration:.2f}秒
|
||||
- 帧率: {video_info.get('fps', 0):.2f}fps
|
||||
|
||||
检测结果:
|
||||
- 检测器: {result.detector_type}
|
||||
- 阈值: {result.threshold}
|
||||
- 场景数: {result.total_scenes}
|
||||
- 检测时间: {result.detection_time:.2f}秒
|
||||
|
||||
场景详情:
|
||||
{self._format_scenes_for_ai(result.scenes)}
|
||||
|
||||
请提供:
|
||||
1. 场景分布分析
|
||||
2. 检测质量评估
|
||||
3. 参数优化建议
|
||||
4. 潜在问题识别
|
||||
"""
|
||||
|
||||
response = self.llm.invoke([{"role": "user", "content": analysis_prompt}])
|
||||
|
||||
return {
|
||||
"current_stage": "ai_analyzed",
|
||||
"progress": 4,
|
||||
"ai_analysis": response.content
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
progress_reporter.warning(f"⚠️ AI分析失败: {e}")
|
||||
return {
|
||||
"current_stage": "analysis_failed",
|
||||
"progress": 4,
|
||||
"ai_analysis": f"AI分析失败: {e}"
|
||||
}
|
||||
|
||||
def finalize_results(state: SceneDetectionWorkflowState) -> Dict[str, Any]:
|
||||
"""整理最终结果"""
|
||||
progress_reporter.info("📋 整理最终结果...")
|
||||
|
||||
# 保存结果（如果指定了输出路径）
|
||||
if state.output_path and state.detection_result:
|
||||
try:
|
||||
output_path = Path(state.output_path)
|
||||
output_format = OutputFormat(state.output_format)
|
||||
self.save_results(state.detection_result, output_path, output_format)
|
||||
except Exception as e:
|
||||
progress_reporter.warning(f"⚠️ 保存结果失败: {e}")
|
||||
|
||||
return {
|
||||
"current_stage": "completed",
|
||||
"progress": 5
|
||||
}
|
||||
|
||||
# 路由函数
|
||||
def route_next_step(state: SceneDetectionWorkflowState) -> Literal["extract_info", "detect", "analyze", "finalize", "error"]:
|
||||
if state.errors:
|
||||
return "error"
|
||||
elif state.current_stage == "validated":
|
||||
return "extract_info"
|
||||
elif state.current_stage == "info_extracted":
|
||||
return "detect"
|
||||
elif state.current_stage == "scenes_detected":
|
||||
return "analyze"
|
||||
elif state.current_stage in ["ai_analyzed", "analysis_skipped", "analysis_failed"]:
|
||||
return "finalize"
|
||||
else:
|
||||
return "error"
|
||||
|
||||
def handle_error(state: SceneDetectionWorkflowState) -> Dict[str, Any]:
|
||||
"""处理错误"""
|
||||
error_msg = "; ".join(state.errors)
|
||||
progress_reporter.error(f"❌ 工作流错误: {error_msg}")
|
||||
return {"current_stage": "failed"}
|
||||
|
||||
# 构建工作流图
|
||||
workflow = StateGraph(SceneDetectionWorkflowState)
|
||||
|
||||
# 添加节点
|
||||
workflow.add_node("validate", validate_input)
|
||||
workflow.add_node("extract_info", extract_video_info)
|
||||
workflow.add_node("detect", detect_scenes)
|
||||
workflow.add_node("analyze", analyze_with_ai)
|
||||
workflow.add_node("finalize", finalize_results)
|
||||
workflow.add_node("error", handle_error)
|
||||
|
||||
# 添加边
|
||||
workflow.add_edge(START, "validate")
|
||||
workflow.add_conditional_edges("validate", route_next_step)
|
||||
workflow.add_conditional_edges("extract_info", route_next_step)
|
||||
workflow.add_conditional_edges("detect", route_next_step)
|
||||
workflow.add_conditional_edges("analyze", route_next_step)
|
||||
workflow.add_edge("finalize", END)
|
||||
workflow.add_edge("error", END)
|
||||
|
||||
# 编译工作流
|
||||
memory = MemorySaver()
|
||||
return workflow.compile(checkpointer=memory)
|
||||
|
||||
def _format_scenes_for_ai(self, scenes: List[SceneInfo]) -> str:
|
||||
"""格式化场景信息供AI分析"""
|
||||
if not scenes:
|
||||
return "无场景数据"
|
||||
|
||||
formatted = []
|
||||
for scene in scenes[:10]: # 只显示前10个场景
|
||||
formatted.append(
|
||||
f"场景 {scene.index}: {scene.start_time:.2f}s - {scene.end_time:.2f}s "
|
||||
f"(时长: {scene.duration:.2f}s)"
|
||||
)
|
||||
|
||||
if len(scenes) > 10:
|
||||
formatted.append(f"... 还有 {len(scenes) - 10} 个场景")
|
||||
|
||||
return "\n".join(formatted)
|
||||
|
||||
def detect_with_workflow(self, video_path: Path, detector_type: DetectorType = DetectorType.CONTENT,
|
||||
threshold: float = 30.0, min_scene_length: float = 1.0,
|
||||
output_path: Optional[Path] = None, output_format: OutputFormat = OutputFormat.JSON,
|
||||
enable_ai_analysis: bool = True) -> Dict[str, Any]:
|
||||
"""使用LangGraph工作流进行场景检测"""
|
||||
|
||||
# 创建工作流
|
||||
workflow = self.create_detection_workflow()
|
||||
if not workflow:
|
||||
raise Exception("无法创建工作流")
|
||||
|
||||
# 初始化状态
|
||||
initial_state = SceneDetectionWorkflowState(
|
||||
video_path=str(video_path),
|
||||
detector_type=detector_type.value,
|
||||
threshold=threshold,
|
||||
min_scene_length=min_scene_length,
|
||||
output_path=str(output_path) if output_path else None,
|
||||
output_format=output_format.value,
|
||||
enable_ai_analysis=enable_ai_analysis # 使用参数
|
||||
)
|
||||
|
||||
# 执行工作流
|
||||
config = {"configurable": {"thread_id": f"detection_{int(time.time())}"}}
|
||||
|
||||
try:
|
||||
final_state = workflow.invoke(initial_state, config)
|
||||
|
||||
return {
|
||||
"detection_result": final_state.get("detection_result"),
|
||||
"ai_analysis": final_state.get("ai_analysis"),
|
||||
"video_info": final_state.get("video_info"),
|
||||
"workflow_state": final_state.get("current_stage"),
|
||||
"errors": final_state.get("errors", [])
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
progress_reporter.error(f"❌ 工作流执行失败: {e}")
|
||||
raise
|
||||
|
||||
# ==================== JSON-RPC 方法注册 ====================
|
||||
|
||||
def register_jsonrpc_methods(self):
|
||||
"""注册JSON-RPC方法到全局注册器"""
|
||||
from python_core.utils.jsonrpc_enhanced import method_registry
|
||||
|
||||
# 注册方法到全局注册器
|
||||
method_registry.register_function(self.jsonrpc_detect_scenes, "scene.detect")
|
||||
method_registry.register_function(self.jsonrpc_detect_with_workflow, "scene.detect_workflow")
|
||||
method_registry.register_function(self.jsonrpc_get_video_info, "scene.get_video_info")
|
||||
method_registry.register_function(self.jsonrpc_batch_detect, "scene.batch_detect")
|
||||
|
||||
def jsonrpc_detect_scenes(self, video_path: str, detector_type: str = "content",
|
||||
threshold: float = 30.0, min_scene_length: float = 1.0) -> Dict[str, Any]:
|
||||
"""JSON-RPC方法：场景检测"""
|
||||
try:
|
||||
result = self.detect_scenes(
|
||||
Path(video_path),
|
||||
DetectorType(detector_type),
|
||||
threshold,
|
||||
min_scene_length
|
||||
)
|
||||
|
||||
return {
|
||||
"success": result.success,
|
||||
"filename": result.filename,
|
||||
"detector_type": result.detector_type,
|
||||
"threshold": result.threshold,
|
||||
"total_scenes": result.total_scenes,
|
||||
"total_duration": result.total_duration,
|
||||
"detection_time": result.detection_time,
|
||||
"scenes": [asdict(scene) for scene in result.scenes],
|
||||
"error": result.error
|
||||
}
|
||||
except Exception as e:
|
||||
return {
|
||||
"success": False,
|
||||
"error": str(e)
|
||||
}
|
||||
|
||||
def jsonrpc_detect_with_workflow(self, video_path: str, detector_type: str = "content",
|
||||
threshold: float = 30.0, min_scene_length: float = 1.0,
|
||||
output_path: Optional[str] = None, output_format: str = "json",
|
||||
enable_ai_analysis: bool = True) -> Dict[str, Any]:
|
||||
"""JSON-RPC方法：工作流场景检测"""
|
||||
try:
|
||||
output_path_obj = Path(output_path) if output_path else None
|
||||
|
||||
result = self.detect_with_workflow(
|
||||
Path(video_path),
|
||||
DetectorType(detector_type),
|
||||
threshold,
|
||||
min_scene_length,
|
||||
output_path_obj,
|
||||
OutputFormat(output_format),
|
||||
enable_ai_analysis
|
||||
)
|
||||
|
||||
# 序列化结果
|
||||
serialized_result = {}
|
||||
for key, value in result.items():
|
||||
if key == "detection_result" and value:
|
||||
serialized_result[key] = {
|
||||
"success": value.success,
|
||||
"filename": value.filename,
|
||||
"detector_type": value.detector_type,
|
||||
"threshold": value.threshold,
|
||||
"total_scenes": value.total_scenes,
|
||||
"total_duration": value.total_duration,
|
||||
"detection_time": value.detection_time,
|
||||
"scenes": [asdict(scene) for scene in value.scenes],
|
||||
"error": value.error
|
||||
}
|
||||
else:
|
||||
serialized_result[key] = value
|
||||
|
||||
return serialized_result
|
||||
|
||||
except Exception as e:
|
||||
return {
|
||||
"success": False,
|
||||
"error": str(e)
|
||||
}
|
||||
|
||||
def get_video_info(self, video_path: Path) -> Dict[str, Any]:
|
||||
"""获取视频信息"""
|
||||
try:
|
||||
import cv2
|
||||
cap = cv2.VideoCapture(str(video_path))
|
||||
|
||||
if not cap.isOpened():
|
||||
raise Exception("无法打开视频文件")
|
||||
|
||||
fps = cap.get(cv2.CAP_PROP_FPS)
|
||||
frame_count = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
|
||||
width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
|
||||
height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
|
||||
duration = frame_count / fps if fps > 0 else 0
|
||||
|
||||
cap.release()
|
||||
|
||||
return {
|
||||
"filename": video_path.name,
|
||||
"fps": fps,
|
||||
"frame_count": frame_count,
|
||||
"width": width,
|
||||
"height": height,
|
||||
"duration": duration,
|
||||
"resolution": f"{width}x{height}",
|
||||
"file_size": video_path.stat().st_size if video_path.exists() else 0
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
raise Exception(f"获取视频信息失败: {e}")
|
||||
|
||||
def jsonrpc_get_video_info(self, video_path: str) -> Dict[str, Any]:
|
||||
"""JSON-RPC方法：获取视频信息"""
|
||||
try:
|
||||
info = self.get_video_info(Path(video_path))
|
||||
return {
|
||||
"success": True,
|
||||
"info": info
|
||||
}
|
||||
except Exception as e:
|
||||
return {
|
||||
"success": False,
|
||||
"error": str(e)
|
||||
}
|
||||
|
||||
def jsonrpc_batch_detect(self, directory: str, detector_type: str = "content",
|
||||
threshold: float = 30.0, min_scene_length: float = 1.0,
|
||||
output_dir: Optional[str] = None, output_format: str = "json") -> Dict[str, Any]:
|
||||
"""JSON-RPC方法：批量场景检测"""
|
||||
try:
|
||||
output_dir_obj = Path(output_dir) if output_dir else None
|
||||
|
||||
results = self.batch_detect(
|
||||
Path(directory),
|
||||
DetectorType(detector_type),
|
||||
threshold,
|
||||
min_scene_length,
|
||||
output_dir_obj,
|
||||
OutputFormat(output_format)
|
||||
)
|
||||
|
||||
# 序列化结果
|
||||
serialized_results = []
|
||||
for result in results:
|
||||
serialized_results.append({
|
||||
"success": result.success,
|
||||
"filename": result.filename,
|
||||
"detector_type": result.detector_type,
|
||||
"threshold": result.threshold,
|
||||
"total_scenes": result.total_scenes,
|
||||
"total_duration": result.total_duration,
|
||||
"detection_time": result.detection_time,
|
||||
"scenes": [asdict(scene) for scene in result.scenes],
|
||||
"error": result.error
|
||||
})
|
||||
|
||||
return {
|
||||
"success": True,
|
||||
"results": serialized_results,
|
||||
"total_processed": len(results)
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
return {
|
||||
"success": False,
|
||||
"error": str(e)
|
||||
}
|
||||
|
||||
|
||||
# 创建全局检测器实例
|
||||
detector = SceneDetector()
|
||||
detector = SceneDetector()
|
||||
|
||||
# 注册JSON-RPC方法
|
||||
detector.register_jsonrpc_methods()
|
||||
Reference in New Issue
Block a user