|
|
@@ -21,52 +21,10 @@ from utils import (
|
|
|
get_image_files_from_list,
|
|
|
get_image_files_from_csv,
|
|
|
split_files,
|
|
|
- create_temp_file_list
|
|
|
+ create_temp_file_list,
|
|
|
+ collect_pid_files
|
|
|
)
|
|
|
|
|
|
-
|
|
|
-def collect_pid_files(pid_output_file: str) -> List[Tuple[str, str]]:
|
|
|
- """
|
|
|
- 从进程输出文件中收集文件
|
|
|
-
|
|
|
- Args:
|
|
|
- pid_output_file: 进程输出文件路径
|
|
|
-
|
|
|
- Returns:
|
|
|
- 文件列表(文件路径，处理结果)
|
|
|
- """
|
|
|
-
|
|
|
- """
|
|
|
- 单进程结果统计文件格式
|
|
|
- "results": [
|
|
|
- {
|
|
|
- "image_path": "docstructbench_dianzishu_zhongwenzaixian-o.O-61520612.pdf_140.jpg",
|
|
|
- "processing_time": 2.0265579223632812e-06,
|
|
|
- "success": true,
|
|
|
- "device": "gpu:3",
|
|
|
- "output_json": "/home/ubuntu/zhch/PaddleX/zhch/OmniDocBench_Results_Scheduler/process_3/docstructbench_dianzishu_zhongwenzaixian-o.O-61520612.pdf_140.json",
|
|
|
- "output_md": "/home/ubuntu/zhch/PaddleX/zhch/OmniDocBench_Results_Scheduler/process_3/docstructbench_dianzishu_zhongwenzaixian-o.O-61520612.pdf_140.md"
|
|
|
- },
|
|
|
- ...
|
|
|
- """
|
|
|
- if not Path(pid_output_file).exists():
|
|
|
- print(f"⚠️ Warning: PID output file not found: {pid_output_file}")
|
|
|
- return []
|
|
|
-
|
|
|
- with open(pid_output_file, 'r', encoding='utf-8') as f:
|
|
|
- data = json.load(f)
|
|
|
-
|
|
|
- if not isinstance(data, dict) or "results" not in data:
|
|
|
- print(f"⚠️ Warning: Invalid PID output file format: {pid_output_file}")
|
|
|
- return []
|
|
|
- # 返回文件路径和处理状态, 如果“success”: True, 则状态为“success”, 否则为“fail”
|
|
|
- file_list = []
|
|
|
- for file_result in data.get("results", []):
|
|
|
- image_path = file_result.get("image_path", "")
|
|
|
- status = "success" if file_result.get("success", False) else "fail"
|
|
|
- file_list.append((image_path, status))
|
|
|
- return file_list
|
|
|
-
|
|
|
def collect_processed_files(results: List[Dict[str, Any]]) -> List[Tuple[str, str]]:
|
|
|
"""
|
|
|
从处理结果中收集文件
|
