Update pdf_server.py

magic_pdf/tools/pdf_server.py

@@ -22,11 +22,10 @@ method = 'auto'
 
 logger.add("parse.log", rotation="10 MB", level="INFO",
            format="{time} {level} {message}", encoding='utf-8', enqueue=True)
-
+config_path = None
 class ocrRequest(BaseModel):
     path: str
     output_dir: str
-    config_path: str
 
 class ocrResponse(BaseModel):
     status_code: int
@@ -68,6 +67,8 @@ def ocr_pdf_serve(args: str):
     config.read(args.config_path)
     host = config.get('server', 'pdf_host')
     port = int(config.get('server', 'pdf_port'))
+    global config_path
+    config_path = args.config_path
     uvicorn.run(app, host=host, port=port)
 
 @app.post("/pdf_ocr")
@@ -82,7 +83,7 @@ async def pdf_ocr(request: ocrRequest):
     debug_able = False
     start_page_id = 0
     end_page_id = None
-    logger.info(f"method: {method}, path: {path}, output_dir: {output_dir}, config_path: {request.config_path}")
+    logger.info(f"method: {method}, path: {path}, output_dir: {output_dir}, config_path: {config_path}")
 
     def read_fn(path):
         disk_rw = DiskReaderWriter(os.path.dirname(path))
@@ -110,16 +111,15 @@ async def pdf_ocr(request: ocrRequest):
         except Exception as e:
             logger.exception(e)
 
-    logger.info(f'config_path：{request.config_path}')
-    try:
-        output_path = parse_doc(path,request.config_path)
-        logger.info(f'文件解析成功：{output_path}')
+    logger.info(f'config_path：{config_path}')
 
+    output_path = parse_doc(path,config_path)
+    if output_path:
+        logger.info(f'文件解析成功：{output_path}')
         return {"status_code": 200, "output_path": output_path}
-    except Exception as e:
-        logger.exception(e)
-        # Return error response with error details
-        raise HTTPException(status_code=500, detail=str(e))
+    else:
+        logger.error(f'文件解析失败，文件为：{path}')
+        raise HTTPException(status_code=500)
 
 def main():
     args = parse_args()