新版本

app/core/ocr/table_ocr.py

@@ -11,7 +11,7 @@ import json
 import base64
 from datetime import datetime
 from concurrent.futures import ThreadPoolExecutor
-from typing import Dict, List, Optional, Tuple, Union, Any
+from typing import Dict, List, Optional, Tuple, Union, Any, Callable
 
 from ...config.settings import ConfigManager
 from ..utils.log_utils import get_logger
@@ -332,7 +332,7 @@ class OCRProcessor:
             logger.error(f"处理图片时出错: {image_path}, 错误: {e}")
             return None
     
-    def process_images_batch(self, batch_size: int = None, max_workers: int = None) -> Tuple[int, int]:
+    def process_images_batch(self, batch_size: int = None, max_workers: int = None, progress_cb: Optional[Callable[[int], None]] = None) -> Tuple[int, int]:
         """
         批量处理图片
         
@@ -369,6 +369,13 @@ class OCRProcessor:
         for i in range(0, total, batch_size):
             batch = unprocessed_images[i:i+batch_size]
             logger.info(f"处理批次 {i//batch_size+1}/{(total+batch_size-1)//batch_size}: {len(batch)} 个文件")
+            try:
+                if progress_cb:
+                    # 以批次为单位估算进度（0-90%），保留10%给后续阶段
+                    percent = int(10 + (i / max(total, 1)) * 80)
+                    progress_cb(min(percent, 90))
+            except Exception:
+                pass
         
             # 使用多线程处理批次
             with ThreadPoolExecutor(max_workers=max_workers) as executor:
@@ -378,4 +385,9 @@ class OCRProcessor:
                 success_count += sum(1 for result in results if result is not None)
     
         logger.info(f"所有图片处理完成, 总计: {total}, 成功: {success_count}")
+        try:
+            if progress_cb:
+                progress_cb(90)
+        except Exception:
+            pass
         return total, success_count