feat: 添加进度反馈机制（--progress参数）

skills/kb-ocr-processor/ocr_processor.py

@@ -93,46 +93,81 @@ class OCRProcessor:
             "confidence": 0.0
         }
     
-    def process_frames(self, input_dir: str, fps: float = 0.1) -> List[Dict]:
+    def process_frames(self, input_dir: str, fps: float = 0.1, progress_file: Optional[str] = None) -> List[Dict]:
         """
         处理目录下所有帧图片
-        
+
         Args:
             input_dir: 帧图片目录
             fps: 采样帧率
-            
+            progress_file: 可选，进度文件路径（会实时更新）
+
         Returns:
             OCR 结果列表
         """
         if not os.path.isdir(input_dir):
             print(f"Error: Directory not found: {input_dir}")
             return []
-        
+
         # 支持的图片格式
         image_extensions = ["*.jpg", "*.jpeg", "*.png", "*.bmp", "*.webp"]
         image_files = []
-        
+
         for ext in image_extensions:
             image_files.extend(glob.glob(os.path.join(input_dir, ext)))
             image_files.extend(glob.glob(os.path.join(input_dir, "**", ext), recursive=True))
-        
+
         # 按文件名排序
         image_files = sorted(image_files)
-        
+
         if not image_files:
             print(f"No images found in {input_dir}")
             return []
-        
-        print(f"Found {len(image_files)} images in {input_dir}")
+
+        total = len(image_files)
+        print(f"Found {total} images in {input_dir}")
         print(f"Processing with {self.engine} engine...")
-        
+
+        def update_progress(current, status="running", last_result=None):
+            """更新进度文件"""
+            if progress_file:
+                import json
+                import time
+                prog = {
+                    "current": current,
+                    "total": total,
+                    "percent": round(current / total * 100, 1) if total > 0 else 0,
+                    "status": status,
+                    "last_result": last_result,
+                    "updated_at": time.strftime("%Y-%m-%d %H:%M:%S")
+                }
+                with open(progress_file, 'w', encoding='utf-8') as f:
+                    json.dump(prog, f, ensure_ascii=False, indent=2)
+
+        # 初始化进度
+        update_progress(0, "started")
+
         results = []
-        for i, image_path in enumerate(image_files):
-            print(f"Processing [{i+1}/{len(image_files)}]: {image_path}")
+        for i, image_path in enumerate(image_files, 1):
+            basename = os.path.basename(image_path)
+            print(f"Processing [{i}/{total}]: {basename}")
+
             ocr_result = self.process_image(image_path)
-            ocr_result["source"] = os.path.basename(image_path)
+            ocr_result["source"] = basename
+
+            # 记录结果摘要
+            text_count = len(ocr_result.get("text", "").split()) if ocr_result.get("text") else 0
+            last_result = f"✓ {text_count} 处文字" if ocr_result.get("text") else "✗ 无文字"
+
             results.append(ocr_result)
-        
+
+            # 实时更新进度
+            update_progress(i, "running", last_result)
+
+        # 完成
+        update_progress(total, "completed", f"完成 {total} 张")
+
+        print(f"\n✅ Processed {total} frames")
         return results
     
     def merge_texts(self, results: List[Dict]) -> str:
@@ -205,11 +240,12 @@ def main():
     parser.add_argument("--input", "-i", required=True, help="输入帧图片目录")
     parser.add_argument("--output", "-o", required=True, help="输出 JSON 文件路径")
     parser.add_argument("--fps", "-f", type=float, default=0.1, help="采样帧率 (默认: 0.1)")
-    parser.add_argument("--engine", "-e", choices=["easyocr", "tesseract"], 
+    parser.add_argument("--engine", "-e", choices=["easyocr", "tesseract"],
                        default="easyocr", help="OCR 引擎 (默认: easyocr)")
     parser.add_argument("--merge", action="store_true", help="同时保存合并的文本文件")
-    parser.add_argument("--languages", "-l", nargs="+", 
+    parser.add_argument("--languages", "-l", nargs="+",
                        default=["ch_sim", "en"], help="语言列表")
+    parser.add_argument("--progress", "-p", help="可选：进度文件路径（会实时更新）")
     
     args = parser.parse_args()
     
@@ -217,7 +253,7 @@ def main():
     processor = OCRProcessor(engine=args.engine, languages=args.languages)
     
     # 处理帧
-    results = processor.process_frames(args.input, fps=args.fps)
+    results = processor.process_frames(args.input, fps=args.fps, progress_file=args.progress)
     
     if results:
         # 保存结果