feat: 移除详细验证和调试日志，简化网格结构恢复逻辑

ocr_tools/universal_doc_parser/models/adapters/wired_table/grid_recovery.py

@@ -481,113 +481,6 @@ class GridRecovery:
         
         bboxes.sort(key=lambda b: (int(b[1] / 10), b[0]))
 
-        # 添加详细验证
-        if len(bboxes) > 0:
-            min_y = min(b[1] for b in bboxes)
-            max_y = max(b[3] for b in bboxes)
-            coverage_h = max_y - min_y
-            expected_h = orig_h if orig_h else h / upscale
-            
-            logger.debug(
-                f"📏 单元格Y轴覆盖验证:\n"
-                f"  - 最小Y: {min_y:.1f}\n"
-                f"  - 最大Y: {max_y:.1f}\n"
-                f"  - 覆盖高度: {coverage_h:.1f}\n"
-                f"  - 原图高度: {expected_h:.1f}\n"
-                f"  - 覆盖率: {coverage_h/expected_h*100:.1f}%\n"
-                f"  - 顶部空白: {min_y:.1f}px ({min_y/expected_h*100:.1f}%)\n"
-                f"  - 底部空白: {expected_h - max_y:.1f}px ({(expected_h-max_y)/expected_h*100:.1f}%)"
-            )
-        
-        # 可视化验证：保存调试图像，显示上采样mask上的连通域bbox和转换后的原图坐标
-        if debug_dir and len(bboxes) > 0:
-            try:
-                os.makedirs(debug_dir, exist_ok=True)
-                
-                # 创建可视化图像：上采样mask上的连通域bbox（绿色）
-                vis_mask = np.zeros((h, w, 3), dtype=np.uint8)
-                vis_mask[:, :, 0] = inv_grid  # 背景用反转的grid
-                vis_mask[:, :, 1] = inv_grid
-                vis_mask[:, :, 2] = inv_grid
-                
-                # 在上采样mask上绘制连通域bbox（使用上采样坐标）
-                for idx, bbox_orig in enumerate(bboxes[:min(20, len(bboxes))]):  # 只绘制前20个，避免太密集
-                    # 反推上采样坐标
-                    x_up = int(bbox_orig[0] * scale_w)
-                    y_up = int(bbox_orig[1] * scale_h)
-                    x2_up = int(bbox_orig[2] * scale_w)
-                    y2_up = int(bbox_orig[3] * scale_h)
-                    
-                    # 确保坐标在范围内
-                    x_up = max(0, min(x_up, w - 1))
-                    y_up = max(0, min(y_up, h - 1))
-                    x2_up = max(0, min(x2_up, w - 1))
-                    y2_up = max(0, min(y2_up, h - 1))
-                    
-                    if x2_up > x_up and y2_up > y_up:
-                        cv2.rectangle(vis_mask, (x_up, y_up), (x2_up, y2_up), (0, 255, 0), 2)
-                        # 标注单元格索引
-                        cv2.putText(vis_mask, str(idx), (x_up + 2, y_up + 15), 
-                                   cv2.FONT_HERSHEY_SIMPLEX, 0.4, (0, 255, 0), 1)
-                
-                name = f"{debug_prefix}_coordinate_verification_mask.png" if debug_prefix else "coordinate_verification_mask.png"
-                path = os.path.join(debug_dir, name)
-                cv2.imwrite(path, vis_mask)
-                logger.debug(f"保存坐标验证图像（上采样mask）: {path}")
-                
-            except Exception as e:
-                logger.warning(f"保存坐标验证图像失败: {e}")
-        
-        # 详细的坐标转换调试日志
-        if len(bboxes) > 0:
-            logger.debug(
-                f"🔍 坐标转换验证:\n"
-                f"  - mask尺寸: [{h}, {w}]\n"
-                f"  - 原图尺寸: [{orig_h}, {orig_w}]\n"
-                f"  - 缩放比例: scale_h={scale_h:.6f}, scale_w={scale_w:.6f}\n"
-                f"  - 缩放比例差异: {abs(scale_h - scale_w):.6f}\n"
-                f"  - 提取到 {len(bboxes)} 个单元格"
-            )
-            
-            # 记录前几个和后几个单元格的详细坐标转换过程
-            sample_indices = [0, 1, 2] + [len(bboxes) - 3, len(bboxes) - 2, len(bboxes) - 1]
-            sample_indices = [i for i in sample_indices if 0 <= i < len(bboxes)]
-            
-            logger.debug("🔍 样本单元格坐标转换详情:")
-            for idx in sample_indices:
-                bbox_orig = bboxes[idx]
-                # 反推上采样坐标（用于验证）
-                x_up = bbox_orig[0] * scale_w
-                y_up = bbox_orig[1] * scale_h
-                w_up = (bbox_orig[2] - bbox_orig[0]) * scale_w
-                h_up = (bbox_orig[3] - bbox_orig[1]) * scale_h
-                
-                logger.debug(
-                    f"  单元格 {idx}: 原图坐标 [{bbox_orig[0]:.1f}, {bbox_orig[1]:.1f}, "
-                    f"{bbox_orig[2]:.1f}, {bbox_orig[3]:.1f}] "
-                    f"(尺寸: {bbox_orig[2]-bbox_orig[0]:.1f}x{bbox_orig[3]-bbox_orig[1]:.1f}) "
-                    f"-> 反推上采样坐标 [{x_up:.1f}, {y_up:.1f}, {x_up+w_up:.1f}, {y_up+h_up:.1f}] "
-                    f"(尺寸: {w_up:.1f}x{h_up:.1f})"
-                )
-            
-            # 检查是否有系统性偏移
-            if len(bboxes) >= 2:
-                first_y = bboxes[0][1]
-                last_y = bboxes[-1][3]
-                expected_height = last_y - first_y
-                actual_image_height = orig_h if orig_h else h / upscale
-                logger.debug(
-                    f"🔍 系统性偏移检查:\n"
-                    f"  - 第一个单元格y1: {first_y:.1f}\n"
-                    f"  - 最后一个单元格y2: {last_y:.1f}\n"
-                    f"  - 单元格覆盖高度: {expected_height:.1f}\n"
-                    f"  - 原图实际高度: {actual_image_height:.1f}\n"
-                    f"  - 高度差异: {abs(expected_height - actual_image_height):.1f}"
-                )
-            
-            logger.debug(f"bbox 坐标范围: x=[{min(b[0] for b in bboxes):.1f}, {max(b[2] for b in bboxes):.1f}], "
-                        f"y=[{min(b[1] for b in bboxes):.1f}, {max(b[3] for b in bboxes):.1f}]")
-        
         if orig_h is not None and orig_w is not None:
             logger.info(
                 f"矢量重构分析提取到 {len(bboxes)} 个单元格 "