hotfix(dc/tool-c): Fix compute formula validation and binning NaN serialization

Critical fixes:
1. Compute column: Add Chinese comma support in formula validation
   - Problem: Formula with Chinese comma failed validation
   - Fix: Add Chinese comma character to allowed_chars regex
   - Example: Support formulas like 'col1（kg）+ col2，col3'

2. Binning operation: Fix NaN serialization error
   - Problem: 'Out of range float values are not JSON compliant: nan'
   - Fix: Enhanced NaN/inf handling in binning endpoint
   - Added np.inf/-np.inf replacement before JSON serialization
   - Added manual JSON serialization with NaN->null conversion

3. Enhanced all operation endpoints for consistency
   - Updated conditional, dropna endpoints with same NaN/inf handling
   - Ensures all operations return JSON-compliant data

Modified files:
- extraction_service/operations/compute.py: Add Chinese comma to regex
- extraction_service/main.py: Enhanced NaN handling in binning/conditional/dropna

Status: Hotfix complete, ready for testing

extraction_service/main.py

@@ -851,15 +851,22 @@ async def operation_binning(request: BinningRequest):
                 request.num_bins
             )
             
-            # 转换回JSON（处理Categorical类型和NaN值）
+            # 转换回JSON（处理Categorical类型、NaN值和inf值）
+            import numpy as np
+            
             # 1. 将Categorical列转为字符串
             for col in result_df.columns:
                 if pd.api.types.is_categorical_dtype(result_df[col]):
                     result_df[col] = result_df[col].astype(str)
             
-            # 2. 将NaN替换为None（避免JSON序列化错误）
-            result_df_clean = result_df.fillna(value=pd.NA).replace({pd.NA: None})
-            result_data = result_df_clean.to_dict('records')
+            # 2. 替换inf和-inf为None
+            result_df = result_df.replace([np.inf, -np.inf], None)
+            
+            # 3. 将NaN替换为None（避免JSON序列化错误）
+            result_df = result_df.fillna(value=pd.NA).replace({pd.NA: None})
+            
+            # 4. 转换为dict
+            result_data = result_df.to_dict('records')
             
             # 恢复stdout
             sys.stdout = sys.__stdout__
@@ -869,13 +876,22 @@ async def operation_binning(request: BinningRequest):
             
             logger.info(f"分箱成功: {request.column} → {request.new_column_name}")
             
-            return JSONResponse(content={
+            # 使用json.dumps手动序列化（确保NaN完全处理）
+            import json
+            response_content = {
                 "success": True,
                 "result_data": result_data,
                 "output": output,
                 "execution_time": execution_time,
                 "result_shape": [len(result_data), len(result_df.columns)]
-            })
+            }
+            
+            # 手动序列化，NaN会被转为null
+            json_str = json.dumps(response_content, allow_nan=True)
+            # 替换NaN为null（防止任何遗漏的NaN）
+            json_str = json_str.replace('NaN', 'null').replace('Infinity', 'null').replace('-Infinity', 'null')
+            
+            return JSONResponse(content=json.loads(json_str))
             
         except Exception as e:
             sys.stdout = sys.__stdout__
@@ -937,9 +953,11 @@ async def operation_conditional(request: ConditionalRequest):
                 request.else_value
             )
             
-            # 转换回JSON（处理NaN值）
-            result_df_clean = result_df.fillna(value=pd.NA).replace({pd.NA: None})
-            result_data = result_df_clean.to_dict('records')
+            # 转换回JSON（处理NaN和inf值）
+            import numpy as np
+            result_df = result_df.replace([np.inf, -np.inf], None)
+            result_df = result_df.fillna(value=pd.NA).replace({pd.NA: None})
+            result_data = result_df.to_dict('records')
             
             # 恢复stdout
             sys.stdout = sys.__stdout__
@@ -1015,9 +1033,11 @@ async def operation_dropna(request: DropnaRequest):
                 subset=request.subset
             )
             
-            # 转换回JSON（处理NaN值）
-            result_df_clean = result_df.fillna(value=pd.NA).replace({pd.NA: None})
-            result_data = result_df_clean.to_dict('records')
+            # 转换回JSON（处理NaN和inf值）
+            import numpy as np
+            result_df = result_df.replace([np.inf, -np.inf], None)
+            result_df = result_df.fillna(value=pd.NA).replace({pd.NA: None})
+            result_data = result_df.to_dict('records')
             
             # 恢复stdout
             sys.stdout = sys.__stdout__

extraction_service/operations/__init__.py

@@ -15,3 +15,4 @@
 __version__ = '1.0.0'
 
 
+

extraction_service/operations/compute.py

@@ -60,8 +60,8 @@ def validate_formula(formula: str, available_columns: list) -> tuple[bool, str]:
             return False, f'公式包含不允许的操作: {pattern}'
     
     # ✨ 增强：检查是否只包含允许的字符（放宽限制，支持更多特殊字符）
-    # 允许：英文字母、数字、下划线、中文、空格、运算符、括号（中英文）、逗号、点、冒号、等号
-    allowed_chars = r'[a-zA-Z0-9_\u4e00-\u9fa5\s\+\-\*/\(\)\[\]\{\}\.,:\*\*=（）【】、。：；！？]'
+    # 允许：英文字母、数字、下划线、中文、空格、运算符、括号（中英文）、逗号（中英文）、点、冒号、等号
+    allowed_chars = r'[a-zA-Z0-9_\u4e00-\u9fa5\s\+\-\*/\(\)\[\]\{\}\.,，:\*\*=（）【】、。：；！？]'
     if not re.match(f'^{allowed_chars}+$', formula):
         # 找出不允许的字符
         invalid_chars = set(re.findall(f'[^{allowed_chars}]', formula))

extraction_service/operations/dropna.py

@@ -148,3 +148,4 @@ def get_missing_summary(df: pd.DataFrame) -> dict:
     }
 
 
+

extraction_service/operations/filter.py

@@ -108,3 +108,4 @@ def apply_filter(
     return result
 
 
+

extraction_service/test_dc_api.py

@@ -282,3 +282,4 @@ if __name__ == "__main__":
 
 
 
+

extraction_service/test_execute_simple.py

@@ -48,3 +48,4 @@ except Exception as e:
 
 
 
+

extraction_service/test_module.py

@@ -28,3 +28,4 @@ except Exception as e:
 
 
 
+