mdbq 3.11.0__py3-none-any.whl → 3.11.2__py3-none-any.whl

mdbq/__version__.py

@@ -1 +1 @@
-VERSION = '3.11.0'
+VERSION = '3.11.2'

mdbq/mysql/uploader.py

@@ -346,8 +346,9 @@ class MySQLUploader:
             logger.error('无效的标识符', {'标识符': identifier})
             raise ValueError(f"无效的标识符: `{identifier}`")
         if not self.case_sensitive:
-            
-        cleaned = re.sub(r'[^\w\u4e00-\u9fff$]', '_', identifier)
+            cleaned = re.sub(r'[^\w\u4e00-\u9fff$]', '_', identifier)
+        else:
+            cleaned = identifier
         cleaned = re.sub(r'_+', '_', cleaned).strip('_')
         if not cleaned:
             logger.error('无法清理异常标识符', {'原始标识符': identifier})
@@ -592,7 +593,10 @@ class MySQLUploader:
             with self._get_connection() as conn:
                 with conn.cursor() as cursor:
                     cursor.execute(sql, (db_name, table_name))
-                    set_typ = {row['COLUMN_NAME'].lower(): row['DATA_TYPE'] for row in cursor.fetchall()}
+                    if self.case_sensitive:
+                        set_typ = {row['COLUMN_NAME']: row['DATA_TYPE'] for row in cursor.fetchall()}
+                    else:
+                        set_typ = {row['COLUMN_NAME'].lower(): row['DATA_TYPE'] for row in cursor.fetchall()}
                     logger.debug('获取表的列信息', {'库': db_name, '表': table_name, '列信息': set_typ})
                     return set_typ
         except Exception as e:
@@ -726,17 +730,18 @@ class MySQLUploader:
         """
         1. pandas：规范化列名
         2. 字典列表：规范化每个字典的键
-
-        参数：
-            data: 输入数据，支持两种类型：
-                  - pandas.DataFrame：将规范化其列名
-                  - List[Dict[str, Any]]：将规范化列表中每个字典的键
         """
         if isinstance(data, pd.DataFrame):
-            data.columns = [self._validate_identifier(col) for col in data.columns]
+            if self.case_sensitive:
+                data.columns = [self._validate_identifier(col) for col in data.columns]
+            else:
+                data.columns = [self._validate_identifier(col).lower() for col in data.columns]
             return data
         elif isinstance(data, list):
-            return [{self._validate_identifier(k): v for k, v in item.items()} for item in data]
+            if self.case_sensitive:
+                return [{self._validate_identifier(k): v for k, v in item.items()} for item in data]
+            else:
+                return [{self._validate_identifier(k).lower(): v for k, v in item.items()} for item in data]
         return data
 
     def _prepare_data(
@@ -747,18 +752,14 @@ class MySQLUploader:
     ) -> Tuple[List[Dict], Dict[str, str]]:
         """
         准备要上传的数据，验证并转换数据类型
-
-        :param data: 输入数据，可以是字典、字典列表或DataFrame
-        :param set_typ: 列名和数据类型字典 {列名: 数据类型}
-        :param allow_null: 是否允许空值
-        :return: 元组(准备好的数据列表, 过滤后的列类型字典)
-        :raises ValueError: 当数据验证失败时抛出
         """
         # 统一数据格式为字典列表
         if isinstance(data, pd.DataFrame):
             try:
-                # 将列名转为小写
-                data.columns = [col.lower() for col in data.columns]
+                if self.case_sensitive:
+                    data.columns = [col for col in data.columns]
+                else:
+                    data.columns = [col.lower() for col in data.columns]
                 data = data.replace({pd.NA: None}).to_dict('records')
             except Exception as e:
                 logger.error('数据转字典时发生错误', {
@@ -768,10 +769,15 @@ class MySQLUploader:
                 })
                 raise ValueError(f"数据转字典时发生错误: {e}")
         elif isinstance(data, dict):
-            data = [{k.lower(): v for k, v in data.items()}]
+            if self.case_sensitive:
+                data = [{k: v for k, v in data.items()}]
+            else:
+                data = [{k.lower(): v for k, v in data.items()}]
         elif isinstance(data, list) and all(isinstance(item, dict) for item in data):
-            # 将列表中的每个字典键转为小写
-            data = [{k.lower(): v for k, v in item.items()} for item in data]
+            if self.case_sensitive:
+                data = [{k: v for k, v in item.items()} for item in data]
+            else:
+                data = [{k.lower(): v for k, v in item.items()} for item in data]
         else:
             logger.error('数据结构必须是字典、列表、字典列表或dataframe', {
                 'data': self._shorten_for_log(data),
@@ -782,8 +788,11 @@ class MySQLUploader:
         # 统一处理原始数据中列名的特殊字符
         data = self.normalize_column_names(data)
 
-        # 将set_typ的键转为小写
-        set_typ = {k.lower(): v for k, v in set_typ.items()}
+        # set_typ的键处理
+        if self.case_sensitive:
+            set_typ = {k: v for k, v in set_typ.items()}
+        else:
+            set_typ = {k.lower(): v for k, v in set_typ.items()}
 
         # 获取数据中实际存在的列名
         data_columns = set()
@@ -803,7 +812,6 @@ class MySQLUploader:
                     filtered_set_typ[col] = inferred_type
                     logger.debug(f"自动推断列 `{col}` 的数据类型为: `{inferred_type}`")
                 else:
-                    # 没有样本值，使用默认类型
                     filtered_set_typ[col] = 'VARCHAR(255)'
                     logger.debug(f"列 `{col}` 使用默认数据类型: VARCHAR(255)")
 
@@ -812,9 +820,8 @@ class MySQLUploader:
             prepared_row = {}
             for col_name in filtered_set_typ:
                 # 跳过id列，不允许外部传入id
-                if col_name.lower() == 'id':
+                if (self.case_sensitive and col_name == 'id') or (not self.case_sensitive and col_name.lower() == 'id'):
                     continue
-
                 if col_name not in row:
                     if not allow_null:
                         error_msg = f"行号:{row_idx} -> 缺失列: `{col_name}`"

{mdbq-3.11.0.dist-info → mdbq-3.11.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: mdbq
-Version: 3.11.0
+Version: 3.11.2
 Home-page: https://pypi.org/project/mdbq
 Author: xigua, 
 Author-email: 2587125111@qq.com

{mdbq-3.11.0.dist-info → mdbq-3.11.2.dist-info}/RECORD

@@ -1,5 +1,5 @@
 mdbq/__init__.py,sha256=Il5Q9ATdX8yXqVxtP_nYqUhExzxPC_qk_WXQ_4h0exg,16
-mdbq/__version__.py,sha256=vrerkwEDL5E5nSSdgLRAwkxPSJb14-hLfjbjj6J7G3I,18
+mdbq/__version__.py,sha256=wv5KMeim2R9kZhUwwfGA21oZwJF5NDKfYM8gzWNjR-I,18
 mdbq/aggregation/__init__.py,sha256=EeDqX2Aml6SPx8363J-v1lz0EcZtgwIBYyCJV6CcEDU,40
 mdbq/aggregation/query_data.py,sha256=fdotW8qdAyDB13p7r3p6AGBkavcHnf6hIvSMtcS7vqE,179875
 mdbq/config/__init__.py,sha256=jso1oHcy6cJEfa7udS_9uO5X6kZLoPBF8l3wCYmr5dM,18
@@ -11,7 +11,7 @@ mdbq/mysql/__init__.py,sha256=A_DPJyAoEvTSFojiI2e94zP0FKtCkkwKP1kYUCSyQzo,11
 mdbq/mysql/deduplicator.py,sha256=ibmxpzenhPgT_ei61TjQB2ZxYs9ztkG_ygbLSa8RIlM,32990
 mdbq/mysql/mysql.py,sha256=Lfy9PsEdgmdRtcG_UUgegH3bFTJPhByTWkcAYl8G6m0,56788
 mdbq/mysql/s_query.py,sha256=dlnrVJ3-Vp1Suv9CNbPxyYSRqRJUHjOpF39tb2F-wBc,10190
-mdbq/mysql/uploader.py,sha256=6b1NXGtQnhpSWMXnw0ai07ejS1GzMUZWzcjG8G68pbY,66451
+mdbq/mysql/uploader.py,sha256=Mufu39jNm0Y6LGUOwO-HZxYCE34nn8aVwp2MJPqopMc,66824
 mdbq/other/__init__.py,sha256=jso1oHcy6cJEfa7udS_9uO5X6kZLoPBF8l3wCYmr5dM,18
 mdbq/other/download_sku_picture.py,sha256=YU8DxKMXbdeE1OOKEA848WVp62jYHw5O4tXTjUdq9H0,44832
 mdbq/other/otk.py,sha256=iclBIFbQbhlqzUbcMMoePXBpcP1eZ06ZtjnhcA_EbmE,7241
@@ -24,7 +24,7 @@ mdbq/redis/__init__.py,sha256=YtgBlVSMDphtpwYX248wGge1x-Ex_mMufz4-8W0XRmA,12
 mdbq/redis/getredis.py,sha256=YHgCKO8mEsslwet33K5tGss-nrDDwPnOSlhA9iBu0jY,24078
 mdbq/spider/__init__.py,sha256=RBMFXGy_jd1HXZhngB2T2XTvJqki8P_Fr-pBcwijnew,18
 mdbq/spider/aikucun.py,sha256=YyPWa_nOH1zs8wgTDcgzn5w8szGKWPyWzmWMVIPkFnU,21638
-mdbq-3.11.0.dist-info/METADATA,sha256=go0OKEPPSfRYS3OQJ0A2bJP1FPNCbtAtp-LHZlrh9NM,364
-mdbq-3.11.0.dist-info/WHEEL,sha256=jB7zZ3N9hIM9adW7qlTAyycLYW9npaWKLRzaoVcLKcM,91
-mdbq-3.11.0.dist-info/top_level.txt,sha256=2FQ-uLnCSB-OwFiWntzmwosW3X2Xqsg0ewh1axsaylA,5
-mdbq-3.11.0.dist-info/RECORD,,
+mdbq-3.11.2.dist-info/METADATA,sha256=nxrvJWSRWH09rrPuxsS6RVGTOm7W0tFw3dYXaDPDCd8,364
+mdbq-3.11.2.dist-info/WHEEL,sha256=jB7zZ3N9hIM9adW7qlTAyycLYW9npaWKLRzaoVcLKcM,91
+mdbq-3.11.2.dist-info/top_level.txt,sha256=2FQ-uLnCSB-OwFiWntzmwosW3X2Xqsg0ewh1axsaylA,5
+mdbq-3.11.2.dist-info/RECORD,,