sqlServerConnector 0.1.3__tar.gz → 0.1.5__tar.gz

{sqlserverconnector-0.1.3 → sqlserverconnector-0.1.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sqlServerConnector
-Version: 0.1.3
+Version: 0.1.5
 Summary: A custom SQL Server Connector for ETL processes with Pandas
 Author-email: Nguyen Minh Son <nguyen.minhson1511@gmail.com>
 Project-URL: Homepage, https://github.com/johnnyb1509/sqlServerConnector

{sqlserverconnector-0.1.3 → sqlserverconnector-0.1.5}/pyproject.toml

@@ -6,7 +6,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "sqlServerConnector"
-version = "0.1.3"
+version = "0.1.5"
 description = "A custom SQL Server Connector for ETL processes with Pandas"
 readme = "README.md"
 requires-python = ">=3.8"

{sqlserverconnector-0.1.3 → sqlserverconnector-0.1.5}/src/connector.py

@@ -67,38 +67,34 @@ class SQLServerConnector:
     # CORE ETL METHODS
     # ========================================================
 
-    def upsert_data(self, 
-                    df: pd.DataFrame, 
-                    target_table: str, 
-                    primary_key: str = None, 
-                    match_columns: Optional[List[str]] = None, 
-                    auto_evolve_schema: bool = True,
+    def upsert_data(self, df: pd.DataFrame, target_table: str, primary_key: str = None, 
+                    match_columns: Optional[List[str]] = None, auto_evolve_schema: bool = True,
                     conflict_strategy: str = 'sum'):
-        """
-        Upsert data into SQL Server with generalized conflict handling.
-        Args:
-            conflict_strategy: 'sum' (aggregates numeric rows), 'last' (keeps most recent row).
-        """
         if df.empty: return
 
         join_keys = match_columns if match_columns else ([primary_key] if primary_key else [])
-        if not join_keys:
-            raise ValueError("Upsert requires match_columns or primary_key.")
-
-        # 1. Sanitize Data
+        
+        # 1. Sanitize & lọc lấy các cột cần thiết
+        # Chỉ giữ lại join_keys và các cột có dữ liệu để tránh "phân mảnh" dữ liệu khi gộp
         df_clean = self._sanitize_dataframe(df, exclude_cols=join_keys)
         
-        # 2. Generalization: Handle Duplicates/Conflicts in Source
+        # 2. Xử lý trùng lặp triệt để
         initial_len = len(df_clean)
         if conflict_strategy == 'sum':
-            # Logic: Group by keys and SUM all numeric columns to prevent MERGE errors
+            # Xác định cột số để cộng dồn
             num_cols = df_clean.select_dtypes(include=[np.number]).columns.tolist()
-            agg_map = {col: 'sum' for col in num_cols if col not in join_keys}
-            # For non-numeric columns, just take the last record
-            for col in df_clean.columns:
-                if col not in join_keys and col not in agg_map:
-                    agg_map[col] = 'last'
-            df_clean = df_clean.groupby(join_keys, as_index=False).agg(agg_map)
+            num_cols = [c for c in num_cols if c not in join_keys]
+            
+            # Chỉ gộp trên các cột số, các cột text khác key sẽ bị loại bỏ hoặc lấy dòng đầu
+            # Điều này đảm bảo kết quả trả về CHỈ CÓ 1 DÒNG cho mỗi cặp Key
+            agg_logic = {col: 'sum' for col in num_cols}
+            
+            # Đối với các cột không phải số và không phải key, chúng ta lấy dòng đầu tiên
+            other_cols = [c for c in df_clean.columns if c not in join_keys and c not in num_cols]
+            for c in other_cols:
+                agg_logic[c] = 'first'
+                
+            df_clean = df_clean.groupby(join_keys, as_index=False).agg(agg_logic)
         else:
             df_clean = df_clean.drop_duplicates(subset=join_keys, keep='last')
 
@@ -181,4 +177,46 @@ class SQLServerConnector:
                 for col in new_cols:
                     sql_type = "NVARCHAR(MAX)" if df[col].dtype == 'object' else "FLOAT"
                     conn.execute(text(f"ALTER TABLE [{table_name}] ADD [{col}] {sql_type} NULL"))
-                conn.commit()
+                conn.commit()
+
+    # ========================================================
+    # DATA RETRIEVAL METHODS
+    # ========================================================
+    def get_data(self,  query: str, params: Optional[Dict[str, Any]] = None, chunksize: Optional[int] = None) -> Union[pd.DataFrame, Any]:
+        """
+        Executes a SQL query and returns a Pandas DataFrame.
+        
+        Args:
+            query (str): The SQL query string. Use :param_name for parameters.
+            params (dict, optional): Dictionary of parameters to bind to the query.
+            chunksize (int, optional): If specified, returns an iterator where each chunk is the given size.
+        
+        Returns:
+            pd.DataFrame or Iterator[pd.DataFrame]
+        """
+        try:
+            with self.engine.connect() as conn:
+                # Use text() explicitly for SQLAlchemy 2.0 compatibility
+                sql_query = text(query)
+                
+                # If chunksize is provided, read_sql returns a generator
+                result = pd.read_sql(
+                    sql_query, 
+                    conn, 
+                    params=params, 
+                    chunksize=chunksize
+                )
+                
+                if chunksize is None:
+                    logger.info(f"Successfully retrieved {len(result)} rows.")
+                else:
+                    logger.info(f"Retrieving data in chunks of {chunksize} rows.")
+                    
+                return result
+                
+        except SQLAlchemyError as e:
+            logger.error(f"Failed to retrieve data: {e}")
+            raise
+        except Exception as e:
+            logger.error(f"An unexpected error occurred during get_data: {e}")
+            raise

{sqlserverconnector-0.1.3 → sqlserverconnector-0.1.5}/src/sqlServerConnector.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sqlServerConnector
-Version: 0.1.3
+Version: 0.1.5
 Summary: A custom SQL Server Connector for ETL processes with Pandas
 Author-email: Nguyen Minh Son <nguyen.minhson1511@gmail.com>
 Project-URL: Homepage, https://github.com/johnnyb1509/sqlServerConnector