mdbq 4.0.54__tar.gz → 4.0.56__tar.gz

{mdbq-4.0.54 → mdbq-4.0.56}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: mdbq
-Version: 4.0.54
+Version: 4.0.56
 Home-page: https://pypi.org/project/mdbq
 Author: xigua, 
 Author-email: 2587125111@qq.com

mdbq-4.0.56/mdbq/__version__.py

@@ -0,0 +1 @@
+VERSION = '4.0.56'

{mdbq-4.0.54 → mdbq-4.0.56}/mdbq/mysql/s_query.py

@@ -695,7 +695,7 @@ class QueryDatas:
 
     def _build_query_sql(self, db_name: str, table_name: str, selected_columns: List[str], 
                         date_column: Optional[str] = None, start_date: Optional[str] = None, 
-                        end_date: Optional[str] = None, limit: Optional[int] = None) -> Tuple[str, List[Any]]:
+                        end_date: Optional[str] = None, limit: Optional[int] = None, order_by: Optional[str] = None) -> Tuple[str, List[Any]]:
         """
         构建SQL查询语句和参数。
         
@@ -707,6 +707,7 @@ class QueryDatas:
             start_date: 开始日期
             end_date: 结束日期
             limit: 限制返回行数，None表示不限制
+            order_by: 排序字段名
             
         Returns:
             SQL语句和参数列表的元组
@@ -748,6 +749,11 @@ class QueryDatas:
             if conditions:
                 base_sql += " WHERE " + " AND ".join(conditions)
             
+        # 默认排序
+        if not order_by:
+            order_by = 'id'
+        base_sql += f" ORDER BY `{order_by}`"
+        
         # 只在显式指定limit时添加限制
         if limit is not None:
             if not isinstance(limit, int) or limit <= 0:
@@ -910,7 +916,7 @@ class QueryDatas:
                     # 构建基础SQL
                     base_sql, params, param_names = self._build_query_sql(
                         db_name, table_name, selected_columns, 
-                        date_column, start_date, end_date, None
+                        date_column, start_date, end_date, None, order_by=None
                     )
 
                     # 如果指定了limit且没有指定page_size，使用简单查询
@@ -945,11 +951,7 @@ class QueryDatas:
                     # 分页查询
                     offset = 0
                     all_results = []
-                    min_size, max_size = 1000, 10000
-                    target_time = 1.0  # 期望每批1秒
-
                     while offset < total_count:
-                        _p_time = time.time()
                         # 添加分页参数
                         page_sql = f"{base_sql} LIMIT %s OFFSET %s"
                         page_params = list(params) + [page_size, offset]
@@ -959,45 +961,26 @@ class QueryDatas:
                         if not page_results:
                             break
 
-                        if return_format == 'list_dict':
-                            all_results.extend(page_results)
-                        else:
-                            if len(all_results) == 0:
-                                all_results = pd.DataFrame(page_results)
-                            else:
-                                all_results = pd.concat([all_results, pd.DataFrame(page_results)], ignore_index=True)
-
-                        duration = time.time() - _p_time
-                        page_size = self._adjust_page_size(duration, page_size, min_size, max_size, target_time)
+                        all_results.extend(page_results)
                         offset += len(page_results)
-                        logger.debug('分页查询进度', {
-                            '库': db_name,
-                            '表': table_name,
-                            # '当前偏移量': offset,
-                            '总记录数': total_count,
-                            '已获取记录数': len(all_results) if return_format == 'list_dict' else len(all_results.index),
-                            '本批耗时': f'{duration:.2f}',
-                            '下批page_size': page_size
-                        })
+                        if len(page_results) < page_size:
+                            break  # 最后一页
 
-                    if return_format == 'df' and isinstance(all_results, pd.DataFrame) and not all_results.empty:
-                        all_results = self._convert_decimal_columns(all_results)
-                    logger.info('查询完成', {
+                    logger.info('分页查询完成', {
                         '库': db_name,
                         '表': table_name,
                         '总记录数': total_count,
-                        '已获取记录数': len(all_results) if return_format == 'list_dict' else len(all_results.index),
+                        '已获取记录数': len(all_results),
                         '查询耗时': f'{time.time() - start_time:.2f}s',
-                        '查询参数': {
-                            '开始日期': start_date,
-                            '结束日期': end_date,
-                            '日期字段': date_column,
-                            '限制行数': limit,
-                            '分页大小': page_size,
-                            '返回数据格式': return_format,
-                        }
                     })
-                    return all_results
+
+                    if return_format == 'list_dict':
+                        return all_results
+                    else:
+                        df = pd.DataFrame(all_results)
+                        if not df.empty:
+                            df = self._convert_decimal_columns(df)
+                        return df
 
         except Exception as e:
             logger.error('数据查询失败', {
@@ -1034,4 +1017,4 @@ def main():
 
 if __name__ == '__main__':
     main()
-    pass
+    pass

{mdbq-4.0.54 → mdbq-4.0.56}/mdbq.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: mdbq
-Version: 4.0.54
+Version: 4.0.56
 Home-page: https://pypi.org/project/mdbq
 Author: xigua, 
 Author-email: 2587125111@qq.com

{mdbq-4.0.54 → mdbq-4.0.56}/mdbq.egg-info/SOURCES.txt

@@ -6,9 +6,6 @@ mdbq.egg-info/PKG-INFO
 mdbq.egg-info/SOURCES.txt
 mdbq.egg-info/dependency_links.txt
 mdbq.egg-info/top_level.txt
-mdbq/aggregation/__init__.py
-mdbq/aggregation/query_data.py
-mdbq/aggregation/set_typ_dict.py
 mdbq/log/__init__.py
 mdbq/log/mylogger.py
 mdbq/myconf/__init__.py

mdbq-4.0.54/mdbq/__version__.py

@@ -1 +0,0 @@
-VERSION = '4.0.54'

mdbq-4.0.54/mdbq/aggregation/__init__.py

@@ -1,4 +0,0 @@
-
-
-
-# 数据清洗, 数据聚合, 入库