cppackage 0.2.9__tar.gz → 0.3.0__tar.gz

{cppackage-0.2.9 → cppackage-0.3.0}/CPpackage/db/sql_model.py

@@ -1,8 +1,6 @@
 import pymysql
 import time
 from pymysql import Error
-import pandas as pd
-# 条件导入：支持直接运行和包模式
 try:
     from .config import get_db_config
 except (ImportError, ValueError):
@@ -161,6 +159,13 @@ def find_duplicate_records(table_name, database, unique_index_fields, port=None)
     """
     
     try:
+        # Lazy import pandas here to avoid heavy imports during module import
+        try:
+            import pandas as pd
+        except Exception as e:
+            print("无法导入 pandas:", e)
+            return None
+
         with _get_connection(database, port) as conn:
             df_duplicates = pd.read_sql(sql, conn)
             if df_duplicates.empty:
@@ -168,8 +173,8 @@ def find_duplicate_records(table_name, database, unique_index_fields, port=None)
             else:
                 print(f"发现 {len(df_duplicates)} 条重复记录（{len(df_duplicates.drop_duplicates(subset=unique_index_fields))} 组重复组合）")
                 # 可选：保存重复记录到CSV
-                df_duplicates.to_csv(f"duplicate_records_{table_name}.csv", index=False, encoding="utf-8-sig")
-                print("重复记录已保存到 duplicate_records_{table_name}.csv")
+                # df_duplicates.to_csv(f"duplicate_records_{table_name}.csv", index=False, encoding="utf-8-sig")
+                # print("重复记录已保存到 duplicate_records_{table_name}.csv")
             return df_duplicates
     except pymysql.MySQLError as e:
         print("数据库查询失败:", e)
@@ -178,7 +183,7 @@ def find_duplicate_records(table_name, database, unique_index_fields, port=None)
         print("未知错误:", e)
         return None
 # ===================== 删除重复记录函数（修复参数+调用逻辑） =====================
-def delete_duplicate_records(table_name, database, unique_index_fields, port=None, keep_strategy="min_id"):
+def delete_duplicate_records(table_name, database, unique_index_fields, port=None, keep_strategy="max_id"):
     """
     删除重复记录，仅保留每组唯一值的一条记录
     参数:
@@ -190,10 +195,6 @@ def delete_duplicate_records(table_name, database, unique_index_fields, port=Non
     返回:
         int: 删除的记录数；None: 出错；0: 无重复
     """
-    # 1. 先调用修复后的find_duplicate_records查询重复数据
-    duplicate_df = find_duplicate_records(table_name, database, unique_index_fields, port)
-    if duplicate_df is None or duplicate_df.empty:
-        return 0
     
     # 2. 构建删除SQL（核心逻辑）
     group_by_str = ",".join([f"`{field}`" for field in unique_index_fields])
@@ -248,6 +249,9 @@ def update_datas(df, table_name, database):
     conn = None
     for i in range(2):
         try:
+            if df.empty:
+                print("数据为空，无需入库")
+                return
             conn = _get_connection(database)
             cursor = conn.cursor()
             cols = list(df.columns)
@@ -262,7 +266,6 @@ def update_datas(df, table_name, database):
             VALUES {values_str}
             ON DUPLICATE KEY UPDATE {update_clause}
             """
-            print(sql)
             data = [tuple(row) for row in df.values]
             flat_data = [v for row in data for v in row]
             cursor.execute(sql, flat_data)
@@ -281,5 +284,3 @@ def update_datas(df, table_name, database):
         finally:
             if conn:
                 conn.close()
-
-

cppackage-0.3.0/CPpackage/db/test.py

@@ -0,0 +1,25 @@
+from CPpackage.db.sql_model import find_duplicate_records,delete_duplicate_records
+import os
+
+           
+if __name__ == "__main__":
+    # 配置你的参数
+    TABLE_NAME = "liuliang_plly"  
+    DATABASE_NAME = "shengyicanmou"  
+    # 你的唯一索引字段列表（必须是列表类型！）
+    UNIQUE_FIELDS = ['begindate', 'value_l', 'pageName', 'itemId', 'name_l1', 'name_l2', 'date_effect', 'store_id']
+    PORT = 3306  # 可选，默认从配置获取
+    
+    # 第一步：查询重复记录
+    # dup_df = find_duplicate_records(TABLE_NAME, DATABASE_NAME, UNIQUE_FIELDS, PORT)
+    
+    # # 第二步：确认有重复后删除
+    # if dup_df is not None and not dup_df.empty:
+
+    delete_count = delete_duplicate_records(
+        table_name=TABLE_NAME,
+        database=DATABASE_NAME,
+        unique_index_fields=UNIQUE_FIELDS,  # 必须传列表！
+        port=PORT,
+        keep_strategy="max_id"
+    )

{cppackage-0.2.9 → cppackage-0.3.0}/CPpackage.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.1
 Name: cppackage
-Version: 0.2.9
+Version: 0.3.0
 Summary: 超品集团自用的Python包
 Home-page: https://github.com/example/CPpackage
 Author: team-数智组
@@ -17,19 +17,6 @@ Classifier: Programming Language :: Python :: 3.12
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: pymysql
-Requires-Dist: pandas
-Requires-Dist: numpy
-Dynamic: author
-Dynamic: author-email
-Dynamic: classifier
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: home-page
-Dynamic: license-file
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary
 
 # CPpackage
 

{cppackage-0.2.9 → cppackage-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.1
 Name: cppackage
-Version: 0.2.9
+Version: 0.3.0
 Summary: 超品集团自用的Python包
 Home-page: https://github.com/example/CPpackage
 Author: team-数智组
@@ -17,19 +17,6 @@ Classifier: Programming Language :: Python :: 3.12
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: pymysql
-Requires-Dist: pandas
-Requires-Dist: numpy
-Dynamic: author
-Dynamic: author-email
-Dynamic: classifier
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: home-page
-Dynamic: license-file
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary
 
 # CPpackage
 

{cppackage-0.2.9 → cppackage-0.3.0}/setup.py

@@ -10,7 +10,7 @@ with open('readme.md', 'r', encoding='utf-8') as f:
 # 包的基本信息
 setup(
     name='cppackage',
-    version='0.2.9',
+    version='0.3.0',
     description='超品集团自用的Python包',
     long_description=long_description,
     long_description_content_type='text/markdown',

cppackage-0.2.9/CPpackage/db/test.py

@@ -1,24 +0,0 @@
-from CPpackage.db.sql_model import find_duplicate_records,delete_duplicate_records
-import os
-
-           
-if __name__ == "__main__":
-    # 配置你的参数
-    TABLE_NAME = "pinlei_hgjk"  # 替换为实际表名
-    DATABASE_NAME = "shengyicanmou_copy"  # 替换为实际数据库名
-    # 你的唯一索引字段列表（必须是列表类型！）
-    UNIQUE_FIELDS = ['begindate', 'enddate', 'value_l', 'sellerId', 'statDate', 'date_effect', 'store_id']
-    PORT = 3306  # 可选，默认从配置获取
-    
-    # 第一步：查询重复记录
-    dup_df = find_duplicate_records(TABLE_NAME, DATABASE_NAME, UNIQUE_FIELDS, PORT)
-    
-    # 第二步：确认有重复后删除
-    if dup_df is not None and not dup_df.empty:
-        delete_count = delete_duplicate_records(
-            table_name=TABLE_NAME,
-            database=DATABASE_NAME,
-            unique_index_fields=UNIQUE_FIELDS,  # 必须传列表！
-            port=PORT,
-            keep_strategy="min_id"
-        )