Bonus-Transfer-Machines/materialSite/clz_slt_agreement_info_update.py

import configparser
import pandas as pd
from sqlalchemy import create_engine, text
from urllib.parse import quote_plus
import logging

# 配置日志
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
logger = logging.getLogger(__name__)

# 读取配置文件
config = configparser.ConfigParser()
config.read('config.ini')

# 获取数据库连接配置
source_config = {
    'host': config.get('source_db', 'host'),
    'user': config.get('source_db', 'user'),
    'password': config.get('source_db', 'password'),
    'database': config.get('source_db', 'database'),
    'port': config.getint('source_db', 'port')
}

target_config = {
    'host': config.get('target_db', 'host'),
    'user': config.get('target_db', 'user'),
    'password': config.get('target_db', 'password'),
    'database': config.get('target_db', 'database'),
    'port': config.getint('target_db', 'port')
}

# 创建数据库引擎
source_engine = create_engine(
    f"mysql+pymysql://{source_config['user']}:{quote_plus(source_config['password'])}@{source_config['host']}:{source_config['port']}/{source_config['database']}"
)
target_engine = create_engine(
    f"mysql+pymysql://{target_config['user']}:{quote_plus(target_config['password'])}@{target_config['host']}:{target_config['port']}/{target_config['database']}"
)


class ClzSltAgreementInfoUpdater:
    """clz_slt_agreement_info表数据对比和更新器"""
    
    def __init__(self):
        self.source_engine = source_engine
        self.target_engine = target_engine
        
    def query_target_data(self):
        """
        从目标数据库查询ma_machine数据
        """
        try:
            sql = """
            SELECT
                mm.type_id,
                mm.ma_code,
                mm.ma_id
            FROM
                ma_machine mm
            """
            
            logger.info("执行目标数据库查询...")
            df = pd.read_sql(sql, self.target_engine)
            logger.info(f"目标数据库查询到 {len(df)} 条记录")
            return df
            
        except Exception as e:
            logger.error(f"查询目标数据库时发生错误: {str(e)}")
            return pd.DataFrame()
    
    def query_source_data(self):
        """
        从源数据库查询clz_slt_agreement_info数据
        """
        try:
            sql = """
            SELECT
                cod.id,
                cod.type_id,
                mm.ma_code,
                mm.ma_id
            FROM
                clz_slt_agreement_info cod
            LEFT JOIN ma_machine mm on cod.ma_id = mm.ma_id
            WHERE cod.type_id > 6000 and cod.ma_id is not null AND mm.ma_code is not null
            """
            
            logger.info("执行源数据库查询...")
            df = pd.read_sql(sql, self.source_engine)
            logger.info(f"源数据库查询到 {len(df)} 条记录")
            return df
            
        except Exception as e:
            logger.error(f"查询源数据库时发生错误: {str(e)}")
            return pd.DataFrame()
    
    def compare_and_update_data(self, target_df, source_df):
        """
        对比数据并执行更新
        
        Args:
            target_df: 目标数据库数据
            source_df: 源数据库数据
            
        Returns:
            int: 更新的记录数
        """
        try:
            update_count = 0
            
            # 创建对比条件：type_id和ma_code都相同
            logger.info("开始数据对比...")
            
            # 使用pandas merge进行数据对比
            merged_df = pd.merge(
                target_df, 
                source_df, 
                on=['type_id', 'ma_code'], 
                how='inner',
                suffixes=('_target', '_source')
            )
            
            logger.info(f"找到 {len(merged_df)} 条匹配记录")
            
            if merged_df.empty:
                logger.warning("没有找到匹配的数据")
                return 0
            
            # 执行更新操作
            with self.source_engine.connect() as conn:
                for _, row in merged_df.iterrows():
                    # 检查目标表的ma_id字段是否有值
                    target_ma_id = row.get('ma_id_target')
                    source_id = row.get('id')
                    
                    if pd.notna(target_ma_id) and pd.notna(source_id):
                        # 构建UPDATE语句 - 更新cod.ma_id字段
                        sql = f"""
                        UPDATE clz_slt_agreement_info 
                        SET ma_id = {target_ma_id} 
                        WHERE id = {source_id}
                        """
                        
                        logger.debug(f"执行更新SQL: {sql}")
                        result = conn.execute(text(sql))
                        update_count += result.rowcount
                
                conn.commit()
            
            logger.info(f"成功更新 {update_count} 条记录")
            return update_count
            
        except Exception as e:
            logger.error(f"数据对比和更新时发生错误: {str(e)}")
            return 0
    
    def execute_update(self):
        """
        执行完整的数据对比和更新流程
        """
        try:
            logger.info("=== 开始clz_slt_agreement_info表数据对比和更新 ===")
            
            # 1. 查询目标数据库数据
            target_df = self.query_target_data()
            if target_df.empty:
                logger.error("目标数据库查询结果为空")
                return False
            
            # 2. 查询源数据库数据
            source_df = self.query_source_data()
            if source_df.empty:
                logger.error("源数据库查询结果为空")
                return False
            
            # 3. 对比数据并执行更新
            update_count = self.compare_and_update_data(target_df, source_df)
            
            if update_count > 0:
                logger.info(f"✅ 数据对比和更新完成，共更新 {update_count} 条记录")
                return True
            else:
                logger.warning("⚠️ 没有找到需要更新的数据")
                return True
                
        except Exception as e:
            logger.error(f"执行更新流程时发生错误: {str(e)}")
            return False
    
    def preview_changes(self):
        """
        预览将要进行的更改（不实际执行更新）
        """
        try:
            logger.info("=== 预览数据对比结果 ===")
            
            # 查询数据
            target_df = self.query_target_data()
            source_df = self.query_source_data()
            
            if target_df.empty or source_df.empty:
                logger.warning("查询结果为空，无法预览")
                return
            
            # 对比数据
            merged_df = pd.merge(
                target_df, 
                source_df, 
                on=['type_id', 'ma_code'], 
                how='inner',
                suffixes=('_target', '_source')
            )
            
            logger.info(f"找到 {len(merged_df)} 条匹配记录")
            
            if not merged_df.empty:
                logger.info("预览将要更新的记录:")
                for idx, row in merged_df.head(10).iterrows():  # 只显示前10条
                    logger.info(f"ID: {row['id']}, "
                              f"type_id: {row['type_id']}, "
                              f"ma_code: {row['ma_code']}, "
                              f"原cod.ma_id: {row.get('ma_id_source', 'NULL')}, "
                              f"新cod.ma_id: {row.get('ma_id_target', 'NULL')}")
                
                if len(merged_df) > 10:
                    logger.info(f"... 还有 {len(merged_df) - 10} 条记录")
            
        except Exception as e:
            logger.error(f"预览时发生错误: {str(e)}")


def main():
    """主函数"""
    updater = ClzSltAgreementInfoUpdater()
    
    # 询问用户是否要预览更改
    preview = input("是否要预览将要进行的更改？(y/N): ")
    if preview.lower() == 'y':
        updater.preview_changes()
    
    # 询问用户是否要执行更新
    confirm = input("是否要执行数据更新？(y/N): ")
    if confirm.lower() == 'y':
        success = updater.execute_update()
        if success:
            print("✅ 更新操作完成")
        else:
            print("❌ 更新操作失败")
    else:
        print("操作已取消")


if __name__ == "__main__":
    main()