AcidMap/scripts/import_cross_section.py

"""
Cross_section数据导入脚本
@description: 从Excel文件读取河流断面数据并导入到cross_section表
"""

import os
import sys
import pandas as pd
import logging
from datetime import datetime
from sqlalchemy.orm import sessionmaker

# 添加项目根目录到Python路径
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))

from app.database import engine, SessionLocal
from app.models.cross_section import CrossSection  # 需创建对应的ORM模型

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


class CrossSectionDataImporter:
    """
    河流断面数据导入器

    @description: 从Excel文件读取河流断面数据并导入到数据库
    """

    def __init__(self, excel_path, sheet_name='Cross_section'):
        """
        初始化导入器

        @param {str} excel_path - Excel文件路径
        @param {str} sheet_name - Sheet名称，默认为'Cross_section'
        """
        self.excel_path = excel_path
        self.sheet_name = sheet_name

        # 定义必需字段列表（根据数据库设计文档，除ID外）
        self.required_columns = ['River', 'Position', 'County', 'Lon', 'Lan', 'Cd']

    def read_excel_data(self):
        """
        读取Excel文件数据

        @returns: DataFrame 读取的数据
        """
        try:
            logger.info(f"开始读取Excel文件: {self.excel_path}")
            logger.info(f"Sheet名称: {self.sheet_name}")

            # 检查文件是否存在
            if not os.path.exists(self.excel_path):
                raise FileNotFoundError(f"Excel文件不存在: {self.excel_path}")

            # 读取Excel文件
            df = pd.read_excel(self.excel_path, sheet_name=self.sheet_name)

            logger.info(f"成功读取数据，共 {len(df)} 行")
            logger.info(f"数据列: {list(df.columns)}")

            # 显示前几行数据供确认
            logger.info("前5行数据预览:")
            logger.info(df.head().to_string())

            return df

        except Exception as e:
            logger.error(f"读取Excel文件失败: {str(e)}")
            raise

    def validate_data(self, df):
        """
        验证数据格式和完整性

        @param {DataFrame} df - 要验证的数据
        @returns: DataFrame 验证后的数据
        """
        try:
            logger.info("开始验证数据...")

            # 检查必需的列是否存在
            missing_columns = [col for col in self.required_columns if col not in df.columns]

            if missing_columns:
                raise ValueError(f"缺少必需的列: {missing_columns}")

            # 将列名转换为小写（带下划线）以匹配数据库字段
            df.columns = [col.lower() for col in df.columns]
            required_columns_lower = [col.lower() for col in self.required_columns]

            # 检查数据类型
            logger.info("检查数据类型...")

            # 转换数值类型
            numeric_columns = ['lon', 'lan', 'cd']
            for col in numeric_columns:
                if col in df.columns:
                    # 对于数值列，转换为浮点数
                    df[col] = pd.to_numeric(df[col], errors='coerce')

            # 处理空值 - 所有字段必须非空
            original_count = len(df)
            df = df.dropna(subset=required_columns_lower)
            new_count = len(df)
            if new_count < original_count:
                logger.warning(f"删除空值行 {original_count - new_count} 行")

            # 验证经纬度范围
            longitude_errors = df[(df['lon'] < -180) | (df['lon'] > 180)]
            latitude_errors = df[(df['lan'] < -90) | (df['lan'] > 90)]

            if not longitude_errors.empty or not latitude_errors.empty:
                logger.warning("发现经纬度无效值，将删除这些行")
                # 保留有效经纬度行
                valid_mask = (df['lon'].between(-180, 180)) & (df['lan'].between(-90, 90))
                invalid_df = df[~valid_mask]
                df = df[valid_mask]

                logger.warning(f"删除无效经纬度数据 {len(invalid_df)} 行")
                if not invalid_df.empty:
                    logger.warning("部分无效行示例:")
                    logger.warning(invalid_df[['lon', 'lan', 'position']].head().to_string())

            logger.info(f"数据验证完成，有效数据 {len(df)} 行")

            return df

        except Exception as e:
            logger.error(f"数据验证失败: {str(e)}")
            raise

    def import_data(self, df):
        """
        将数据导入到数据库

        @param {DataFrame} df - 要导入的数据
        """
        try:
            logger.info("开始导入数据到数据库...")

            # 创建数据库会话
            db = SessionLocal()

            try:
                # 检查是否有重复数据
                existing_count = db.query(CrossSection).count()
                logger.info(f"数据库中现有数据: {existing_count} 条")

                # 批量创建对象
                batch_size = 1000
                total_rows = len(df)
                imported_count = 0

                for i in range(0, total_rows, batch_size):
                    batch_df = df.iloc[i:i + batch_size]
                    batch_objects = []

                    for _, row in batch_df.iterrows():
                        try:
                            # 创建CrossSectionData对象
                            cross_section = CrossSection(
                                river_name=str(row['river']),
                                position=str(row['position']),
                                county=str(row['county']),
                                longitude=float(row['lon']),
                                latitude=float(row['lan']),
                                cd_concentration=float(row['cd'])
                            )
                            batch_objects.append(cross_section)

                        except Exception as e:
                            logger.warning(f"跳过行 {i + _}: {str(e)}")
                            continue

                    if batch_objects:
                        # 批量插入
                        db.add_all(batch_objects)
                        db.commit()
                        imported_count += len(batch_objects)
                        logger.info(f"已导入 {imported_count}/{total_rows} 条数据")

                logger.info(f"数据导入完成! 成功导入 {imported_count} 条数据")

                # 验证导入结果
                final_count = db.query(CrossSection).count()
                logger.info(f"导入后数据库总数据: {final_count} 条")

            except Exception as e:
                db.rollback()
                logger.error(f"数据导入失败，已回滚: {str(e)}")
                raise
            finally:
                db.close()

        except Exception as e:
            logger.error(f"数据导入过程失败: {str(e)}")
            raise

    def run_import(self):
        """
        执行完整的导入流程
        """
        try:
            logger.info("=" * 60)
            logger.info("开始河流断面数据导入流程")
            logger.info("=" * 60)

            # 1. 读取Excel数据
            df = self.read_excel_data()

            # 2. 验证数据
            df = self.validate_data(df)

            # 3. 导入数据
            self.import_data(df)

            logger.info("=" * 60)
            logger.info("河流断面数据导入流程完成!")
            logger.info = "=" * 60

        except Exception as e:
            logger.error(f"导入流程失败: {str(e)}")
            raise


def main():
    """
    主函数
    """
    # Excel文件路径
    excel_path = r"D:\destkop\数据库对应数据.xlsx"
    sheet_name = "Cross_section"

    try:
        # 创建导入器并执行导入
        importer = CrossSectionDataImporter(excel_path, sheet_name)
        importer.run_import()

    except Exception as e:
        logger.error(f"程序执行失败: {str(e)}")
        sys.exit(1)


if __name__ == "__main__":
    main()