# 读取 Doc目录 数据库-2015-2024-v2.xlsx 文件内容
# pip install openpyxl

import openpyxl

from Config.Config import EXCEL_PATH
from Util.AreaUtil import query_area_info

file_name = EXCEL_PATH

# 初始化统计变量
success_count = 0
error_count = 0
error_details = []

# 读取Excel文件并获取所有sheet名称
try:
    # 加载工作簿
    workbook = openpyxl.load_workbook(file_name, read_only=True)
    sheet_names = workbook.sheetnames

    if sheet_names:
        first_sheet = workbook[sheet_names[0]]
        # 读取所有行数据
        rows = list(first_sheet.iter_rows(values_only=True))
        total_count = len(rows[2:])  # 排除表头的总数据行数

        # 跳过前两行表头，从第三行开始处理数据
        for row_num, row in enumerate(rows[2:], start=3):
            # 假设行政区划名称在第一列（索引0）
            if row and row[0]:
                area_name = row[0]
                result = query_area_info(area_name)

                if result:
                    success_count += 1
                    print(f"✅ 行 {row_num}: {area_name} -> 全称: {result['full_name']}, 行政区划码: {result['area_code']}")
                else:
                    error_count += 1
                    error_details.append(f"行 {row_num}: '{area_name}'")
                    print(f"❌ 行 {row_num}: 未找到 '{area_name}' 的相关信息")

        # 输出汇总结果
        print("\n==================== 匹配结果汇总 ====================")
        print(f"📊 总记录数: {total_count}, 成功匹配: {success_count}, 匹配失败: {error_count}")
        print(f"📈 匹配成功率: {success_count/total_count*100:.2f}%\n")

        if error_details:
            print("❌ 匹配失败详情:")
            for detail in error_details:
                print(f"  - {detail}")
        else:
            print("✅ 所有记录均成功匹配!")

    workbook.close()

except FileNotFoundError:
    print(f"🔴 错误：找不到文件 '{file_name}'")
except Exception as e:
    print(f"🔴 读取Excel时发生错误：{str(e)}")