YunNanProject/Tools/T1_RenKou.py

import openpyxl
import os
from typing import List, Dict, Any

from Config.Config import EXCEL_PATH
from Util.DataUtil import (
    init_directories, process_value, print_conversion_stats,
    convert_area_name, save_to_json, load_workbook_sheet
)

# ======================= 配置常量 =======================
DATA_DIR = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'Data')
JSON_PATH = os.path.join(DATA_DIR, 'RenKou.json')
SHEET_NAME = '人口'                  # 工作表名称
REGION_NAME_COLUMN = 'A'            # 区域名称所在列
START_ROW = 3                       # 数据起始行
YEAR_RANGE = range(2015, 2025)      # 年份范围

# 数据列配置 (指标: (起始列, 结束列))
DATA_COLUMNS = {
    'total_population': ('B', 'K'),      # 年末总人口
    'urban_population': ('L', 'U'),      # 城镇人口
    'rural_population': ('V', 'AE'),     # 乡村人口
    'urbanization_rate': ('AF', 'AO'),   # 城镇化率
    'birth_population': ('AP', 'AY')     # 出生人口
}

# ======================= 核心逻辑 =======================
def extract_area_data(sheet: openpyxl.worksheet.worksheet.Worksheet) -> List[Dict[str, Any]]:
    """从工作表提取区域数据"""
    population_data: List[Dict[str, Any]] = []
    conversion_records: List[Dict[str, str]] = []
    name_conversion_errors: List[str] = []
    
    # 计算区域名称列索引
    region_col_idx = openpyxl.utils.column_index_from_string(REGION_NAME_COLUMN) - 1
    
    # 遍历数据行
    for row_num in range(START_ROW, sheet.max_row + 1):
        row = sheet[row_num]
        
        # 获取区域名称并转换
        raw_name = row[region_col_idx].value
        area_name, area_code, conv_records, errors = convert_area_name(raw_name, row_num)
        conversion_records.extend(conv_records)
        name_conversion_errors.extend(errors)
        
        if not area_name:
            continue
        
        # 构建区域数据
        area_data = {
            'area_name': area_name,
            'area_code': area_code,
            'raw_name': str(raw_name).strip() if raw_name else '未知地区'
        }
        
        # 提取各指标年度数据
        for metric, (start_col, end_col) in DATA_COLUMNS.items():
            start_idx = openpyxl.utils.column_index_from_string(start_col) - 1
            end_idx = openpyxl.utils.column_index_from_string(end_col) - 1
            year_data = {}
            
            for col_idx, year in zip(range(start_idx, end_idx + 1), YEAR_RANGE):
                cell_value = row[col_idx].value
                year_data[str(year)] = process_value(cell_value)
            
            area_data[metric] = year_data
        
        population_data.append(area_data)
    
    # 输出转换统计
    print_conversion_stats(conversion_records, name_conversion_errors)
    return population_data

# ======================= 主函数 =======================
def main() -> None:
    """人口数据提取主函数"""
    init_directories(DATA_DIR)
    
    # 加载工作表
    sheet = load_workbook_sheet(EXCEL_PATH, SHEET_NAME)
    if not sheet:
        return
    
    # 提取并处理数据
    population_data = extract_area_data(sheet)
    
    # 保存结果
    save_to_json(population_data, JSON_PATH)

if __name__ == '__main__':
    main()