YunNanProject/Tools/T7_TeacherCount.py

import os
import traceback
from typing import List, Dict, Any, Tuple
import openpyxl
from openpyxl.utils import column_index_from_string
from openpyxl.worksheet.worksheet import Worksheet

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 ======================== #
# 数据目录与输出路径
DATA_DIR = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'Data')
JSON_PATH = os.path.join(DATA_DIR, 'TeacherCount.json')

# Excel配置
SHEET_NAME = '教职工数、专任教师数'
REGION_NAME_COLUMN = 'B'  # 区域名称所在列
START_ROW = 5  # 数据起始行（从第5行开始）

# 教育阶段数据列配置
EDUCATION_STAGES = {
    'preschool_teachers': {
        'years': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024],
        'columns': [
            {'year': 2015, 'total_staff': 'D', 'urban_staff': 'E', 'town_staff': 'F', 'rural_staff': 'G', 'total_teacher': 'H', 'urban_teacher': 'I', 'town_teacher': 'J', 'rural_teacher': 'K'},
            {'year': 2016, 'total_staff': 'L', 'urban_staff': 'M', 'town_staff': 'N', 'rural_staff': 'O', 'total_teacher': 'P', 'urban_teacher': 'Q', 'town_teacher': 'R', 'rural_teacher': 'S'},
            {'year': 2017, 'total_staff': 'T', 'urban_staff': 'U', 'town_staff': 'V', 'rural_staff': 'W', 'total_teacher': 'X', 'urban_teacher': 'Y', 'town_teacher': 'Z', 'rural_teacher': 'AA'},
            {'year': 2018, 'total_staff': 'AB', 'urban_staff': 'AC', 'town_staff': 'AD', 'rural_staff': 'AE', 'total_teacher': 'AF', 'urban_teacher': 'AG', 'town_teacher': 'AH', 'rural_teacher': 'AI'},
            {'year': 2019, 'total_staff': 'AJ', 'urban_staff': 'AK', 'town_staff': 'AL', 'rural_staff': 'AM', 'total_teacher': 'AN', 'urban_teacher': 'AO', 'town_teacher': 'AP', 'rural_teacher': 'AQ'},
            {'year': 2020, 'total_staff': 'AR', 'urban_staff': 'AS', 'town_staff': 'AT', 'rural_staff': 'AU', 'total_teacher': 'AV', 'urban_teacher': 'AW', 'town_teacher': 'AX', 'rural_teacher': 'AY'},
            {'year': 2021, 'total_staff': 'AZ', 'urban_staff': 'BA', 'town_staff': 'BB', 'rural_staff': 'BC', 'total_teacher': 'BD', 'urban_teacher': 'BE', 'town_teacher': 'BF', 'rural_teacher': 'BG'},
            {'year': 2022, 'total_staff': 'BH', 'urban_staff': 'BI', 'town_staff': 'BJ', 'rural_staff': 'BK', 'total_teacher': 'BL', 'urban_teacher': 'BM', 'town_teacher': 'BN', 'rural_teacher': 'BO'},
            {'year': 2023, 'total_staff': 'BP', 'urban_staff': 'BQ', 'town_staff': 'BR', 'rural_staff': 'BS', 'total_teacher': 'BT', 'urban_teacher': 'BU', 'town_teacher': 'BV', 'rural_teacher': 'BW'},
            {'year': 2024, 'total_staff': 'BX', 'urban_staff': 'BY', 'town_staff': 'BZ', 'rural_staff': 'CA', 'total_teacher': 'CB', 'urban_teacher': 'CC', 'town_teacher': 'CD', 'rural_teacher': 'CE'}
        ]
    },
    'primary_teachers': {
        'years': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024],
        'columns': [
            {'year': 2015, 'total_staff': 'CF', 'urban_staff': 'CG', 'town_staff': 'CH', 'rural_staff': 'CI', 'total_teacher': 'CJ', 'urban_teacher': 'CK', 'town_teacher': 'CL', 'rural_teacher': 'CM'},
            {'year': 2016, 'total_staff': 'CN', 'urban_staff': 'CO', 'town_staff': 'CP', 'rural_staff': 'CQ', 'total_teacher': 'CR', 'urban_teacher': 'CS', 'town_teacher': 'CT', 'rural_teacher': 'CU'},
            {'year': 2017, 'total_staff': 'CV', 'urban_staff': 'CW', 'town_staff': 'CX', 'rural_staff': 'CY', 'total_teacher': 'CZ', 'urban_teacher': 'DA', 'town_teacher': 'DB', 'rural_teacher': 'DC'},
            {'year': 2018, 'total_staff': 'DD', 'urban_staff': 'DE', 'town_staff': 'DF', 'rural_staff': 'DG', 'total_teacher': 'DH', 'urban_teacher': 'DI', 'town_teacher': 'DJ', 'rural_teacher': 'DK'},
            {'year': 2019, 'total_staff': 'DL', 'urban_staff': 'DM', 'town_staff': 'DN', 'rural_staff': 'DO', 'total_teacher': 'DP', 'urban_teacher': 'DQ', 'town_teacher': 'DR', 'rural_teacher': 'DS'},
            {'year': 2020, 'total_staff': 'DT', 'urban_staff': 'DU', 'town_staff': 'DV', 'rural_staff': 'DW', 'total_teacher': 'DX', 'urban_teacher': 'DY', 'town_teacher': 'DZ', 'rural_teacher': 'EA'},
            {'year': 2021, 'total_staff': 'EB', 'urban_staff': 'EC', 'town_staff': 'ED', 'rural_staff': 'EE', 'total_teacher': 'EF', 'urban_teacher': 'EG', 'town_teacher': 'EH', 'rural_teacher': 'EI'},
            {'year': 2022, 'total_staff': 'EJ', 'urban_staff': 'EK', 'town_staff': 'EL', 'rural_staff': 'EM', 'total_teacher': 'EN', 'urban_teacher': 'EO', 'town_teacher': 'EP', 'rural_teacher': 'EQ'},
            {'year': 2023, 'total_staff': 'ER', 'urban_staff': 'ES', 'town_staff': 'ET', 'rural_staff': 'EU', 'total_teacher': 'EV', 'urban_teacher': 'EW', 'town_teacher': 'EX', 'rural_teacher': 'EY'},
            {'year': 2024, 'total_staff': 'EZ', 'urban_staff': 'FA', 'town_staff': 'FB', 'rural_staff': 'FC', 'total_teacher': 'FD', 'urban_teacher': 'FE', 'town_teacher': 'FF', 'rural_teacher': 'FG'}
        ]
    },
    'junior_teachers': {
        'years': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024],
        'columns': [
            {'year': 2015, 'total_staff': 'FH', 'urban_staff': 'FI', 'town_staff': 'FJ', 'rural_staff': 'FK', 'total_teacher': 'FL', 'urban_teacher': 'FM', 'town_teacher': 'FN', 'rural_teacher': 'FO'},
            {'year': 2016, 'total_staff': 'FP', 'urban_staff': 'FQ', 'town_staff': 'FR', 'rural_staff': 'FS', 'total_teacher': 'FT', 'urban_teacher': 'FU', 'town_teacher': 'FV', 'rural_teacher': 'FW'},
            {'year': 2017, 'total_staff': 'FX', 'urban_staff': 'FY', 'town_staff': 'FZ', 'rural_staff': 'GA', 'total_teacher': 'GB', 'urban_teacher': 'GC', 'town_teacher': 'GD', 'rural_teacher': 'GE'},
            {'year': 2018, 'total_staff': 'GF', 'urban_staff': 'GG', 'town_staff': 'GH', 'rural_staff': 'GI', 'total_teacher': 'GJ', 'urban_teacher': 'GK', 'town_teacher': 'GL', 'rural_teacher': 'GM'},
            {'year': 2019, 'total_staff': 'GN', 'urban_staff': 'GO', 'town_staff': 'GP', 'rural_staff': 'GQ', 'total_teacher': 'GR', 'urban_teacher': 'GS', 'town_teacher': 'GT', 'rural_teacher': 'GU'},
            {'year': 2020, 'total_staff': 'GV', 'urban_staff': 'GW', 'town_staff': 'GX', 'rural_staff': 'GY', 'total_teacher': 'GZ', 'urban_teacher': 'HA', 'town_teacher': 'HB', 'rural_teacher': 'HC'},
            {'year': 2021, 'total_staff': 'HD', 'urban_staff': 'HE', 'town_staff': 'HF', 'rural_staff': 'HG', 'total_teacher': 'HH', 'urban_teacher': 'HI', 'town_teacher': 'HJ', 'rural_teacher': 'HK'},
            {'year': 2022, 'total_staff': 'HL', 'urban_staff': 'HM', 'town_staff': 'HN', 'rural_staff': 'HO', 'total_teacher': 'HP', 'urban_teacher': 'HQ', 'town_teacher': 'HR', 'rural_teacher': 'HS'},
            {'year': 2023, 'total_staff': 'HT', 'urban_staff': 'HU', 'town_staff': 'HV', 'rural_staff': 'HW', 'total_teacher': 'HX', 'urban_teacher': 'HY', 'town_teacher': 'HZ', 'rural_teacher': 'IA'},
            {'year': 2024, 'total_staff': 'IB', 'urban_staff': 'IC', 'town_staff': 'ID', 'rural_staff': 'IE', 'total_teacher': 'IF', 'urban_teacher': 'IG', 'town_teacher': 'IH', 'rural_teacher': 'II'}
        ]
    },
    'senior_teachers': {
        'years': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024],
        'columns': [
            {'year': 2015, 'total_staff': 'IJ', 'urban_staff': 'IK', 'town_staff': 'IL', 'rural_staff': 'IM', 'total_teacher': 'IN', 'urban_teacher': 'IO', 'town_teacher': 'IP', 'rural_teacher': 'IQ'},
            {'year': 2016, 'total_staff': 'IR', 'urban_staff': 'IS', 'town_staff': 'IT', 'rural_staff': 'IU', 'total_teacher': 'IV', 'urban_teacher': 'IW', 'town_teacher': 'IX', 'rural_teacher': 'IY'},
            {'year': 2017, 'total_staff': 'IZ', 'urban_staff': 'JA', 'town_staff': 'JB', 'rural_staff': 'JC', 'total_teacher': 'JD', 'urban_teacher': 'JE', 'town_teacher': 'JF', 'rural_teacher': 'JG'},
            {'year': 2018, 'total_staff': 'JH', 'urban_staff': 'JI', 'town_staff': 'JJ', 'rural_staff': 'JK', 'total_teacher': 'JL', 'urban_teacher': 'JM', 'town_teacher': 'JN', 'rural_teacher': 'JO'},
            {'year': 2019, 'total_staff': 'JP', 'urban_staff': 'JQ', 'town_staff': 'JR', 'rural_staff': 'JS', 'total_teacher': 'JT', 'urban_teacher': 'JU', 'town_teacher': 'JV', 'rural_teacher': 'JW'},
            {'year': 2020, 'total_staff': 'JX', 'urban_staff': 'JY', 'town_staff': 'JZ', 'rural_staff': 'KA', 'total_teacher': 'KB', 'urban_teacher': 'KC', 'town_teacher': 'KD', 'rural_teacher': 'KE'},
            {'year': 2021, 'total_staff': 'KF', 'urban_staff': 'KG', 'town_staff': 'KH', 'rural_staff': 'KI', 'total_teacher': 'KJ', 'urban_teacher': 'KK', 'town_teacher': 'KL', 'rural_teacher': 'KM'},
            {'year': 2022, 'total_staff': 'KN', 'urban_staff': 'KO', 'town_staff': 'KP', 'rural_staff': 'KQ', 'total_teacher': 'KR', 'urban_teacher': 'KS', 'town_teacher': 'KT', 'rural_teacher': 'KU'},
            {'year': 2023, 'total_staff': 'KV', 'urban_staff': 'KW', 'town_staff': 'KX', 'rural_staff': 'KY', 'total_teacher': 'KZ', 'urban_teacher': 'LA', 'town_teacher': 'LB', 'rural_teacher': 'LC'},
            {'year': 2024, 'total_staff': 'LD', 'urban_staff': 'LE', 'town_staff': 'LF', 'rural_staff': 'LG', 'total_teacher': 'LH', 'urban_teacher': 'LI', 'town_teacher': 'LJ', 'rural_teacher': 'LK'}
        ]
    },
    'vocational_teachers': {
        'years': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024],
        'columns': [
            {'year': 2015, 'total_staff': 'LL', 'total_teacher': 'LM'},
            {'year': 2016, 'total_staff': 'LN', 'total_teacher': 'LO'},
            {'year': 2017, 'total_staff': 'LP', 'total_teacher': 'LQ'},
            {'year': 2018, 'total_staff': 'LR', 'total_teacher': 'LS'},
            {'year': 2019, 'total_staff': 'LT', 'total_teacher': 'LU'},
            {'year': 2020, 'total_staff': 'LV', 'total_teacher': 'LW'},
            {'year': 2021, 'total_staff': 'LX', 'total_teacher': 'LY'},
            {'year': 2022, 'total_staff': 'LZ', 'total_teacher': 'MA'},
            {'year': 2023, 'total_staff': 'MB', 'total_teacher': 'MC'},
            {'year': 2024, 'total_staff': 'MD', 'total_teacher': 'ME'}
        ]
    }
}


def extract_stage_data(row: Tuple[Any, ...], year_config: Dict[str, str]) -> Dict[str, int]:
    """提取单个教育阶段单一年份的教师数据

    Args:
        row: 工作表行数据
        year_config: 年份配置字典

    Returns:
        包含教职工和教师数据的字典
    """
    year_data = {}
    # 处理教职工数据
    staff_cols = ['total_staff', 'urban_staff', 'town_staff', 'rural_staff']
    has_staff_categories = all(col in year_config for col in staff_cols)
    
    if has_staff_categories:
        # 处理分类职工数据
        for col in staff_cols:
            col_name = year_config[col]
            col_idx = column_index_from_string(col_name) - 1
            value = row[col_idx] if col_idx < len(row) else None
            year_data[col] = process_value(value)
    else:
        # 处理中职职工总数
        col_name = year_config['total_staff']
        col_idx = column_index_from_string(col_name) - 1
        value = row[col_idx] if col_idx < len(row) else None
        year_data['total_staff'] = process_value(value)
    
    # 处理专任教师数据
    teacher_cols = ['total_teacher', 'urban_teacher', 'town_teacher', 'rural_teacher']
    has_teacher_categories = all(col in year_config for col in teacher_cols)
    
    if has_teacher_categories:
        # 处理分类专任教师数据
        for col in teacher_cols:
            col_name = year_config[col]
            col_idx = column_index_from_string(col_name) - 1
            value = row[col_idx] if col_idx < len(row) else None
            year_data[col] = process_value(value)
    else:
        # 处理中职专任教师总数
        col_name = year_config['total_teacher']
        col_idx = column_index_from_string(col_name) - 1
        value = row[col_idx] if col_idx < len(row) else None
        year_data['total_teacher'] = process_value(value)
    
    return year_data


def extract_teacher_data(sheet: Worksheet) -> Tuple[List[Dict[str, Any]], List[Dict[str, str]], List[str], int]:
    """提取所有区域的教师数据

    Args:
        sheet: 工作表对象

    Returns:
        教师数据列表、转换记录列表、错误列表、处理总数
    """
    teacher_data = []
    conversion_records = []
    name_conversion_errors = []
    processed_count = 0
    region_col_index = column_index_from_string(REGION_NAME_COLUMN) - 1
    
    print(f"✅ 开始处理教师数据，共{sheet.max_row}行数据")
    
    # 遍历行数据
    for row_idx, row in enumerate(sheet.iter_rows(min_row=START_ROW, values_only=True), start=START_ROW):
        processed_count += 1
        
        # 区域名称处理
        raw_name = row[region_col_index] if (len(row) > region_col_index and row[region_col_index] is not None) else '未知地区'
        if not raw_name:  # 跳过空行
            continue
        
        # 区域名称转换
        area_name, area_code, new_conversion, new_errors = convert_area_name(raw_name, row_idx)
        conversion_records.extend(new_conversion)
        name_conversion_errors.extend(new_errors)
        
        # 创建区域数据对象
        area_data = {
            'area_name': area_name,
            'area_code': area_code,
            'raw_name': str(raw_name).strip(),
        }
        
        # 提取各教育阶段数据
        for stage, config in EDUCATION_STAGES.items():
            stage_data = {}
            for year_config in config['columns']:
                year = year_config['year']
                stage_data[str(year)] = extract_stage_data(row, year_config)
            area_data[stage] = stage_data
        
        teacher_data.append(area_data)
    
    return teacher_data, conversion_records, name_conversion_errors, processed_count


def main() -> None:
    """主函数：教师数据提取主流程"""
    try:
        # 初始化目录
        init_directories(DATA_DIR)
        
        # 加载工作表
        sheet = load_workbook_sheet(EXCEL_PATH, SHEET_NAME)
        if not sheet:
            print("❌ 无法加载工作表，程序退出")
            return
        
        # 提取教师数据
        teacher_data, conversion_records, name_conversion_errors, processed_count = extract_teacher_data(sheet)
        
        # 保存数据到JSON
        save_to_json(teacher_data, JSON_PATH)
        
        # 打印转换统计
        print_conversion_stats(conversion_records, name_conversion_errors)
        
    except Exception as e:
        print(f"🔴 处理数据时发生错误：{str(e)}{traceback.format_exc()}")
    

if __name__ == "__main__":
    main()