YunNanProject/Tools/T4_4_ClassCount.py

import openpyxl  # 添加缺少的导入
import json
import os
import traceback

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

# 创建数据保存目录
DATA_DIR = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'Data')
os.makedirs(DATA_DIR, exist_ok=True)
JSON_PATH = os.path.join(DATA_DIR, 'ClassCount.json')  # 班级数JSON路径

file_name = EXCEL_PATH
class_data = []
name_conversion_errors = []  # 记录转换失败的名称
conversion_records = []  # 定义转换记录变量

try:
    # 加载工作簿并选择招生数Sheet
    workbook = openpyxl.load_workbook(file_name, read_only=True)
    if '招生数' not in workbook.sheetnames:
        print("❌ 错误：未找到'招生数'Sheet")
        exit(1)
    sheet = workbook['招生数']

    # 定义数据列范围与英文属性映射
    data_columns = {
        # 学前教育（每年份3列：城区/镇区/乡村）
        'preschool_classes': {
            'years': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024],
            'columns': [
                {'year': 2015, 'urban': 'D', 'town': 'E', 'rural': 'F'},
                {'year': 2016, 'urban': 'H', 'town': 'I', 'rural': 'J'},
                {'year': 2017, 'urban': 'L', 'town': 'M', 'rural': 'N'},
                {'year': 2018, 'urban': 'P', 'town': 'Q', 'rural': 'R'},
                {'year': 2019, 'urban': 'T', 'town': 'U', 'rural': 'V'},
                {'year': 2020, 'urban': 'X', 'town': 'Y', 'rural': 'Z'},
                {'year': 2021, 'urban': 'AB', 'town': 'AC', 'rural': 'AD'},
                {'year': 2022, 'urban': 'AF', 'town': 'AG', 'rural': 'AH'},
                {'year': 2023, 'urban': 'AJ', 'town': 'AK', 'rural': 'AL'},
                {'year': 2024, 'urban': 'AN', 'town': 'AO', 'rural': 'AP'}
            ],
            'categories': ['urban', 'town', 'rural']
        },

        # 小学教育
        'primary_classes': {
            'years': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024],
            'columns': [
                {'year': 2015, 'urban': 'AR', 'town': 'AS', 'rural': 'AT'},
                {'year': 2016, 'urban': 'AV', 'town': 'AW', 'rural': 'AX'},
                {'year': 2017, 'urban': 'AZ', 'town': 'BA', 'rural': 'BB'},
                {'year': 2018, 'urban': 'BD', 'town': 'BE', 'rural': 'BF'},
                {'year': 2019, 'urban': 'BH', 'town': 'BI', 'rural': 'BJ'},
                {'year': 2020, 'urban': 'BL', 'town': 'BM', 'rural': 'BN'},
                {'year': 2021, 'urban': 'BP', 'town': 'BQ', 'rural': 'BR'},
                {'year': 2022, 'urban': 'BT', 'town': 'BU', 'rural': 'BV'},
                {'year': 2023, 'urban': 'BX', 'town': 'BY', 'rural': 'BZ'},
                {'year': 2024, 'urban': 'CB', 'town': 'CC', 'rural': 'CD'}
            ],
            'categories': ['urban', 'town', 'rural']
        },

        # 初中教育
        'junior_high_classes': {
            'years': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024],
            'columns': [
                {'year': 2015, 'urban': 'CF', 'town': 'CG', 'rural': 'CH'},
                {'year': 2016, 'urban': 'CJ', 'town': 'CK', 'rural': 'CL'},
                {'year': 2017, 'urban': 'CN', 'town': 'CO', 'rural': 'CP'},
                {'year': 2018, 'urban': 'CR', 'town': 'CS', 'rural': 'CT'},
                {'year': 2019, 'urban': 'CV', 'town': 'CW', 'rural': 'CX'},
                {'year': 2020, 'urban': 'CZ', 'town': 'DA', 'rural': 'DB'},
                {'year': 2021, 'urban': 'DD', 'town': 'DE', 'rural': 'DF'},
                {'year': 2022, 'urban': 'DH', 'town': 'DI', 'rural': 'DJ'},
                {'year': 2023, 'urban': 'DL', 'town': 'DM', 'rural': 'DN'},
                {'year': 2024, 'urban': 'DP', 'town': 'DQ', 'rural': 'DR'}
            ],
            'categories': ['urban', 'town', 'rural']
        },

        # 高中教育
        'senior_high_classes': {
            'years': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024],
            'columns': [
                {'year': 2015, 'urban': 'DT', 'town': 'DU', 'rural': 'DV'},
                {'year': 2016, 'urban': 'DX', 'town': 'DY', 'rural': 'DZ'},
                {'year': 2017, 'urban': 'EB', 'town': 'EC', 'rural': 'ED'},
                {'year': 2018, 'urban': 'EF', 'town': 'EG', 'rural': 'EH'},
                {'year': 2019, 'urban': 'EJ', 'town': 'EK', 'rural': 'EL'},
                {'year': 2020, 'urban': 'EN', 'town': 'EO', 'rural': 'EP'},
                {'year': 2021, 'urban': 'ER', 'town': 'ES', 'rural': 'ET'},
                {'year': 2022, 'urban': 'EV', 'town': 'EW', 'rural': 'EX'},
                {'year': 2023, 'urban': 'EZ', 'town': 'FA', 'rural': 'FB'},
                {'year': 2024, 'urban': 'FD', 'town': 'FE', 'rural': 'FF'}
            ],
            'categories': ['urban', 'town', 'rural']
        },

        # 中职教育（特殊：每年1列）
        'vocational_classes': {
            'years': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024],
            'columns': [
                {'year': 2015, 'column': 'FH'},
                {'year': 2016, 'column': 'FI'},
                {'year': 2017, 'column': 'FJ'},
                {'year': 2018, 'column': 'FK'},
                {'year': 2019, 'column': 'FL'},
                {'year': 2020, 'column': 'FM'},
                {'year': 2021, 'column': 'FN'},
                {'year': 2022, 'column': 'FO'},
                {'year': 2023, 'column': 'FP'},
                {'year': 2024, 'column': 'FQ'}
            ]
        }
    }

    # 遍历数据行（跳过前3行表头，根据实际情况调整）
    for row_num, row in enumerate(sheet.iter_rows(min_row=4, values_only=True), start=4):
        # 区域名称从B列获取（索引1）
        raw_name = row[1] if (len(row) > 1 and row[1] is not None) else '未知地区'
        if not raw_name:  # 跳过空行
            continue

        # 区域名称转换
        str_raw_name = str(raw_name).strip() if raw_name is not None else '未知地区'
        area_info = query_area_info(str_raw_name)
        if area_info:
            area_name = area_info['full_name']
            area_code = area_info['area_code']
            if raw_name != area_name:
                conversion_records.append({
                    'row': row_num,
                    'raw_name': raw_name,
                    'converted_name': area_name
                })
        else:
            area_name = raw_name
            area_code = 'unknown'
            name_conversion_errors.append(f"行 {row_num}: '{raw_name}'")

        area_data = {
            'area_name': area_name,
            'area_code': area_code,
            'raw_name': raw_name
        }

        # 提取各教育阶段班级数据
        for stage, config in data_columns.items():
            stage_data = {}
            # 处理多类别教育阶段
            if 'categories' in config:
                for year_config in config['columns']:
                    year = year_config['year']
                    year_data = {}
                    for category in config['categories']:
                        col_name = year_config[category]
                        col_idx = openpyxl.utils.column_index_from_string(col_name) - 1
                        if col_idx < len(row):
                            value = row[col_idx]
                            # 数据清洗与转换
                            if value is None:
                                year_data[category] = 0
                            else:
                                str_value = str(value).strip()
                                if str_value in ['', '####']:
                                    year_data[category] = 0
                                else:
                                    year_data[category] = int(str_value) if str_value.isdigit() else 0
                    stage_data[str(year)] = year_data
            # 处理中职教育（单值）
            else:
                for year_config in config['columns']:
                    year = year_config['year']
                    col_name = year_config['column']
                    col_idx = openpyxl.utils.column_index_from_string(col_name) - 1
                    if col_idx < len(row):
                        value = row[col_idx]
                        if value is None:
                            stage_data[str(year)] = 0
                        else:
                            str_value = str(value).strip()
                            stage_data[str(year)] = int(str_value) if str_value.isdigit() else 0
            area_data[stage] = stage_data

        class_data.append(area_data)

    workbook.close()

    # 保存JSON文件
    with open(JSON_PATH, 'w', encoding='utf-8') as f:
        json.dump(class_data, f, ensure_ascii=False, indent=2)

    # 输出统计信息
    print(f"✅ 班级数数据提取完成，已保存至：{JSON_PATH}")
    print(f"📊 共处理 {len(class_data)} 条地区数据")
    print("\n=== 名称转换记录 ===")
    if conversion_records:
        for record in conversion_records:
            print(f"🔄 行 {record['row']}: {record['raw_name']} → {record['converted_name']}")
        print(f"📊 共检测到 {len(conversion_records)} 项名称转换")
    else:
        print("📝 不存在名称转换的情况")
    if name_conversion_errors:
        print(f"⚠️ 发现 {len(name_conversion_errors)} 个区域名称转换失败：")
        for error in name_conversion_errors:
            print(f"  - {error}")

except FileNotFoundError:
    print(f"🔴 错误：Excel文件 '{file_name}' 不存在")
except Exception as e:
    print(f"🔴 处理数据时发生错误：{str(e)}{traceback.format_exc()}")