import os
import json
import openpyxl
import re

excel_dir = 'excel'
output_dir = 'src/ReplicatedStorage/Data'

if not os.path.exists(output_dir):
    os.makedirs(output_dir)

def parse_array_field(value, elem_type):
    """
    解析数组类型字段，支持[1,2,3]或1,2,3写法，自动去除空格和空字符串。
    elem_type: 'int', 'float', 'string'等
    """
    if value is None:
        return []
    s = str(value).strip()
    # 支持带中括号写法
    if s.startswith("[") and s.endswith("]"):
        s = s[1:-1]
    # 支持英文逗号和中文逗号
    items = re.split(r'[，,]', s)
    result = []
    for v in items:
        v = v.strip()
        if v == "":
            continue
        if elem_type == "int":
            try:
                result.append(int(v))
            except Exception:
                pass
        elif elem_type == "float":
            try:
                result.append(float(v))
            except Exception:
                pass
        else:
            result.append(v)
    return result

for filename in os.listdir(excel_dir):
    if filename.endswith('.xlsx'):
        filepath = os.path.join(excel_dir, filename)
        wb = openpyxl.load_workbook(filepath)
        for sheet_name in wb.sheetnames:
            ws = wb[sheet_name]
            rows = list(ws.iter_rows(values_only=True))
            if len(rows) < 2:
                continue
            headers = rows[0]
            types = rows[1]
            # 只保留字段名和类型都不为空的字段
            valid_indices = [
                i for i, (h, t) in enumerate(zip(headers, types))
                if h is not None and str(h).strip() != "" and t is not None and str(t).strip() != ""
            ]
            valid_headers = [headers[i] for i in valid_indices]
            valid_types = [types[i] for i in valid_indices]
            data = []
            for row in rows[2:]:
                filtered_row = [row[i] if i < len(row) else None for i in valid_indices]
                row_dict = {}
                for h, t, v in zip(valid_headers, valid_types, filtered_row):
                    if t.endswith("[]"):
                        elem_type = t[:-2]
                        row_dict[h] = parse_array_field(v, elem_type)
                    else:
                        row_dict[h] = v
                id_value = row_dict.get("id")
                # 只导出id为数字且不为空的行
                if id_value is not None and isinstance(id_value, (int, float)) and str(int(id_value)).isdigit():
                    data.append(row_dict)
            if not data:
                continue
            out_name = f"{sheet_name}.json"
            out_path = os.path.join(output_dir, out_name)
            # 写入json，每个对象单独一行
            with open(out_path, 'w', encoding='utf-8') as f:
                f.write('[\n')
                for i, obj in enumerate(data):
                    line = json.dumps(obj, ensure_ascii=False, separators=(',', ':'))
                    if i < len(data) - 1:
                        f.write(line + ',\n')
                    else:
                        f.write(line + '\n')
                f.write(']')
            print(f"导出: {out_path}")