from datetime import datetime, timedelta

from utils.file.trans_methods import *


def convert_and_calculate_time_range(time_str):
    # 解析原始字符串
    date_part = time_str[:6]
    time_part = time_str[7:]

    # 将短日期格式转换为完整年份
    year = '20' + date_part[:2]
    month = date_part[2:4]
    day = date_part[4:]

    hour = time_part[:2]
    minute = time_part[2:]

    # 创建 datetime 对象
    base_time = datetime.datetime.strptime(f"{year}-{month}-{day} {hour}:{minute}", "%Y-%m-%d %H:%M")

    # 计算时间区间
    start_time = base_time.replace(second=0, microsecond=0) - timedelta(minutes=2)
    end_time = base_time.replace(second=0, microsecond=0) + timedelta(minutes=3)

    return base_time.strftime("%Y-%m-%d %H:%M"), start_time.strftime("%Y-%m-%d %H:%M:%S"), end_time.strftime(
        "%Y-%m-%d %H:%M:%S")


all_df = read_file_to_df(r"D:\data\淄博\故障记录_filtered.csv")
all_df['激活时间'] = pd.to_datetime(all_df['激活时间'])

all_files = read_excel_files(r"D:\data\淄博\淄博风场buffer文件(1)")

dfs = pd.DataFrame()

for file in all_files:
    base_name = os.path.basename(file)
    if base_name.startswith("b"):
        try:
            turbnine_no = int(base_name.split("_")[0].replace("b", ""))
            base_time, start_time, end_time = convert_and_calculate_time_range(
                base_name.replace(base_name.split("_")[0] + "_", "")[0:11])
        except Exception as e:
            print("error:", file)
            raise e

        condation1 = (all_df['激活时间'] >= start_time) & (all_df['风机名'] == turbnine_no)
        condation2 = (all_df['激活时间'] < end_time) & (all_df['风机名'] == turbnine_no)
        condation = condation1 & condation2
        dfs = pd.concat([dfs, all_df[condation]])

dfs.drop_duplicates(inplace=True)

dfs.to_csv(r"D:\data\淄博\result.csv", encoding='utf8', index=False)