import ast
import os
import sys
import pandas as pd

os.environ["PYARROW_IGNORE_TIMEZONE"] = "1"
sys.path.append(os.path.dirname(sys.path[0]))  # 上级目录
from utils.templates import Templates
# from ..utils.templates import Templates
from pyspark.sql import functions as F
from pyspark.sql.types import ArrayType, FloatType


class PicturesDimFeaturesSlice(Templates):

    def __init__(self, site_name='us'):
        super(PicturesDimFeaturesSlice, self).__init__()
        self.site_name = site_name
        self.db_save = f'pictures_dim_features_slice'
        self.spark = self.create_spark_object(
            app_name=f"{self.db_save}: {self.site_name}")
        self.df_asin_features = self.spark.sql(f"select 1+1;")
        self.df_save = self.spark.sql(f"select 1+1;")
        # self.partitions_by = ['site_name', 'block']
        self.partitions_by = ['site_name']
        self.partitions_num = 1000

    def read_data(self):
        # sql = f"select id, asin, img_vector as embedding from ods_asin_extract_features;"
        sql = f"select id, asin, features as embedding from pictures_ods_features;"
        print("sql:", sql)
        self.df_save = self.spark.sql(sql).cache()
        self.df_save.show(10)

        # 由于不需要在这一步生成array类型
        # partitions_num = self.df_asin_features.rdd.getNumPartitions()
        # print("分区数量:", partitions_num)  # 642
        # # self.partitions_num = 1000
        # self.df_save = self.df_save.repartition(self.partitions_num)
        # print("重置分区数量:", self.partitions_num)  # 642

    def handle_data(self):
        # 定义一个将字符串转换为列表的UDF
        # str_to_list_udf = F.udf(lambda s: ast.literal_eval(s), ArrayType(FloatType()))
        # # 对DataFrame中的列应用这个UDF
        # self.df_save = self.df_save.withColumn("embedding", str_to_list_udf(self.df_save["embedding"]))
        self.df_save = self.df_save.withColumn('site_name', F.lit(self.site_name))


if __name__ == '__main__':
    site_name = sys.argv[1]  # 参数1：站点
    handle_obj = PicturesDimFeaturesSlice(site_name=site_name)
    handle_obj.run()