import os
import sys

sys.path.append(os.path.dirname(sys.path[0]))  # 上级目录
from utils.templates import Templates
from pyspark.sql import functions as F


class UsStKeepaSyn(Templates):

    def __init__(self, site_name='us'):
        super().__init__()
        self.site_name = site_name
        self.db_save = f'us_st_keepa_syn_2023_copy'
        self.spark = self.create_spark_object(
            app_name=f"{self.db_save}: {self.site_name}")
        self.reset_partitions(partitions_num=10)
        self.partitions_by = ['site_name']
        self.df_asin = self.spark.sql(f"select 1+1;")
        self.df_parent_asin = self.spark.sql(f"select 1+1;")
        self.df_save = self.spark.sql(f"select 1+1;")


    def read_data(self):
        sql = f"""
        select 
            *
        from
            us_st_keepa_syn_2023
        where
            site_name = '{self.site_name}';
        """
        print(sql)
        self.df_asin = self.spark.sql(sqlQuery=sql).cache()

        sql = f"""
        select 
            asin,
            parent_asin,
            updated_time
        from
            ods_asin_variat
        where
            site_name = '{self.site_name}';
        """
        print(sql)
        self.df_parent_asin = self.spark.sql(sqlQuery=sql).cache()

    def handle_data(self):
        self.df_parent_asin = self.df_parent_asin.orderBy(self.df_parent_asin.updated_time.desc_nulls_last())
        self.df_parent_asin = self.df_parent_asin.drop_duplicates(['asin']).cache()
        self.df_parent_asin = self.df_parent_asin.drop('updated_time')
        self.df_save = self.df_asin.join(self.df_parent_asin, 'asin', 'left')
        self.df_save.show(10)
        self.df_save = self.df_save.withColumn("site_name", F.lit(self.site_name))


if __name__ == '__main__':
    site_name = sys.argv[1]
    handle_obj = UsStKeepaSyn(site_name=site_name)
    handle_obj.run()