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 DwtBulkMarketPg(Templates):

    def __init__(self, site_name='us', date_type="week", date_info='2023-44'):
        super().__init__()
        self.site_name = site_name
        self.date_type = date_type
        self.date_info = date_info
        self.db_save = f'dwt_bulk_market_pg'
        self.spark = self.create_spark_object(
            app_name=f"{self.db_save}: {self.site_name}, {self.date_type}, {self.date_info}")
        self.reset_partitions(partitions_num=5)
        self.partitions_by = ['site_name', 'date_type', 'date_info']
        self.df_ods = self.spark.sql(f"select 1+1;")
        self.df_dwt = self.spark.sql(f"select 1+1;")
        self.df_save = self.spark.sql(f"select 1+1;")


    def read_data(self):
        sql1 = f"""
        select 
            search_term,
            search_volume,
            search_volume_avg3_month,
            search_volume_avg12_month,
            st_asin_count,
            st_asin_page1_review_count,
            st_depth,
            st_sponsored_ads,
            st_appearance
        from 
            ods_bulk_market
        where
            site_name = '{self.site_name}' 
        and date_type = '{self.date_type}' 
        and date_info = '{self.date_info}';
        """
        print(sql1)
        self.df_ods = self.spark.sql(sqlQuery=sql1).cache()

        sql2 = f"""
        select 
            search_term,
            asin_count,
            self_asin_count,
            proportion
        from 
            dwt_bulk_market
        where
            site_name = '{self.site_name}' 
        and date_type = '{self.date_type}' 
        and date_info = '{self.date_info}';
        """
        print(sql2)
        self.df_dwt = self.spark.sql(sqlQuery=sql2).cache()


    def handle_data(self):
        self.df_save = self.df_ods.join(self.df_dwt, 'search_term', 'left')
        # 填充分区字段
        self.df_save = self.df_save.withColumn("site_name", F.lit(self.site_name))
        self.df_save = self.df_save.withColumn("date_type", F.lit(self.date_type))
        self.df_save = self.df_save.withColumn("date_info", F.lit(self.date_info))


if __name__ == '__main__':
    site_name = sys.argv[1]
    date_type = sys.argv[2]
    date_info = sys.argv[3]
    handle_obj = DwtBulkMarketPg(site_name=site_name, date_type=date_type, date_info=date_info)
    handle_obj.run()