import os
import re
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
from pyspark.sql.types import IntegerType

class DwtBulkMarket(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'
        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_dwd = self.spark.sql(f"select 1+1;")
        self.df_dim = self.spark.sql(f"select 1+1;")
        self.df_joined = self.spark.sql(f"select 1+1;")
        self.df_save = self.spark.sql(f"select 1+1;")
        self.u_match = self.spark.udf.register('u_match',self.udf_ele_mattch,IntegerType())


    def read_data(self):
        sql1 = f"""
        select 
            search_term,
            asin,
            is_self_asin
        from 
            dwd_bulk_market
        where
            site_name = '{self.site_name}' 
        and date_type = '{self.date_type}' 
        and date_info = '{self.date_info}';
        """
        print(sql1)
        self.df_dwd = self.spark.sql(sqlQuery=sql1).cache()

        sql2 = f"""
        select 
            asin,
            lower(asin_title) as asin_title
        from 
            dim_cal_asin_history_detail
        where
            site_name = '{self.site_name}';
        """
        print(sql2)
        self.df_dim = self.spark.sql(sqlQuery=sql2).cache()


    def handle_data(self):
        self.df_joined = self.df_dwd.join(self.df_dim, 'asin', 'left')
        self.df_joined = self.df_joined.withColumn("bulk_match", self.u_match(F.col("asin_title")))
        self.df_save = self.df_joined.groupby(['search_term'])\
            .agg(
            F.count("asin").alias("asin_count"),
            F.sum(F.when(F.col("is_self_asin") == "1", 1).otherwise(0)).alias("self_asin_count"),
            F.round((F.sum(F.when(F.col("is_self_asin") == "1", 1).otherwise(0)) / F.count("asin")), 4).alias("proportion"),
            F.sum(F.when(F.col("is_self_asin") == "1", F.col("bulk_match")).otherwise(0)).alias("self_asin_title_including_bulk"),
        )
        # 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))


    @staticmethod
    def udf_ele_mattch(match_text: str):
        pattern = re.compile(r'(?<!\+|\*|\-|\%|\.)\b(bulk)\b', flags=re.IGNORECASE)
        ele_list = re.findall(pattern, match_text)
        if ele_list:
            return 1
        else:
            return 0


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