流量选品-account_name解析优化-与account_id配套

Pyspark_job/dwt/dwt_flow_asin.py

@@ -545,11 +545,11 @@ class DwtFlowAsin(Templates):
             .withColumnRenamed('account_name', 'fd_account_name')
         # 1. 关联df2，用于填充dim表中account_id和account_name为空的情况
         self.df_asin_detail = self.df_asin_detail.join(df_asin_account, on=['asin'], how='left')
-        # 2. 优先使用dim表中的数据（已从seller_json提取），为空则使用df2的数据
+        # 2. 优先使用dim表数据，account_id为空时account_id和account_name整体取fd表数据
         self.df_asin_detail = self.df_asin_detail.withColumn(
-            "account_id", F.coalesce(F.col("account_id"), F.col("fd_account_id"))
+            "account_name", F.when(F.col("account_id").isNull(), F.col("fd_account_name")).otherwise(F.col("account_name"))
         ).withColumn(
-            "account_name", F.coalesce(F.col("account_name"), F.col("fd_account_name"))
+            "account_id", F.when(F.col("account_id").isNull(), F.col("fd_account_id")).otherwise(F.col("account_id"))
         ).drop("fd_account_id", "fd_account_name")
         # 3. 关联df1获取seller_country_name
         self.df_asin_detail = self.df_asin_detail.join(df_seller_country, on=['account_id'], how='left')