Hive 不支持 intersect 的解决办法

问题

有一个SQL语句要在hive里执行但是hive不支持intersect,所以要使用其他方法代替

思路

intersect就是取交集,可以使用inner join进行连接然后取其中一列并去重

原SQL

select  s_store_name
      ,sum(ss_net_profit)
 from store_sales
     ,date_dim
     ,store,
     (select ca_zip
     from (
      SELECT substr(ca_zip,1,5) ca_zip
      FROM customer_address
      WHERE substr(ca_zip,1,5) IN ('27385','58049','58200','16808','21360',
                          '32961','18586','79307','15492')
     intersect
      select ca_zip
      from (SELECT substr(ca_zip,1,5) ca_zip,count(*) cnt
            FROM customer_address, customer
            WHERE ca_address_sk = c_current_addr_sk and
                  c_preferred_cust_flag='Y'
            group by ca_zip
            having count(*) > 10)A1)A2) V1
 where ss_store_sk = s_store_sk
  and ss_sold_date_sk = d_date_sk
  and d_qoy = 1 and d_year = 2002
  and (substr(s_zip,1,2) = substr(V1.ca_zip,1,2))
 group by s_store_name
 order by s_store_name
 limit 100;

更改后的HQL

代码没有格式化,如要测试可以先格式化一下

SELECT s_store_name ,
       sum(ss_net_profit)
FROM store_sales ,
     date_dim ,
     store,
  (  (SELECT DISTINCT A.ca_zip
FROM (
        (SELECT substr(ca_zip,1,5) ca_zip
         FROM customer_address
         WHERE substr(ca_zip,1,5) IN ('27385','58049','58200','16808','21360',
                          '32961','18586','79307','15492'))A
      INNER JOIN
        (SELECT substr(ca_zip,1,5) ca_zip,
                count(*) cnt
         FROM customer_address,
              customer
         WHERE ca_address_sk = c_current_addr_sk
           AND c_preferred_cust_flag='Y'
         GROUP BY ca_zip
         HAVING count(*) > 10) B 
      on(A.ca_zip=B.ca_zip) ))C  )  
WHERE ss_store_sk = s_store_sk
  AND ss_sold_date_sk = d_date_sk
  AND d_qoy = 1
  AND d_year = 2002
  AND (substr(s_zip,1,2) = substr(C.ca_zip,1,2))
GROUP BY s_store_name
ORDER BY s_store_name LIMIT 100;

欢迎点赞