You are a database expert and SQL optimizer. You will be given a SQL query and its…
- User
You are a database expert and SQL optimizer. You will be given a SQL query and its rewritten variant. The rewritten query improves performance upon the original while maintaining equivalence. Your task is to create a new pair of original and rewritten queries that invoke a similar rewrite.
[ORIGINAL QUERY]
select case when (select count(*) from store_sales where ss_quantity between 1 and 20) > 1071 then (select avg(ss_ext_tax) from store_sales where ss_quantity between 1 and 20) else (select avg(ss_net_paid_inc_tax) from store_sales where ss_quantity between 1 and 20) end bucket1,case when (select count(*) from store_sales where ss_quantity between 21 and 40) > 39161 then (select avg(ss_ext_tax) from store_sales where ss_quantity between 21 and 40) else (select avg(ss_net_paid_inc_tax) from store_sales where ss_quantity between 21 and 40) end bucket2,case when (select count(*) from store_sales where ss_quantity between 41 and 60) > 29434 then (select avg(ss_ext_tax) from store_sales where ss_quantity between 41 and 60) else (select avg(ss_net_paid_inc_tax) from store_sales where ss_quantity between 41 and 60) end bucket3,case when (select count(*) from store_sales where ss_quantity between 61 and 80) > 6568 then (select avg(ss_ext_tax) from store_sales where ss_quantity between 61 and 80) else (select avg(ss_net_paid_inc_tax) from store_sales where ss_quantity between 61 and 80) end bucket4,case when (select count(*) from store_sales where ss_quantity between 81 and 100) > 21216 then (select avg(ss_ext_tax) from store_sales where ss_quantity between 81 and 100) else (select avg(ss_net_paid_inc_tax) from store_sales where ss_quantity between 81 and 100) end bucket5 from reason where r_reason_sk = 1 ;[REWRITTEN QUERY]
WITH bucket AS ( SELECT CASE WHEN ss_quantity BETWEEN 1 AND 20 THEN 1 WHEN ss_quantity BETWEEN 21 AND 40 THEN 2 WHEN ss_quantity BETWEEN 41 AND 60 THEN 3 WHEN ss_quantity BETWEEN 61 AND 80 THEN 4 WHEN ss_quantity BETWEEN 81 AND 100 THEN 5 END AS quantity_range, COUNT(*) AS cnt, AVG(ss_ext_tax) AS avg_ext_tax, AVG(ss_net_paid_inc_tax) AS avg_net_paid_inc_tax FROM store_sales GROUP BY CASE WHEN ss_quantity BETWEEN 1 AND 20 THEN 1 WHEN ss_quantity BETWEEN 21 AND 40 THEN 2 WHEN ss_quantity BETWEEN 41 AND 60 THEN 3 WHEN ss_quantity BETWEEN 61 AND 80 THEN 4 WHEN ss_quantity BETWEEN 81 AND 100 THEN 5 END ) SELECT CASE WHEN b1.cnt > 1071 THEN b1.avg_ext_tax ELSE b1.avg_net_paid_inc_tax END AS bucket1, CASE WHEN b2.cnt > 39161 THEN b2.avg_ext_tax ELSE b2.avg_net_paid_inc_tax END AS bucket2, CASE WHEN b3.cnt > 29434 THEN b3.avg_ext_tax ELSE b3.avg_net_paid_inc_tax END AS bucket3, CASE WHEN b4.cnt > 6568 THEN b4.avg_ext_tax ELSE b4.avg_net_paid_inc_tax END AS bucket4, CASE WHEN b5.cnt > 21216 THEN b5.avg_ext_tax ELSE b5.avg_net_paid_inc_tax END AS bucket5 FROM (SELECT * FROM bucket WHERE quantity_range = 1) b1, (SELECT * FROM bucket WHERE quantity_range = 2) b2, (SELECT * FROM bucket WHERE quantity_range = 3) b3, (SELECT * FROM bucket WHERE quantity_range = 4) b4, (SELECT * FROM bucket WHERE quantity_range = 5) b5, reason WHERE r_reason_sk = 1;Now, consider the TPC-DS schema and create a new original and equivalent rewritten query pair such that the rewrite operation is similar to the provided demonstration.Keep the following points in mind while creating the new query pair:
- The original query must not have any CTEs.
- The original query must make use of the following fact tables: ['web_sales']. Below is the join graph for these fact tables: ['web_sales(ws_web_site_sk) references web_site(web_site_sk);', 'web_sales(ws_ship_customer_sk) references customer(c_customer_sk);', 'web_sales(ws_bill_cdemo_sk) references customer_demographics(cd_demo_sk);']
- The original query must employ 2 joins.
- The original query must employ the following operators in its WHERE clause: ['max', 'count', 'sum'].
- The rewritten query must be equivalent to the original query, and must follow a similar rewrite pattern as in the given example. Enclose the original and rewritten queries within
and.
- Assistant
Sure! Here's the new pair of original and rewritten queries that follow the guidelines and employ a similar rewrite pattern to the given example:
[ORIGINAL QUERY]
SELECT CASE WHEN (SELECT MAX(ws_quantity) FROM web_sales WHERE ws_web_site_sk = web_site_sk) > 50 THEN (SELECT SUM(ws_ext_sales_price) FROM web_sales WHERE ws_ship_customer_sk = c_customer_sk) ELSE (SELECT SUM(ws_net_paid) FROM web_sales WHERE ws_bill_cdemo_sk = cd_demo_sk) END AS sales_value FROM web_site, customer, customer_demographics WHERE web_site.web_site_sk = web_sales.ws_web_site_sk AND customer.c_customer_sk = web_sales.ws_ship_customer_sk AND customer_demographics.cd_demo_sk = web_sales.ws_bill_cdemo_sk AND (SELECT COUNT(*) FROM web_sales WHERE ws_web_site_sk = web_site_sk) > 100;[REWRITTEN QUERY]
WITH sales_data AS ( SELECT ws_web_site_sk, ws_ship_customer_sk, ws_bill_cdemo_sk, MAX(ws_quantity) AS max_quantity, SUM(ws_ext_sales_price) AS total_ext_sales_price, SUM(ws_net_paid) AS total_net_paid FROM web_sales GROUP BY ws_web_site_sk, ws_ship_customer_sk, ws_bill_cdemo_sk HAVING COUNT(*) > 100 ) SELECT CASE WHEN sd.max_quantity > 50 THEN sd.total_ext_sales_price ELSE sd.total_net_paid END AS sales_value FROM sales_data sd, web_site, customer, customer_demographics WHERE web_site.web_site_sk = sd.ws_web_site_sk AND customer.c_customer_sk = sd.ws_ship_customer_sk AND customer_demographics.cd_demo_sk = sd.ws_bill_cdemo_sk;In this example, the original query performs multiple subqueries to calculate aggregated values for conditions within a single outer query. The rewritten query leverages a Common Table Expression (CTE) to pre-calculate and store the aggregates, simplifying and potentially speeding up the query execution. The goal is to optimize by reducing redundant calculations and restructuring the query execution plan.