[SPARK-23167][SQL] Add TPCDS queries v2.7 in TPCDSQuerySuite

sql/core/src/test/resources/tpcds-v2.7.0/q10a.sql

@@ -0,0 +1,69 @@
+-- This is a new query in TPCDS v2.7
+select
+  cd_gender,
+  cd_marital_status,
+  cd_education_status,
+  count(*) cnt1,
+  cd_purchase_estimate,
+  count(*) cnt2,
+  cd_credit_rating,
+  count(*) cnt3,
+  cd_dep_count,
+  count(*) cnt4,
+  cd_dep_employed_count,
+  count(*) cnt5,
+  cd_dep_college_count,
+  count(*) cnt6
+from
+  customer c,customer_address ca,customer_demographics
+where
+  c.c_current_addr_sk = ca.ca_address_sk
+    and ca_county in ('Walker County', 'Richland County', 'Gaines County', 'Douglas County', 'Dona Ana County')
+    and cd_demo_sk = c.c_current_cdemo_sk
+    and exists (
+        select *
+        from store_sales,date_dim
+        where c.c_customer_sk = ss_customer_sk
+          and ss_sold_date_sk = d_date_sk
+          and d_year = 2002
+          and d_moy between 4 and 4 + 3)
+    and exists (
+        select *
+        from (
+            select
+              ws_bill_customer_sk as customer_sk,
+              d_year,
+              d_moy
+            from web_sales, date_dim
+            where ws_sold_date_sk = d_date_sk
+              and d_year = 2002
+              and d_moy between 4 and 4 + 3
+            union all
+            select
+              cs_ship_customer_sk as customer_sk,
+              d_year,
+              d_moy
+            from catalog_sales, date_dim
+            where cs_sold_date_sk = d_date_sk
+              and d_year = 2002
+              and d_moy between 4 and 4 + 3) x
+    where c.c_customer_sk = customer_sk)
+group by
+  cd_gender,
+  cd_marital_status,
+  cd_education_status,
+  cd_purchase_estimate,
+  cd_credit_rating,
+  cd_dep_count,
+  cd_dep_employed_count,
+  cd_dep_college_count
+order by
+  cd_gender,
+  cd_marital_status,
+  cd_education_status,
+  cd_purchase_estimate,
+  cd_credit_rating,
+  cd_dep_count,
+  cd_dep_employed_count,
+  cd_dep_college_count
+limit 100

sql/core/src/test/resources/tpcds-v2.7.0/q11.sql

@@ -0,0 +1,84 @@
+WITH year_total AS (
+  SELECT
+    c_customer_id customer_id,
+    c_first_name customer_first_name,
+    c_last_name customer_last_name,
+    c_preferred_cust_flag customer_preferred_cust_flag,
+    c_birth_country customer_birth_country,
+    c_login customer_login,
+    c_email_address customer_email_address,
+    d_year dyear,
+    sum(ss_ext_list_price - ss_ext_discount_amt) year_total,
+    's' sale_type
+  FROM customer, store_sales, date_dim
+  WHERE c_customer_sk = ss_customer_sk
+    AND ss_sold_date_sk = d_date_sk
+  GROUP BY c_customer_id
+    , c_first_name
+    , c_last_name
+    , d_year
+    , c_preferred_cust_flag
+    , c_birth_country
+    , c_login
+    , c_email_address
+    , d_year
+  UNION ALL
+  SELECT
+    c_customer_id customer_id,
+    c_first_name customer_first_name,
+    c_last_name customer_last_name,
+    c_preferred_cust_flag customer_preferred_cust_flag,
+    c_birth_country customer_birth_country,
+    c_login customer_login,
+    c_email_address customer_email_address,
+    d_year dyear,
+    sum(ws_ext_list_price - ws_ext_discount_amt) year_total,
+    'w' sale_type
+  FROM customer, web_sales, date_dim
+  WHERE c_customer_sk = ws_bill_customer_sk
+    AND ws_sold_date_sk = d_date_sk
+  GROUP BY
+    c_customer_id, c_first_name, c_last_name, c_preferred_cust_flag, c_birth_country,
+    c_login, c_email_address, d_year)
+SELECT
+  -- select list of q11 in TPCDS v1.4 is below:
+  -- t_s_secyear.customer_preferred_cust_flag
+  t_s_secyear.customer_id,
+  t_s_secyear.customer_first_name,
+  t_s_secyear.customer_last_name,
+  t_s_secyear.customer_email_address
+FROM year_total t_s_firstyear
+  , year_total t_s_secyear
+  , year_total t_w_firstyear
+  , year_total t_w_secyear
+WHERE t_s_secyear.customer_id = t_s_firstyear.customer_id
+  AND t_s_firstyear.customer_id = t_w_secyear.customer_id
+  AND t_s_firstyear.customer_id = t_w_firstyear.customer_id
+  AND t_s_firstyear.sale_type = 's'
+  AND t_w_firstyear.sale_type = 'w'
+  AND t_s_secyear.sale_type = 's'
+  AND t_w_secyear.sale_type = 'w'
+  AND t_s_firstyear.dyear = 2001
+  AND t_s_secyear.dyear = 2001 + 1
+  AND t_w_firstyear.dyear = 2001
+  AND t_w_secyear.dyear = 2001 + 1
+  AND t_s_firstyear.year_total > 0
+  AND t_w_firstyear.year_total > 0
+  AND CASE WHEN t_w_firstyear.year_total > 0
+  THEN t_w_secyear.year_total / t_w_firstyear.year_total
+  -- q11 in TPCDS v1.4 used NULL
+  --     ELSE NULL END
+      ELSE 0.0 END
+  > CASE WHEN t_s_firstyear.year_total > 0
+  THEN t_s_secyear.year_total / t_s_firstyear.year_total
+  -- q11 in TPCDS v1.4 used NULL
+  --   ELSE NULL END
+    ELSE 0.0 END
+ORDER BY
+  -- order-by list of q11 in TPCDS v1.4 is below:
+  -- t_s_secyear.customer_preferred_cust_flag
+  t_s_secyear.customer_id,
+  t_s_secyear.customer_first_name,
+  t_s_secyear.customer_last_name,
+  t_s_secyear.customer_email_address
+LIMIT 100

sql/core/src/test/resources/tpcds-v2.7.0/q12.sql

@@ -0,0 +1,23 @@
+SELECT
+  i_item_id, -- This column did not exist in TPCDS v1.4
+  i_item_desc,
+  i_category,
+  i_class,
+  i_current_price,
+  sum(ws_ext_sales_price) AS itemrevenue,
+  sum(ws_ext_sales_price) * 100 / sum(sum(ws_ext_sales_price))
+  OVER
+  (PARTITION BY i_class) AS revenueratio
+FROM
+  web_sales, item, date_dim
+WHERE
+  ws_item_sk = i_item_sk
+    AND i_category IN ('Sports', 'Books', 'Home')
+    AND ws_sold_date_sk = d_date_sk
+    AND d_date BETWEEN cast('1999-02-22' AS DATE)
+  AND (cast('1999-02-22' AS DATE) + INTERVAL 30 days)
+GROUP BY
+  i_item_id, i_item_desc, i_category, i_class, i_current_price
+ORDER BY
+  i_category, i_class, i_item_id, i_item_desc, revenueratio
+LIMIT 100

sql/core/src/test/resources/tpcds-v2.7.0/q14.sql

@@ -0,0 +1,135 @@
+-- This query is the alternative form of sql/core/src/test/resources/tpcds/q14a.sql
+with cross_items as (
+  select
+    i_item_sk ss_item_sk
+  from item, (
+      select
+        iss.i_brand_id brand_id,
+        iss.i_class_id class_id,
+        iss.i_category_id category_id
+      from
+        store_sales, item iss, date_dim d1
+      where
+        ss_item_sk = iss.i_item_sk
+          and ss_sold_date_sk = d1.d_date_sk
+          and d1.d_year between 1998 AND 1998 + 2
+      intersect
+      select
+        ics.i_brand_id,
+        ics.i_class_id,
+        ics.i_category_id
+      from
+        catalog_sales, item ics, date_dim d2
+      where
+        cs_item_sk = ics.i_item_sk
+          and cs_sold_date_sk = d2.d_date_sk
+          and d2.d_year between 1998 AND 1998 + 2
+      intersect
+      select
+        iws.i_brand_id,
+        iws.i_class_id,
+        iws.i_category_id
+      from
+        web_sales, item iws, date_dim d3
+      where
+        ws_item_sk = iws.i_item_sk
+          and ws_sold_date_sk = d3.d_date_sk
+          and d3.d_year between 1998 AND 1998 + 2) x
+      where
+        i_brand_id = brand_id
+          and i_class_id = class_id
+          and i_category_id = category_id),
+avg_sales as (
+  select
+    avg(quantity*list_price) average_sales
+  from (
+      select
+        ss_quantity quantity,
+        ss_list_price list_price
+      from
+        store_sales, date_dim
+      where
+        ss_sold_date_sk = d_date_sk
+          and d_year between 1998 and 1998 + 2
+      union all
+      select
+        cs_quantity quantity,
+        cs_list_price list_price
+      from
+        catalog_sales, date_dim
+      where
+        cs_sold_date_sk = d_date_sk
+          and d_year between 1998 and 1998 + 2
+      union all
+      select
+        ws_quantity quantity,
+        ws_list_price list_price
+      from
+        web_sales, date_dim
+      where
+        ws_sold_date_sk = d_date_sk
+          and d_year between 1998 and 1998 + 2) x)
+select
+  *
+from (
+    select
+      'store' channel,
+      i_brand_id,
+      i_class_id,
+      i_category_id,
+      sum(ss_quantity * ss_list_price) sales,
+      count(*) number_sales
+    from
+      store_sales, item, date_dim
+    where
+      ss_item_sk in (select ss_item_sk from cross_items)
+        and ss_item_sk = i_item_sk
+        and ss_sold_date_sk = d_date_sk
+        and d_week_seq = (
+            select d_week_seq
+            from date_dim
+            where d_year = 1998 + 1
+              and d_moy = 12
+              and d_dom = 16)
+    group by
+      i_brand_id,
+      i_class_id,
+      i_category_id
+    having
+      sum(ss_quantity*ss_list_price) > (select average_sales from avg_sales)) this_year,
+  (
+    select
+      'store' channel,
+      i_brand_id,
+      i_class_id,
+      i_category_id,
+      sum(ss_quantity * ss_list_price) sales,
+      count(*) number_sales
+    from
+      store_sales, item, date_dim
+    where
+      ss_item_sk in (select ss_item_sk from cross_items)
+        and ss_item_sk = i_item_sk
+        and ss_sold_date_sk = d_date_sk
+        and d_week_seq = (
+            select d_week_seq
+            from date_dim
+            where d_year = 1998
+              and d_moy = 12
+              and d_dom = 16)
+    group by
+      i_brand_id,
+      i_class_id,
+      i_category_id
+    having
+      sum(ss_quantity * ss_list_price) > (select average_sales from avg_sales)) last_year
+where
+  this_year.i_brand_id = last_year.i_brand_id
+    and this_year.i_class_id = last_year.i_class_id
+    and this_year.i_category_id = last_year.i_category_id
+order by
+  this_year.channel,
+  this_year.i_brand_id,
+  this_year.i_class_id,
+  this_year.i_category_id
+limit 100