Unsupported TPC-DS queries

Using https://gist.github.com/marcocitus/59dc232f222ebe8cc8d0df20470b7dbc

Q10 has a correlated subquery with a reference table on the outside:
```sql
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 ('Fairfield County','Campbell County','Washtenaw County','Escambia County','Cleburne 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 = 2001 and
d_moy between 3 and 3+3) and
(exists (select *
from web_sales,date_dim
where c.c_customer_sk = ws_bill_customer_sk and
ws_sold_date_sk = d_date_sk and
d_year = 2001 and
d_moy between 3 ANd 3+3) or
exists (select *
from catalog_sales,date_dim
where c.c_customer_sk = cs_ship_customer_sk and
cs_sold_date_sk = d_date_sk and
d_year = 2001 and
d_moy between 3 and 3+3))
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;
ERROR: complex joins are only supported when all distributed tables are co-located and joined on their distribution columns
```

Q16 has a non-co-located correlated subquery:
```sql
select
count(distinct cs_order_number) as "order count"
,sum(cs_ext_ship_cost) as "total shipping cost"
,sum(cs_net_profit) as "total net profit"
from
catalog_sales cs1
,date_dim
,customer_address
,call_center
where
d_date between '2002-4-01' and
(cast('2002-4-01' as date) + interval '60 days')
and cs1.cs_ship_date_sk = d_date_sk
and cs1.cs_ship_addr_sk = ca_address_sk
and ca_state = 'PA'
and cs1.cs_call_center_sk = cc_call_center_sk
and cc_county in ('Williamson County','Williamson County','Williamson County','Williamson County',
'Williamson County'
)
and exists (select *
from catalog_sales cs2
where cs1.cs_order_number = cs2.cs_order_number
and cs1.cs_warehouse_sk <> cs2.cs_warehouse_sk)
and not exists(select *
from catalog_returns cr1
where cs1.cs_order_number = cr1.cr_order_number)
order by count(distinct cs_order_number)
limit 100;
ERROR: complex joins are only supported when all distributed tables are co-located and joined on their distribution columns
```

Q17 uses grouping sets
```sql
select i_item_id,
ca_country,
ca_state,
ca_county,
avg( cast(cs_quantity as decimal(12,2))) agg1,
avg( cast(cs_list_price as decimal(12,2))) agg2,
avg( cast(cs_coupon_amt as decimal(12,2))) agg3,
avg( cast(cs_sales_price as decimal(12,2))) agg4,
avg( cast(cs_net_profit as decimal(12,2))) agg5,
avg( cast(c_birth_year as decimal(12,2))) agg6,
avg( cast(cd1.cd_dep_count as decimal(12,2))) agg7
from catalog_sales, customer_demographics cd1,
customer_demographics cd2, customer, customer_address, date_dim, item
where cs_sold_date_sk = d_date_sk and
cs_item_sk = i_item_sk and
cs_bill_cdemo_sk = cd1.cd_demo_sk and
cs_bill_customer_sk = c_customer_sk and
cd1.cd_gender = 'F' and
cd1.cd_education_status = 'Primary' and
c_current_cdemo_sk = cd2.cd_demo_sk and
c_current_addr_sk = ca_address_sk and
c_birth_month in (1,3,7,11,10,4) and
d_year = 2001 and
ca_state in ('AL','MO','TN'
,'GA','MT','IN','CA')
group by rollup (i_item_id, ca_country, ca_state, ca_county)
order by ca_country,
ca_state,
ca_county,
i_item_id
limit 100;
ERROR: could not run distributed query with GROUPING SETS, CUBE, or ROLLUP
HINT: Consider using an equality filter on the distributed table's partition column.
```

Q22 uses grouping sets
```sql
select i_product_name
,i_brand
,i_class
,i_category
,avg(inv_quantity_on_hand) qoh
from inventory
,date_dim
,item
where inv_date_sk=d_date_sk
and inv_item_sk=i_item_sk
and d_month_seq between 1200 and 1200 + 11
group by rollup(i_product_name
,i_brand
,i_class
,i_category)
order by qoh, i_product_name, i_brand, i_class, i_category
limit 100;
ERROR: could not run distributed query with GROUPING SETS, CUBE, or ROLLUP
HINT: Consider using an equality filter on the distributed table's partition column.
```
Q27 uses grouping sets
```sql
select i_item_id,
s_state, grouping(s_state) g_state,
avg(ss_quantity) agg1,
avg(ss_list_price) agg2,
avg(ss_coupon_amt) agg3,
avg(ss_sales_price) agg4
from store_sales, customer_demographics, date_dim, store, item
where ss_sold_date_sk = d_date_sk and
ss_item_sk = i_item_sk and
ss_store_sk = s_store_sk and
ss_cdemo_sk = cd_demo_sk and
cd_gender = 'M' and
cd_marital_status = 'W' and
cd_education_status = 'Secondary' and
d_year = 1999 and
s_state in ('TN','TN', 'TN', 'TN', 'TN', 'TN')
group by rollup (i_item_id, s_state)
order by i_item_id
,s_state
limit 100;
ERROR: could not run distributed query with GROUPING
HINT: Consider using an equality filter on the distributed table's partition column.
```

Q32 has a co-located correlated subquery, planner does not recognize equivalence via reference table:
```
select sum(cs_ext_discount_amt) as "excess discount amount"
from
catalog_sales
,item
,date_dim
where
i_manufact_id = 722
and i_item_sk = cs_item_sk
and d_date between '2001-03-09' and
(cast('2001-03-09' as date) + interval '90 days')
and d_date_sk = cs_sold_date_sk
and cs_ext_discount_amt
> (
select
1.3 * avg(cs_ext_discount_amt)
from
catalog_sales
,date_dim
where
cs_item_sk = i_item_sk
and d_date between '2001-03-09' and
(cast('2001-03-09' as date) + interval '90 days')
and d_date_sk = cs_sold_date_sk
)
limit 100;
ERROR: complex joins are only supported when all distributed tables are co-located and joined on their distribution columns
```

Q34 has a correlated subquery with reference table on the outside
```sql
select
ca_state,
cd_gender,
cd_marital_status,
cd_dep_count,
count(*) cnt1,
avg(cd_dep_count),
stddev_samp(cd_dep_count),
sum(cd_dep_count),
cd_dep_employed_count,
count(*) cnt2,
avg(cd_dep_employed_count),
stddev_samp(cd_dep_employed_count),
sum(cd_dep_employed_count),
cd_dep_college_count,
count(*) cnt3,
avg(cd_dep_college_count),
stddev_samp(cd_dep_college_count),
sum(cd_dep_college_count)
from
customer c,customer_address ca,customer_demographics
where
c.c_current_addr_sk = ca.ca_address_sk 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 = 1999 and
d_qoy < 4) and
(exists (select *
from web_sales,date_dim
where c.c_customer_sk = ws_bill_customer_sk and
ws_sold_date_sk = d_date_sk and
d_year = 1999 and
d_qoy < 4) or
exists (select *
from catalog_sales,date_dim
where c.c_customer_sk = cs_ship_customer_sk and
cs_sold_date_sk = d_date_sk and
d_year = 1999 and
d_qoy < 4))
group by ca_state,
cd_gender,
cd_marital_status,
cd_dep_count,
cd_dep_employed_count,
cd_dep_college_count
order by ca_state,
cd_gender,
cd_marital_status,
cd_dep_count,
cd_dep_employed_count,
cd_dep_college_count
limit 100;
ERROR: complex joins are only supported when all distributed tables are co-located and joined on their distribution columns
```

Q36 has a grouping
```sql
select * from (
select
sum(ss_net_profit)/sum(ss_ext_sales_price) as gross_margin
,i_category
,i_class
,grouping(i_category)+grouping(i_class) as lochierarchy
,rank() over (
partition by grouping(i_category)+grouping(i_class),
case when grouping(i_class) = 0 then i_category end
order by sum(ss_net_profit)/sum(ss_ext_sales_price) asc) as rank_within_parent
from
store_sales
,date_dim d1
,item
,store
where
d1.d_year = 2000
and d1.d_date_sk = ss_sold_date_sk
and i_item_sk = ss_item_sk
and s_store_sk = ss_store_sk
and s_state in ('TN','TN','TN','TN',
'TN','TN','TN','TN')
group by rollup(i_category,i_class)
) z
order by
lochierarchy desc
,case when lochierarchy = 0 then i_category end
,rank_within_parent
limit 100;
ERROR: could not run distributed query with GROUPING
```

Q67 uses grouping sets
```sql
select *
from (select i_category
,i_class
,i_brand
,i_product_name
,d_year
,d_qoy
,d_moy
,s_store_id
,sumsales
,rank() over (partition by i_category order by sumsales desc) rk
from (select i_category
,i_class
,i_brand
,i_product_name
,d_year
,d_qoy
,d_moy
,s_store_id
,sum(coalesce(ss_sales_price*ss_quantity,0)) sumsales
from store_sales
,date_dim
,store
,item
where ss_sold_date_sk=d_date_sk
and ss_item_sk=i_item_sk
and ss_store_sk = s_store_sk
and d_month_seq between 1217 and 1217+11
group by rollup(i_category, i_class, i_brand, i_product_name, d_year, d_qoy, d_moy,s_store_id))dw1) dw2
where rk <= 100
order by i_category
,i_class
,i_brand
,i_product_name
,d_year
,d_qoy
,d_moy
,s_store_id
,sumsales
,rk
limit 100;
ERROR: could not run distributed query with GROUPING SETS, CUBE, or ROLLUP
HINT: Consider using an equality filter on the distributed table's partition column.
```

Q69 has a correlated subquery with a reference table on the outside
```sql
select
cd_gender,
cd_marital_status,
cd_education_status,
count(*) cnt1,
cd_purchase_estimate,
count(*) cnt2,
cd_credit_rating,
count(*) cnt3
from
customer c,customer_address ca,customer_demographics
where
c.c_current_addr_sk = ca.ca_address_sk and
ca_state in ('IL','TX','ME') 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 1 and 1+2) and
(not exists (select *
from web_sales,date_dim
where c.c_customer_sk = ws_bill_customer_sk and
ws_sold_date_sk = d_date_sk and
d_year = 2002 and
d_moy between 1 and 1+2) and
not exists (select *
from catalog_sales,date_dim
where c.c_customer_sk = cs_ship_customer_sk and
cs_sold_date_sk = d_date_sk and
d_year = 2002 and
d_moy between 1 and 1+2))
group by cd_gender,
cd_marital_status,
cd_education_status,
cd_purchase_estimate,
cd_credit_rating
order by cd_gender,
cd_marital_status,
cd_education_status,
cd_purchase_estimate,
cd_credit_rating
limit 100;
ERROR: complex joins are only supported when all distributed tables are co-located and joined on their distribution columns
```

Q70 uses grouping
```
select * from (
select
sum(ss_net_profit) as total_sum
,s_state
,s_county
,grouping(s_state)+grouping(s_county) as lochierarchy
,rank() over (
partition by grouping(s_state)+grouping(s_county),
case when grouping(s_county) = 0 then s_state end
order by sum(ss_net_profit) desc) as rank_within_parent
from
store_sales
,date_dim d1
,store
where
d1.d_month_seq between 1220 and 1220+11
and d1.d_date_sk = ss_sold_date_sk
and s_store_sk = ss_store_sk
and s_state in
( select s_state
from (select s_state as s_state,
rank() over ( partition by s_state order by sum(ss_net_profit) desc) as ranking
from store_sales, store, date_dim
where d_month_seq between 1220 and 1220+11
and d_date_sk = ss_sold_date_sk
and s_store_sk = ss_store_sk
group by s_state
) tmp1
where ranking <= 5
)
group by rollup(s_state,s_county)
) z
order by
case when lochierarchy = 0 then s_state end
desc ,rank_within_parent desc
limit 100;
ERROR: could not run distributed query with GROUPING
HINT: Consider using an equality filter on the distributed table's partition column.
```
Q86 uses grouping
```sql
select * from (
select
sum(ws_net_paid) as total_sum
,i_category
,i_class
,grouping(i_category)+grouping(i_class) as lochierarchy
,rank() over (
partition by grouping(i_category)+grouping(i_class),
case when grouping(i_class) = 0 then i_category end
order by sum(ws_net_paid) desc) as rank_within_parent
from
web_sales
,date_dim d1
,item
where
d1.d_month_seq between 1186 and 1186+11
and d1.d_date_sk = ws_sold_date_sk
and i_item_sk = ws_item_sk
group by rollup(i_category,i_class)
) z
order by
lochierarchy desc,
case when lochierarchy = 0 then i_category end,
rank_within_parent
limit 100;
ERROR: could not run distributed query with GROUPING
HINT: Consider using an equality filter on the distributed table's partition column.
```

Q92 has a co-located correlated subquery, planner does not recognize equivalence via reference table
```sql
select
sum(ws_ext_discount_amt) as "Excess Discount Amount"
from
web_sales
,item
,date_dim
where
i_manufact_id = 714
and i_item_sk = ws_item_sk
and d_date between '2000-02-01' and
(cast('2000-02-01' as date) + interval '90 days')
and d_date_sk = ws_sold_date_sk
and ws_ext_discount_amt
> (
SELECT
1.3 * avg(ws_ext_discount_amt)
FROM
web_sales
,date_dim
WHERE
ws_item_sk = i_item_sk
and d_date between '2000-02-01' and
(cast('2000-02-01' as date) + interval '90 days')
and d_date_sk = ws_sold_date_sk
)
order by sum(ws_ext_discount_amt)
limit 100;
ERROR: complex joins are only supported when all distributed tables are co-located and joined on their distribution columns
```

Q94 has non-co-located correlated subqueries
```sql
select
count(distinct ws_order_number) as "order count"
,sum(ws_ext_ship_cost) as "total shipping cost"
,sum(ws_net_profit) as "total net profit"
from
web_sales ws1
,date_dim
,customer_address
,web_site
where
d_date between '2002-5-01' and
(cast('2002-5-01' as date) + interval '60 days')
and ws1.ws_ship_date_sk = d_date_sk
and ws1.ws_ship_addr_sk = ca_address_sk
and ca_state = 'OK'
and ws1.ws_web_site_sk = web_site_sk
and web_company_name = 'pri'
and exists (select *
from web_sales ws2
where ws1.ws_order_number = ws2.ws_order_number
and ws1.ws_warehouse_sk <> ws2.ws_warehouse_sk)
and not exists(select *
from web_returns wr1
where ws1.ws_order_number = wr1.wr_order_number)
order by count(distinct ws_order_number)
limit 100;
ERROR: complex joins are only supported when all distributed tables are co-located and joined on their distribution columns
```