Validate TPC-DS results against Vortex and Parquet

vortex-sqllogictest/README.md

@@ -37,12 +37,11 @@ working directory accordingly.
 TPC-H scripts live under `slt/tpch/datafusion/` and `slt/tpch/duckdb/`, TPC-DS scripts under
 `slt/tpcds/datafusion/` and `slt/tpcds/duckdb/`, ClickBench scripts under
 `slt/clickbench/datafusion/` and `slt/clickbench/duckdb/`. Each engine has its own
-`create.slt.no`, `results/q*.slt.no` (`q1` to `q22` for TPC-H, `q0` to `q42` for ClickBench,
-matching the upstream numbering), and `drop.slt.no`. Its `tpch.slt`/`clickbench.slt` runs these
-against Vortex and asserts EXPLAIN output from the matching `plans/q*.slt.no`. Its `parquet.slt`
-runs the same queries against the original Parquet fixtures and checks the same expected results.
-TPC-DS asserts plans only for now: `tpcds.slt` runs `plans/q1.slt.no` to `plans/q99.slt.no`
-against Vortex, without result records or a Parquet comparison.
+`create.slt.no`, `results/q*.slt.no` (`q1` to `q22` for TPC-H, `q1` to `q99` for TPC-DS, `q0` to
+`q42` for ClickBench, matching the upstream numbering), and `drop.slt.no`. Its
+`tpch.slt`/`tpcds.slt`/`clickbench.slt` runs these against Vortex and asserts EXPLAIN output from
+the matching `plans/q*.slt.no`. Its `parquet.slt` runs the same queries against the original
+Parquet fixtures and checks the same expected results.
 DataFusion uses external tables; DuckDB uses views over files. The `FILE_FORMAT` substitution
 variable selects the format in each engine's table setup.
 

vortex-sqllogictest/slt/tpcds/datafusion/parquet.slt

@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright the Vortex contributors
+
+include ../../setup.slt.no
+
+let FILE_FORMAT
+SELECT 'parquet';
+
+include ./create.slt.no
+include ./results/*.slt.no
+include ./drop.slt.no

vortex-sqllogictest/slt/tpcds/datafusion/results/q1.slt.no

@@ -0,0 +1,128 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright the Vortex contributors
+
+query T
+WITH customer_total_return AS
+  (SELECT sr_customer_sk AS ctr_customer_sk,
+          sr_store_sk AS ctr_store_sk,
+          sum(sr_return_amt) AS ctr_total_return
+   FROM store_returns,
+        date_dim
+   WHERE sr_returned_date_sk = d_date_sk
+     AND d_year = 2000
+   GROUP BY sr_customer_sk,
+            sr_store_sk)
+SELECT c_customer_id
+FROM customer_total_return ctr1,
+     store,
+     customer
+WHERE ctr1.ctr_total_return >
+    (SELECT avg(ctr_total_return)*1.2
+     FROM customer_total_return ctr2
+     WHERE ctr1.ctr_store_sk = ctr2.ctr_store_sk)
+  AND s_store_sk = ctr1.ctr_store_sk
+  AND s_state = 'TN'
+  AND ctr1.ctr_customer_sk = c_customer_sk
+ORDER BY c_customer_id
+LIMIT 100;
+----
+AAAAAAAAAAFBAAAA
+AAAAAAAAAANAAAAA
+AAAAAAAAABDBAAAA
+AAAAAAAAABEBAAAA
+AAAAAAAAABECAAAA
+AAAAAAAAABHBAAAA
+AAAAAAAAABKBAAAA
+AAAAAAAAABMAAAAA
+AAAAAAAAACFCAAAA
+AAAAAAAAACJBAAAA
+AAAAAAAAADBBAAAA
+AAAAAAAAADCCAAAA
+AAAAAAAAADJAAAAA
+AAAAAAAAADNAAAAA
+AAAAAAAAAEEBAAAA
+AAAAAAAAAEGCAAAA
+AAAAAAAAAEJBAAAA
+AAAAAAAAAEKAAAAA
+AAAAAAAAAEPAAAAA
+AAAAAAAAAFDCAAAA
+AAAAAAAAAFKBAAAA
+AAAAAAAAAGFBAAAA
+AAAAAAAAAGPBAAAA
+AAAAAAAAAHFBAAAA
+AAAAAAAAAHHAAAAA
+AAAAAAAAAHJAAAAA
+AAAAAAAAAHMAAAAA
+AAAAAAAAAHPBAAAA
+AAAAAAAAAIKBAAAA
+AAAAAAAAAILBAAAA
+AAAAAAAAAJJAAAAA
+AAAAAAAAAJMAAAAA
+AAAAAAAAAKCAAAAA
+AAAAAAAAAKCCAAAA
+AAAAAAAAAKFBAAAA
+AAAAAAAAAKJAAAAA
+AAAAAAAAALAAAAAA
+AAAAAAAAALDCAAAA
+AAAAAAAAALEBAAAA
+AAAAAAAAALOAAAAA
+AAAAAAAAAMAAAAAA
+AAAAAAAAAMEAAAAA
+AAAAAAAAAMGAAAAA
+AAAAAAAAAMPAAAAA
+AAAAAAAAANDBAAAA
+AAAAAAAAANIBAAAA
+AAAAAAAAANKBAAAA
+AAAAAAAAANPBAAAA
+AAAAAAAAAOFAAAAA
+AAAAAAAAAOIBAAAA
+AAAAAAAAAOLBAAAA
+AAAAAAAAAPIAAAAA
+AAAAAAAAAPJAAAAA
+AAAAAAAAAPKAAAAA
+AAAAAAAAAPNBAAAA
+AAAAAAAABAFBAAAA
+AAAAAAAABAGAAAAA
+AAAAAAAABAHCAAAA
+AAAAAAAABAMAAAAA
+AAAAAAAABBBAAAAA
+AAAAAAAABBFCAAAA
+AAAAAAAABBGCAAAA
+AAAAAAAABBOAAAAA
+AAAAAAAABBPAAAAA
+AAAAAAAABCCAAAAA
+AAAAAAAABCDBAAAA
+AAAAAAAABCKBAAAA
+AAAAAAAABDACAAAA
+AAAAAAAABDCAAAAA
+AAAAAAAABDDBAAAA
+AAAAAAAABDJAAAAA
+AAAAAAAABDMBAAAA
+AAAAAAAABEACAAAA
+AAAAAAAABEIAAAAA
+AAAAAAAABEMAAAAA
+AAAAAAAABFFBAAAA
+AAAAAAAABFIBAAAA
+AAAAAAAABFJBAAAA
+AAAAAAAABGABAAAA
+AAAAAAAABHACAAAA
+AAAAAAAABHBCAAAA
+AAAAAAAABHCAAAAA
+AAAAAAAABIABAAAA
+AAAAAAAABIDBAAAA
+AAAAAAAABJDAAAAA
+AAAAAAAABJJAAAAA
+AAAAAAAABJKBAAAA
+AAAAAAAABJMBAAAA
+AAAAAAAABJNAAAAA
+AAAAAAAABKCBAAAA
+AAAAAAAABKCCAAAA
+AAAAAAAABKECAAAA
+AAAAAAAABLDBAAAA
+AAAAAAAABLMBAAAA
+AAAAAAAABLPAAAAA
+AAAAAAAABMBCAAAA
+AAAAAAAABMCAAAAA
+AAAAAAAABMCBAAAA
+AAAAAAAABMDBAAAA
+AAAAAAAABMEBAAAA

vortex-sqllogictest/slt/tpcds/datafusion/results/q10.slt.no

@@ -0,0 +1,71 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright the Vortex contributors
+
+query TTTIIITIIIIIII
+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 ('Rush County',
+                    'Toole County',
+                    'Jefferson County',
+                    'Dona Ana County',
+                    'La Porte 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 1 AND 1+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 = 2002
+            AND d_moy BETWEEN 1 AND 1+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 = 2002
+            AND d_moy BETWEEN 1 AND 1+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;
+----
+M D College 1 9500 1 Good 1 5 1 1 1 0 1

vortex-sqllogictest/slt/tpcds/datafusion/results/q11.slt.no

@@ -0,0 +1,89 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright the Vortex contributors
+
+query TTTT
+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,
+            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 t_s_secyear.customer_id,
+       t_s_secyear.customer_first_name,
+       t_s_secyear.customer_last_name,
+       t_s_secyear.customer_preferred_cust_flag
+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*1.0000) / t_w_firstyear.year_total
+          ELSE 0.0
+      END > CASE
+                WHEN t_s_firstyear.year_total > 0 THEN (t_s_secyear.year_total*1.0000) / t_s_firstyear.year_total
+                ELSE 0.0
+            END
+ORDER BY t_s_secyear.customer_id NULLS FIRST,
+         t_s_secyear.customer_first_name NULLS FIRST,
+         t_s_secyear.customer_last_name NULLS FIRST,
+         t_s_secyear.customer_preferred_cust_flag NULLS FIRST
+LIMIT 100;
+----
+AAAAAAAAFNMBAAAA Shawnna Freeland Y
+AAAAAAAAKJHBAAAA Roderick Ballard Y
+AAAAAAAALFNAAAAA David Gonzalez N
+AAAAAAAALKIAAAAA John Robbins Y