DylanGuedes commented on a change in pull request #24881: [SPARK-23160][SQL][TEST] Port window.sql URL: https://github.com/apache/spark/pull/24881#discussion_r308373086
########## File path: sql/core/src/test/resources/sql-tests/inputs/pgSQL/window.sql ########## @@ -0,0 +1,903 @@ +-- Portions Copyright (c) 1996-2019, PostgreSQL Global Development Group +-- +-- Window Functions Testing +-- https://github.com/postgres/postgres/blob/REL_12_BETA2/src/test/regress/sql/window.sql + +CREATE TEMPORARY VIEW tenk2 AS SELECT * FROM tenk1; + +CREATE TABLE empsalary ( + depname string, + empno integer, + salary int, + enroll_date date +) USING parquet; + +INSERT INTO empsalary VALUES +('develop', 10, 5200, '2007-08-01'), +('sales', 1, 5000, '2006-10-01'), +('personnel', 5, 3500, '2007-12-10'), +('sales', 4, 4800, '2007-08-08'), +('personnel', 2, 3900, '2006-12-23'), +('develop', 7, 4200, '2008-01-01'), +('develop', 9, 4500, '2008-01-01'), +('sales', 3, 4800, '2007-08-01'), +('develop', 8, 6000, '2006-10-01'), +('develop', 11, 5200, '2007-08-15'); + +SELECT depname, empno, salary, sum(salary) OVER (PARTITION BY depname) FROM empsalary ORDER BY depname, salary; + +SELECT depname, empno, salary, rank() OVER (PARTITION BY depname ORDER BY salary) FROM empsalary; + +SELECT four, ten, SUM(SUM(four)) OVER (PARTITION BY four), AVG(ten) FROM tenk1 +GROUP BY four, ten ORDER BY four, ten; + +SELECT depname, empno, salary, sum(salary) OVER w FROM empsalary WINDOW w AS (PARTITION BY depname); + +-- [SPARK-28064] Order by does not accept a call to rank() +-- SELECT depname, empno, salary, rank() OVER w FROM empsalary WINDOW w AS (PARTITION BY depname ORDER BY salary) ORDER BY rank() OVER w; + +SELECT COUNT(*) OVER () FROM tenk1 WHERE unique2 < 10; + +SELECT COUNT(*) OVER w FROM tenk1 WHERE unique2 < 10 WINDOW w AS (); + +SELECT four FROM tenk1 WHERE FALSE WINDOW w AS (PARTITION BY ten); + +SELECT sum(four) OVER (PARTITION BY ten ORDER BY unique2) AS sum_1, ten, four FROM tenk1 WHERE unique2 < 10; + +SELECT row_number() OVER (ORDER BY unique2) FROM tenk1 WHERE unique2 < 10; + +SELECT rank() OVER (PARTITION BY four ORDER BY ten) AS rank_1, ten, four FROM tenk1 WHERE unique2 < 10; + +SELECT dense_rank() OVER (PARTITION BY four ORDER BY ten), ten, four FROM tenk1 WHERE unique2 < 10; + +SELECT percent_rank() OVER (PARTITION BY four ORDER BY ten), ten, four FROM tenk1 WHERE unique2 < 10; + +SELECT cume_dist() OVER (PARTITION BY four ORDER BY ten), ten, four FROM tenk1 WHERE unique2 < 10; + +SELECT ntile(3) OVER (ORDER BY ten, four), ten, four FROM tenk1 WHERE unique2 < 10; + +-- [SPARK-28065] ntile does not accept NULL as input +-- SELECT ntile(NULL) OVER (ORDER BY ten, four), ten, four FROM tenk1 LIMIT 2; + +SELECT lag(ten) OVER (PARTITION BY four ORDER BY ten), ten, four FROM tenk1 WHERE unique2 < 10; + +-- [SPARK-28068] `lag` second argument must be a literal in Spark +-- SELECT lag(ten, four) OVER (PARTITION BY four ORDER BY ten), ten, four FROM tenk1 WHERE unique2 < 10; +-- SELECT lag(ten, four, 0) OVER (PARTITION BY four ORDER BY ten), ten, four FROM tenk1 WHERE unique2 < 10; + +SELECT lead(ten) OVER (PARTITION BY four ORDER BY ten), ten, four FROM tenk1 WHERE unique2 < 10; + +SELECT lead(ten * 2, 1) OVER (PARTITION BY four ORDER BY ten), ten, four FROM tenk1 WHERE unique2 < 10; + +SELECT lead(ten * 2, 1, -1) OVER (PARTITION BY four ORDER BY ten), ten, four FROM tenk1 WHERE unique2 < 10; + +SELECT first(ten) OVER (PARTITION BY four ORDER BY ten), ten, four FROM tenk1 WHERE unique2 < 10; + +SELECT last(four) OVER (ORDER BY ten), ten, four FROM tenk1 WHERE unique2 < 10; + +SELECT last(ten) OVER (PARTITION BY four), ten, four FROM +(SELECT * FROM tenk1 WHERE unique2 < 10 ORDER BY four, ten)s +ORDER BY four, ten; + +-- [SPARK-27951] ANSI SQL: NTH_VALUE function +-- SELECT nth_value(ten, four + 1) OVER (PARTITION BY four), ten, four +-- FROM (SELECT * FROM tenk1 WHERE unique2 < 10 ORDER BY four, ten)s; + +SELECT ten, two, sum(hundred) AS gsum, sum(sum(hundred)) OVER (PARTITION BY two ORDER BY ten) AS wsum +FROM tenk1 GROUP BY ten, two; + +SELECT count(*) OVER (PARTITION BY four), four FROM (SELECT * FROM tenk1 WHERE two = 1)s WHERE unique2 < 10; + +SELECT (count(*) OVER (PARTITION BY four ORDER BY ten) + + sum(hundred) OVER (PARTITION BY four ORDER BY ten)) AS cntsum + FROM tenk1 WHERE unique2 < 10; + +SELECT * FROM( + SELECT count(*) OVER (PARTITION BY four ORDER BY ten) + + sum(hundred) OVER (PARTITION BY two ORDER BY ten) AS total, + count(*) OVER (PARTITION BY four ORDER BY ten) AS fourcount, + sum(hundred) OVER (PARTITION BY two ORDER BY ten) AS twosum + FROM tenk1 +)sub WHERE total <> fourcount + twosum; + +SELECT avg(four) OVER (PARTITION BY four ORDER BY thousand / 100) FROM tenk1 WHERE unique2 < 10; + +SELECT ten, two, sum(hundred) AS gsum, sum(sum(hundred)) OVER win AS wsum +FROM tenk1 GROUP BY ten, two WINDOW win AS (PARTITION BY two ORDER BY ten); + +SELECT sum(salary), +row_number() OVER (ORDER BY depname), +sum(sum(salary)) OVER (ORDER BY depname DESC) +FROM empsalary GROUP BY depname; + +SELECT sum(salary) OVER w1, count(*) OVER w2 +FROM empsalary WINDOW w1 AS (ORDER BY salary), w2 AS (ORDER BY salary); + +-- Correlated scalar subqueries must be aggregated: Filter (outer(unique2#x) = unique2#x) +-- SELECT lead(ten, (SELECT two FROM tenk1 WHERE s.unique2 = unique2)) OVER (PARTITION BY four ORDER BY ten) +-- FROM tenk1 s WHERE unique2 < 10; + +SELECT count(*) OVER (PARTITION BY four) FROM (SELECT * FROM tenk1 WHERE FALSE)s; + +SELECT sum(salary) OVER w, rank() OVER w FROM empsalary WINDOW w AS (PARTITION BY depname ORDER BY salary DESC); + +-- no viable alternative at input 'year' Review comment: @dongjoon-hyun Nice, now with this config it also do not pass in my host spark-sql shell. However, [have look at this comment](https://github.com/apache/spark/pull/25114#issuecomment-512229758). Looks like the problem is such keywords being reserved. Should I JIRA them? ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
