Github user dilipbiswal commented on a diff in the pull request: https://github.com/apache/spark/pull/16759#discussion_r98807908 --- Diff: sql/core/src/test/resources/sql-tests/results/subquery/in-subquery/not-in-group-by.sql.out --- @@ -0,0 +1,150 @@ +-- Automatically generated by SQLQueryTestSuite +-- Number of queries: 8 + + +-- !query 0 +create temporary view t1 as select * from values + ("val1a", 6S, 8, 10L, float(15.0), 20D, 20E2, timestamp '2014-04-04 01:00:00.000', date '2014-04-04'), + ("val1b", 8S, 16, 19L, float(17.0), 25D, 26E2, timestamp '2014-05-04 01:01:00.000', date '2014-05-04'), + ("val1a", 16S, 12, 21L, float(15.0), 20D, 20E2, timestamp '2014-06-04 01:02:00.001', date '2014-06-04'), + ("val1a", 16S, 12, 10L, float(15.0), 20D, 20E2, timestamp '2014-07-04 01:01:00.000', date '2014-07-04'), + ("val1c", 8S, 16, 19L, float(17.0), 25D, 26E2, timestamp '2014-05-04 01:02:00.001', date '2014-05-05'), + ("val1d", null, 16, 22L, float(17.0), 25D, 26E2, timestamp '2014-06-04 01:01:00.000', null), + ("val1d", null, 16, 19L, float(17.0), 25D, 26E2, timestamp '2014-07-04 01:02:00.001', null), + ("val1e", 10S, null, 25L, float(17.0), 25D, 26E2, timestamp '2014-08-04 01:01:00.000', date '2014-08-04'), + ("val1e", 10S, null, 19L, float(17.0), 25D, 26E2, timestamp '2014-09-04 01:02:00.001', date '2014-09-04'), + ("val1d", 10S, null, 12L, float(17.0), 25D, 26E2, timestamp '2015-05-04 01:01:00.000', date '2015-05-04'), + ("val1a", 6S, 8, 10L, float(15.0), 20D, 20E2, timestamp '2014-04-04 01:02:00.001', date '2014-04-04'), + ("val1e", 10S, null, 19L, float(17.0), 25D, 26E2, timestamp '2014-05-04 01:01:00.000', date '2014-05-04') + as t1(t1a, t1b, t1c, t1d, t1e, t1f, t1g, t1h, t1i) +-- !query 0 schema +struct<> +-- !query 0 output + + + +-- !query 1 +create temporary view t2 as select * from values + ("val2a", 6S, 12, 14L, float(15), 20D, 20E2, timestamp '2014-04-04 01:01:00.000', date '2014-04-04'), + ("val1b", 10S, 12, 19L, float(17), 25D, 26E2, timestamp '2014-05-04 01:01:00.000', date '2014-05-04'), + ("val1b", 8S, 16, 119L, float(17), 25D, 26E2, timestamp '2015-05-04 01:01:00.000', date '2015-05-04'), + ("val1c", 12S, 16, 219L, float(17), 25D, 26E2, timestamp '2016-05-04 01:01:00.000', date '2016-05-04'), + ("val1b", null, 16, 319L, float(17), 25D, 26E2, timestamp '2017-05-04 01:01:00.000', null), + ("val2e", 8S, null, 419L, float(17), 25D, 26E2, timestamp '2014-06-04 01:01:00.000', date '2014-06-04'), + ("val1f", 19S, null, 519L, float(17), 25D, 26E2, timestamp '2014-05-04 01:01:00.000', date '2014-05-04'), + ("val1b", 10S, 12, 19L, float(17), 25D, 26E2, timestamp '2014-06-04 01:01:00.000', date '2014-06-04'), + ("val1b", 8S, 16, 19L, float(17), 25D, 26E2, timestamp '2014-07-04 01:01:00.000', date '2014-07-04'), + ("val1c", 12S, 16, 19L, float(17), 25D, 26E2, timestamp '2014-08-04 01:01:00.000', date '2014-08-05'), + ("val1e", 8S, null, 19L, float(17), 25D, 26E2, timestamp '2014-09-04 01:01:00.000', date '2014-09-04'), + ("val1f", 19S, null, 19L, float(17), 25D, 26E2, timestamp '2014-10-04 01:01:00.000', date '2014-10-04'), + ("val1b", null, 16, 19L, float(17), 25D, 26E2, timestamp '2014-05-04 01:01:00.000', null) + as t2(t2a, t2b, t2c, t2d, t2e, t2f, t2g, t2h, t2i) +-- !query 1 schema +struct<> +-- !query 1 output + + + +-- !query 2 +create temporary view t3 as select * from values + ("val3a", 6S, 12, 110L, float(15), 20D, 20E2, timestamp '2014-04-04 01:02:00.000', date '2014-04-04'), + ("val3a", 6S, 12, 10L, float(15), 20D, 20E2, timestamp '2014-05-04 01:02:00.000', date '2014-05-04'), + ("val1b", 10S, 12, 219L, float(17), 25D, 26E2, timestamp '2014-05-04 01:02:00.000', date '2014-05-04'), + ("val1b", 10S, 12, 19L, float(17), 25D, 26E2, timestamp '2014-05-04 01:02:00.000', date '2014-05-04'), + ("val1b", 8S, 16, 319L, float(17), 25D, 26E2, timestamp '2014-06-04 01:02:00.000', date '2014-06-04'), + ("val1b", 8S, 16, 19L, float(17), 25D, 26E2, timestamp '2014-07-04 01:02:00.000', date '2014-07-04'), + ("val3c", 17S, 16, 519L, float(17), 25D, 26E2, timestamp '2014-08-04 01:02:00.000', date '2014-08-04'), + ("val3c", 17S, 16, 19L, float(17), 25D, 26E2, timestamp '2014-09-04 01:02:00.000', date '2014-09-05'), + ("val1b", null, 16, 419L, float(17), 25D, 26E2, timestamp '2014-10-04 01:02:00.000', null), + ("val1b", null, 16, 19L, float(17), 25D, 26E2, timestamp '2014-11-04 01:02:00.000', null), + ("val3b", 8S, null, 719L, float(17), 25D, 26E2, timestamp '2014-05-04 01:02:00.000', date '2014-05-04'), + ("val3b", 8S, null, 19L, float(17), 25D, 26E2, timestamp '2015-05-04 01:02:00.000', date '2015-05-04') + as t3(t3a, t3b, t3c, t3d, t3e, t3f, t3g, t3h, t3i) +-- !query 2 schema +struct<> +-- !query 2 output + + + +-- !query 3 +SELECT t1a, + Avg(t1b) +FROM t1 +WHERE t1a NOT IN (SELECT t2a + FROM t2) +GROUP BY t1a +-- !query 3 schema +struct<t1a:string,avg(t1b):double> +-- !query 3 output +val1a 11.0 +val1d 10.0 + + +-- !query 4 +SELECT t1a, + Sum(DISTINCT( t1b )) +FROM t1 +WHERE t1d NOT IN (SELECT t2d + FROM t2 + WHERE t1h < t2h) +GROUP BY t1a +-- !query 4 schema +struct<t1a:string,sum(DISTINCT t1b):bigint> +-- !query 4 output +val1a 22 +val1d 10 +val1e 10 + + +-- !query 5 +SELECT Count(*) +FROM (SELECT * + FROM t2 + WHERE t2a NOT IN (SELECT t3a + FROM t3 + WHERE t3h != t2h)) t2 +WHERE t2b NOT IN (SELECT Min(t2b) + FROM t2 + WHERE t2b = t2b + GROUP BY t2c) +-- !query 5 schema +struct<count(1):bigint> +-- !query 5 output +4 + + +-- !query 6 +SELECT t1a, + max(t1b) +FROM t1 +WHERE t1c NOT IN (SELECT Max(t2b) + FROM t2 + WHERE t1a = t2a + GROUP BY t2a) +GROUP BY t1a +-- !query 6 schema +struct<t1a:string,max(t1b):smallint> +-- !query 6 output +val1a 16 +val1b 8 +val1c 8 +val1d 10 + + +-- !query 7 +SELECT t1a, + t1b +FROM t1 +WHERE t1c IN (SELECT t2b + FROM t2 + WHERE t2a NOT IN (SELECT Min(t3a) + FROM t3 + WHERE t3a = t2a + GROUP BY t3b) order by t2a) +-- !query 7 schema +struct<t1a:string,t1b:smallint> +-- !query 7 output +val1a 16 +val1a 16 +val1a 6 +val1a 6 --- End diff -- I have compared the result set matched with the result from DB2.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org