Github user dilipbiswal commented on a diff in the pull request: https://github.com/apache/spark/pull/16759#discussion_r98807939 --- Diff: sql/core/src/test/resources/sql-tests/results/subquery/in-subquery/in-order-by.sql.out --- @@ -0,0 +1,328 @@ +-- Automatically generated by SQLQueryTestSuite +-- Number of queries: 18 + + +-- !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 * +FROM t1 +WHERE t1a IN (SELECT t2a + FROM t2) +ORDER BY t1a +-- !query 3 schema +struct<t1a:string,t1b:smallint,t1c:int,t1d:bigint,t1e:float,t1f:double,t1g:decimal(2,-2),t1h:timestamp,t1i:date> +-- !query 3 output +val1b 8 16 19 17.0 25.0 2600 2014-05-04 01:01:00 2014-05-04 +val1c 8 16 19 17.0 25.0 2600 2014-05-04 01:02:00.001 2014-05-05 +val1e 10 NULL 25 17.0 25.0 2600 2014-08-04 01:01:00 2014-08-04 +val1e 10 NULL 19 17.0 25.0 2600 2014-09-04 01:02:00.001 2014-09-04 +val1e 10 NULL 19 17.0 25.0 2600 2014-05-04 01:01:00 2014-05-04 + + +-- !query 4 +SELECT t1a +FROM t1 +WHERE t1b IN (SELECT t2b + FROM t2 + WHERE t1a = t2a) +ORDER BY t1b DESC +-- !query 4 schema +struct<t1a:string> +-- !query 4 output +val1b + + +-- !query 5 +SELECT t1a, + t1b +FROM t1 +WHERE t1c IN (SELECT t2c + FROM t2 + WHERE t1a = t2a) +ORDER BY 2 DESC nulls last +-- !query 5 schema +struct<t1a:string,t1b:smallint> +-- !query 5 output +val1b 8 +val1c 8 + + +-- !query 6 +SELECT Count(DISTINCT( t1a )) +FROM t1 +WHERE t1b IN (SELECT t2b + FROM t2 + WHERE t1a = t2a) +ORDER BY Count(DISTINCT( t1a )) +-- !query 6 schema +struct<count(DISTINCT t1a):bigint> +-- !query 6 output +1 + + +-- !query 7 +SELECT * +FROM t1 +WHERE t1b IN (SELECT t2c + FROM t2 + ORDER BY t2d) +-- !query 7 schema +struct<t1a:string,t1b:smallint,t1c:int,t1d:bigint,t1e:float,t1f:double,t1g:decimal(2,-2),t1h:timestamp,t1i:date> +-- !query 7 output +val1a 16 12 10 15.0 20.0 2000 2014-07-04 01:01:00 2014-07-04 +val1a 16 12 21 15.0 20.0 2000 2014-06-04 01:02:00.001 2014-06-04 + + +-- !query 8 +SELECT * +FROM t1 +WHERE t1b IN (SELECT Min(t2b) + FROM t2 + WHERE t1b = t2b + ORDER BY Min(t2b)) +ORDER BY t1c DESC nulls first +-- !query 8 schema +struct<t1a:string,t1b:smallint,t1c:int,t1d:bigint,t1e:float,t1f:double,t1g:decimal(2,-2),t1h:timestamp,t1i:date> +-- !query 8 output +val1e 10 NULL 25 17.0 25.0 2600 2014-08-04 01:01:00 2014-08-04 +val1e 10 NULL 19 17.0 25.0 2600 2014-09-04 01:02:00.001 2014-09-04 +val1d 10 NULL 12 17.0 25.0 2600 2015-05-04 01:01:00 2015-05-04 +val1e 10 NULL 19 17.0 25.0 2600 2014-05-04 01:01:00 2014-05-04 +val1b 8 16 19 17.0 25.0 2600 2014-05-04 01:01:00 2014-05-04 +val1c 8 16 19 17.0 25.0 2600 2014-05-04 01:02:00.001 2014-05-05 +val1a 6 8 10 15.0 20.0 2000 2014-04-04 01:00:00 2014-04-04 +val1a 6 8 10 15.0 20.0 2000 2014-04-04 01:02:00.001 2014-04-04 + + +-- !query 9 +SELECT t1a, + t1b, + t1h +FROM t1 +WHERE t1c IN (SELECT t2c + FROM t2 + WHERE t1a = t2a + ORDER BY t2b DESC nulls first) + OR t1h IN (SELECT t2h + FROM t2 + WHERE t1h > t2h) +ORDER BY t1h DESC nulls last +-- !query 9 schema +struct<t1a:string,t1b:smallint,t1h:timestamp> +-- !query 9 output +val1c 8 2014-05-04 01:02:00.001 +val1b 8 2014-05-04 01:01:00 + + +-- !query 10 +SELECT * +FROM t1 +WHERE t1a NOT IN (SELECT t2a + FROM t2) +ORDER BY t1a +-- !query 10 schema +struct<t1a:string,t1b:smallint,t1c:int,t1d:bigint,t1e:float,t1f:double,t1g:decimal(2,-2),t1h:timestamp,t1i:date> +-- !query 10 output +val1a 6 8 10 15.0 20.0 2000 2014-04-04 01:00:00 2014-04-04 +val1a 16 12 21 15.0 20.0 2000 2014-06-04 01:02:00.001 2014-06-04 +val1a 16 12 10 15.0 20.0 2000 2014-07-04 01:01:00 2014-07-04 +val1a 6 8 10 15.0 20.0 2000 2014-04-04 01:02:00.001 2014-04-04 +val1d NULL 16 22 17.0 25.0 2600 2014-06-04 01:01:00 NULL +val1d NULL 16 19 17.0 25.0 2600 2014-07-04 01:02:00.001 NULL +val1d 10 NULL 12 17.0 25.0 2600 2015-05-04 01:01:00 2015-05-04 + + +-- !query 11 +SELECT t1a, + t1b +FROM t1 +WHERE t1a NOT IN (SELECT t2a + FROM t2 + WHERE t1a = t2a) +ORDER BY t1b DESC nulls last +-- !query 11 schema +struct<t1a:string,t1b:smallint> +-- !query 11 output +val1a 16 +val1a 16 +val1d 10 +val1a 6 +val1a 6 +val1d NULL +val1d NULL + + +-- !query 12 +SELECT * +FROM t1 +WHERE t1a NOT IN (SELECT t2a + FROM t2 + ORDER BY t2a DESC nulls first) + and t1c IN (SELECT t2c + FROM t2 + ORDER BY t2b DESC nulls last) +ORDER BY t1c DESC nulls last +-- !query 12 schema +struct<t1a:string,t1b:smallint,t1c:int,t1d:bigint,t1e:float,t1f:double,t1g:decimal(2,-2),t1h:timestamp,t1i:date> +-- !query 12 output +val1d NULL 16 22 17.0 25.0 2600 2014-06-04 01:01:00 NULL +val1d NULL 16 19 17.0 25.0 2600 2014-07-04 01:02:00.001 NULL +val1a 16 12 21 15.0 20.0 2000 2014-06-04 01:02:00.001 2014-06-04 +val1a 16 12 10 15.0 20.0 2000 2014-07-04 01:01:00 2014-07-04 + + +-- !query 13 +SELECT * +FROM t1 +WHERE t1b IN (SELECT Min(t2b) + FROM t2 + GROUP BY t2a + ORDER BY t2a DESC) +-- !query 13 schema +struct<t1a:string,t1b:smallint,t1c:int,t1d:bigint,t1e:float,t1f:double,t1g:decimal(2,-2),t1h:timestamp,t1i:date> +-- !query 13 output +val1a 6 8 10 15.0 20.0 2000 2014-04-04 01:00:00 2014-04-04 +val1a 6 8 10 15.0 20.0 2000 2014-04-04 01:02:00.001 2014-04-04 +val1b 8 16 19 17.0 25.0 2600 2014-05-04 01:01:00 2014-05-04 +val1c 8 16 19 17.0 25.0 2600 2014-05-04 01:02:00.001 2014-05-05 + + +-- !query 14 +SELECT t1a, + Count(DISTINCT( t1b )) +FROM t1 +WHERE t1b IN (SELECT Min(t2b) + FROM t2 + WHERE t1a = t2a + GROUP BY t2a + ORDER BY t2a) +GROUP BY t1a, + t1h +ORDER BY t1a +-- !query 14 schema +struct<t1a:string,count(DISTINCT t1b):bigint> +-- !query 14 output +val1b 1 + + +-- !query 15 +SELECT * +FROM t1 +WHERE t1b NOT IN (SELECT Min(t2b) + FROM t2 + GROUP BY t2a + ORDER BY t2a) +-- !query 15 schema +struct<t1a:string,t1b:smallint,t1c:int,t1d:bigint,t1e:float,t1f:double,t1g:decimal(2,-2),t1h:timestamp,t1i:date> +-- !query 15 output +val1a 16 12 10 15.0 20.0 2000 2014-07-04 01:01:00 2014-07-04 +val1a 16 12 21 15.0 20.0 2000 2014-06-04 01:02:00.001 2014-06-04 +val1d 10 NULL 12 17.0 25.0 2600 2015-05-04 01:01:00 2015-05-04 +val1e 10 NULL 19 17.0 25.0 2600 2014-05-04 01:01:00 2014-05-04 +val1e 10 NULL 19 17.0 25.0 2600 2014-09-04 01:02:00.001 2014-09-04 +val1e 10 NULL 25 17.0 25.0 2600 2014-08-04 01:01:00 2014-08-04 + + +-- !query 16 +SELECT t1a, + Sum(DISTINCT( t1b )) +FROM t1 +WHERE t1b NOT IN (SELECT Min(t2b) + FROM t2 + WHERE t1a = t2a + GROUP BY t2c + ORDER BY t2c DESC nulls last) +GROUP BY t1a +-- !query 16 schema +struct<t1a:string,sum(DISTINCT t1b):bigint> +-- !query 16 output +val1a 22 +val1c 8 +val1d 10 +val1e 10 + + +-- !query 17 +SELECT Count(DISTINCT( t1a )), + t1b +FROM t1 +WHERE t1h NOT IN (SELECT t2h + FROM t2 + where t1a = t2a + order by t2d DESC nulls first + ) +GROUP BY t1a, + t1b +ORDER BY t1b DESC nulls last +-- !query 17 schema +struct<count(DISTINCT t1a):bigint,t1b:smallint> +-- !query 17 output +1 16 +1 10 +1 10 +1 8 +1 6 +1 NULL --- 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