[SPARK-28391][SQL][PYTHON][TESTS] Convert and port 'pgSQL/select_implicit.sql' into UDF test base
## What changes were proposed in this pull request? This PR adds some tests converted from 'pgSQL/select_implicit.sql' to test UDFs <details><summary>Diff comparing to 'pgSQL/select_implicit.sql'</summary> <p> ```diff ... diff --git a/sql/core/src/test/resources/sql-tests/results/pgSQL/select_implicit.sql.out b/sql/core/src/test/resources/sql-tests/results/udf/pgSQL/udf-select_implicit.sql.out index 0675820..e6a5995 100755 --- a/sql/core/src/test/resources/sql-tests/results/pgSQL/select_implicit.sql.out +++ b/sql/core/src/test/resources/sql-tests/results/udf/pgSQL/udf-select_implicit.sql.out -91,9 +91,11 struct<> -- !query 11 -SELECT c, count(*) FROM test_missing_target GROUP BY test_missing_target.c ORDER BY c +SELECT udf(c), udf(count(*)) FROM test_missing_target GROUP BY +test_missing_target.c +ORDER BY udf(c) -- !query 11 schema -struct<c:string,count(1):bigint> +struct<CAST(udf(cast(c as string)) AS STRING):string,CAST(udf(cast(count(1) as string)) AS BIGINT):bigint> -- !query 11 output ABAB 2 BBBB 2 -104,9 +106,10 cccc 2 -- !query 12 -SELECT count(*) FROM test_missing_target GROUP BY test_missing_target.c ORDER BY c +SELECT udf(count(*)) FROM test_missing_target GROUP BY test_missing_target.c +ORDER BY udf(c) -- !query 12 schema -struct<count(1):bigint> +struct<CAST(udf(cast(count(1) as string)) AS BIGINT):bigint> -- !query 12 output 2 2 -117,18 +120,18 struct<count(1):bigint> -- !query 13 -SELECT count(*) FROM test_missing_target GROUP BY a ORDER BY b +SELECT udf(count(*)) FROM test_missing_target GROUP BY a ORDER BY udf(b) -- !query 13 schema struct<> -- !query 13 output org.apache.spark.sql.AnalysisException -cannot resolve '`b`' given input columns: [count(1)]; line 1 pos 61 +cannot resolve '`b`' given input columns: [CAST(udf(cast(count(1) as string)) AS BIGINT)]; line 1 pos 70 -- !query 14 -SELECT count(*) FROM test_missing_target GROUP BY b ORDER BY b +SELECT udf(count(*)) FROM test_missing_target GROUP BY b ORDER BY udf(b) -- !query 14 schema -struct<count(1):bigint> +struct<CAST(udf(cast(count(1) as string)) AS BIGINT):bigint> -- !query 14 output 1 2 -137,10 +140,10 struct<count(1):bigint> -- !query 15 -SELECT test_missing_target.b, count(*) - FROM test_missing_target GROUP BY b ORDER BY b +SELECT udf(test_missing_target.b), udf(count(*)) + FROM test_missing_target GROUP BY b ORDER BY udf(b) -- !query 15 schema -struct<b:int,count(1):bigint> +struct<CAST(udf(cast(b as string)) AS INT):int,CAST(udf(cast(count(1) as string)) AS BIGINT):bigint> -- !query 15 output 1 1 2 2 -149,9 +152,9 struct<b:int,count(1):bigint> -- !query 16 -SELECT c FROM test_missing_target ORDER BY a +SELECT udf(c) FROM test_missing_target ORDER BY udf(a) -- !query 16 schema -struct<c:string> +struct<CAST(udf(cast(c as string)) AS STRING):string> -- !query 16 output XXXX ABAB -166,9 +169,9 CCCC -- !query 17 -SELECT count(*) FROM test_missing_target GROUP BY b ORDER BY b desc +SELECT udf(count(*)) FROM test_missing_target GROUP BY b ORDER BY udf(b) desc -- !query 17 schema -struct<count(1):bigint> +struct<CAST(udf(cast(count(1) as string)) AS BIGINT):bigint> -- !query 17 output 4 3 -177,17 +180,17 struct<count(1):bigint> -- !query 18 -SELECT count(*) FROM test_missing_target ORDER BY 1 desc +SELECT udf(count(*)) FROM test_missing_target ORDER BY udf(1) desc -- !query 18 schema -struct<count(1):bigint> +struct<CAST(udf(cast(count(1) as string)) AS BIGINT):bigint> -- !query 18 output 10 -- !query 19 -SELECT c, count(*) FROM test_missing_target GROUP BY 1 ORDER BY 1 +SELECT udf(c), udf(count(*)) FROM test_missing_target GROUP BY 1 ORDER BY 1 -- !query 19 schema -struct<c:string,count(1):bigint> +struct<CAST(udf(cast(c as string)) AS STRING):string,CAST(udf(cast(count(1) as string)) AS BIGINT):bigint> -- !query 19 output ABAB 2 BBBB 2 -198,18 +201,18 cccc 2 -- !query 20 -SELECT c, count(*) FROM test_missing_target GROUP BY 3 +SELECT udf(c), udf(count(*)) FROM test_missing_target GROUP BY 3 -- !query 20 schema struct<> -- !query 20 output org.apache.spark.sql.AnalysisException -GROUP BY position 3 is not in select list (valid range is [1, 2]); line 1 pos 53 +GROUP BY position 3 is not in select list (valid range is [1, 2]); line 1 pos 63 -- !query 21 -SELECT count(*) FROM test_missing_target x, test_missing_target y - WHERE x.a = y.a - GROUP BY b ORDER BY b +SELECT udf(count(*)) FROM test_missing_target x, test_missing_target y + WHERE udf(x.a) = udf(y.a) + GROUP BY b ORDER BY udf(b) -- !query 21 schema struct<> -- !query 21 output -218,10 +221,10 Reference 'b' is ambiguous, could be: x.b, y.b.; line 3 pos 10 -- !query 22 -SELECT a, a FROM test_missing_target - ORDER BY a +SELECT udf(a), udf(a) FROM test_missing_target + ORDER BY udf(a) -- !query 22 schema -struct<a:int,a:int> +struct<CAST(udf(cast(a as string)) AS INT):int,CAST(udf(cast(a as string)) AS INT):int> -- !query 22 output 0 0 1 1 -236,10 +239,10 struct<a:int,a:int> -- !query 23 -SELECT a/2, a/2 FROM test_missing_target - ORDER BY a/2 +SELECT udf(udf(a)/2), udf(udf(a)/2) FROM test_missing_target + ORDER BY udf(udf(a)/2) -- !query 23 schema -struct<(a div 2):int,(a div 2):int> +struct<CAST(udf(cast((cast(udf(cast(a as string)) as int) div 2) as string)) AS INT):int,CAST(udf(cast((cast(udf(cast(a as string)) as int) div 2) as string)) AS INT):int> -- !query 23 output 0 0 0 0 -254,10 +257,10 struct<(a div 2):int,(a div 2):int> -- !query 24 -SELECT a/2, a/2 FROM test_missing_target - GROUP BY a/2 ORDER BY a/2 +SELECT udf(a/2), udf(a/2) FROM test_missing_target + GROUP BY a/2 ORDER BY udf(a/2) -- !query 24 schema -struct<(a div 2):int,(a div 2):int> +struct<CAST(udf(cast((a div 2) as string)) AS INT):int,CAST(udf(cast((a div 2) as string)) AS INT):int> -- !query 24 output 0 0 1 1 -267,11 +270,11 struct<(a div 2):int,(a div 2):int> -- !query 25 -SELECT x.b, count(*) FROM test_missing_target x, test_missing_target y - WHERE x.a = y.a - GROUP BY x.b ORDER BY x.b +SELECT udf(x.b), udf(count(*)) FROM test_missing_target x, test_missing_target y + WHERE udf(x.a) = udf(y.a) + GROUP BY x.b ORDER BY udf(x.b) -- !query 25 schema -struct<b:int,count(1):bigint> +struct<CAST(udf(cast(b as string)) AS INT):int,CAST(udf(cast(count(1) as string)) AS BIGINT):bigint> -- !query 25 output 1 1 2 2 -280,11 +283,11 struct<b:int,count(1):bigint> -- !query 26 -SELECT count(*) FROM test_missing_target x, test_missing_target y - WHERE x.a = y.a - GROUP BY x.b ORDER BY x.b +SELECT udf(count(*)) FROM test_missing_target x, test_missing_target y + WHERE udf(x.a) = udf(y.a) + GROUP BY x.b ORDER BY udf(x.b) -- !query 26 schema -struct<count(1):bigint> +struct<CAST(udf(cast(count(1) as string)) AS BIGINT):bigint> -- !query 26 output 1 2 -293,22 +296,22 struct<count(1):bigint> -- !query 27 -SELECT a%2, count(b) FROM test_missing_target +SELECT a%2, udf(count(udf(b))) FROM test_missing_target GROUP BY test_missing_target.a%2 -ORDER BY test_missing_target.a%2 +ORDER BY udf(test_missing_target.a%2) -- !query 27 schema -struct<(a % 2):int,count(b):bigint> +struct<(a % 2):int,CAST(udf(cast(count(cast(udf(cast(b as string)) as int)) as string)) AS BIGINT):bigint> -- !query 27 output 0 5 1 5 -- !query 28 -SELECT count(c) FROM test_missing_target +SELECT udf(count(c)) FROM test_missing_target GROUP BY lower(test_missing_target.c) -ORDER BY lower(test_missing_target.c) +ORDER BY udf(lower(test_missing_target.c)) -- !query 28 schema -struct<count(c):bigint> +struct<CAST(udf(cast(count(c) as string)) AS BIGINT):bigint> -- !query 28 output 2 3 -317,18 +320,18 struct<count(c):bigint> -- !query 29 -SELECT count(a) FROM test_missing_target GROUP BY a ORDER BY b +SELECT udf(count(udf(a))) FROM test_missing_target GROUP BY a ORDER BY udf(b) -- !query 29 schema struct<> -- !query 29 output org.apache.spark.sql.AnalysisException -cannot resolve '`b`' given input columns: [count(a)]; line 1 pos 61 +cannot resolve '`b`' given input columns: [CAST(udf(cast(count(cast(udf(cast(a as string)) as int)) as string)) AS BIGINT)]; line 1 pos 75 -- !query 30 -SELECT count(b) FROM test_missing_target GROUP BY b/2 ORDER BY b/2 +SELECT udf(count(b)) FROM test_missing_target GROUP BY b/2 ORDER BY udf(b/2) -- !query 30 schema -struct<count(b):bigint> +struct<CAST(udf(cast(count(b) as string)) AS BIGINT):bigint> -- !query 30 output 1 5 -336,10 +339,10 struct<count(b):bigint> -- !query 31 -SELECT lower(test_missing_target.c), count(c) - FROM test_missing_target GROUP BY lower(c) ORDER BY lower(c) +SELECT udf(lower(test_missing_target.c)), udf(count(udf(c))) + FROM test_missing_target GROUP BY lower(c) ORDER BY udf(lower(c)) -- !query 31 schema -struct<lower(c):string,count(c):bigint> +struct<CAST(udf(cast(lower(c) as string)) AS STRING):string,CAST(udf(cast(count(cast(udf(cast(c as string)) as string)) as string)) AS BIGINT):bigint> -- !query 31 output abab 2 bbbb 3 -348,9 +351,9 xxxx 1 -- !query 32 -SELECT a FROM test_missing_target ORDER BY upper(d) +SELECT udf(a) FROM test_missing_target ORDER BY udf(upper(udf(d))) -- !query 32 schema -struct<a:int> +struct<CAST(udf(cast(a as string)) AS INT):int> -- !query 32 output 0 1 -365,19 +368,19 struct<a:int> -- !query 33 -SELECT count(b) FROM test_missing_target - GROUP BY (b + 1) / 2 ORDER BY (b + 1) / 2 desc +SELECT udf(count(b)) FROM test_missing_target + GROUP BY (b + 1) / 2 ORDER BY udf((b + 1) / 2) desc -- !query 33 schema -struct<count(b):bigint> +struct<CAST(udf(cast(count(b) as string)) AS BIGINT):bigint> -- !query 33 output 7 3 -- !query 34 -SELECT count(x.a) FROM test_missing_target x, test_missing_target y - WHERE x.a = y.a - GROUP BY b/2 ORDER BY b/2 +SELECT udf(count(udf(x.a))) FROM test_missing_target x, test_missing_target y + WHERE udf(x.a) = udf(y.a) + GROUP BY b/2 ORDER BY udf(b/2) -- !query 34 schema struct<> -- !query 34 output -386,11 +389,12 Reference 'b' is ambiguous, could be: x.b, y.b.; line 3 pos 10 -- !query 35 -SELECT x.b/2, count(x.b) FROM test_missing_target x, test_missing_target y - WHERE x.a = y.a - GROUP BY x.b/2 ORDER BY x.b/2 +SELECT udf(x.b/2), udf(count(udf(x.b))) FROM test_missing_target x, +test_missing_target y + WHERE udf(x.a) = udf(y.a) + GROUP BY x.b/2 ORDER BY udf(x.b/2) -- !query 35 schema -struct<(b div 2):int,count(b):bigint> +struct<CAST(udf(cast((b div 2) as string)) AS INT):int,CAST(udf(cast(count(cast(udf(cast(b as string)) as int)) as string)) AS BIGINT):bigint> -- !query 35 output 0 1 1 5 -398,14 +402,14 struct<(b div 2):int,count(b):bigint> -- !query 36 -SELECT count(b) FROM test_missing_target x, test_missing_target y - WHERE x.a = y.a +SELECT udf(count(udf(b))) FROM test_missing_target x, test_missing_target y + WHERE udf(x.a) = udf(y.a) GROUP BY x.b/2 -- !query 36 schema struct<> -- !query 36 output org.apache.spark.sql.AnalysisException -Reference 'b' is ambiguous, could be: x.b, y.b.; line 1 pos 13 +Reference 'b' is ambiguous, could be: x.b, y.b.; line 1 pos 21 -- !query 37 ``` </p> </details> ## How was this patch tested? Tested as Guided in SPARK-27921 Closes #25233 from Udbhav30/master. Authored-by: Udbhav30 <u.agrawal30@gmail.com> Signed-off-by: HyukjinKwon <gurwls223@apache.org>
This commit is contained in:
Udbhav30
HyukjinKwon
parent
8fc5cb6285
commit
86dad404bd
167
sql/core/src/test/resources/sql-tests/inputs/udf/pgSQL/udf-select_implicit.sql
Executable file
167
sql/core/src/test/resources/sql-tests/inputs/udf/pgSQL/udf-select_implicit.sql
Executable file
|
|
@ -0,0 +1,167 @@
|
|||
--
|
||||
-- Portions Copyright (c) 1996-2019, PostgreSQL Global Development Group
|
||||
--
|
||||
--
|
||||
-- SELECT_IMPLICIT
|
||||
-- Test cases for queries with ordering terms missing from the target list.
|
||||
-- This used to be called "junkfilter.sql".
|
||||
-- The parser uses the term "resjunk" to handle these cases.
|
||||
-- - thomas 1998-07-09
|
||||
-- https://github.com/postgres/postgres/blob/REL_12_BETA2/src/test/regress/sql/select_implicit.sql
|
||||
--
|
||||
-- This test file was converted from pgSQL/select_implicit.sql
|
||||
-- [SPARK-28445] Inconsistency between Scala and Python/Panda udfs when groupby with udf() is used
|
||||
-- TODO: We should add UDFs in GROUP BY clause when [SPARK-28445] is resolved.
|
||||
|
||||
-- load test data
|
||||
CREATE TABLE test_missing_target (a int, b int, c string, d string) using parquet;
|
||||
INSERT INTO test_missing_target VALUES (0, 1, 'XXXX', 'A');
|
||||
INSERT INTO test_missing_target VALUES (1, 2, 'ABAB', 'b');
|
||||
INSERT INTO test_missing_target VALUES (2, 2, 'ABAB', 'c');
|
||||
INSERT INTO test_missing_target VALUES (3, 3, 'BBBB', 'D');
|
||||
INSERT INTO test_missing_target VALUES (4, 3, 'BBBB', 'e');
|
||||
INSERT INTO test_missing_target VALUES (5, 3, 'bbbb', 'F');
|
||||
INSERT INTO test_missing_target VALUES (6, 4, 'cccc', 'g');
|
||||
INSERT INTO test_missing_target VALUES (7, 4, 'cccc', 'h');
|
||||
INSERT INTO test_missing_target VALUES (8, 4, 'CCCC', 'I');
|
||||
INSERT INTO test_missing_target VALUES (9, 4, 'CCCC', 'j');
|
||||
|
||||
|
||||
-- w/ existing GROUP BY target
|
||||
SELECT udf(c), udf(count(*)) FROM test_missing_target GROUP BY
|
||||
test_missing_target.c
|
||||
ORDER BY udf(c);
|
||||
|
||||
-- w/o existing GROUP BY target using a relation name in GROUP BY clause
|
||||
SELECT udf(count(*)) FROM test_missing_target GROUP BY test_missing_target.c
|
||||
ORDER BY udf(c);
|
||||
|
||||
-- w/o existing GROUP BY target and w/o existing a different ORDER BY target
|
||||
-- failure expected
|
||||
SELECT udf(count(*)) FROM test_missing_target GROUP BY a ORDER BY udf(b);
|
||||
|
||||
-- w/o existing GROUP BY target and w/o existing same ORDER BY target
|
||||
SELECT udf(count(*)) FROM test_missing_target GROUP BY b ORDER BY udf(b);
|
||||
|
||||
-- w/ existing GROUP BY target using a relation name in target
|
||||
SELECT udf(test_missing_target.b), udf(count(*))
|
||||
FROM test_missing_target GROUP BY b ORDER BY udf(b);
|
||||
|
||||
-- w/o existing GROUP BY target
|
||||
SELECT udf(c) FROM test_missing_target ORDER BY udf(a);
|
||||
|
||||
-- w/o existing ORDER BY target
|
||||
SELECT udf(count(*)) FROM test_missing_target GROUP BY b ORDER BY udf(b) desc;
|
||||
|
||||
-- group using reference number
|
||||
SELECT udf(count(*)) FROM test_missing_target ORDER BY udf(1) desc;
|
||||
|
||||
-- order using reference number
|
||||
SELECT udf(c), udf(count(*)) FROM test_missing_target GROUP BY 1 ORDER BY 1;
|
||||
|
||||
-- group using reference number out of range
|
||||
-- failure expected
|
||||
SELECT udf(c), udf(count(*)) FROM test_missing_target GROUP BY 3;
|
||||
|
||||
-- group w/o existing GROUP BY and ORDER BY target under ambiguous condition
|
||||
-- failure expected
|
||||
SELECT udf(count(*)) FROM test_missing_target x, test_missing_target y
|
||||
WHERE udf(x.a) = udf(y.a)
|
||||
GROUP BY b ORDER BY udf(b);
|
||||
|
||||
-- order w/ target under ambiguous condition
|
||||
-- failure NOT expected
|
||||
SELECT udf(a), udf(a) FROM test_missing_target
|
||||
ORDER BY udf(a);
|
||||
|
||||
-- order expression w/ target under ambiguous condition
|
||||
-- failure NOT expected
|
||||
SELECT udf(udf(a)/2), udf(udf(a)/2) FROM test_missing_target
|
||||
ORDER BY udf(udf(a)/2);
|
||||
|
||||
-- group expression w/ target under ambiguous condition
|
||||
-- failure NOT expected
|
||||
SELECT udf(a/2), udf(a/2) FROM test_missing_target
|
||||
GROUP BY a/2 ORDER BY udf(a/2);
|
||||
|
||||
-- group w/ existing GROUP BY target under ambiguous condition
|
||||
SELECT udf(x.b), udf(count(*)) FROM test_missing_target x, test_missing_target y
|
||||
WHERE udf(x.a) = udf(y.a)
|
||||
GROUP BY x.b ORDER BY udf(x.b);
|
||||
|
||||
-- group w/o existing GROUP BY target under ambiguous condition
|
||||
SELECT udf(count(*)) FROM test_missing_target x, test_missing_target y
|
||||
WHERE udf(x.a) = udf(y.a)
|
||||
GROUP BY x.b ORDER BY udf(x.b);
|
||||
|
||||
-- [SPARK-28329] SELECT INTO syntax
|
||||
-- group w/o existing GROUP BY target under ambiguous condition
|
||||
-- into a table
|
||||
-- SELECT count(*) INTO TABLE test_missing_target2
|
||||
-- FROM test_missing_target x, test_missing_target y
|
||||
-- WHERE x.a = y.a
|
||||
-- GROUP BY x.b ORDER BY x.b;
|
||||
-- SELECT * FROM test_missing_target2;
|
||||
|
||||
|
||||
-- Functions and expressions
|
||||
|
||||
-- w/ existing GROUP BY target
|
||||
SELECT a%2, udf(count(udf(b))) FROM test_missing_target
|
||||
GROUP BY test_missing_target.a%2
|
||||
ORDER BY udf(test_missing_target.a%2);
|
||||
|
||||
-- w/o existing GROUP BY target using a relation name in GROUP BY clause
|
||||
SELECT udf(count(c)) FROM test_missing_target
|
||||
GROUP BY lower(test_missing_target.c)
|
||||
ORDER BY udf(lower(test_missing_target.c));
|
||||
|
||||
-- w/o existing GROUP BY target and w/o existing a different ORDER BY target
|
||||
-- failure expected
|
||||
SELECT udf(count(udf(a))) FROM test_missing_target GROUP BY a ORDER BY udf(b);
|
||||
|
||||
-- w/o existing GROUP BY target and w/o existing same ORDER BY target
|
||||
SELECT udf(count(b)) FROM test_missing_target GROUP BY b/2 ORDER BY udf(b/2);
|
||||
|
||||
-- w/ existing GROUP BY target using a relation name in target
|
||||
SELECT udf(lower(test_missing_target.c)), udf(count(udf(c)))
|
||||
FROM test_missing_target GROUP BY lower(c) ORDER BY udf(lower(c));
|
||||
|
||||
-- w/o existing GROUP BY target
|
||||
SELECT udf(a) FROM test_missing_target ORDER BY udf(upper(udf(d)));
|
||||
|
||||
-- w/o existing ORDER BY target
|
||||
SELECT udf(count(b)) FROM test_missing_target
|
||||
GROUP BY (b + 1) / 2 ORDER BY udf((b + 1) / 2) desc;
|
||||
|
||||
-- group w/o existing GROUP BY and ORDER BY target under ambiguous condition
|
||||
-- failure expected
|
||||
SELECT udf(count(udf(x.a))) FROM test_missing_target x, test_missing_target y
|
||||
WHERE udf(x.a) = udf(y.a)
|
||||
GROUP BY b/2 ORDER BY udf(b/2);
|
||||
|
||||
-- group w/ existing GROUP BY target under ambiguous condition
|
||||
SELECT udf(x.b/2), udf(count(udf(x.b))) FROM test_missing_target x,
|
||||
test_missing_target y
|
||||
WHERE udf(x.a) = udf(y.a)
|
||||
GROUP BY x.b/2 ORDER BY udf(x.b/2);
|
||||
|
||||
-- group w/o existing GROUP BY target under ambiguous condition
|
||||
-- failure expected due to ambiguous b in count(b)
|
||||
SELECT udf(count(udf(b))) FROM test_missing_target x, test_missing_target y
|
||||
WHERE udf(x.a) = udf(y.a)
|
||||
GROUP BY x.b/2;
|
||||
|
||||
-- [SPARK-28329] SELECT INTO syntax
|
||||
-- group w/o existing GROUP BY target under ambiguous condition
|
||||
-- into a table
|
||||
-- SELECT count(x.b) INTO TABLE test_missing_target3
|
||||
-- FROM test_missing_target x, test_missing_target y
|
||||
-- WHERE x.a = y.a
|
||||
-- GROUP BY x.b/2 ORDER BY x.b/2;
|
||||
-- SELECT * FROM test_missing_target3;
|
||||
|
||||
-- Cleanup
|
||||
DROP TABLE test_missing_target;
|
||||
-- DROP TABLE test_missing_target2;
|
||||
-- DROP TABLE test_missing_target3;
|
||||
|
|
@ -0,0 +1,420 @@
|
|||
-- Automatically generated by SQLQueryTestSuite
|
||||
-- Number of queries: 38
|
||||
|
||||
|
||||
-- !query 0
|
||||
CREATE TABLE test_missing_target (a int, b int, c string, d string) using parquet
|
||||
-- !query 0 schema
|
||||
struct<>
|
||||
-- !query 0 output
|
||||
|
||||
|
||||
|
||||
-- !query 1
|
||||
INSERT INTO test_missing_target VALUES (0, 1, 'XXXX', 'A')
|
||||
-- !query 1 schema
|
||||
struct<>
|
||||
-- !query 1 output
|
||||
|
||||
|
||||
|
||||
-- !query 2
|
||||
INSERT INTO test_missing_target VALUES (1, 2, 'ABAB', 'b')
|
||||
-- !query 2 schema
|
||||
struct<>
|
||||
-- !query 2 output
|
||||
|
||||
|
||||
|
||||
-- !query 3
|
||||
INSERT INTO test_missing_target VALUES (2, 2, 'ABAB', 'c')
|
||||
-- !query 3 schema
|
||||
struct<>
|
||||
-- !query 3 output
|
||||
|
||||
|
||||
|
||||
-- !query 4
|
||||
INSERT INTO test_missing_target VALUES (3, 3, 'BBBB', 'D')
|
||||
-- !query 4 schema
|
||||
struct<>
|
||||
-- !query 4 output
|
||||
|
||||
|
||||
|
||||
-- !query 5
|
||||
INSERT INTO test_missing_target VALUES (4, 3, 'BBBB', 'e')
|
||||
-- !query 5 schema
|
||||
struct<>
|
||||
-- !query 5 output
|
||||
|
||||
|
||||
|
||||
-- !query 6
|
||||
INSERT INTO test_missing_target VALUES (5, 3, 'bbbb', 'F')
|
||||
-- !query 6 schema
|
||||
struct<>
|
||||
-- !query 6 output
|
||||
|
||||
|
||||
|
||||
-- !query 7
|
||||
INSERT INTO test_missing_target VALUES (6, 4, 'cccc', 'g')
|
||||
-- !query 7 schema
|
||||
struct<>
|
||||
-- !query 7 output
|
||||
|
||||
|
||||
|
||||
-- !query 8
|
||||
INSERT INTO test_missing_target VALUES (7, 4, 'cccc', 'h')
|
||||
-- !query 8 schema
|
||||
struct<>
|
||||
-- !query 8 output
|
||||
|
||||
|
||||
|
||||
-- !query 9
|
||||
INSERT INTO test_missing_target VALUES (8, 4, 'CCCC', 'I')
|
||||
-- !query 9 schema
|
||||
struct<>
|
||||
-- !query 9 output
|
||||
|
||||
|
||||
|
||||
-- !query 10
|
||||
INSERT INTO test_missing_target VALUES (9, 4, 'CCCC', 'j')
|
||||
-- !query 10 schema
|
||||
struct<>
|
||||
-- !query 10 output
|
||||
|
||||
|
||||
|
||||
-- !query 11
|
||||
SELECT udf(c), udf(count(*)) FROM test_missing_target GROUP BY
|
||||
test_missing_target.c
|
||||
ORDER BY udf(c)
|
||||
-- !query 11 schema
|
||||
struct<CAST(udf(cast(c as string)) AS STRING):string,CAST(udf(cast(count(1) as string)) AS BIGINT):bigint>
|
||||
-- !query 11 output
|
||||
ABAB 2
|
||||
BBBB 2
|
||||
CCCC 2
|
||||
XXXX 1
|
||||
bbbb 1
|
||||
cccc 2
|
||||
|
||||
|
||||
-- !query 12
|
||||
SELECT udf(count(*)) FROM test_missing_target GROUP BY test_missing_target.c
|
||||
ORDER BY udf(c)
|
||||
-- !query 12 schema
|
||||
struct<CAST(udf(cast(count(1) as string)) AS BIGINT):bigint>
|
||||
-- !query 12 output
|
||||
2
|
||||
2
|
||||
2
|
||||
1
|
||||
1
|
||||
2
|
||||
|
||||
|
||||
-- !query 13
|
||||
SELECT udf(count(*)) FROM test_missing_target GROUP BY a ORDER BY udf(b)
|
||||
-- !query 13 schema
|
||||
struct<>
|
||||
-- !query 13 output
|
||||
org.apache.spark.sql.AnalysisException
|
||||
cannot resolve '`b`' given input columns: [CAST(udf(cast(count(1) as string)) AS BIGINT)]; line 1 pos 70
|
||||
|
||||
|
||||
-- !query 14
|
||||
SELECT udf(count(*)) FROM test_missing_target GROUP BY b ORDER BY udf(b)
|
||||
-- !query 14 schema
|
||||
struct<CAST(udf(cast(count(1) as string)) AS BIGINT):bigint>
|
||||
-- !query 14 output
|
||||
1
|
||||
2
|
||||
3
|
||||
4
|
||||
|
||||
|
||||
-- !query 15
|
||||
SELECT udf(test_missing_target.b), udf(count(*))
|
||||
FROM test_missing_target GROUP BY b ORDER BY udf(b)
|
||||
-- !query 15 schema
|
||||
struct<CAST(udf(cast(b as string)) AS INT):int,CAST(udf(cast(count(1) as string)) AS BIGINT):bigint>
|
||||
-- !query 15 output
|
||||
1 1
|
||||
2 2
|
||||
3 3
|
||||
4 4
|
||||
|
||||
|
||||
-- !query 16
|
||||
SELECT udf(c) FROM test_missing_target ORDER BY udf(a)
|
||||
-- !query 16 schema
|
||||
struct<CAST(udf(cast(c as string)) AS STRING):string>
|
||||
-- !query 16 output
|
||||
XXXX
|
||||
ABAB
|
||||
ABAB
|
||||
BBBB
|
||||
BBBB
|
||||
bbbb
|
||||
cccc
|
||||
cccc
|
||||
CCCC
|
||||
CCCC
|
||||
|
||||
|
||||
-- !query 17
|
||||
SELECT udf(count(*)) FROM test_missing_target GROUP BY b ORDER BY udf(b) desc
|
||||
-- !query 17 schema
|
||||
struct<CAST(udf(cast(count(1) as string)) AS BIGINT):bigint>
|
||||
-- !query 17 output
|
||||
4
|
||||
3
|
||||
2
|
||||
1
|
||||
|
||||
|
||||
-- !query 18
|
||||
SELECT udf(count(*)) FROM test_missing_target ORDER BY udf(1) desc
|
||||
-- !query 18 schema
|
||||
struct<CAST(udf(cast(count(1) as string)) AS BIGINT):bigint>
|
||||
-- !query 18 output
|
||||
10
|
||||
|
||||
|
||||
-- !query 19
|
||||
SELECT udf(c), udf(count(*)) FROM test_missing_target GROUP BY 1 ORDER BY 1
|
||||
-- !query 19 schema
|
||||
struct<CAST(udf(cast(c as string)) AS STRING):string,CAST(udf(cast(count(1) as string)) AS BIGINT):bigint>
|
||||
-- !query 19 output
|
||||
ABAB 2
|
||||
BBBB 2
|
||||
CCCC 2
|
||||
XXXX 1
|
||||
bbbb 1
|
||||
cccc 2
|
||||
|
||||
|
||||
-- !query 20
|
||||
SELECT udf(c), udf(count(*)) FROM test_missing_target GROUP BY 3
|
||||
-- !query 20 schema
|
||||
struct<>
|
||||
-- !query 20 output
|
||||
org.apache.spark.sql.AnalysisException
|
||||
GROUP BY position 3 is not in select list (valid range is [1, 2]); line 1 pos 63
|
||||
|
||||
|
||||
-- !query 21
|
||||
SELECT udf(count(*)) FROM test_missing_target x, test_missing_target y
|
||||
WHERE udf(x.a) = udf(y.a)
|
||||
GROUP BY b ORDER BY udf(b)
|
||||
-- !query 21 schema
|
||||
struct<>
|
||||
-- !query 21 output
|
||||
org.apache.spark.sql.AnalysisException
|
||||
Reference 'b' is ambiguous, could be: x.b, y.b.; line 3 pos 10
|
||||
|
||||
|
||||
-- !query 22
|
||||
SELECT udf(a), udf(a) FROM test_missing_target
|
||||
ORDER BY udf(a)
|
||||
-- !query 22 schema
|
||||
struct<CAST(udf(cast(a as string)) AS INT):int,CAST(udf(cast(a as string)) AS INT):int>
|
||||
-- !query 22 output
|
||||
0 0
|
||||
1 1
|
||||
2 2
|
||||
3 3
|
||||
4 4
|
||||
5 5
|
||||
6 6
|
||||
7 7
|
||||
8 8
|
||||
9 9
|
||||
|
||||
|
||||
-- !query 23
|
||||
SELECT udf(udf(a)/2), udf(udf(a)/2) FROM test_missing_target
|
||||
ORDER BY udf(udf(a)/2)
|
||||
-- !query 23 schema
|
||||
struct<CAST(udf(cast((cast(udf(cast(a as string)) as int) div 2) as string)) AS INT):int,CAST(udf(cast((cast(udf(cast(a as string)) as int) div 2) as string)) AS INT):int>
|
||||
-- !query 23 output
|
||||
0 0
|
||||
0 0
|
||||
1 1
|
||||
1 1
|
||||
2 2
|
||||
2 2
|
||||
3 3
|
||||
3 3
|
||||
4 4
|
||||
4 4
|
||||
|
||||
|
||||
-- !query 24
|
||||
SELECT udf(a/2), udf(a/2) FROM test_missing_target
|
||||
GROUP BY a/2 ORDER BY udf(a/2)
|
||||
-- !query 24 schema
|
||||
struct<CAST(udf(cast((a div 2) as string)) AS INT):int,CAST(udf(cast((a div 2) as string)) AS INT):int>
|
||||
-- !query 24 output
|
||||
0 0
|
||||
1 1
|
||||
2 2
|
||||
3 3
|
||||
4 4
|
||||
|
||||
|
||||
-- !query 25
|
||||
SELECT udf(x.b), udf(count(*)) FROM test_missing_target x, test_missing_target y
|
||||
WHERE udf(x.a) = udf(y.a)
|
||||
GROUP BY x.b ORDER BY udf(x.b)
|
||||
-- !query 25 schema
|
||||
struct<CAST(udf(cast(b as string)) AS INT):int,CAST(udf(cast(count(1) as string)) AS BIGINT):bigint>
|
||||
-- !query 25 output
|
||||
1 1
|
||||
2 2
|
||||
3 3
|
||||
4 4
|
||||
|
||||
|
||||
-- !query 26
|
||||
SELECT udf(count(*)) FROM test_missing_target x, test_missing_target y
|
||||
WHERE udf(x.a) = udf(y.a)
|
||||
GROUP BY x.b ORDER BY udf(x.b)
|
||||
-- !query 26 schema
|
||||
struct<CAST(udf(cast(count(1) as string)) AS BIGINT):bigint>
|
||||
-- !query 26 output
|
||||
1
|
||||
2
|
||||
3
|
||||
4
|
||||
|
||||
|
||||
-- !query 27
|
||||
SELECT a%2, udf(count(udf(b))) FROM test_missing_target
|
||||
GROUP BY test_missing_target.a%2
|
||||
ORDER BY udf(test_missing_target.a%2)
|
||||
-- !query 27 schema
|
||||
struct<(a % 2):int,CAST(udf(cast(count(cast(udf(cast(b as string)) as int)) as string)) AS BIGINT):bigint>
|
||||
-- !query 27 output
|
||||
0 5
|
||||
1 5
|
||||
|
||||
|
||||
-- !query 28
|
||||
SELECT udf(count(c)) FROM test_missing_target
|
||||
GROUP BY lower(test_missing_target.c)
|
||||
ORDER BY udf(lower(test_missing_target.c))
|
||||
-- !query 28 schema
|
||||
struct<CAST(udf(cast(count(c) as string)) AS BIGINT):bigint>
|
||||
-- !query 28 output
|
||||
2
|
||||
3
|
||||
4
|
||||
1
|
||||
|
||||
|
||||
-- !query 29
|
||||
SELECT udf(count(udf(a))) FROM test_missing_target GROUP BY a ORDER BY udf(b)
|
||||
-- !query 29 schema
|
||||
struct<>
|
||||
-- !query 29 output
|
||||
org.apache.spark.sql.AnalysisException
|
||||
cannot resolve '`b`' given input columns: [CAST(udf(cast(count(cast(udf(cast(a as string)) as int)) as string)) AS BIGINT)]; line 1 pos 75
|
||||
|
||||
|
||||
-- !query 30
|
||||
SELECT udf(count(b)) FROM test_missing_target GROUP BY b/2 ORDER BY udf(b/2)
|
||||
-- !query 30 schema
|
||||
struct<CAST(udf(cast(count(b) as string)) AS BIGINT):bigint>
|
||||
-- !query 30 output
|
||||
1
|
||||
5
|
||||
4
|
||||
|
||||
|
||||
-- !query 31
|
||||
SELECT udf(lower(test_missing_target.c)), udf(count(udf(c)))
|
||||
FROM test_missing_target GROUP BY lower(c) ORDER BY udf(lower(c))
|
||||
-- !query 31 schema
|
||||
struct<CAST(udf(cast(lower(c) as string)) AS STRING):string,CAST(udf(cast(count(cast(udf(cast(c as string)) as string)) as string)) AS BIGINT):bigint>
|
||||
-- !query 31 output
|
||||
abab 2
|
||||
bbbb 3
|
||||
cccc 4
|
||||
xxxx 1
|
||||
|
||||
|
||||
-- !query 32
|
||||
SELECT udf(a) FROM test_missing_target ORDER BY udf(upper(udf(d)))
|
||||
-- !query 32 schema
|
||||
struct<CAST(udf(cast(a as string)) AS INT):int>
|
||||
-- !query 32 output
|
||||
0
|
||||
1
|
||||
2
|
||||
3
|
||||
4
|
||||
5
|
||||
6
|
||||
7
|
||||
8
|
||||
9
|
||||
|
||||
|
||||
-- !query 33
|
||||
SELECT udf(count(b)) FROM test_missing_target
|
||||
GROUP BY (b + 1) / 2 ORDER BY udf((b + 1) / 2) desc
|
||||
-- !query 33 schema
|
||||
struct<CAST(udf(cast(count(b) as string)) AS BIGINT):bigint>
|
||||
-- !query 33 output
|
||||
7
|
||||
3
|
||||
|
||||
|
||||
-- !query 34
|
||||
SELECT udf(count(udf(x.a))) FROM test_missing_target x, test_missing_target y
|
||||
WHERE udf(x.a) = udf(y.a)
|
||||
GROUP BY b/2 ORDER BY udf(b/2)
|
||||
-- !query 34 schema
|
||||
struct<>
|
||||
-- !query 34 output
|
||||
org.apache.spark.sql.AnalysisException
|
||||
Reference 'b' is ambiguous, could be: x.b, y.b.; line 3 pos 10
|
||||
|
||||
|
||||
-- !query 35
|
||||
SELECT udf(x.b/2), udf(count(udf(x.b))) FROM test_missing_target x,
|
||||
test_missing_target y
|
||||
WHERE udf(x.a) = udf(y.a)
|
||||
GROUP BY x.b/2 ORDER BY udf(x.b/2)
|
||||
-- !query 35 schema
|
||||
struct<CAST(udf(cast((b div 2) as string)) AS INT):int,CAST(udf(cast(count(cast(udf(cast(b as string)) as int)) as string)) AS BIGINT):bigint>
|
||||
-- !query 35 output
|
||||
0 1
|
||||
1 5
|
||||
2 4
|
||||
|
||||
|
||||
-- !query 36
|
||||
SELECT udf(count(udf(b))) FROM test_missing_target x, test_missing_target y
|
||||
WHERE udf(x.a) = udf(y.a)
|
||||
GROUP BY x.b/2
|
||||
-- !query 36 schema
|
||||
struct<>
|
||||
-- !query 36 output
|
||||
org.apache.spark.sql.AnalysisException
|
||||
Reference 'b' is ambiguous, could be: x.b, y.b.; line 1 pos 21
|
||||
|
||||
|
||||
-- !query 37
|
||||
DROP TABLE test_missing_target
|
||||
-- !query 37 schema
|
||||
struct<>
|
||||
-- !query 37 output
|
||||
|
||||
Loading…
Reference in a new issue