Skip to content

[SPARK-28279][SQL][PYTHON][TESTS] Convert and port 'group-analytics.sql' into UDF test base #25196

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
skonto wants to merge 1 commit into from
Closed

[SPARK-28279][SQL][PYTHON][TESTS] Convert and port 'group-analytics.sql' into UDF test base #25196

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
64 changes: 64 additions & 0 deletions sql/core/src/test/resources/sql-tests/inputs/udf/udf-group-analytics.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,64 @@
-- This test file was converted from group-analytics.sql.
-- TODO: UDF should be inserted and tested at GROUP BY clause after SPARK-28445
CREATE OR REPLACE TEMPORARY VIEW testData AS SELECT * FROM VALUES
(1, 1), (1, 2), (2, 1), (2, 2), (3, 1), (3, 2)
AS testData(a, b);

-- CUBE on overlapping columns
SELECT a + b, b, udf(SUM(a - b)) FROM testData GROUP BY a + b, b WITH CUBE;

SELECT a, udf(b), SUM(b) FROM testData GROUP BY a, b WITH CUBE;

-- ROLLUP on overlapping columns
SELECT udf(a + b), b, SUM(a - b) FROM testData GROUP BY a + b, b WITH ROLLUP;

SELECT a, b, udf(SUM(b)) FROM testData GROUP BY a, b WITH ROLLUP;

CREATE OR REPLACE TEMPORARY VIEW courseSales AS SELECT * FROM VALUES
("dotNET", 2012, 10000), ("Java", 2012, 20000), ("dotNET", 2012, 5000), ("dotNET", 2013, 48000), ("Java", 2013, 30000)
AS courseSales(course, year, earnings);

-- ROLLUP
SELECT course, year, SUM(earnings) FROM courseSales GROUP BY ROLLUP(course, year) ORDER BY udf(course), year;

-- CUBE
SELECT course, year, SUM(earnings) FROM courseSales GROUP BY CUBE(course, year) ORDER BY course, udf(year);

-- GROUPING SETS
SELECT course, udf(year), SUM(earnings) FROM courseSales GROUP BY course, year GROUPING SETS(course, year);
SELECT course, year, udf(SUM(earnings)) FROM courseSales GROUP BY course, year GROUPING SETS(course);
SELECT udf(course), year, SUM(earnings) FROM courseSales GROUP BY course, year GROUPING SETS(year);

-- GROUPING SETS with aggregate functions containing groupBy columns
SELECT course, udf(SUM(earnings)) AS sum FROM courseSales
GROUP BY course, earnings GROUPING SETS((), (course), (course, earnings)) ORDER BY course, udf(sum);
SELECT course, SUM(earnings) AS sum, GROUPING_ID(course, earnings) FROM courseSales
GROUP BY course, earnings GROUPING SETS((), (course), (course, earnings)) ORDER BY udf(course), sum;

-- GROUPING/GROUPING_ID
SELECT udf(course), udf(year), GROUPING(course), GROUPING(year), GROUPING_ID(course, year) FROM courseSales
GROUP BY CUBE(course, year);
SELECT course, udf(year), GROUPING(course) FROM courseSales GROUP BY course, year;
SELECT course, udf(year), GROUPING_ID(course, year) FROM courseSales GROUP BY course, year;
SELECT course, year, grouping__id FROM courseSales GROUP BY CUBE(course, year) ORDER BY grouping__id, course, udf(year);

-- GROUPING/GROUPING_ID in having clause
SELECT course, year FROM courseSales GROUP BY CUBE(course, year)
HAVING GROUPING(year) = 1 AND GROUPING_ID(course, year) > 0 ORDER BY course, udf(year);
SELECT course, udf(year) FROM courseSales GROUP BY course, year HAVING GROUPING(course) > 0;
SELECT course, udf(udf(year)) FROM courseSales GROUP BY course, year HAVING GROUPING_ID(course) > 0;
SELECT udf(course), year FROM courseSales GROUP BY CUBE(course, year) HAVING grouping__id > 0;

-- GROUPING/GROUPING_ID in orderBy clause
SELECT course, year, GROUPING(course), GROUPING(year) FROM courseSales GROUP BY CUBE(course, year)
ORDER BY GROUPING(course), GROUPING(year), course, udf(year);
SELECT course, year, GROUPING_ID(course, year) FROM courseSales GROUP BY CUBE(course, year)
ORDER BY GROUPING(course), GROUPING(year), course, udf(year);
SELECT course, udf(year) FROM courseSales GROUP BY course, udf(year) ORDER BY GROUPING(course);
SELECT course, udf(year) FROM courseSales GROUP BY course, udf(year) ORDER BY GROUPING_ID(course);
SELECT course, year FROM courseSales GROUP BY CUBE(course, year) ORDER BY grouping__id, udf(course), year;

-- Aliases in SELECT could be used in ROLLUP/CUBE/GROUPING SETS
SELECT udf(a + b) AS k1, udf(b) AS k2, SUM(a - b) FROM testData GROUP BY CUBE(k1, k2);
SELECT udf(udf(a + b)) AS k, b, SUM(a - b) FROM testData GROUP BY ROLLUP(k, b);
SELECT udf(a + b), udf(udf(b)) AS k, SUM(a - b) FROM testData GROUP BY a + b, k GROUPING SETS(k)
Loading