Skip to content

[SPARK-28275][SQL][PYTHON][TESTS] Convert and port 'count.sql' into UDF test base #25089

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
vinodkc wants to merge 2 commits into from
Closed

[SPARK-28275][SQL][PYTHON][TESTS] Convert and port 'count.sql' into UDF test base #25089

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c7b4c46
sql/core/src/test/resources/sql-tests/inputs/udf/udf-count.sql
vinodkc Jul 10, 2019
b173330
added udf-count.sql.out
vinodkc Jul 10, 2019
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
28 changes: 28 additions & 0 deletions sql/core/src/test/resources/sql-tests/inputs/udf/udf-count.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,28 @@
-- This test file was converted from count.sql
-- Test data.
CREATE OR REPLACE TEMPORARY VIEW testData AS SELECT * FROM VALUES
(1, 1), (1, 2), (2, 1), (1, 1), (null, 2), (1, null), (null, null)
AS testData(a, b);

-- count with single expression
SELECT
udf(count(*)), udf(count(1)), udf(count(null)), udf(count(a)), udf(count(b)), udf(count(a + b)), udf(count((a, b)))
Copy link
Member

@HyukjinKwon HyukjinKwon Jul 10, 2019 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@vinodkc, can make some other conbinations like udf(count(*)), count(udf(a)), udf(count(udf(a)))?

FROM testData;

-- distinct count with single expression
SELECT
udf(count(DISTINCT 1)),
udf(count(DISTINCT null)),
udf(count(DISTINCT a)),
udf(count(DISTINCT b)),
udf(count(DISTINCT (a + b))),
udf(count(DISTINCT (a, b)))
Copy link
Member

@HyukjinKwon HyukjinKwon Jul 10, 2019

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Here too :-)

FROM testData;

-- count with multiple expressions
SELECT udf(count(a, b)), udf(count(b, a)), udf(count(testData.*)) FROM testData;

-- distinct count with multiple expressions
SELECT
udf(count(DISTINCT a, b)), udf(count(DISTINCT b, a)), udf(count(DISTINCT *)), udf(count(DISTINCT testData.*))
FROM testData;
55 changes: 55 additions & 0 deletions sql/core/src/test/resources/sql-tests/results/udf/udf-count.sql.out
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,55 @@
-- Automatically generated by SQLQueryTestSuite
-- Number of queries: 5


-- !query 0
CREATE OR REPLACE TEMPORARY VIEW testData AS SELECT * FROM VALUES
(1, 1), (1, 2), (2, 1), (1, 1), (null, 2), (1, null), (null, null)
AS testData(a, b)
-- !query 0 schema
struct<>
-- !query 0 output



-- !query 1
SELECT
udf(count(*)), udf(count(1)), udf(count(null)), udf(count(a)), udf(count(b)), udf(count(a + b)), udf(count((a, b)))
FROM testData
-- !query 1 schema
struct<udf(count(1)):string,udf(count(1)):string,udf(count(null)):string,udf(count(a)):string,udf(count(b)):string,udf(count((a + b))):string,udf(count(named_struct(a, a, b, b))):string>
-- !query 1 output
7 7 0 5 5 4 7


-- !query 2
SELECT
udf(count(DISTINCT 1)),
udf(count(DISTINCT null)),
udf(count(DISTINCT a)),
udf(count(DISTINCT b)),
udf(count(DISTINCT (a + b))),
udf(count(DISTINCT (a, b)))
FROM testData
-- !query 2 schema
struct<udf(count(distinct 1)):string,udf(count(distinct null)):string,udf(count(distinct a)):string,udf(count(distinct b)):string,udf(count(distinct (a + b))):string,udf(count(distinct named_struct(a, a, b, b))):string>
-- !query 2 output
1 0 2 2 2 6


-- !query 3
SELECT udf(count(a, b)), udf(count(b, a)), udf(count(testData.*)) FROM testData
-- !query 3 schema
struct<udf(count(a, b)):string,udf(count(b, a)):string,udf(count(a, b)):string>
-- !query 3 output
4 4 4


-- !query 4
SELECT
udf(count(DISTINCT a, b)), udf(count(DISTINCT b, a)), udf(count(DISTINCT *)), udf(count(DISTINCT testData.*))
FROM testData
-- !query 4 schema
struct<udf(count(distinct a, b)):string,udf(count(distinct b, a)):string,udf(count(distinct a, b)):string,udf(count(distinct a, b)):string>
-- !query 4 output
3 3 3 3