cloud-fan commented on a change in pull request #26656: [SPARK-27986][SQL] Support ANSI SQL filter clause for aggregate expression URL: https://github.com/apache/spark/pull/26656#discussion_r360388053
########## File path: sql/core/src/test/resources/sql-tests/inputs/group-by-filter.sql ########## @@ -0,0 +1,156 @@ +-- Test filter clause for aggregate expression. + +-- Test data. +CREATE OR REPLACE TEMPORARY VIEW testData AS SELECT * FROM VALUES +(1, 1), (1, 2), (2, 1), (2, 2), (3, 1), (3, 2), (null, 1), (3, null), (null, null) +AS testData(a, b); + +CREATE OR REPLACE TEMPORARY VIEW EMP AS SELECT * FROM VALUES + (100, "emp 1", date "2005-01-01", 100.00D, 10), + (100, "emp 1", date "2005-01-01", 100.00D, 10), + (200, "emp 2", date "2003-01-01", 200.00D, 10), + (300, "emp 3", date "2002-01-01", 300.00D, 20), + (400, "emp 4", date "2005-01-01", 400.00D, 30), + (500, "emp 5", date "2001-01-01", 400.00D, NULL), + (600, "emp 6 - no dept", date "2001-01-01", 400.00D, 100), + (700, "emp 7", date "2010-01-01", 400.00D, 100), + (800, "emp 8", date "2016-01-01", 150.00D, 70) +AS EMP(id, emp_name, hiredate, salary, dept_id); + +CREATE OR REPLACE TEMPORARY VIEW DEPT AS SELECT * FROM VALUES + (10, "dept 1", "CA"), + (20, "dept 2", "NY"), + (30, "dept 3", "TX"), + (40, "dept 4 - unassigned", "OR"), + (50, "dept 5 - unassigned", "NJ"), + (70, "dept 7", "FL") +AS DEPT(dept_id, dept_name, state); + +-- Aggregate with filter and empty GroupBy expressions. +SELECT a, COUNT(b) FILTER (WHERE a >= 2) FROM testData; +SELECT COUNT(a) FILTER (WHERE a = 1), COUNT(b) FILTER (WHERE a > 1) FROM testData; +SELECT COUNT(id) FILTER (WHERE hiredate = date "2001-01-01") FROM emp; +SELECT COUNT(id) FILTER (WHERE hiredate = to_date('2001-01-01 00:00:00')) FROM emp; +SELECT COUNT(id) FILTER (WHERE hiredate = to_timestamp("2001-01-01 00:00:00")) FROM emp; +SELECT COUNT(id) FILTER (WHERE date_format(hiredate, "yyyy-MM-dd") = "2001-01-01") FROM emp; Review comment: can we test something like `FILTER (WHERE a + b> 3)` ? ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org