dtenedor commented on a change in pull request #35735:
URL: https://github.com/apache/spark/pull/35735#discussion_r821251789
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala
##########
@@ -3562,6 +3562,18 @@ object SQLConf {
.booleanConf
.createWithDefault(false)
+ val HISTOGRAM_NUMERIC_PROPAGATE_INPUT_TYPE =
+ buildConf("spark.sql.legacy.histogramNumericPropagateInputType")
+ .internal()
+ .doc("The histogram_numeric function computes a histogram on numeric
'expr' using nb bins. " +
+ "The return value is an array of (x,y) pairs representing the centers
of the histogram's " +
+ "bins. If this config is set to true, the output type of the 'x' field
in the return " +
+ "value is propagated from the input value consumed in the aggregate
function. Otherwise, " +
+ "'x' always has double type.")
+ .version("3.4.0")
+ .booleanConf
+ .createWithDefault(true)
Review comment:
Done.
##########
File path: sql/core/src/test/resources/sql-tests/inputs/group-by.sql
##########
@@ -211,6 +211,27 @@ FROM VALUES
(31), (32), (33), (34), (35), (3), (37), (38), (39), (40),
(41), (42), (43), (44), (45), (46), (47), (48), (49), (50) AS tab(col);
+-- Histogram aggregates with different numeric input types
+SELECT histogram_numeric(col, 3) FROM VALUES (1), (2), (3) AS tab(col);
+SELECT histogram_numeric(col, 3) FROM VALUES (1L), (2L), (3L) AS tab(col);
+SELECT histogram_numeric(col, 3) FROM VALUES (1F), (2F), (3F) AS tab(col);
+SELECT histogram_numeric(col, 3) FROM VALUES (1D), (2D), (3D) AS tab(col);
+SELECT histogram_numeric(col, 3) FROM VALUES (1S), (2S), (3S) AS tab(col);
+SELECT histogram_numeric(col, 3) FROM VALUES
+ (CAST(1 AS BYTE)), (CAST(2 AS BYTE)), (CAST(3 AS BYTE)) AS tab(col);
+SELECT histogram_numeric(col, 3) FROM VALUES
+ (CAST(1 AS TINYINT)), (CAST(2 AS TINYINT)), (CAST(3 AS TINYINT)) AS tab(col);
+SELECT histogram_numeric(col, 3) FROM VALUES
+ (CAST(1 AS SMALLINT)), (CAST(2 AS SMALLINT)), (CAST(3 AS SMALLINT)) AS
tab(col);
+SELECT histogram_numeric(col, 3) FROM VALUES
+ (CAST(1 AS BIGINT)), (CAST(2 AS BIGINT)), (CAST(3 AS BIGINT)) AS tab(col);
+SELECT histogram_numeric(col, 3) FROM VALUES (TIMESTAMP '2017-03-01 00:00:00'),
+ (TIMESTAMP '2017-04-01 00:00:00'), (TIMESTAMP '2017-05-01 00:00:00') AS
tab(col);
+SELECT histogram_numeric(col, 3) FROM VALUES (INTERVAL '100-00' YEAR TO MONTH),
+ (INTERVAL '110-00' YEAR TO MONTH), (INTERVAL '120-00' YEAR TO MONTH) AS
tab(col);
+SELECT histogram_numeric(col, 3) FROM VALUES (INTERVAL '12 20:4:0' DAY TO
SECOND),
+ (INTERVAL '12 21:4:0' DAY TO SECOND), (INTERVAL '12 22:4:0' DAY TO SECOND)
AS tab(col);
Review comment:
Done.
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
