This is an automated email from the ASF dual-hosted git repository.
maxgekk pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new 9af216d7ac2 [MINOR][SQL] Fix the pretty name of the `AnyValue`
expression
9af216d7ac2 is described below
commit 9af216d7ac26f0ec916833c2e80a01aef8933529
Author: Max Gekk <max.g...@gmail.com>
AuthorDate: Sun Nov 27 10:33:26 2022 +0300
[MINOR][SQL] Fix the pretty name of the `AnyValue` expression
### What changes were proposed in this pull request?
In the PR, I propose to override the `prettyName` method of the `AnyValue`
expression and set to `any_value` by default as in `FunctionRegistry`:
https://github.com/apache/spark/blob/40b7d29e14cfa96984c5b0a231a75b210dd85a7e/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionRegistry.scala#L466
### Why are the changes needed?
To don't confuse users by non-existent function name, and print correct
name in errors.
### Does this PR introduce _any_ user-facing change?
Yes, it could be.
### How was this patch tested?
By running the affected test suite:
```
$ build/sbt "sql/testOnly *ExpressionsSchemaSuite"
```
Closes #38805 from MaxGekk/any_value-pretty-name.
Authored-by: Max Gekk <max.g...@gmail.com>
Signed-off-by: Max Gekk <max.g...@gmail.com>
---
.../apache/spark/sql/catalyst/expressions/aggregate/AnyValue.scala | 4 ++++
sql/core/src/test/resources/sql-functions/sql-expression-schema.md | 2 +-
2 files changed, 5 insertions(+), 1 deletion(-)
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/AnyValue.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/AnyValue.scala
index 47559b90e9c..9fbca1629c9 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/AnyValue.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/AnyValue.scala
@@ -17,6 +17,7 @@
package org.apache.spark.sql.catalyst.expressions.aggregate
+import org.apache.spark.sql.catalyst.analysis.FunctionRegistry
import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.catalyst.trees.UnaryLike
import org.apache.spark.sql.types._
@@ -61,4 +62,7 @@ case class AnyValue(child: Expression, ignoreNulls: Boolean)
override protected def withNewChildInternal(newChild: Expression): AnyValue =
copy(child = newChild)
override def inputTypes: Seq[AbstractDataType] = Seq(AnyDataType,
BooleanType)
+
+ override def prettyName: String =
+ getTagValue(FunctionRegistry.FUNC_ALIAS).getOrElse("any_value")
}
diff --git a/sql/core/src/test/resources/sql-functions/sql-expression-schema.md
b/sql/core/src/test/resources/sql-functions/sql-expression-schema.md
index 482c72679bb..8d47878de15 100644
--- a/sql/core/src/test/resources/sql-functions/sql-expression-schema.md
+++ b/sql/core/src/test/resources/sql-functions/sql-expression-schema.md
@@ -349,7 +349,7 @@
| org.apache.spark.sql.catalyst.expressions.XxHash64 | xxhash64 | SELECT
xxhash64('Spark', array(123), 2) | struct<xxhash64(Spark, array(123),
2):bigint> |
| org.apache.spark.sql.catalyst.expressions.Year | year | SELECT
year('2016-07-30') | struct<year(2016-07-30):int> |
| org.apache.spark.sql.catalyst.expressions.ZipWith | zip_with | SELECT
zip_with(array(1, 2, 3), array('a', 'b', 'c'), (x, y) -> (y, x)) |
struct<zip_with(array(1, 2, 3), array(a, b, c), lambdafunction(named_struct(y,
namedlambdavariable(), x, namedlambdavariable()), namedlambdavariable(),
namedlambdavariable())):array<struct<y:string,x:int>>> |
-| org.apache.spark.sql.catalyst.expressions.aggregate.AnyValue | any_value |
SELECT any_value(col) FROM VALUES (10), (5), (20) AS tab(col) |
struct<anyvalue(col):int> |
+| org.apache.spark.sql.catalyst.expressions.aggregate.AnyValue | any_value |
SELECT any_value(col) FROM VALUES (10), (5), (20) AS tab(col) |
struct<any_value(col):int> |
| org.apache.spark.sql.catalyst.expressions.aggregate.ApproximatePercentile |
approx_percentile | SELECT approx_percentile(col, array(0.5, 0.4, 0.1), 100)
FROM VALUES (0), (1), (2), (10) AS tab(col) | struct<approx_percentile(col,
array(0.5, 0.4, 0.1), 100):array<int>> |
| org.apache.spark.sql.catalyst.expressions.aggregate.ApproximatePercentile |
percentile_approx | SELECT percentile_approx(col, array(0.5, 0.4, 0.1), 100)
FROM VALUES (0), (1), (2), (10) AS tab(col) | struct<percentile_approx(col,
array(0.5, 0.4, 0.1), 100):array<int>> |
| org.apache.spark.sql.catalyst.expressions.aggregate.Average | avg | SELECT
avg(col) FROM VALUES (1), (2), (3) AS tab(col) | struct<avg(col):double> |
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org
For additional commands, e-mail: commits-h...@spark.apache.org
