This is an automated email from the ASF dual-hosted git repository.
wenchen 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 12638b851f3 [SPARK-45418][SQL][PYTHON][CONNECT] Change
current_database() column alias to current_schema()
12638b851f3 is described below
commit 12638b851f37832ed85b63374d7f83dfbb924cd6
Author: Michael Zhang <[email protected]>
AuthorDate: Fri Oct 13 08:21:01 2023 +0800
[SPARK-45418][SQL][PYTHON][CONNECT] Change current_database() column alias
to current_schema()
### What changes were proposed in this pull request?
Change column alias for current_database() to current_schema.
### Why are the changes needed?
To better align with preferred usage of schema rather than database for
three part namespace.
### Does this PR introduce _any_ user-facing change?
Yes, `current_database()` column alias is now `current_schema()`.
### How was this patch tested?
Unit tests pass.
### Was this patch authored or co-authored using generative AI tooling?
No.
Closes #43235 from michaelzhan-db/SPARK-45418.
Authored-by: Michael Zhang <[email protected]>
Signed-off-by: Wenchen Fan <[email protected]>
---
.../function_current_database.explain | 2 +-
.../explain-results/function_current_schema.explain | 2 +-
python/pyspark/sql/functions.py | 20 ++++++++++----------
.../apache/spark/sql/catalyst/expressions/misc.scala | 2 +-
.../resources/sql-functions/sql-expression-schema.md | 4 ++--
.../current_database_catalog.sql.out | 2 +-
.../analyzer-results/sql-session-variables.sql.out | 2 +-
.../results/current_database_catalog.sql.out | 2 +-
8 files changed, 18 insertions(+), 18 deletions(-)
diff --git
a/connector/connect/common/src/test/resources/query-tests/explain-results/function_current_database.explain
b/connector/connect/common/src/test/resources/query-tests/explain-results/function_current_database.explain
index 93dfac524d9..481c0a478c8 100644
---
a/connector/connect/common/src/test/resources/query-tests/explain-results/function_current_database.explain
+++
b/connector/connect/common/src/test/resources/query-tests/explain-results/function_current_database.explain
@@ -1,2 +1,2 @@
-Project [current_database() AS current_database()#0]
+Project [current_schema() AS current_schema()#0]
+- LocalRelation <empty>, [id#0L, a#0, b#0, d#0, e#0, f#0, g#0]
diff --git
a/connector/connect/common/src/test/resources/query-tests/explain-results/function_current_schema.explain
b/connector/connect/common/src/test/resources/query-tests/explain-results/function_current_schema.explain
index 93dfac524d9..481c0a478c8 100644
---
a/connector/connect/common/src/test/resources/query-tests/explain-results/function_current_schema.explain
+++
b/connector/connect/common/src/test/resources/query-tests/explain-results/function_current_schema.explain
@@ -1,2 +1,2 @@
-Project [current_database() AS current_database()#0]
+Project [current_schema() AS current_schema()#0]
+- LocalRelation <empty>, [id#0L, a#0, b#0, d#0, e#0, f#0, g#0]
diff --git a/python/pyspark/sql/functions.py b/python/pyspark/sql/functions.py
index 25958bdf15d..31e5884e9eb 100644
--- a/python/pyspark/sql/functions.py
+++ b/python/pyspark/sql/functions.py
@@ -8719,11 +8719,11 @@ def current_database() -> Column:
Examples
--------
>>> spark.range(1).select(current_database()).show()
- +------------------+
- |current_database()|
- +------------------+
- | default|
- +------------------+
+ +----------------+
+ |current_schema()|
+ +----------------+
+ | default|
+ +----------------+
"""
return _invoke_function("current_database")
@@ -8738,11 +8738,11 @@ def current_schema() -> Column:
--------
>>> import pyspark.sql.functions as sf
>>> spark.range(1).select(sf.current_schema()).show()
- +------------------+
- |current_database()|
- +------------------+
- | default|
- +------------------+
+ +----------------+
+ |current_schema()|
+ +----------------+
+ | default|
+ +----------------+
"""
return _invoke_function("current_schema")
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala
index 4a54ccf4a31..60bf5c603d9 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala
@@ -189,7 +189,7 @@ object AssertTrue {
case class CurrentDatabase() extends LeafExpression with Unevaluable {
override def dataType: DataType = StringType
override def nullable: Boolean = false
- override def prettyName: String = "current_database"
+ override def prettyName: String = "current_schema"
final override val nodePatterns: Seq[TreePattern] = Seq(CURRENT_LIKE)
}
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 1573b5c5608..42907b52cda 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
@@ -98,8 +98,8 @@
| org.apache.spark.sql.catalyst.expressions.CumeDist | cume_dist | SELECT a,
b, cume_dist() OVER (PARTITION BY a ORDER BY b) FROM VALUES ('A1', 2), ('A1',
1), ('A2', 3), ('A1', 1) tab(a, b) | struct<a:string,b:int,cume_dist() OVER
(PARTITION BY a ORDER BY b ASC NULLS FIRST RANGE BETWEEN UNBOUNDED PRECEDING
AND CURRENT ROW):double> |
| org.apache.spark.sql.catalyst.expressions.CurDateExpressionBuilder | curdate
| SELECT curdate() | struct<current_date():date> |
| org.apache.spark.sql.catalyst.expressions.CurrentCatalog | current_catalog |
SELECT current_catalog() | struct<current_catalog():string> |
-| org.apache.spark.sql.catalyst.expressions.CurrentDatabase | current_database
| SELECT current_database() | struct<current_database():string> |
-| org.apache.spark.sql.catalyst.expressions.CurrentDatabase | current_schema |
SELECT current_schema() | struct<current_database():string> |
+| org.apache.spark.sql.catalyst.expressions.CurrentDatabase | current_database
| SELECT current_database() | struct<current_schema():string> |
+| org.apache.spark.sql.catalyst.expressions.CurrentDatabase | current_schema |
SELECT current_schema() | struct<current_schema():string> |
| org.apache.spark.sql.catalyst.expressions.CurrentDate | current_date |
SELECT current_date() | struct<current_date():date> |
| org.apache.spark.sql.catalyst.expressions.CurrentTimeZone | current_timezone
| SELECT current_timezone() | struct<current_timezone():string> |
| org.apache.spark.sql.catalyst.expressions.CurrentTimestamp |
current_timestamp | SELECT current_timestamp() |
struct<current_timestamp():timestamp> |
diff --git
a/sql/core/src/test/resources/sql-tests/analyzer-results/current_database_catalog.sql.out
b/sql/core/src/test/resources/sql-tests/analyzer-results/current_database_catalog.sql.out
index ad72e19b6bb..1a71594f849 100644
---
a/sql/core/src/test/resources/sql-tests/analyzer-results/current_database_catalog.sql.out
+++
b/sql/core/src/test/resources/sql-tests/analyzer-results/current_database_catalog.sql.out
@@ -2,5 +2,5 @@
-- !query
select current_database(), current_schema(), current_catalog()
-- !query analysis
-Project [current_database() AS current_database()#x, current_database() AS
current_database()#x, current_catalog() AS current_catalog()#x]
+Project [current_schema() AS current_schema()#x, current_schema() AS
current_schema()#x, current_catalog() AS current_catalog()#x]
+- OneRowRelation
diff --git
a/sql/core/src/test/resources/sql-tests/analyzer-results/sql-session-variables.sql.out
b/sql/core/src/test/resources/sql-tests/analyzer-results/sql-session-variables.sql.out
index ff645867415..ee6bb1559a2 100644
---
a/sql/core/src/test/resources/sql-tests/analyzer-results/sql-session-variables.sql.out
+++
b/sql/core/src/test/resources/sql-tests/analyzer-results/sql-session-variables.sql.out
@@ -776,7 +776,7 @@ Project [NULL AS Expected#x,
variablereference(system.session.var1=CAST(NULL AS
-- !query
DECLARE OR REPLACE VARIABLE var1 STRING DEFAULT CURRENT_DATABASE()
-- !query analysis
-CreateVariable defaultvalueexpression(cast(current_database() as string),
CURRENT_DATABASE()), true
+CreateVariable defaultvalueexpression(cast(current_schema() as string),
CURRENT_DATABASE()), true
+- ResolvedIdentifier
org.apache.spark.sql.catalyst.analysis.FakeSystemCatalog$@xxxxxxxx, session.var1
diff --git
a/sql/core/src/test/resources/sql-tests/results/current_database_catalog.sql.out
b/sql/core/src/test/resources/sql-tests/results/current_database_catalog.sql.out
index 379bf01e645..67db0adee7f 100644
---
a/sql/core/src/test/resources/sql-tests/results/current_database_catalog.sql.out
+++
b/sql/core/src/test/resources/sql-tests/results/current_database_catalog.sql.out
@@ -2,6 +2,6 @@
-- !query
select current_database(), current_schema(), current_catalog()
-- !query schema
-struct<current_database():string,current_database():string,current_catalog():string>
+struct<current_schema():string,current_schema():string,current_catalog():string>
-- !query output
default default spark_catalog
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
