Skip to content

[SPARK-8356][SQL] Reconcile callUDF and callUdf #6902

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
wants to merge 3 commits into from
Closed

[SPARK-8356][SQL] Reconcile callUDF and callUdf #6902

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
cbd80a5
deprecated callUdf in favor of callUDF
BenFradet Jun 17, 2015
9b1de4d
reinstated unit test for the deprecated callUdf
BenFradet Jun 19, 2015
ef4e9d8
deprecated callUDF, use udf instead
BenFradet Jun 22, 2015
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
45 changes: 45 additions & 0 deletions sql/core/src/main/scala/org/apache/spark/sql/functions.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1385,7 +1385,9 @@ object functions {
*
* @group udf_funcs
* @since 1.3.0
* @deprecated As of 1.5.0, since it's redundant with udf()
*/
@deprecated("Use udf", "1.5.0")
def callUDF(f: Function$x[$fTypes], returnType: DataType${if (args.length > 0) ", " + args else ""}): Column = {
ScalaUdf(f, returnType, Seq($argsInUdf))
}""")
Expand Down Expand Up @@ -1521,7 +1523,9 @@ object functions {
*
* @group udf_funcs
* @since 1.3.0
* @deprecated As of 1.5.0, since it's redundant with udf()
*/
@deprecated("Use udf", "1.5.0")
def callUDF(f: Function0[_], returnType: DataType): Column = {
ScalaUdf(f, returnType, Seq())
}
Expand All @@ -1532,7 +1536,9 @@ object functions {
*
* @group udf_funcs
* @since 1.3.0
* @deprecated As of 1.5.0, since it's redundant with udf()
*/
@deprecated("Use udf", "1.5.0")
def callUDF(f: Function1[_, _], returnType: DataType, arg1: Column): Column = {
ScalaUdf(f, returnType, Seq(arg1.expr))
}
Expand All @@ -1543,7 +1549,9 @@ object functions {
*
* @group udf_funcs
* @since 1.3.0
* @deprecated As of 1.5.0, since it's redundant with udf()
*/
@deprecated("Use udf", "1.5.0")
def callUDF(f: Function2[_, _, _], returnType: DataType, arg1: Column, arg2: Column): Column = {
ScalaUdf(f, returnType, Seq(arg1.expr, arg2.expr))
}
Expand All @@ -1554,7 +1562,9 @@ object functions {
*
* @group udf_funcs
* @since 1.3.0
* @deprecated As of 1.5.0, since it's redundant with udf()
*/
@deprecated("Use udf", "1.5.0")
def callUDF(f: Function3[_, _, _, _], returnType: DataType, arg1: Column, arg2: Column, arg3: Column): Column = {
ScalaUdf(f, returnType, Seq(arg1.expr, arg2.expr, arg3.expr))
}
Expand All @@ -1565,7 +1575,9 @@ object functions {
*
* @group udf_funcs
* @since 1.3.0
* @deprecated As of 1.5.0, since it's redundant with udf()
*/
@deprecated("Use udf", "1.5.0")
def callUDF(f: Function4[_, _, _, _, _], returnType: DataType, arg1: Column, arg2: Column, arg3: Column, arg4: Column): Column = {
ScalaUdf(f, returnType, Seq(arg1.expr, arg2.expr, arg3.expr, arg4.expr))
}
Expand All @@ -1576,7 +1588,9 @@ object functions {
*
* @group udf_funcs
* @since 1.3.0
* @deprecated As of 1.5.0, since it's redundant with udf()
*/
@deprecated("Use udf", "1.5.0")
def callUDF(f: Function5[_, _, _, _, _, _], returnType: DataType, arg1: Column, arg2: Column, arg3: Column, arg4: Column, arg5: Column): Column = {
ScalaUdf(f, returnType, Seq(arg1.expr, arg2.expr, arg3.expr, arg4.expr, arg5.expr))
}
Expand All @@ -1587,7 +1601,9 @@ object functions {
*
* @group udf_funcs
* @since 1.3.0
* @deprecated As of 1.5.0, since it's redundant with udf()
*/
@deprecated("Use udf", "1.5.0")
def callUDF(f: Function6[_, _, _, _, _, _, _], returnType: DataType, arg1: Column, arg2: Column, arg3: Column, arg4: Column, arg5: Column, arg6: Column): Column = {
ScalaUdf(f, returnType, Seq(arg1.expr, arg2.expr, arg3.expr, arg4.expr, arg5.expr, arg6.expr))
}
Expand All @@ -1598,7 +1614,9 @@ object functions {
*
* @group udf_funcs
* @since 1.3.0
* @deprecated As of 1.5.0, since it's redundant with udf()
*/
@deprecated("Use udf", "1.5.0")
def callUDF(f: Function7[_, _, _, _, _, _, _, _], returnType: DataType, arg1: Column, arg2: Column, arg3: Column, arg4: Column, arg5: Column, arg6: Column, arg7: Column): Column = {
ScalaUdf(f, returnType, Seq(arg1.expr, arg2.expr, arg3.expr, arg4.expr, arg5.expr, arg6.expr, arg7.expr))
}
Expand All @@ -1609,7 +1627,9 @@ object functions {
*
* @group udf_funcs
* @since 1.3.0
* @deprecated As of 1.5.0, since it's redundant with udf()
*/
@deprecated("Use udf", "1.5.0")
def callUDF(f: Function8[_, _, _, _, _, _, _, _, _], returnType: DataType, arg1: Column, arg2: Column, arg3: Column, arg4: Column, arg5: Column, arg6: Column, arg7: Column, arg8: Column): Column = {
ScalaUdf(f, returnType, Seq(arg1.expr, arg2.expr, arg3.expr, arg4.expr, arg5.expr, arg6.expr, arg7.expr, arg8.expr))
}
Expand All @@ -1620,7 +1640,9 @@ object functions {
*
* @group udf_funcs
* @since 1.3.0
* @deprecated As of 1.5.0, since it's redundant with udf()
*/
@deprecated("Use udf", "1.5.0")
def callUDF(f: Function9[_, _, _, _, _, _, _, _, _, _], returnType: DataType, arg1: Column, arg2: Column, arg3: Column, arg4: Column, arg5: Column, arg6: Column, arg7: Column, arg8: Column, arg9: Column): Column = {
ScalaUdf(f, returnType, Seq(arg1.expr, arg2.expr, arg3.expr, arg4.expr, arg5.expr, arg6.expr, arg7.expr, arg8.expr, arg9.expr))
}
Expand All @@ -1631,13 +1653,34 @@ object functions {
*
* @group udf_funcs
* @since 1.3.0
* @deprecated As of 1.5.0, since it's redundant with udf()
*/
@deprecated("Use udf", "1.5.0")
def callUDF(f: Function10[_, _, _, _, _, _, _, _, _, _, _], returnType: DataType, arg1: Column, arg2: Column, arg3: Column, arg4: Column, arg5: Column, arg6: Column, arg7: Column, arg8: Column, arg9: Column, arg10: Column): Column = {
ScalaUdf(f, returnType, Seq(arg1.expr, arg2.expr, arg3.expr, arg4.expr, arg5.expr, arg6.expr, arg7.expr, arg8.expr, arg9.expr, arg10.expr))
}

// scalastyle:on

/**
* Call an user-defined function.
* Example:
* {{{
* import org.apache.spark.sql._
*
* val df = Seq(("id1", 1), ("id2", 4), ("id3", 5)).toDF("id", "value")
* val sqlContext = df.sqlContext
* sqlContext.udf.register("simpleUdf", (v: Int) => v * v)
* df.select($"id", callUDF("simpleUdf", $"value"))
* }}}
*
* @group udf_funcs
* @since 1.5.0
*/
def callUDF(udfName: String, cols: Column*): Column = {
UnresolvedFunction(udfName, cols.map(_.expr))
}

/**
* Call an user-defined function.
* Example:
Expand All @@ -1652,7 +1695,9 @@ object functions {
*
* @group udf_funcs
* @since 1.4.0
* @deprecated As of 1.5.0, since it was not coherent to have two functions callUdf and callUDF
*/
@deprecated("Use callUDF", "1.5.0")
def callUdf(udfName: String, cols: Column*): Column = {
UnresolvedFunction(udfName, cols.map(_.expr))
}
Expand Down
11 changes: 10 additions & 1 deletion sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -301,7 +301,7 @@ class DataFrameSuite extends QueryTest {
)
}

test("call udf in SQLContext") {
test("deprecated callUdf in SQLContext") {
val df = Seq(("id1", 1), ("id2", 4), ("id3", 5)).toDF("id", "value")
val sqlctx = df.sqlContext
sqlctx.udf.register("simpleUdf", (v: Int) => v * v)
Expand All @@ -310,6 +310,15 @@ class DataFrameSuite extends QueryTest {
Row("id1", 1) :: Row("id2", 16) :: Row("id3", 25) :: Nil)
}

test("callUDF in SQLContext") {
val df = Seq(("id1", 1), ("id2", 4), ("id3", 5)).toDF("id", "value")
val sqlctx = df.sqlContext
sqlctx.udf.register("simpleUDF", (v: Int) => v * v)
checkAnswer(
df.select($"id", callUDF("simpleUDF", $"value")),
Row("id1", 1) :: Row("id2", 16) :: Row("id3", 25) :: Nil)
}

test("withColumn") {
val df = testData.toDF().withColumn("newCol", col("key") + 1)
checkAnswer(
Expand Down