Repository: spark Updated Branches: refs/heads/master b1f3a489e -> 50d3242d6
[SPARK-8356] [SQL] Reconcile callUDF and callUdf Deprecates ```callUdf``` in favor of ```callUDF```. Author: BenFradet <benjamin.fra...@gmail.com> Closes #6902 from BenFradet/SPARK-8356 and squashes the following commits: ef4e9d8 [BenFradet] deprecated callUDF, use udf instead 9b1de4d [BenFradet] reinstated unit test for the deprecated callUdf cbd80a5 [BenFradet] deprecated callUdf in favor of callUDF Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/50d3242d Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/50d3242d Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/50d3242d Branch: refs/heads/master Commit: 50d3242d6a5530a51dacab249e3f3d49e2d50635 Parents: b1f3a48 Author: BenFradet <benjamin.fra...@gmail.com> Authored: Mon Jun 22 15:06:47 2015 -0700 Committer: Michael Armbrust <mich...@databricks.com> Committed: Mon Jun 22 15:06:47 2015 -0700 ---------------------------------------------------------------------- .../scala/org/apache/spark/sql/functions.scala | 45 ++++++++++++++++++++ .../org/apache/spark/sql/DataFrameSuite.scala | 11 ++++- 2 files changed, 55 insertions(+), 1 deletion(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/50d3242d/sql/core/src/main/scala/org/apache/spark/sql/functions.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/functions.scala b/sql/core/src/main/scala/org/apache/spark/sql/functions.scala index 7e7a099..8cea826 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/functions.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/functions.scala @@ -1448,7 +1448,9 @@ 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)) }""") @@ -1584,7 +1586,9 @@ 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()) } @@ -1595,7 +1599,9 @@ 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)) } @@ -1606,7 +1612,9 @@ 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)) } @@ -1617,7 +1625,9 @@ 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)) } @@ -1628,7 +1638,9 @@ 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)) } @@ -1639,7 +1651,9 @@ 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)) } @@ -1650,7 +1664,9 @@ 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)) } @@ -1661,7 +1677,9 @@ 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)) } @@ -1672,7 +1690,9 @@ 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)) } @@ -1683,7 +1703,9 @@ 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)) } @@ -1694,7 +1716,9 @@ 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: 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)) } @@ -1710,12 +1734,33 @@ object functions { * 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", $"value")) + * }}} + * + * @group udf_funcs + * @since 1.5.0 + */ + def callUDF(udfName: String, cols: Column*): Column = { + UnresolvedFunction(udfName, cols.map(_.expr)) + } + + /** + * Call an user-defined function. + * Example: + * {{{ + * import org.apache.spark.sql._ + * + * val df = Seq(("id1", 1), ("id2", 4), ("id3", 5)).toDF("id", "value") + * val sqlContext = df.sqlContext + * sqlContext.udf.register("simpleUdf", (v: Int) => v * v) * df.select($"id", callUdf("simpleUdf", $"value")) * }}} * * @group udf_funcs * @since 1.4.0 + * @deprecated As of 1.5.0, since it was not coherent to have two functions callUdf and callUDF */ + @deprecated("Use callUDF", "1.5.0") def callUdf(udfName: String, cols: Column*): Column = { UnresolvedFunction(udfName, cols.map(_.expr)) } http://git-wip-us.apache.org/repos/asf/spark/blob/50d3242d/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala index ba1d020..47443a9 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala @@ -301,7 +301,7 @@ class DataFrameSuite extends QueryTest { ) } - test("call udf in SQLContext") { + test("deprecated callUdf in SQLContext") { val df = Seq(("id1", 1), ("id2", 4), ("id3", 5)).toDF("id", "value") val sqlctx = df.sqlContext sqlctx.udf.register("simpleUdf", (v: Int) => v * v) @@ -310,6 +310,15 @@ class DataFrameSuite extends QueryTest { Row("id1", 1) :: Row("id2", 16) :: Row("id3", 25) :: Nil) } + test("callUDF in SQLContext") { + val df = Seq(("id1", 1), ("id2", 4), ("id3", 5)).toDF("id", "value") + val sqlctx = df.sqlContext + sqlctx.udf.register("simpleUDF", (v: Int) => v * v) + checkAnswer( + df.select($"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( --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org