This is an automated email from the ASF dual-hosted git repository. jmalkin pushed a commit to branch as_binary in repository https://gitbox.apache.org/repos/asf/datasketches-spark.git
commit 3a4e900c9ad30d81866a83b2daec6b37eca0028f Author: Jon <[email protected]> AuthorDate: Thu Mar 27 21:39:56 2025 -0700 rename cast_to_binary to cast_as_binary --- python/src/datasketches_spark/common.py | 2 +- python/tests/kll_test.py | 4 ++-- .../datasketches/common/{CastToBinary.scala => CastAsBinary.scala} | 6 +++--- .../sql/datasketches/common/DatasketchesFunctionRegistry.scala | 2 +- .../scala/org/apache/spark/sql/datasketches/common/functions.scala | 2 +- src/test/scala/org/apache/spark/sql/datasketches/kll/KllTest.scala | 4 ++-- 6 files changed, 10 insertions(+), 10 deletions(-) diff --git a/python/src/datasketches_spark/common.py b/python/src/datasketches_spark/common.py index 31bc935..b0e477d 100644 --- a/python/src/datasketches_spark/common.py +++ b/python/src/datasketches_spark/common.py @@ -132,5 +132,5 @@ def _get_common_functions_class() -> JavaClass: @try_remote_functions -def cast_to_binary(col: "ColumnOrName") -> Column: +def cast_as_binary(col: "ColumnOrName") -> Column: return _invoke_function_over_columns(_get_common_functions_class(), "cast_to_binary", col) diff --git a/python/tests/kll_test.py b/python/tests/kll_test.py index eb115fa..c530580 100644 --- a/python/tests/kll_test.py +++ b/python/tests/kll_test.py @@ -18,7 +18,7 @@ from pyspark.sql.types import StructType, StructField, BinaryType, DoubleType, IntegerType #from datasketches import kll_doubles_sketch -from datasketches_spark.common import cast_to_binary +from datasketches_spark.common import cast_as_binary from datasketches_spark.kll import * def test_kll_build(spark): @@ -48,7 +48,7 @@ def test_kll_build(spark): df_types = df_agg.select( "sketch", - cast_to_binary("sketch").alias("asBinary") + cast_as_binary("sketch").alias("asBinary") ) assert(df_types.schema["sketch"].dataType == KllDoublesSketchUDT()) assert(df_types.schema["asBinary"].dataType == BinaryType()) diff --git a/src/main/scala/org/apache/spark/sql/datasketches/common/CastToBinary.scala b/src/main/scala/org/apache/spark/sql/datasketches/common/CastAsBinary.scala similarity index 94% rename from src/main/scala/org/apache/spark/sql/datasketches/common/CastToBinary.scala rename to src/main/scala/org/apache/spark/sql/datasketches/common/CastAsBinary.scala index 5b51fc8..e8a373a 100644 --- a/src/main/scala/org/apache/spark/sql/datasketches/common/CastToBinary.scala +++ b/src/main/scala/org/apache/spark/sql/datasketches/common/CastAsBinary.scala @@ -27,17 +27,17 @@ import org.apache.spark.sql.catalyst.expressions.codegen.{CodeBlock, CodegenCont _FUNC_(expr) - Returns the input as a BinaryType (Array[Byte]). """ //group = "misc_funcs", ) -case class CastToBinary(sketchExpr: Expression) +case class CastAsBinary(sketchExpr: Expression) extends UnaryExpression with ExpectsInputTypes { override def child: Expression = sketchExpr - override protected def withNewChildInternal(newChild: Expression): CastToBinary = { + override protected def withNewChildInternal(newChild: Expression): CastAsBinary = { copy(sketchExpr = newChild) } - override def prettyName: String = "cast_to_binary" + override def prettyName: String = "cast_as_binary" override def inputTypes: Seq[AbstractDataType] = Seq(AnyDataType) diff --git a/src/main/scala/org/apache/spark/sql/datasketches/common/DatasketchesFunctionRegistry.scala b/src/main/scala/org/apache/spark/sql/datasketches/common/DatasketchesFunctionRegistry.scala index 29207b0..bb0b970 100644 --- a/src/main/scala/org/apache/spark/sql/datasketches/common/DatasketchesFunctionRegistry.scala +++ b/src/main/scala/org/apache/spark/sql/datasketches/common/DatasketchesFunctionRegistry.scala @@ -62,6 +62,6 @@ trait DatasketchesFunctionRegistry { // object for common functions object CommonFunctionRegistry extends DatasketchesFunctionRegistry { override val expressions: Map[String, (ExpressionInfo, FunctionBuilder)] = Map( - expression[CastToBinary]("cast_to_binary"), + expression[CastAsBinary]("cast_to_binary"), ) } diff --git a/src/main/scala/org/apache/spark/sql/datasketches/common/functions.scala b/src/main/scala/org/apache/spark/sql/datasketches/common/functions.scala index ff8fcf0..7150e61 100644 --- a/src/main/scala/org/apache/spark/sql/datasketches/common/functions.scala +++ b/src/main/scala/org/apache/spark/sql/datasketches/common/functions.scala @@ -22,7 +22,7 @@ import org.apache.spark.sql.Column object functions extends DatasketchesScalaFunctionBase { def cast_to_binary(expr: Column): Column = withExpr { - new CastToBinary(expr.expr) + new CastAsBinary(expr.expr) } def sketch_to_binary(columnName: String): Column = { diff --git a/src/test/scala/org/apache/spark/sql/datasketches/kll/KllTest.scala b/src/test/scala/org/apache/spark/sql/datasketches/kll/KllTest.scala index acb8f0d..873fa68 100644 --- a/src/test/scala/org/apache/spark/sql/datasketches/kll/KllTest.scala +++ b/src/test/scala/org/apache/spark/sql/datasketches/kll/KllTest.scala @@ -26,7 +26,7 @@ import org.apache.datasketches.kll.KllDoublesSketch import org.apache.spark.sql.datasketches.kll.functions._ import org.apache.spark.sql.datasketches.kll.types.KllDoublesSketchType import org.apache.spark.sql.datasketches.common.{SparkSessionManager, CommonFunctionRegistry} -import org.apache.spark.sql.datasketches.common.functions.cast_to_binary +import org.apache.spark.sql.datasketches.common.functions.cast_as_binary class KllTest extends SparkSessionManager { import spark.implicits._ @@ -118,7 +118,7 @@ class KllTest extends SparkSessionManager { val cdf_excl = Array[Double](0.2, 0.49, 1.0, 1.0) compareArrays(cdf_excl, pmfCdfResult.getAs[Seq[Double]]("cdf_exclusive").toArray) - val resultSchema = sketchDf.select($"sketch", cast_to_binary($"sketch").as("asBinary")).schema + val resultSchema = sketchDf.select($"sketch", cast_as_binary($"sketch").as("asBinary")).schema assert(resultSchema.apply("sketch").dataType.equals(KllDoublesSketchType)) assert(resultSchema.apply("asBinary").dataType.equals(BinaryType)) } --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
