cloud-fan commented on a change in pull request #35352:
URL: https://github.com/apache/spark/pull/35352#discussion_r833866263
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala
##########
@@ -2943,3 +2943,73 @@ case class Sentences(
copy(str = newFirst, language = newSecond, country = newThird)
}
+
+/**
+ * Splits a given string by a specified delimiter and return splits into a
+ * GenericArrayData.
+ */
+case class StringSplitSQL(
+ str: Expression,
+ delimiter: Expression) extends BinaryExpression with NullIntolerant {
+ override def dataType: DataType = ArrayType(StringType, containsNull = false)
+ override def left: Expression = str
+ override def right: Expression = delimiter
+
+ override def nullSafeEval(string: Any, delimiter: Any): Any = {
+ val strings = string.asInstanceOf[UTF8String].splitSQL(
+ delimiter.asInstanceOf[UTF8String], -1);
+ new GenericArrayData(strings.asInstanceOf[Array[Any]])
+ }
+
+ override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
+ val arrayClass = classOf[GenericArrayData].getName
+ nullSafeCodeGen(ctx, ev, (str, delimiter) => {
+ // Array in java is covariant, so we don't need to cast UTF8String[] to
Object[].
+ s"""${ev.value} = new
$arrayClass($str.splitSQL($delimiter,-1));""".stripMargin
Review comment:
```suggestion
s"${ev.value} = new
$arrayClass($str.splitSQL($delimiter,-1));".stripMargin
```
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala
##########
@@ -2943,3 +2943,73 @@ case class Sentences(
copy(str = newFirst, language = newSecond, country = newThird)
}
+
+/**
+ * Splits a given string by a specified delimiter and return splits into a
+ * GenericArrayData.
+ */
+case class StringSplitSQL(
+ str: Expression,
+ delimiter: Expression) extends BinaryExpression with NullIntolerant {
+ override def dataType: DataType = ArrayType(StringType, containsNull = false)
+ override def left: Expression = str
+ override def right: Expression = delimiter
+
+ override def nullSafeEval(string: Any, delimiter: Any): Any = {
+ val strings = string.asInstanceOf[UTF8String].splitSQL(
+ delimiter.asInstanceOf[UTF8String], -1);
+ new GenericArrayData(strings.asInstanceOf[Array[Any]])
+ }
+
+ override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
+ val arrayClass = classOf[GenericArrayData].getName
+ nullSafeCodeGen(ctx, ev, (str, delimiter) => {
+ // Array in java is covariant, so we don't need to cast UTF8String[] to
Object[].
+ s"""${ev.value} = new
$arrayClass($str.splitSQL($delimiter,-1));""".stripMargin
Review comment:
```suggestion
s"${ev.value} = new $arrayClass($str.splitSQL($delimiter,-1));"
```
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala
##########
@@ -2943,3 +2943,73 @@ case class Sentences(
copy(str = newFirst, language = newSecond, country = newThird)
}
+
+/**
+ * Splits a given string by a specified delimiter and return splits into a
+ * GenericArrayData.
+ */
+case class StringSplitSQL(
+ str: Expression,
+ delimiter: Expression) extends BinaryExpression with NullIntolerant {
+ override def dataType: DataType = ArrayType(StringType, containsNull = false)
+ override def left: Expression = str
+ override def right: Expression = delimiter
+
+ override def nullSafeEval(string: Any, delimiter: Any): Any = {
+ val strings = string.asInstanceOf[UTF8String].splitSQL(
+ delimiter.asInstanceOf[UTF8String], -1);
+ new GenericArrayData(strings.asInstanceOf[Array[Any]])
+ }
+
+ override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
+ val arrayClass = classOf[GenericArrayData].getName
+ nullSafeCodeGen(ctx, ev, (str, delimiter) => {
+ // Array in java is covariant, so we don't need to cast UTF8String[] to
Object[].
+ s"""${ev.value} = new
$arrayClass($str.splitSQL($delimiter,-1));""".stripMargin
+ })
+ }
+
+ override def withNewChildrenInternal(
+ newFirst: Expression, newSecond: Expression): StringSplitSQL =
Review comment:
```suggestion
newFirst: Expression, newSecond: Expression): StringSplitSQL =
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
