Github user felixcheung commented on a diff in the pull request:
https://github.com/apache/spark/pull/17192#discussion_r106794013
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala
---
@@ -624,41 +627,58 @@ case class StructToJson(
lazy val writer = new CharArrayWriter()
@transient
- lazy val gen =
- new JacksonGenerator(
- child.dataType.asInstanceOf[StructType],
- writer,
- new JSONOptions(options, timeZoneId.get))
+ lazy val gen = new JacksonGenerator(
+ rowSchema, writer, new JSONOptions(options, timeZoneId.get))
+
+ @transient
+ lazy val rowSchema = child.dataType match {
+ case st: StructType => st
+ case ArrayType(st: StructType, _) => st
+ }
+
+ // This converts rows to the JSON output according to the given schema.
+ @transient
+ lazy val converter: Any => UTF8String = {
+ def getAndReset(): UTF8String = {
+ gen.flush()
+ val json = writer.toString
+ writer.reset()
+ UTF8String.fromString(json)
+ }
+
+ child.dataType match {
+ case _: StructType =>
+ (row: Any) =>
+ gen.write(row.asInstanceOf[InternalRow])
+ getAndReset()
+ case ArrayType(_: StructType, _) =>
+ (arr: Any) =>
+ gen.write(arr.asInstanceOf[ArrayData])
+ getAndReset()
+ }
+ }
override def dataType: DataType = StringType
- override def checkInputDataTypes(): TypeCheckResult = {
- if (StructType.acceptsType(child.dataType)) {
+ override def checkInputDataTypes(): TypeCheckResult = child.dataType
match {
+ case _: StructType | ArrayType(_: StructType, _) =>
--- End diff --
this seems to become a bit more strict from before?
was: `StructType.acceptsType` - anything can be accepted as struct
now: `match { case _: StructType` - must be struct
am I understand this correctly?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
