cshuo commented on code in PR #14351:
URL: https://github.com/apache/hudi/pull/14351#discussion_r2563679488
##########
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/cdc/InternalRowToJsonStringConverter.scala:
##########
@@ -36,15 +37,63 @@ class InternalRowToJsonStringConverter(schema: StructType) {
}
def convert(record: InternalRow): UTF8String = {
- val map = scala.collection.mutable.Map.empty[String, Any]
+ // Use LinkedHashMap to preserve field order
+ val map = scala.collection.mutable.LinkedHashMap.empty[String, Any]
schema.zipWithIndex.foreach {
case (field, idx) =>
- if (field.dataType.isInstanceOf[StringType]) {
- map(field.name) =
Option(record.getUTF8String(idx)).map(_.toString).orNull
- } else {
- map(field.name) = record.get(idx, field.dataType)
- }
+ map(field.name) = convertField(record.get(idx, field.dataType),
field.dataType)
}
UTF8String.fromString(mapper.writeValueAsString(map))
}
+
+ private def convertField(value: Any, dataType: DataType): Any = {
+ if (value == null) {
+ null
+ } else {
+ dataType match {
+ case StringType => value.toString
Review Comment:
yeah, we can simply use `record.get(idx, field.dataType)`, and result is
Utf8String if the field type is STRING.
--
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]
