MaxGekk commented on a change in pull request #27366:
URL: https://github.com/apache/spark/pull/27366#discussion_r443664813
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonParser.scala
##########
@@ -375,15 +378,19 @@ class JacksonParser(
private def convertObject(
parser: JsonParser,
schema: StructType,
- fieldConverters: Array[ValueConverter]): InternalRow = {
+ fieldConverters: Array[ValueConverter],
+ structFilters: StructFilters = new NoopFilters()): Option[InternalRow] =
{
val row = new GenericInternalRow(schema.length)
var badRecordException: Option[Throwable] = None
+ var skipRow = false
- while (nextUntil(parser, JsonToken.END_OBJECT)) {
+ structFilters.reset()
+ while (!skipRow && nextUntil(parser, JsonToken.END_OBJECT)) {
schema.getFieldIndex(parser.getCurrentName) match {
case Some(index) =>
try {
row.update(index, fieldConverters(index).apply(parser))
+ skipRow = structFilters.skipRow(row, index)
} catch {
case e: SparkUpgradeException => throw e
case NonFatal(e) =>
Review comment:
> Do we always have Filter on top of Json scan operator to catch them?
As far as I know yes, we do.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
