yaooqinn commented on a change in pull request #33706:
URL: https://github.com/apache/spark/pull/33706#discussion_r687435652
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JsonInferSchema.scala
##########
@@ -68,21 +73,27 @@ private[sql] class JsonInferSchema(options: JSONOptions)
extends Serializable {
Some(inferField(parser))
}
} catch {
- case e @ (_: RuntimeException | _: JsonProcessingException) =>
parseMode match {
- case PermissiveMode =>
- Some(StructType(Seq(StructField(columnNameOfCorruptRecord,
StringType))))
- case DropMalformedMode =>
- None
- case FailFastMode =>
- throw
QueryExecutionErrors.malformedRecordsDetectedInSchemaInferenceError(e)
+ case e @ (_: JsonProcessingException | _: CharConversionException)
+ if ignoreCorruptFiles =>
+ logWarning("Skipped inferring json schema from the corrupted data:
" +
+ s"${row.asInstanceOf[InternalRow].getString(0)}", e)
+ None
+ case e @ (_: RuntimeException | _: JsonProcessingException |
+ _: CharConversionException) =>
Review comment:
thanks, can you take a look again to see if I did get your point
--
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]
