AngersZhuuuu commented on a change in pull request #34337:
URL: https://github.com/apache/spark/pull/34337#discussion_r739668516
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/FilePartitionReader.scala
##########
@@ -66,17 +64,16 @@ class FilePartitionReader[T](readers:
Iterator[PartitionedFileReader[T]])
case e: SchemaColumnConvertNotSupportedException =>
throw QueryExecutionErrors.unsupportedSchemaColumnConvertError(
currentReader.file.filePath, e.getColumn, e.getLogicalType,
e.getPhysicalType, e)
- case e: ParquetDecodingException =>
- if (e.getCause.isInstanceOf[SparkUpgradeException]) {
- throw e.getCause
- } else if (e.getMessage.contains("Can not read value at")) {
- throw QueryExecutionErrors.cannotReadParquetFilesError(e)
- }
- throw e
case e @ (_: RuntimeException | _: IOException) if ignoreCorruptFiles =>
logWarning(
s"Skipped the rest of the content in the corrupted file:
$currentReader", e)
false
+ case e: Exception =>
Review comment:
> No big deal, but these could be:
>
> ```
> e.getCause match {
> case sue: SparkUpgradeException => throw sue
> case _ => throw ...
> }
> ```
Good Suggestion, updated
--
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]
