Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/15562#discussion_r84220232
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetOutputWriter.scala
---
@@ -122,47 +122,29 @@ private[parquet] class ParquetOutputWriterFactory(
}
/** Disable the use of the older API. */
- def newInstance(
+ override def newInstance(
path: String,
- bucketId: Option[Int],
+ fileNamePrefix: String,
dataSchema: StructType,
context: TaskAttemptContext): OutputWriter = {
- throw new UnsupportedOperationException(
- "this version of newInstance not supported for " +
+ throw new UnsupportedOperationException("this version of newInstance
not supported for " +
"ParquetOutputWriterFactory")
}
}
// NOTE: This class is instantiated and used on executor side only, no
need to be serializable.
private[parquet] class ParquetOutputWriter(
- path: String,
- bucketId: Option[Int],
+ stagingDir: String,
+ fileNamePrefix: String,
context: TaskAttemptContext)
extends OutputWriter {
private val recordWriter: RecordWriter[Void, InternalRow] = {
val outputFormat = {
new ParquetOutputFormat[InternalRow]() {
- // Here we override `getDefaultWorkFile` for two reasons:
--- End diff --
why remove this comment?
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
