Github user HyukjinKwon commented on a diff in the pull request:
https://github.com/apache/spark/pull/23052#discussion_r234062564
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVFileFormat.scala
---
@@ -174,13 +174,18 @@ private[csv] class CsvOutputWriter(
context: TaskAttemptContext,
params: CSVOptions) extends OutputWriter with Logging {
- private val charset = Charset.forName(params.charset)
+ private var univocityGenerator: Option[UnivocityGenerator] = None
- private val writer = CodecStreams.createOutputStreamWriter(context, new
Path(path), charset)
-
- private val gen = new UnivocityGenerator(dataSchema, writer, params)
+ override def write(row: InternalRow): Unit = {
+ val gen = univocityGenerator.getOrElse {
--- End diff --
Also, one thing we should not forget about is, CSV _could_ have headers
even if the records are empty.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
