Github user rxin commented on a diff in the pull request:
https://github.com/apache/spark/pull/14279#discussion_r75196399
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVRelation.scala
---
@@ -204,18 +213,50 @@ private[csv] class CsvOutputWriter(
private var records: Long = 0L
private val csvWriter = new LineCsvWriter(params,
dataSchema.fieldNames.toSeq)
- private def rowToString(row: Seq[Any]): Seq[String] = row.map { field =>
- if (field != null) {
- field.toString
- } else {
- params.nullValue
+ private def rowToString(row: InternalRow): Seq[String] = {
+ var i = 0
+ val values = new Array[String](row.numFields)
+ while (i < row.numFields) {
+ if (!row.isNullAt(i)) {
+ values(i) = valueConverters(i).apply(row, i)
+ } else {
+ values(i) = params.nullValue
+ }
+ i += 1
}
+ values
+ }
+
+ private def makeConverter(dataType: DataType): ValueConverter = dataType
match {
+ case DateType if params.dateFormat != null =>
--- End diff --
why not consolidate the two cases and always use params.dateFormat?
---
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]
