Github user HyukjinKwon commented on a diff in the pull request:
https://github.com/apache/spark/pull/13912#discussion_r71124928
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVRelation.scala
---
@@ -195,18 +202,40 @@ private[sql] 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) = fieldsConverters(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 =>
+ (row: InternalRow, ordinal: Int) =>
+
params.dateFormat.format(DateTimeUtils.toJavaDate(row.getInt(ordinal)))
+
+ case TimestampType if params.dateFormat != null =>
+ (row: InternalRow, ordinal: Int) =>
+
params.dateFormat.format(DateTimeUtils.toJavaTimestamp(row.getLong(ordinal)))
--- End diff --
This was merged before [here](https://github.com/apache/spark/pull/11550)
but `timezone` was not concerned.
So, this PR adds the support for..
- `timezone` for both reading and writing
- `dateFormat` for writing.
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
