Github user HyukjinKwon commented on a diff in the pull request:
https://github.com/apache/spark/pull/13809#discussion_r67860055
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVRelation.scala
---
@@ -177,38 +180,61 @@ private[sql] class CsvOutputWriter(
}.getRecordWriter(context)
}
- private val FLUSH_BATCH_SIZE = 1024L
- private var records: Long = 0L
- private val csvWriter = new LineCsvWriter(params,
dataSchema.fieldNames.toSeq)
+ private val headers = dataSchema.fieldNames
- private def rowToString(row: Seq[Any]): Seq[String] = row.map { field =>
- if (field != null) {
- field.toString
- } else {
- params.nullValue
- }
+ private[this] val writer = new CharArrayWriter()
+ private[this] val csvWriter = {
+ val writerSettings = new CsvWriterSettings
+ val format = writerSettings.getFormat
+
+ format.setDelimiter(options.delimiter)
+ format.setLineSeparator(options.rowSeparator)
+ format.setQuote(options.quote)
+ format.setQuoteEscape(options.escape)
+ format.setComment(options.comment)
+
+ writerSettings.setNullValue(options.nullValue)
+ writerSettings.setEmptyValue(options.nullValue)
+ writerSettings.setSkipEmptyLines(true)
+ writerSettings.setQuoteAllFields(false)
+ writerSettings.setHeaders(headers: _*)
+ writerSettings.setQuoteEscapingEnabled(options.escapeQuotes)
+
+ new CsvWriter(writer, writerSettings)
--- End diff --
Please let me organise this in a separate class at the PR for refactoring
this.
---
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
