Github user HyukjinKwon commented on a diff in the pull request:
https://github.com/apache/spark/pull/20959#discussion_r182488630
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVDataSource.scala
---
@@ -161,7 +161,8 @@ object TextInputCSVDataSource extends CSVDataSource {
val firstRow = new
CsvParser(parsedOptions.asParserSettings).parseLine(firstLine)
val caseSensitive =
sparkSession.sessionState.conf.caseSensitiveAnalysis
val header = makeSafeHeader(firstRow, caseSensitive, parsedOptions)
- val tokenRDD = csv.rdd.mapPartitions { iter =>
+ val sampled: Dataset[String] = CSVUtils.sample(csv, parsedOptions)
+ val tokenRDD = sampled.rdd.mapPartitions { iter =>
--- End diff --
wait .. does this work when `multiLine` is enabled?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
