Github user gatorsmile commented on a diff in the pull request:
https://github.com/apache/spark/pull/21657#discussion_r202528391
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/UnivocityParser.scala
---
@@ -197,15 +202,21 @@ class UnivocityParser(
*/
def parse(input: String): InternalRow = doParse(input)
+ private val getToken = if (options.columnPruning) {
+ (tokens: Array[String], index: Int) => tokens(index)
+ } else {
+ (tokens: Array[String], index: Int) => tokens(tokenIndexArr(index))
+ }
+
private def convert(tokens: Array[String]): InternalRow = {
- if (tokens.length != schema.length) {
+ if (tokens.length != parsedSchema.length) {
--- End diff --
If possible, could you add a test case that satisfy `tokens.length !=
parsedSchema.length`
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
