[SPARK-19488][SQL] fix csv infer schema when the field is Nan/Inf etc

## What changes were proposed in this pull request?

when csv infer schema, it does not use user defined csvoptions to parse the field, such as `inf`, `-inf` which are should be parsed to DoubleType

this pr add  `options.nanValue`, `options.negativeInf`, `options.positiveIn`  to check if the field is a DoubleType

## How was this patch tested?
unit test added

Author: windpiger <songjun@outlook.com>

Closes #16834 from windpiger/fixinferInfSchemaCsv.

1 files changed, 5 insertions, 1 deletions

diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVInferSchema.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVInferSchema.scala
index 485b186c7c..3fa30fe240 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVInferSchema.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVInferSchema.scala
@@ -150,6 +150,10 @@ private[csv] object CSVInferSchema {
     }
   }
 
+  private def isInfOrNan(field: String, options: CSVOptions): Boolean = {
+    field == options.nanValue || field == options.negativeInf || field == options.positiveInf
+  }
+
   private def tryParseInteger(field: String, options: CSVOptions): DataType = {
     if ((allCatch opt field.toInt).isDefined) {
       IntegerType
@@ -185,7 +189,7 @@ private[csv] object CSVInferSchema {
   }
 
   private def tryParseDouble(field: String, options: CSVOptions): DataType = {
-    if ((allCatch opt field.toDouble).isDefined) {
+    if ((allCatch opt field.toDouble).isDefined || isInfOrNan(field, options)) {
       DoubleType
     } else {
       tryParseTimestamp(field, options)