cloud-fan commented on code in PR #46280:
URL: https://github.com/apache/spark/pull/46280#discussion_r1603399289
##########
sql/api/src/main/scala/org/apache/spark/sql/types/DataType.scala:
##########
@@ -208,22 +206,35 @@ object DataType {
}
// NOTE: Map fields must be sorted in alphabetical order to keep consistent
with the Python side.
- private[sql] def parseDataType(json: JValue): DataType = json match {
+ private[sql] def parseDataType(
+ json: JValue,
+ fieldPath: String = "",
+ collationsMap: Map[String, String] = Map.empty): DataType = json match {
case JString(name) =>
- nameToType(name)
+ collationsMap.get(fieldPath) match {
+ case Some(collation) =>
+ assertValidTypeForCollations(fieldPath, name, collationsMap)
+ stringTypeWithCollation(collation)
+ case _ => nameToType(name)
+ }
case JSortedObject(
("containsNull", JBool(n)),
("elementType", t: JValue),
("type", JString("array"))) =>
- ArrayType(parseDataType(t), n)
+ assertValidTypeForCollations(fieldPath, "array", collationsMap)
+ val elementType = parseDataTypeWithCollation(t, fieldPath + ".element",
collationsMap)
+ ArrayType(elementType, n)
case JSortedObject(
("keyType", k: JValue),
("type", JString("map")),
("valueContainsNull", JBool(n)),
("valueType", v: JValue)) =>
- MapType(parseDataType(k), parseDataType(v), n)
+ assertValidTypeForCollations(fieldPath, "map", collationsMap)
+ val keyType = parseDataTypeWithCollation(k, fieldPath + ".key",
collationsMap)
+ val valueType = parseDataTypeWithCollation(v, fieldPath + ".value",
collationsMap)
Review Comment:
why do we need `parseDataTypeWithCollation`? It looks correct to just call
`parseDataType`.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
