Github user maropu commented on a diff in the pull request:
https://github.com/apache/spark/pull/21582#discussion_r195950366
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala
---
@@ -59,6 +59,19 @@ private[sql] object OrcFileFormat {
def checkFieldNames(names: Seq[String]): Unit = {
names.foreach(checkFieldName)
}
+
+ def getQuotedSchemaString(dataType: DataType): String = dataType match {
+ case _: AtomicType => dataType.catalogString
+ case StructType(fields) =>
+ fields.map(f => s"`${f.name}`:${getQuotedSchemaString(f.dataType)}")
+ .mkString("struct<", ",", ">")
+ case ArrayType(elementType, _) =>
+ s"array<${getQuotedSchemaString(elementType)}>"
+ case MapType(keyType, valueType, _) =>
+
s"map<${getQuotedSchemaString(keyType)},${getQuotedSchemaString(valueType)}>"
+ case _ => // UDT and others
+ dataType.catalogString
--- End diff --
We don't need to recursively quote `udt.sqlType`?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
