cloud-fan commented on a change in pull request #30869:
URL: https://github.com/apache/spark/pull/30869#discussion_r669668332
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/command/ddl.scala
##########
@@ -933,19 +934,36 @@ object DDLUtils {
case HIVE_PROVIDER =>
val serde = table.storage.serde
if (serde == HiveSerDe.sourceToSerDe("orc").get.serde) {
- OrcFileFormat.checkFieldNames(colNames)
+ checkDataColNames("orc", colNames)
} else if (serde == HiveSerDe.sourceToSerDe("parquet").get.serde ||
serde == Some("parquet.hive.serde.ParquetHiveSerDe") ||
serde ==
Some("org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe")) {
- ParquetSchemaConverter.checkFieldNames(colNames)
+ checkDataColNames("parquet", colNames)
+ } else if (serde == HiveSerDe.sourceToSerDe("avro").get.serde) {
+ checkDataColNames("avro", colNames)
}
- case "parquet" => ParquetSchemaConverter.checkFieldNames(colNames)
- case "orc" => OrcFileFormat.checkFieldNames(colNames)
+ case provider if Seq("parquet", "orc", "avro").contains(provider) =>
Review comment:
why do we limit to only these 3 file sources?
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
