[GitHub] [spark] dongjoon-hyun commented on a change in pull request #24203: [SPARK-27269][SQL] File source v2 should validate data schema only

[GitBox <gi...@apache.org>]

dongjoon-hyun commented on a change in pull request #24203: [SPARK-27269][SQL] File source v2 should validate data schema only
URL: https://github.com/apache/spark/pull/24203#discussion_r268883514
 
 

 ##########
 File path: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/FileTable.scala
 ##########
 @@ -46,17 +46,27 @@ abstract class FileTable(
       sparkSession, rootPathsSpecified, caseSensitiveMap, userSpecifiedSchema, fileStatusCache)
   }
 
-  lazy val dataSchema: StructType = userSpecifiedSchema.orElse {
-    inferSchema(fileIndex.allFiles())
-  }.getOrElse {
-    throw new AnalysisException(
-      s"Unable to infer schema for $name. It must be specified manually.")
-  }.asNullable
+  lazy val dataSchema: StructType = userSpecifiedSchema.map { schema =>
+      val partitionSchema = fileIndex.partitionSchema
+      val equality = sparkSession.sessionState.conf.resolver
+      StructType(schema.filterNot(f => partitionSchema.exists(p => equality(p.name, f.name))))
+    }.orElse {
+      inferSchema(fileIndex.allFiles())
+    }.getOrElse {
+      throw new AnalysisException(
+        s"Unable to infer schema for $name. It must be specified manually.")
+    }.asNullable
 
   override lazy val schema: StructType = {
     val caseSensitive = sparkSession.sessionState.conf.caseSensitiveAnalysis
     SchemaUtils.checkColumnNameDuplication(dataSchema.fieldNames,
       "in the data schema", caseSensitive)
+    dataSchema.foreach { field =>
+      if (!supportsDataType(field.dataType)) {
+        throw new AnalysisException(
+          s"$name data source does not support ${field.dataType.catalogString} data type.")
 
 Review comment:
   Here, `name` is `Table.name`. Previously, this was `formatName`.

----------------------------------------------------------------
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.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org