Github user davies commented on a diff in the pull request:
https://github.com/apache/spark/pull/11509#discussion_r55117300
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/ResolvedDataSource.scala
---
@@ -278,26 +298,61 @@ object ResolvedDataSource extends Logging {
val equality = columnNameEquality(caseSensitive)
val dataSchema = StructType(
data.schema.filterNot(f => partitionColumns.exists(equality(_,
f.name))))
- val r = dataSource.createRelation(
- sqlContext,
- Array(outputPath.toString),
- Some(dataSchema.asNullable),
- Some(partitionColumnsSchema(data.schema, partitionColumns,
caseSensitive)),
- bucketSpec,
- caseInsensitiveOptions)
+
+ // If we are appending to a table that already exists, make sure
the partitioning matches
+ // up. If we fail to load the table for whatever reason, ignore
the check.
+ if (mode == SaveMode.Append) {
+ val existingPartitionColumnSet = try {
+ val resolved = apply(
+ sqlContext,
+ userSpecifiedSchema = Some(data.schema.asNullable),
+ provider = provider,
+ options = options)
+
+ Some(resolved.relation
+ .asInstanceOf[HadoopFsRelation]
+ .location
+ .partitionSpec(None)
+ .partitionColumns
+ .fieldNames
+ .toSet)
+ } catch {
+ case e: Exception =>
+ None
+ }
+
+ existingPartitionColumnSet.foreach { ex =>
+ if (ex.map(_.toLowerCase) !=
partitionColumns.map(_.toLowerCase()).toSet) {
+ throw new AnalysisException(s"$ex ${partitionColumns.toSet}")
--- End diff --
Could you make this error message more readable?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
