Github user gatorsmile commented on a diff in the pull request:
https://github.com/apache/spark/pull/16898#discussion_r101888508
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormatWriter.scala
---
@@ -119,23 +130,45 @@ object FileFormatWriter extends Logging {
uuid = UUID.randomUUID().toString,
serializableHadoopConf = new
SerializableConfiguration(job.getConfiguration),
outputWriterFactory = outputWriterFactory,
- allColumns = queryExecution.logical.output,
- partitionColumns = partitionColumns,
+ allColumns = allColumns,
dataColumns = dataColumns,
- bucketSpec = bucketSpec,
+ partitionColumns = partitionColumns,
+ bucketIdExpression = bucketIdExpression,
path = outputSpec.outputPath,
customPartitionLocations = outputSpec.customPartitionLocations,
maxRecordsPerFile = options.get("maxRecordsPerFile").map(_.toLong)
.getOrElse(sparkSession.sessionState.conf.maxRecordsPerFile)
)
+ // We should first sort by partition columns, then bucket id, and
finally sorting columns.
+ val requiredOrdering = partitionColumns ++ bucketIdExpression ++
sortColumns
+ // the sort order doesn't matter
+ val actualOrdering =
queryExecution.executedPlan.outputOrdering.map(_.child)
+ val orderingMatched = if (requiredOrdering.length >
actualOrdering.length) {
+ false
+ } else {
+ requiredOrdering.zip(actualOrdering).forall {
+ case (requiredOrder, childOutputOrder) =>
+ requiredOrder.semanticEquals(childOutputOrder)
--- End diff --
Because `bucketIdExpression` is `HashPartitioning`, this will never match,
right?
---
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]
