Github user liancheng commented on a diff in the pull request:
https://github.com/apache/spark/pull/10498#discussion_r48609296
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/DataFrameWriter.scala ---
@@ -189,13 +205,45 @@ final class DataFrameWriter private[sql](df:
DataFrame) {
ifNotExists = false)).toRdd
}
- private def normalizedParCols: Option[Seq[String]] =
partitioningColumns.map { parCols =>
- parCols.map { col =>
- df.logicalPlan.output
- .map(_.name)
- .find(df.sqlContext.analyzer.resolver(_, col))
- .getOrElse(throw new AnalysisException(s"Partition column $col not
found in existing " +
- s"columns (${df.logicalPlan.output.map(_.name).mkString(",
")})"))
+ private def normalizedParCols: Option[Seq[String]] =
partitioningColumns.map { cols =>
+ cols.map(normalize(_, "Partition"))
+ }
+
+ private def normalizedBucketCols: Option[Seq[String]] =
bucketingColumns.map { cols =>
+ cols.map(normalize(_, "Bucketing"))
+ }
+
+ private def normalizedSortCols: Option[Seq[String]] = sortingColumns.map
{ cols =>
+ cols.map(normalize(_, "Sorting"))
+ }
+
+ private def getBucketSpec: Option[BucketSpec] = {
+ if (numBuckets.isEmpty && sortingColumns.isDefined) {
+ throw new IllegalArgumentException(
+ "Specify bucketing information by bucketBy when use sortBy.")
+ }
+ if (numBuckets.isDefined && numBuckets.get <= 0) {
+ throw new IllegalArgumentException("numBuckets must be greater than
0.")
+ }
+
+ if (numBuckets.isDefined) {
+ Some(BucketSpec(numBuckets.get, normalizedBucketCols.get,
normalizedSortCols))
+ } else {
+ None
+ }
--- End diff --
This method can be simplified to:
```scala
if (sortingColumns.isDefined) {
require(numBuckets.isDefined, "sortBy must be used together with
bucketBy")
}
for {
n <- numBuckets
cols <- normalizedBucketCols
} yield {
require(n > 0, "Bucket number must be greater than 0.")
BucketSpec(n, cols, normalizedSortCols)
}
```
(`require` throws `IllegalArgumentException` when the condition is not met.)
---
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]
