bryanck commented on code in PR #17499:
URL: https://github.com/apache/iceberg/pull/17499#discussion_r3754537825
##########
spark/v4.1/spark-extensions/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveViews.scala:
##########
@@ -111,16 +119,72 @@ case class ResolveViews(spark: SparkSession) extends
Rule[LogicalPlan] with Look
// Apply the field aliases and column comments
// This logic differs from how Spark handles views in
SessionCatalog.fromCatalogTable.
- // This is more strict because it doesn't allow resolution by field name.
+ // BINDING is more strict because it doesn't allow resolution by field
name. COMPENSATION and
+ // TYPE_EVOLUTION coerce as SessionCatalog.castColToType does for those
modes. Every mode keeps
+ // the stored name and metadata; only the coercion differs.
+ val mode = viewSchemaMode
val aliases = view.schema.fields.zipWithIndex.map { case (expected, pos) =>
val attr = GetColumnByOrdinal(pos, expected.dataType)
- Alias(UpCast(attr, expected.dataType), expected.name)(explicitMetadata =
- Some(expected.metadata))
+ val coerced =
+ if (mode == SparkSQLProperties.VIEW_SCHEMA_MODE_COMPENSATION) {
+ Cast(attr, expected.dataType, ansiEnabled = true)
+ } else if (mode == SparkSQLProperties.VIEW_SCHEMA_MODE_TYPE_EVOLUTION)
{
+ attr
+ } else {
+ UpCast(attr, expected.dataType)
+ }
+ Alias(coerced, expected.name)(explicitMetadata = Some(expected.metadata))
}.toIndexedSeq
SubqueryAlias(nameParts, Project(aliases, rewritten))
}
+ /**
+ * How a view's stored schema is applied to the columns its SQL produces.
+ *
+ * Read on every resolution rather than cached, so that SET takes effect
within a session.
+ */
+ private def viewSchemaMode: String = {
+ spark.conf.getOption(SparkSQLProperties.VIEW_SCHEMA_BINDING_MODE) match {
+ case Some(mode) =>
+ parseSchemaBindingMode(mode)
+ case None =>
+ // Mirror SessionCatalog.castColToType: turning binding mode off
selects SchemaUnsupported,
+ // which compensates with an ANSI cast unless compensation is turned
off as well. Neither conf
+ // can select TYPE_EVOLUTION: in Spark that mode is requested per
view, with
+ // CREATE or ALTER VIEW ... WITH SCHEMA TYPE EVOLUTION, and stored on
the view itself.
Review Comment:
Some of the comments are pretty verbose, are there opportunities to make
them more concise?
--
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]
