aokolnychyi commented on a change in pull request #26751: [SPARK-30107][SQL] Expose nested schema pruning to all V2 sources URL: https://github.com/apache/spark/pull/26751#discussion_r356795707
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/FileScanBuilder.scala ########## @@ -27,15 +27,20 @@ abstract class FileScanBuilder( dataSchema: StructType) extends ScanBuilder with SupportsPushDownRequiredColumns { private val partitionSchema = fileIndex.partitionSchema private val isCaseSensitive = sparkSession.sessionState.conf.caseSensitiveAnalysis + protected val supportsNestedSchemaPruning: Boolean = false protected var requiredSchema = StructType(dataSchema.fields ++ partitionSchema.fields) override def pruneColumns(requiredSchema: StructType): Unit = { + // [SPARK-30107] While the passed `requiredSchema` always have pruned nested columns, the actual + // data schema of this scan is determined in `readDataSchema`. File formats that don't support + // nested schema pruning, use `requiredSchema` as a reference and perform the pruning partially. this.requiredSchema = requiredSchema Review comment: I agree and it will also be trivial because the changes in this layer are minimal. ---------------------------------------------------------------- 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: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org