jintaoguan commented on a change in pull request #3985:
URL: https://github.com/apache/hudi/pull/3985#discussion_r803324790
##########
File path:
hudi-spark-datasource/hudi-spark/src/main/scala/org/apache/hudi/IncrementalRelation.scala
##########
@@ -157,27 +161,40 @@ class IncrementalRelation(val sqlContext: SQLContext,
} else {
log.info("Additional Filters to be applied to incremental source are :"
+ filters)
- var df: DataFrame =
sqlContext.createDataFrame(sqlContext.sparkContext.emptyRDD[Row], usedSchema)
+ var prunedSchema = StructType(Seq())
+ if (!requiredColumns.contains(HoodieRecord.COMMIT_TIME_METADATA_FIELD)) {
+ prunedSchema =
prunedSchema.add(usedSchema(HoodieRecord.COMMIT_TIME_METADATA_FIELD))
+ }
+ requiredColumns.foreach(col => {
+ val field = usedSchema.find(_.name == col)
+ if (field.isDefined) {
+ prunedSchema = prunedSchema.add(field.get)
+ }
+ })
+ var df: DataFrame =
sqlContext.createDataFrame(sqlContext.sparkContext.emptyRDD[Row], prunedSchema)
if (metaBootstrapFileIdToFullPath.nonEmpty) {
df = sqlContext.sparkSession.read
.format("hudi")
- .schema(usedSchema)
+ .schema(prunedSchema)
.option(DataSourceReadOptions.READ_PATHS.key,
filteredMetaBootstrapFullPaths.mkString(","))
.load()
}
if (regularFileIdToFullPath.nonEmpty)
{
df = df.union(sqlContext.read.options(sOpts)
- .schema(usedSchema)
+ .schema(prunedSchema)
.parquet(filteredRegularFullPaths.toList: _*)
.filter(String.format("%s >= '%s'",
HoodieRecord.COMMIT_TIME_METADATA_FIELD,
commitsToReturn.head.getTimestamp))
.filter(String.format("%s <= '%s'",
HoodieRecord.COMMIT_TIME_METADATA_FIELD,
commitsToReturn.last.getTimestamp)))
}
+ if (!requiredColumns.contains(HoodieRecord.COMMIT_TIME_METADATA_FIELD)) {
Review comment:
Because IncrementalRelation extends PrunedScan here, the SparkSQL engine
passes the required columns to IncrementalRelation and it expects the returned
RDD only to have the required columns.
If we don't remove the non-required column here, it will cause schema
mismatch errors.
--
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]
