voonhous commented on code in PR #17573:
URL: https://github.com/apache/hudi/pull/17573#discussion_r2635099057
##########
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/HoodieFileGroupReaderBasedFileFormat.scala:
##########
@@ -212,8 +211,8 @@ class HoodieFileGroupReaderBasedFileFormat(tablePath:
String,
exclusionFields.add("op")
partitionSchema.fields.foreach(f => exclusionFields.add(f.name))
val requestedSchema = StructType(requiredSchema.fields ++
partitionSchema.fields.filter(f => mandatoryFields.contains(f.name)))
- val requestedAvroSchema = AvroSchemaUtils.pruneDataSchema(avroTableSchema,
AvroConversionUtils.convertStructTypeToAvroSchema(requestedSchema,
sanitizedTableName), exclusionFields)
- val dataAvroSchema = AvroSchemaUtils.pruneDataSchema(avroTableSchema,
AvroConversionUtils.convertStructTypeToAvroSchema(dataSchema,
sanitizedTableName), exclusionFields)
+ val requestedHoodieSchema = HoodieSchemaUtils.pruneDataSchema(schema,
HoodieSchemaConversionUtils.convertStructTypeToHoodieSchema(requestedSchema,
sanitizedTableName), exclusionFields)
+ val dataHoodieSchema = HoodieSchemaUtils.pruneDataSchema(schema,
HoodieSchemaConversionUtils.convertStructTypeToHoodieSchema(dataSchema,
sanitizedTableName), exclusionFields)
Review Comment:
Addressed
##########
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/HoodieMergeOnReadRDDV2.scala:
##########
@@ -193,8 +192,8 @@ class HoodieMergeOnReadRDDV2(@transient sc: SparkContext,
.withBaseFileOption(baseFileOption)
.withPartitionPath(partitionPath)
.withProps(properties)
- .withDataSchema(HoodieSchema.parse(tableSchema.avroSchemaStr))
-
.withRequestedSchema(HoodieSchema.parse(requiredSchema.avroSchemaStr))
+ .withDataSchema(tableSchema.tableSchema)
+ .withRequestedSchema(requiredSchema.tableSchema)
Review Comment:
Addressed
--
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]
