alexeykudinkin commented on a change in pull request #4789:
URL: https://github.com/apache/hudi/pull/4789#discussion_r808611371
##########
File path:
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/MergeOnReadIncrementalRelation.scala
##########
@@ -125,41 +114,39 @@ class MergeOnReadIncrementalRelation(sqlContext:
SQLContext,
val (requiredAvroSchema, requiredStructSchema) =
HoodieSparkUtils.getRequiredSchema(tableAvroSchema, requiredColumns)
- val hoodieTableState = HoodieMergeOnReadTableState(
- tableStructSchema,
- requiredStructSchema,
- tableAvroSchema.toString,
- requiredAvroSchema.toString,
- fileIndex,
- preCombineField,
- Option.empty
- )
- val fullSchemaParquetReader =
HoodieDataSourceHelper.buildHoodieParquetReader(
- sparkSession = sqlContext.sparkSession,
- dataSchema = tableStructSchema,
- partitionSchema = StructType(Nil),
- requiredSchema = tableStructSchema,
+ val partitionSchema = StructType(Nil)
+ val tableSchema = HoodieTableSchema(tableStructSchema,
tableAvroSchema.toString)
+ val requiredSchema = HoodieTableSchema(requiredStructSchema,
requiredAvroSchema.toString)
+
+ val fullSchemaParquetReader = createBaseFileReader(
+ spark = sqlContext.sparkSession,
+ partitionSchema = partitionSchema,
+ tableSchema = tableSchema,
+ requiredSchema = tableSchema,
filters = pushDownFilter,
options = optParams,
hadoopConf = sqlContext.sparkSession.sessionState.newHadoopConf()
)
-
- val requiredSchemaParquetReader =
HoodieDataSourceHelper.buildHoodieParquetReader(
- sparkSession = sqlContext.sparkSession,
- dataSchema = tableStructSchema,
- partitionSchema = StructType(Nil),
- requiredSchema = tableStructSchema,
+ val requiredSchemaParquetReader = createBaseFileReader(
+ spark = sqlContext.sparkSession,
+ partitionSchema = partitionSchema,
+ tableSchema = tableSchema,
+ requiredSchema = requiredSchema,
filters = pushDownFilter,
options = optParams,
hadoopConf = sqlContext.sparkSession.sessionState.newHadoopConf()
)
+ val hoodieTableState = HoodieMergeOnReadTableState(fileIndex,
HoodieRecord.RECORD_KEY_METADATA_FIELD, preCombineFieldOpt)
Review comment:
Good catch! MT is not supported in Incremental relation currently.
That would be tackled in a follow-up PR making sure that
Incremental/Snapshot have shared base
--
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]
