lokeshj1703 commented on code in PR #7982:
URL: https://github.com/apache/hudi/pull/7982#discussion_r1118696343
##########
hudi-utilities/src/main/java/org/apache/hudi/utilities/deltastreamer/DeltaSync.java:
##########
@@ -494,9 +505,38 @@ private Pair<SchemaProvider, Pair<String,
JavaRDD<HoodieRecord>>> fetchFromSourc
Option<Dataset<Row>> transformed =
dataAndCheckpoint.getBatch().map(data ->
transformer.get().apply(jssc, sparkSession, data, props));
+ transformed = formatAdapter.processErrorEvents(transformed,
+ ErrorEvent.ErrorReason.CUSTOM_TRANSFORMER_FAILURE);
+
checkpointStr = dataAndCheckpoint.getCheckpointForNextBatch();
boolean reconcileSchema =
props.getBoolean(DataSourceWriteOptions.RECONCILE_SCHEMA().key());
if (this.userProvidedSchemaProvider != null &&
this.userProvidedSchemaProvider.getTargetSchema() != null) {
+ // If the target schema is specified through Avro schema,
+ // pass in the schema for the Row-to-Avro conversion
+ // to avoid nullability mismatch between Avro schema and Row schema
+ Option<BaseErrorTableWriter> schemaValidationErrorWriter =
+ (errorTableWriter.isPresent()
+ &&
props.getBoolean(HoodieErrorTableConfig.ERROR_ENABLE_VALIDATE_TARGET_SCHEMA.key(),
+
HoodieErrorTableConfig.ERROR_ENABLE_VALIDATE_TARGET_SCHEMA.defaultValue()))
+ ? errorTableWriter : Option.empty();
+ avroRDDOptional = transformed
+ .map(row ->
+ schemaValidationErrorWriter
+ .map(impl -> {
+ Tuple2<RDD<GenericRecord>, RDD<String>> safeCreateRDDs =
HoodieSparkUtils.safeCreateRDD(row,
+ HOODIE_RECORD_STRUCT_NAME, HOODIE_RECORD_NAMESPACE,
reconcileSchema,
+
Option.of(this.userProvidedSchemaProvider.getTargetSchema())
+ );
+ impl.addErrorEvents(safeCreateRDDs._2().toJavaRDD()
+ .map(evStr -> new ErrorEvent<>(evStr,
+
ErrorEvent.ErrorReason.AVRO_DESERIALIZATION_FAILURE)));
+ return safeCreateRDDs._1();
+ })
+ .orElseGet(() -> HoodieSparkUtils.createRdd(row,
+ HOODIE_RECORD_STRUCT_NAME, HOODIE_RECORD_NAMESPACE,
reconcileSchema,
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]
