n3nash commented on a change in pull request #2619: URL: https://github.com/apache/hudi/pull/2619#discussion_r597937461
########## File path: hudi-utilities/src/main/java/org/apache/hudi/utilities/deser/KafkaAvroSchemaDeserializer.java ########## @@ -0,0 +1,93 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.hudi.utilities.deser; + +import io.confluent.kafka.schemaregistry.client.SchemaRegistryClient; +import io.confluent.kafka.serializers.KafkaAvroDeserializer; +import org.apache.avro.Schema; + +import org.apache.hudi.DataSourceWriteOptions; +import org.apache.hudi.common.config.TypedProperties; +import org.apache.hudi.common.util.ReflectionUtils; +import org.apache.hudi.exception.HoodieException; +import org.apache.hudi.utilities.schema.SchemaProvider; +import org.apache.kafka.common.errors.SerializationException; +import org.apache.spark.api.java.JavaSparkContext; + +import java.util.Map; +import java.util.Map.Entry; +import java.util.Objects; + +/** + * Extending {@link KafkaAvroSchemaDeserializer} as we need to be able to inject reader schema during deserialization. + */ +public class KafkaAvroSchemaDeserializer extends KafkaAvroDeserializer { + + private Schema sourceSchema; + + public KafkaAvroSchemaDeserializer() {} + + public KafkaAvroSchemaDeserializer(SchemaRegistryClient client, Map<String, ?> props) { + super(client, props); + } + + @Override + public void configure(Map<String, ?> configs, boolean isKey) { + super.configure(configs, isKey); + try { + TypedProperties props = getConvertToTypedProperties(configs); + String className = props.getString(DataSourceWriteOptions.SCHEMA_PROVIDER_CLASS_PROP()); + JavaSparkContext jsc = (JavaSparkContext) props.get(DataSourceWriteOptions.JAVA_SPARK_CONTEXT_PROP()); Review comment: Yes, we should introduce a new constructor which does not take jsc for this PR. We can discuss the need of jsc outside of this PR. ########## File path: hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/DataSourceOptions.scala ########## @@ -373,4 +373,12 @@ object DataSourceWriteOptions { // Async Compaction - Enabled by default for MOR val ASYNC_COMPACT_ENABLE_OPT_KEY = "hoodie.datasource.compaction.async.enable" val DEFAULT_ASYNC_COMPACT_ENABLE_OPT_VAL = "true" + + // Avro Kafka Source configs + val KAFKA_AVRO_VALUE_DESERIALIZER = "hoodie.deltastreamer.source.kafka.value.deserializer.class" + // val DEFAULT_KAFKA_AVRO_VALUE_DESERIALIZER = classOf[io.confluent.kafka.serializers.KafkaAvroDeserializer] + + val SCHEMA_PROVIDER_CLASS_PROP = "hoodie.deltastreamer.schemaprovider.class" + + val JAVA_SPARK_CONTEXT_PROP = "java.spark.context" Review comment: Let's remove this as discussed below -- 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
