Github user JDrit commented on a diff in the pull request: https://github.com/apache/spark/pull/7004#discussion_r35265695 --- Diff: core/src/main/scala/org/apache/spark/SparkConf.scala --- @@ -161,6 +162,25 @@ class SparkConf(loadDefaults: Boolean) extends Cloneable with Logging { this } + private final val avroNamespace = "avro.schema." + + /** + * Use Kryo serialization and register the given set of Avro schemas so that the generic + * record serializer can decrease network IO + */ + def registerAvroSchemas(schemas: Schema*): SparkConf = { + schemas.foldLeft(this) { (conf, schema) => + conf.set(avroNamespace + SchemaNormalization.parsingFingerprint64(schema), schema.toString) + } + } + + /** Gets all the avro schemas in the configuration used in the generic Avro record serializer */ + def getAvroSchema: Map[Long, String] = { --- End diff -- The keys are longs, which represent the a unique ID of the schema and the values are the string representation of the schema.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org